{ "protocol": "rest", "baseUrl": "https://videointelligence.googleapis.com/", "name": "videointelligence", "version_module": true, "documentationLink": "https://cloud.google.com/video-intelligence/docs/", "parameters": { "oauth_token": { "location": "query", "type": "string", "description": "OAuth 2.0 token for the current user." }, "fields": { "location": "query", "type": "string", "description": "Selector specifying which fields to include in a partial response." }, "upload_protocol": { "type": "string", "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").", "location": "query" }, "quotaUser": { "location": "query", "type": "string", "description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters." }, "uploadType": { "type": "string", "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").", "location": "query" }, "callback": { "location": "query", "type": "string", "description": "JSONP" }, "prettyPrint": { "type": "boolean", "description": "Returns response with indentations and line breaks.", "default": "true", "location": "query" }, "key": { "location": "query", "type": "string", "description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token." }, "access_token": { "location": "query", "type": "string", "description": "OAuth access token." }, "$.xgafv": { "enumDescriptions": [ "v1 error format", "v2 error format" ], "enum": [ "1", "2" ], "location": "query", "description": "V1 error format.", "type": "string" }, "alt": { "description": "Data format for response.", "location": "query", "enum": [ "json", "media", "proto" ], "enumDescriptions": [ "Responses with Content-Type of application/json", "Media download with context-dependent Content-Type", "Responses with Content-Type of application/x-protobuf" ], "type": "string", "default": "json" } }, "revision": "20260428", "resources": { "videos": { "methods": { "annotate": { "parameterOrder": [], "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "request": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoRequest" }, "description": "Performs asynchronous video annotation. Progress and results can be retrieved through the `google.longrunning.Operations` interface. `Operation.metadata` contains `AnnotateVideoProgress` (progress). `Operation.response` contains `AnnotateVideoResponse` (results).", "path": "v1p1beta1/videos:annotate", "response": { "$ref": "GoogleLongrunning_Operation" }, "parameters": {}, "flatPath": "v1p1beta1/videos:annotate", "httpMethod": "POST", "id": "videointelligence.videos.annotate" } } } }, "schemas": { "GoogleCloudVideointelligenceV1_ExportToOutputUriStatus": { "properties": { "status": { "description": "Output only. Only set if state is FAILED.", "readOnly": true, "$ref": "GoogleRpc_Status" }, "state": { "type": "string", "description": "Output only. State of the `output_uri` export.", "readOnly": true, "enumDescriptions": [ "Default value.", "Export succeeded.", "Export failed." ], "enum": [ "STATE_UNSPECIFIED", "SUCCEEDED", "FAILED" ] } }, "id": "GoogleCloudVideointelligenceV1_ExportToOutputUriStatus", "description": "Status of exporting annotation response to user specified `output_uri`.", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_DetectedLandmark": { "properties": { "name": { "description": "The name of this landmark, for example, left_hand, right_shoulder.", "type": "string" }, "point": { "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex" }, "confidence": { "description": "The confidence score of the detected landmark. Range [0, 1].", "type": "number", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_DetectedLandmark", "description": "A generic detected landmark represented by name in string format and a 2D location.", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation": { "properties": { "segments": { "description": "All video segments where OCR detected text appears.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextSegment" } }, "text": { "description": "The detected text.", "type": "string" }, "version": { "description": "Feature version.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation", "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_TextAnnotation": { "properties": { "version": { "description": "Feature version.", "type": "string" }, "text": { "description": "The detected text.", "type": "string" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextSegment" }, "description": "All video segments where OCR detected text appears.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_TextAnnotation", "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.", "type": "object" }, "GoogleCloudVideointelligenceV1_FaceSegment": { "id": "GoogleCloudVideointelligenceV1_FaceSegment", "description": "Video segment level annotation results for face detection.", "type": "object", "properties": { "segment": { "description": "Video segment where a face was detected.", "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" } } }, "GoogleCloudVideointelligenceV1p3beta1_TimestampedObject": { "properties": { "normalizedBoundingBox": { "description": "Normalized Bounding box in a frame, where the object is located.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox" }, "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.", "type": "string", "format": "google-duration" }, "attributes": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute" }, "description": "Optional. The attributes of the object in the bounding box.", "type": "array" }, "landmarks": { "description": "Optional. The detected landmarks.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_DetectedLandmark" } } }, "id": "GoogleCloudVideointelligenceV1p3beta1_TimestampedObject", "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_SpeechTranscription": { "properties": { "alternatives": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative" }, "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", "type": "array" }, "languageCode": { "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.", "readOnly": true, "type": "string" } }, "id": "GoogleCloudVideointelligenceV1beta2_SpeechTranscription", "description": "A speech recognition result corresponding to a portion of the audio.", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoProgress": { "properties": { "annotationProgress": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress" }, "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoProgress", "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingPoly": { "id": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingPoly", "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.", "type": "object", "properties": { "vertices": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex" }, "description": "Normalized vertices of the bounding polygon.", "type": "array" } } }, "GoogleCloudVideointelligenceV1p2beta1_FaceAnnotation": { "description": "Deprecated. No effect.", "deprecated": true, "id": "GoogleCloudVideointelligenceV1p2beta1_FaceAnnotation", "type": "object", "properties": { "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceFrame" }, "description": "All video frames where a face was detected.", "type": "array" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceSegment" }, "description": "All video segments where a face was detected.", "type": "array" }, "thumbnail": { "format": "byte", "description": "Thumbnail of a representative face view (in JPEG format).", "type": "string" } } }, "GoogleCloudVideointelligenceV1_VideoAnnotationResults": { "properties": { "frameLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" }, "description": "Label annotations on frame level. There is exactly one element for each unique label.", "type": "array" }, "logoRecognitionAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation" }, "description": "Annotations for list of logos detected, tracked and recognized in video.", "type": "array" }, "segmentLabelAnnotations": { "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" } }, "explicitAnnotation": { "description": "Explicit content annotation.", "$ref": "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation" }, "speechTranscriptions": { "items": { "$ref": "GoogleCloudVideointelligenceV1_SpeechTranscription" }, "description": "Speech transcription.", "type": "array" }, "shotAnnotations": { "description": "Shot annotations. Each shot is represented as a video segment.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" } }, "textAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1_TextAnnotation" }, "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.", "type": "array" }, "error": { "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.", "$ref": "GoogleRpc_Status" }, "segmentPresenceLabelAnnotations": { "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" } }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "faceDetectionAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1_FaceDetectionAnnotation" }, "description": "Face detection annotations.", "type": "array" }, "personDetectionAnnotations": { "description": "Person detection annotations.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_PersonDetectionAnnotation" } }, "segment": { "description": "Video segment on which the annotation is run.", "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" }, "shotPresenceLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" }, "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "type": "array" }, "faceAnnotations": { "description": "Deprecated. Please use `face_detection_annotations` instead.", "type": "array", "deprecated": true, "items": { "$ref": "GoogleCloudVideointelligenceV1_FaceAnnotation" } }, "objectAnnotations": { "description": "Annotations for list of objects detected and tracked in video.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation" } }, "shotLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation" }, "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1_VideoAnnotationResults", "description": "Annotation results for a single video.", "type": "object" }, "GoogleCloudVideointelligenceV1_FaceDetectionAnnotation": { "id": "GoogleCloudVideointelligenceV1_FaceDetectionAnnotation", "description": "Face detection annotation.", "type": "object", "properties": { "tracks": { "items": { "$ref": "GoogleCloudVideointelligenceV1_Track" }, "description": "The face tracks with attributes.", "type": "array" }, "thumbnail": { "format": "byte", "description": "The thumbnail of a person's face.", "type": "string" }, "version": { "description": "Feature version.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p3beta1_ExportToOutputUriStatus": { "properties": { "state": { "type": "string", "enum": [ "STATE_UNSPECIFIED", "SUCCEEDED", "FAILED" ], "enumDescriptions": [ "Default value.", "Export succeeded.", "Export failed." ], "description": "Output only. State of the `output_uri` export.", "readOnly": true }, "status": { "description": "Output only. Only set if state is FAILED.", "readOnly": true, "$ref": "GoogleRpc_Status" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_ExportToOutputUriStatus", "description": "Status of exporting annotation response to user specified `output_uri`.", "type": "object" }, "GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation": { "properties": { "tracks": { "items": { "$ref": "GoogleCloudVideointelligenceV1_Track" }, "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", "type": "array" }, "entity": { "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.", "$ref": "GoogleCloudVideointelligenceV1_Entity" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" }, "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation", "description": "Annotation corresponding to one detected, tracked and recognized logo class.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame": { "properties": { "timeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string" }, "pornographyLikelihood": { "enumDescriptions": [ "Unspecified likelihood.", "Very unlikely.", "Unlikely.", "Possible.", "Likely.", "Very likely." ], "enum": [ "LIKELIHOOD_UNSPECIFIED", "VERY_UNLIKELY", "UNLIKELY", "POSSIBLE", "LIKELY", "VERY_LIKELY" ], "description": "Likelihood of the pornography content..", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame", "description": "Video frame level annotation results for explicit content.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_ShotChangeDetectionConfig": { "id": "GoogleCloudVideointelligenceV1p1beta1_ShotChangeDetectionConfig", "description": "Config for SHOT_CHANGE_DETECTION.", "type": "object", "properties": { "model": { "description": "Model to use for shot change detection. Supported values: \"builtin/stable\" (the default if unset), \"builtin/latest\", and \"builtin/legacy\".", "type": "string" } } }, "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame": { "properties": { "timeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string" }, "pornographyLikelihood": { "description": "Likelihood of the pornography content..", "type": "string", "enumDescriptions": [ "Unspecified likelihood.", "Very unlikely.", "Unlikely.", "Possible.", "Likely.", "Very likely." ], "enum": [ "LIKELIHOOD_UNSPECIFIED", "VERY_UNLIKELY", "UNLIKELY", "POSSIBLE", "LIKELY", "VERY_LIKELY" ] } }, "id": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame", "description": "Video frame level annotation results for explicit content.", "type": "object" }, "GoogleCloudVideointelligenceV1_TextFrame": { "id": "GoogleCloudVideointelligenceV1_TextFrame", "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", "type": "object", "properties": { "rotatedBoundingBox": { "description": "Bounding polygon of the detected text for this frame.", "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly" }, "timeOffset": { "description": "Timestamp of this frame.", "type": "string", "format": "google-duration" } } }, "GoogleCloudVideointelligenceV1p3beta1_VideoSegment": { "properties": { "startTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).", "type": "string", "format": "google-duration" }, "endTimeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment", "description": "Video segment.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoResponse": { "id": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoResponse", "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "type": "object", "properties": { "annotationResults": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults" }, "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", "type": "array" } } }, "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationProgress": { "id": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationProgress", "description": "Annotation progress for a single video.", "type": "object", "properties": { "feature": { "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "CELEBRITY_RECOGNITION", "PERSON_DETECTION" ], "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Celebrity recognition.", "Person detection." ], "description": "Specifies which feature is being tracked if the request contains more than one feature.", "type": "string" }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "updateTime": { "format": "google-datetime", "description": "Time of the most recent update.", "type": "string" }, "startTime": { "description": "Time when the request was received.", "type": "string", "format": "google-datetime" }, "progressPercent": { "format": "int32", "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.", "type": "integer" }, "segment": { "description": "Specifies which segment is being tracked if the request contains more than one segment.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "exportStatus": { "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExportToOutputUriStatus" } } }, "GoogleCloudVideointelligenceV1_PersonDetectionAnnotation": { "id": "GoogleCloudVideointelligenceV1_PersonDetectionAnnotation", "description": "Person detection annotation per video.", "type": "object", "properties": { "tracks": { "description": "The detected tracks of a person.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_Track" } }, "version": { "description": "Feature version.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p1beta1_TextSegment": { "properties": { "segment": { "description": "Video segment where a text snippet was detected.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" }, "confidence": { "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", "type": "number", "format": "float" }, "frames": { "description": "Information related to the frames where OCR detected text appears.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextFrame" } } }, "id": "GoogleCloudVideointelligenceV1p1beta1_TextSegment", "description": "Video segment level annotation results for text detection.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_TextDetectionConfig": { "id": "GoogleCloudVideointelligenceV1p1beta1_TextDetectionConfig", "description": "Config for TEXT_DETECTION.", "type": "object", "properties": { "languageHints": { "description": "Language hint can be specified if the language to be detected is known a priori. It can increase the accuracy of the detection. Language hint must be language code in BCP-47 format. Automatic language detection is performed if no hint is provided.", "type": "array", "items": { "type": "string" } }, "model": { "description": "Model to use for text detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".", "type": "string" } } }, "GoogleCloudVideointelligenceV1p3beta1_FaceAnnotation": { "properties": { "thumbnail": { "description": "Thumbnail of a representative face view (in JPEG format).", "type": "string", "format": "byte" }, "frames": { "description": "All video frames where a face was detected.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceFrame" } }, "segments": { "description": "All video segments where a face was detected.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceSegment" } } }, "id": "GoogleCloudVideointelligenceV1p3beta1_FaceAnnotation", "type": "object", "deprecated": true, "description": "Deprecated. No effect." }, "GoogleCloudVideointelligenceV1p2beta1_VideoSegment": { "id": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment", "description": "Video segment.", "type": "object", "properties": { "startTimeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).", "type": "string" }, "endTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).", "type": "string", "format": "google-duration" } } }, "GoogleCloudVideointelligenceV1beta2_TimestampedObject": { "id": "GoogleCloudVideointelligenceV1beta2_TimestampedObject", "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.", "type": "object", "properties": { "normalizedBoundingBox": { "description": "Normalized Bounding box in a frame, where the object is located.", "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox" }, "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.", "type": "string", "format": "google-duration" }, "attributes": { "description": "Optional. The attributes of the object in the bounding box.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_DetectedAttribute" } }, "landmarks": { "description": "Optional. The detected landmarks.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_DetectedLandmark" } } } }, "GoogleCloudVideointelligenceV1p3beta1_CelebrityTrack": { "properties": { "celebrities": { "description": "Top N match of the celebrities for the face in this track.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_RecognizedCelebrity" } }, "faceTrack": { "description": "A track of a person's face.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_CelebrityTrack", "description": "The annotation result of a celebrity face track. RecognizedCelebrity field could be empty if the face track does not have any matched celebrities.", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription": { "properties": { "languageCode": { "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.", "readOnly": true, "type": "string" }, "alternatives": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative" }, "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription", "description": "A speech recognition result corresponding to a portion of the audio.", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation": { "properties": { "version": { "description": "Feature version.", "type": "string" }, "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelFrame" }, "description": "All video frames where a label was detected.", "type": "array" }, "categoryEntities": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity" }, "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", "type": "array" }, "entity": { "description": "Detected entity.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelSegment" }, "description": "All video segments where a label was detected.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation", "description": "Label annotation.", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_Entity": { "properties": { "entityId": { "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).", "type": "string" }, "description": { "description": "Textual description, e.g., `Fixed-gear bicycle`.", "type": "string" }, "languageCode": { "description": "Language code for `description` in BCP-47 format.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_Entity", "description": "Detected entity from video analysis.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly": { "properties": { "vertices": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex" }, "description": "Normalized vertices of the bounding polygon.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly", "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_WordInfo": { "properties": { "word": { "description": "The word corresponding to this set of information.", "type": "string" }, "endTime": { "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "type": "string", "format": "google-duration" }, "speakerLabel": { "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.", "readOnly": true, "type": "string" }, "speakerTag": { "format": "int32", "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", "readOnly": true, "type": "integer" }, "confidence": { "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "readOnly": true, "type": "number", "format": "float" }, "startTime": { "format": "google-duration", "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1beta2_WordInfo", "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.", "type": "object" }, "GoogleCloudVideointelligenceV1_DetectedAttribute": { "properties": { "value": { "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.", "type": "string" }, "name": { "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.", "type": "string" }, "confidence": { "format": "float", "description": "Detected attribute confidence. Range [0, 1].", "type": "number" } }, "id": "GoogleCloudVideointelligenceV1_DetectedAttribute", "description": "A generic detected attribute represented by name in string format.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_FaceSegment": { "id": "GoogleCloudVideointelligenceV1beta2_FaceSegment", "description": "Video segment level annotation results for face detection.", "type": "object", "properties": { "segment": { "description": "Video segment where a face was detected.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" } } }, "GoogleCloudVideointelligenceV1p3beta1_Celebrity": { "properties": { "description": { "description": "Textual description of additional information about the celebrity, if applicable.", "type": "string" }, "name": { "description": "The resource name of the celebrity. Have the format `video-intelligence/kg-mid` indicates a celebrity from preloaded gallery. kg-mid is the id in Google knowledge graph, which is unique for the celebrity.", "type": "string" }, "displayName": { "description": "The celebrity name.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_Celebrity", "description": "Celebrity definition.", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex": { "id": "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex", "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", "type": "object", "properties": { "x": { "format": "float", "description": "X coordinate.", "type": "number" }, "y": { "format": "float", "description": "Y coordinate.", "type": "number" } } }, "GoogleCloudVideointelligenceV1p3beta1_SpeechRecognitionAlternative": { "id": "GoogleCloudVideointelligenceV1p3beta1_SpeechRecognitionAlternative", "description": "Alternative hypotheses (a.k.a. n-best list).", "type": "object", "properties": { "transcript": { "description": "Transcript text representing the words that the user spoke.", "type": "string" }, "confidence": { "format": "float", "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "readOnly": true, "type": "number" }, "words": { "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", "readOnly": true, "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_WordInfo" } } } }, "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation": { "properties": { "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame" }, "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", "type": "array" }, "version": { "description": "Feature version.", "type": "string" }, "trackId": { "format": "int64", "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.", "type": "string" }, "entity": { "description": "Entity to specify the object category that this track is labeled as.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity" }, "confidence": { "format": "float", "description": "Object category's labeling confidence of this track.", "type": "number" }, "segment": { "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation", "description": "Annotations corresponding to one tracked object.", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_DetectedLandmark": { "id": "GoogleCloudVideointelligenceV1p3beta1_DetectedLandmark", "description": "A generic detected landmark represented by name in string format and a 2D location.", "type": "object", "properties": { "name": { "description": "The name of this landmark, for example, left_hand, right_shoulder.", "type": "string" }, "point": { "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex" }, "confidence": { "description": "The confidence score of the detected landmark. Range [0, 1].", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1p2beta1_FaceFrame": { "description": "Deprecated. No effect.", "deprecated": true, "properties": { "normalizedBoundingBoxes": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox" }, "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", "type": "array" }, "timeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_FaceFrame", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation": { "id": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation", "description": "Annotations corresponding to one tracked object.", "type": "object", "properties": { "frames": { "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingFrame" } }, "version": { "description": "Feature version.", "type": "string" }, "trackId": { "format": "int64", "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.", "type": "string" }, "entity": { "description": "Entity to specify the object category that this track is labeled as.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity" }, "confidence": { "format": "float", "description": "Object category's labeling confidence of this track.", "type": "number" }, "segment": { "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" } } }, "GoogleCloudVideointelligenceV1_DetectedLandmark": { "properties": { "name": { "description": "The name of this landmark, for example, left_hand, right_shoulder.", "type": "string" }, "point": { "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1.", "$ref": "GoogleCloudVideointelligenceV1_NormalizedVertex" }, "confidence": { "description": "The confidence score of the detected landmark. Range [0, 1].", "type": "number", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1_DetectedLandmark", "description": "A generic detected landmark represented by name in string format and a 2D location.", "type": "object" }, "GoogleCloudVideointelligenceV1_VideoSegment": { "id": "GoogleCloudVideointelligenceV1_VideoSegment", "description": "Video segment.", "type": "object", "properties": { "startTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).", "type": "string", "format": "google-duration" }, "endTimeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).", "type": "string", "format": "google-duration" } } }, "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame": { "properties": { "timeOffset": { "description": "The timestamp of the frame in microseconds.", "type": "string", "format": "google-duration" }, "normalizedBoundingBox": { "description": "The normalized bounding box location of this object track for the frame.", "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox" } }, "id": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame", "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly": { "id": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly", "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.", "type": "object", "properties": { "vertices": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex" }, "description": "Normalized vertices of the bounding polygon.", "type": "array" } } }, "GoogleCloudVideointelligenceV1p1beta1_FaceSegment": { "id": "GoogleCloudVideointelligenceV1p1beta1_FaceSegment", "description": "Video segment level annotation results for face detection.", "type": "object", "properties": { "segment": { "description": "Video segment where a face was detected.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" } } }, "GoogleCloudVideointelligenceV1p2beta1_ExportToOutputUriStatus": { "properties": { "state": { "type": "string", "description": "Output only. State of the `output_uri` export.", "readOnly": true, "enum": [ "STATE_UNSPECIFIED", "SUCCEEDED", "FAILED" ], "enumDescriptions": [ "Default value.", "Export succeeded.", "Export failed." ] }, "status": { "description": "Output only. Only set if state is FAILED.", "readOnly": true, "$ref": "GoogleRpc_Status" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_ExportToOutputUriStatus", "description": "Status of exporting annotation response to user specified `output_uri`.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_LabelFrame": { "id": "GoogleCloudVideointelligenceV1beta2_LabelFrame", "description": "Video frame level annotation results for label detection.", "type": "object", "properties": { "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string", "format": "google-duration" }, "confidence": { "format": "float", "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number" } } }, "GoogleCloudVideointelligenceV1_LabelSegment": { "id": "GoogleCloudVideointelligenceV1_LabelSegment", "description": "Video segment level annotation results for label detection.", "type": "object", "properties": { "segment": { "description": "Video segment where a label was detected.", "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" }, "confidence": { "format": "float", "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number" } } }, "GoogleCloudVideointelligenceV1p1beta1_LogoRecognitionAnnotation": { "id": "GoogleCloudVideointelligenceV1p1beta1_LogoRecognitionAnnotation", "description": "Annotation corresponding to one detected, tracked and recognized logo class.", "type": "object", "properties": { "entity": { "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" }, "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.", "type": "array" }, "tracks": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_Track" }, "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", "type": "array" } } }, "GoogleCloudVideointelligenceV1_VideoAnnotationProgress": { "id": "GoogleCloudVideointelligenceV1_VideoAnnotationProgress", "description": "Annotation progress for a single video.", "type": "object", "properties": { "startTime": { "description": "Time when the request was received.", "type": "string", "format": "google-datetime" }, "progressPercent": { "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.", "type": "integer", "format": "int32" }, "segment": { "description": "Specifies which segment is being tracked if the request contains more than one segment.", "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" }, "exportStatus": { "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request.", "$ref": "GoogleCloudVideointelligenceV1_ExportToOutputUriStatus" }, "feature": { "description": "Specifies which feature is being tracked if the request contains more than one feature.", "type": "string", "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "PERSON_DETECTION" ], "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Person detection." ] }, "updateTime": { "description": "Time of the most recent update.", "type": "string", "format": "google-datetime" }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" } } }, "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative": { "properties": { "words": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_WordInfo" }, "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", "readOnly": true, "type": "array" }, "transcript": { "description": "Transcript text representing the words that the user spoke.", "type": "string" }, "confidence": { "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "readOnly": true, "type": "number", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative", "description": "Alternative hypotheses (a.k.a. n-best list).", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame": { "id": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame", "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.", "type": "object", "properties": { "normalizedBoundingBox": { "description": "The normalized bounding box location of this object track for the frame.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox" }, "timeOffset": { "description": "The timestamp of the frame in microseconds.", "type": "string", "format": "google-duration" } } }, "GoogleCloudVideointelligenceV1p3beta1_TextFrame": { "properties": { "rotatedBoundingBox": { "description": "Bounding polygon of the detected text for this frame.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingPoly" }, "timeOffset": { "description": "Timestamp of this frame.", "type": "string", "format": "google-duration" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_TextFrame", "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", "type": "object" }, "GoogleCloudVideointelligenceV1_SpeechTranscription": { "properties": { "languageCode": { "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.", "readOnly": true, "type": "string" }, "alternatives": { "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative" } } }, "id": "GoogleCloudVideointelligenceV1_SpeechTranscription", "description": "A speech recognition result corresponding to a portion of the audio.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation": { "properties": { "entity": { "description": "Detected entity.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelSegment" }, "description": "All video segments where a label was detected.", "type": "array" }, "version": { "description": "Feature version.", "type": "string" }, "frames": { "description": "All video frames where a label was detected.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelFrame" } }, "categoryEntities": { "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity" } } }, "id": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation", "description": "Label annotation.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_Track": { "properties": { "confidence": { "format": "float", "description": "Optional. The confidence score of the tracked object.", "type": "number" }, "segment": { "description": "Video segment of a track.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" }, "timestampedObjects": { "description": "The object with timestamp and attributes per frame in the track.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_TimestampedObject" } }, "attributes": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_DetectedAttribute" }, "description": "Optional. Attributes in the track level.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1beta2_Track", "description": "A track of an object instance.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation": { "properties": { "tracks": { "description": "The detected tracks of a person.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_Track" } }, "version": { "description": "Feature version.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation", "description": "Person detection annotation per video.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex": { "id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex", "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", "type": "object", "properties": { "x": { "description": "X coordinate.", "type": "number", "format": "float" }, "y": { "format": "float", "description": "Y coordinate.", "type": "number" } } }, "GoogleCloudVideointelligenceV1_TextAnnotation": { "properties": { "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1_TextSegment" }, "description": "All video segments where OCR detected text appears.", "type": "array" }, "version": { "description": "Feature version.", "type": "string" }, "text": { "description": "The detected text.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1_TextAnnotation", "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_FaceFrame": { "id": "GoogleCloudVideointelligenceV1p3beta1_FaceFrame", "type": "object", "properties": { "normalizedBoundingBoxes": { "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox" } }, "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string", "format": "google-duration" } }, "description": "Deprecated. No effect.", "deprecated": true }, "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative": { "id": "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative", "description": "Alternative hypotheses (a.k.a. n-best list).", "type": "object", "properties": { "words": { "items": { "$ref": "GoogleCloudVideointelligenceV1_WordInfo" }, "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", "readOnly": true, "type": "array" }, "transcript": { "description": "Transcript text representing the words that the user spoke.", "type": "string" }, "confidence": { "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "readOnly": true, "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1beta2_TextAnnotation": { "properties": { "text": { "description": "The detected text.", "type": "string" }, "version": { "description": "Feature version.", "type": "string" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_TextSegment" }, "description": "All video segments where OCR detected text appears.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1beta2_TextAnnotation", "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoResponse": { "id": "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoResponse", "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "type": "object", "properties": { "annotationResults": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationResults" }, "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", "type": "array" } } }, "GoogleCloudVideointelligenceV1beta2_AnnotateVideoProgress": { "properties": { "annotationProgress": { "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress" } } }, "id": "GoogleCloudVideointelligenceV1beta2_AnnotateVideoProgress", "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "type": "object" }, "GoogleCloudVideointelligenceV1_NormalizedBoundingBox": { "id": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox", "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].", "type": "object", "properties": { "right": { "description": "Right X coordinate.", "type": "number", "format": "float" }, "left": { "description": "Left X coordinate.", "type": "number", "format": "float" }, "top": { "description": "Top Y coordinate.", "type": "number", "format": "float" }, "bottom": { "description": "Bottom Y coordinate.", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1_TimestampedObject": { "id": "GoogleCloudVideointelligenceV1_TimestampedObject", "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.", "type": "object", "properties": { "normalizedBoundingBox": { "description": "Normalized Bounding box in a frame, where the object is located.", "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox" }, "timeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.", "type": "string" }, "attributes": { "description": "Optional. The attributes of the object in the bounding box.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_DetectedAttribute" } }, "landmarks": { "description": "Optional. The detected landmarks.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_DetectedLandmark" } } } }, "GoogleCloudVideointelligenceV1p1beta1_TextFrame": { "id": "GoogleCloudVideointelligenceV1p1beta1_TextFrame", "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", "type": "object", "properties": { "rotatedBoundingBox": { "description": "Bounding polygon of the detected text for this frame.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly" }, "timeOffset": { "description": "Timestamp of this frame.", "type": "string", "format": "google-duration" } } }, "GoogleCloudVideointelligenceV1beta2_NormalizedVertex": { "id": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex", "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", "type": "object", "properties": { "y": { "format": "float", "description": "Y coordinate.", "type": "number" }, "x": { "format": "float", "description": "X coordinate.", "type": "number" } } }, "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationResults": { "id": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationResults", "description": "Annotation results for a single video.", "type": "object", "properties": { "faceDetectionAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionAnnotation" }, "description": "Face detection annotations.", "type": "array" }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "segmentPresenceLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" }, "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "type": "array" }, "textAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextAnnotation" }, "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.", "type": "array" }, "error": { "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.", "$ref": "GoogleRpc_Status" }, "shotAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "description": "Shot annotations. Each shot is represented as a video segment.", "type": "array" }, "segmentLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" }, "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", "type": "array" }, "explicitAnnotation": { "description": "Explicit content annotation.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation" }, "speechTranscriptions": { "description": "Speech transcription.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscription" } }, "frameLabelAnnotations": { "description": "Label annotations on frame level. There is exactly one element for each unique label.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" } }, "logoRecognitionAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LogoRecognitionAnnotation" }, "description": "Annotations for list of logos detected, tracked and recognized in video.", "type": "array" }, "shotLabelAnnotations": { "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" } }, "celebrityRecognitionAnnotations": { "description": "Celebrity recognition annotations.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_CelebrityRecognitionAnnotation" }, "objectAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation" }, "description": "Annotations for list of objects detected and tracked in video.", "type": "array" }, "shotPresenceLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" }, "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "type": "array" }, "faceAnnotations": { "deprecated": true, "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceAnnotation" }, "description": "Deprecated. Please use `face_detection_annotations` instead.", "type": "array" }, "segment": { "description": "Video segment on which the annotation is run.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "personDetectionAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionAnnotation" }, "description": "Person detection annotations.", "type": "array" } } }, "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress": { "id": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress", "description": "Annotation progress for a single video.", "type": "object", "properties": { "startTime": { "description": "Time when the request was received.", "type": "string", "format": "google-datetime" }, "progressPercent": { "format": "int32", "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.", "type": "integer" }, "segment": { "description": "Specifies which segment is being tracked if the request contains more than one segment.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" }, "exportStatus": { "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExportToOutputUriStatus" }, "feature": { "description": "Specifies which feature is being tracked if the request contains more than one feature.", "type": "string", "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "PERSON_DETECTION" ], "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Person detection." ] }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "updateTime": { "format": "google-datetime", "description": "Time of the most recent update.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p2beta1_FaceSegment": { "id": "GoogleCloudVideointelligenceV1p2beta1_FaceSegment", "description": "Video segment level annotation results for face detection.", "type": "object", "properties": { "segment": { "description": "Video segment where a face was detected.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" } } }, "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentDetectionConfig": { "properties": { "model": { "description": "Model to use for explicit content detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentDetectionConfig", "description": "Config for EXPLICIT_CONTENT_DETECTION.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_LabelAnnotation": { "properties": { "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelFrame" }, "description": "All video frames where a label was detected.", "type": "array" }, "categoryEntities": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_Entity" }, "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", "type": "array" }, "version": { "description": "Feature version.", "type": "string" }, "entity": { "description": "Detected entity.", "$ref": "GoogleCloudVideointelligenceV1beta2_Entity" }, "segments": { "description": "All video segments where a label was detected.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelSegment" } } }, "id": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation", "description": "Label annotation.", "type": "object" }, "GoogleCloudVideointelligenceV1_FaceFrame": { "properties": { "normalizedBoundingBoxes": { "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox" } }, "timeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1_FaceFrame", "type": "object", "description": "Deprecated. No effect.", "deprecated": true }, "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation": { "id": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation", "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", "type": "object", "properties": { "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame" }, "description": "All video frames where explicit content was detected.", "type": "array" }, "version": { "description": "Feature version.", "type": "string" } } }, "GoogleCloudVideointelligenceV1beta2_AnnotateVideoResponse": { "id": "GoogleCloudVideointelligenceV1beta2_AnnotateVideoResponse", "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "type": "object", "properties": { "annotationResults": { "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults" } } } }, "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative": { "id": "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative", "description": "Alternative hypotheses (a.k.a. n-best list).", "type": "object", "properties": { "words": { "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", "readOnly": true, "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_WordInfo" } }, "transcript": { "description": "Transcript text representing the words that the user spoke.", "type": "string" }, "confidence": { "format": "float", "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "readOnly": true, "type": "number" } } }, "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionAnnotation": { "id": "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionAnnotation", "description": "Person detection annotation per video.", "type": "object", "properties": { "tracks": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track" }, "description": "The detected tracks of a person.", "type": "array" }, "version": { "description": "Feature version.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionAnnotation": { "properties": { "tracks": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track" }, "description": "The face tracks with attributes.", "type": "array" }, "thumbnail": { "format": "byte", "description": "The thumbnail of a person's face.", "type": "string" }, "version": { "description": "Feature version.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionAnnotation", "description": "Face detection annotation.", "type": "object" }, "GoogleCloudVideointelligenceV1_Entity": { "properties": { "languageCode": { "description": "Language code for `description` in BCP-47 format.", "type": "string" }, "entityId": { "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).", "type": "string" }, "description": { "description": "Textual description, e.g., `Fixed-gear bicycle`.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1_Entity", "description": "Detected entity from video analysis.", "type": "object" }, "GoogleCloudVideointelligenceV1_LabelFrame": { "id": "GoogleCloudVideointelligenceV1_LabelFrame", "description": "Video frame level annotation results for label detection.", "type": "object", "properties": { "timeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string" }, "confidence": { "format": "float", "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number" } } }, "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly": { "properties": { "vertices": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex" }, "description": "Normalized vertices of the bounding polygon.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly", "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_LabelSegment": { "id": "GoogleCloudVideointelligenceV1p1beta1_LabelSegment", "description": "Video segment level annotation results for label detection.", "type": "object", "properties": { "segment": { "description": "Video segment where a label was detected.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" }, "confidence": { "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentFrame": { "properties": { "timeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string" }, "pornographyLikelihood": { "description": "Likelihood of the pornography content..", "type": "string", "enumDescriptions": [ "Unspecified likelihood.", "Very unlikely.", "Unlikely.", "Possible.", "Likely.", "Very likely." ], "enum": [ "LIKELIHOOD_UNSPECIFIED", "VERY_UNLIKELY", "UNLIKELY", "POSSIBLE", "LIKELY", "VERY_LIKELY" ] } }, "id": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentFrame", "description": "Video frame level annotation results for explicit content.", "type": "object" }, "GoogleCloudVideointelligenceV1_AnnotateVideoProgress": { "properties": { "annotationProgress": { "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_VideoAnnotationProgress" } } }, "id": "GoogleCloudVideointelligenceV1_AnnotateVideoProgress", "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_FaceFrame": { "properties": { "normalizedBoundingBoxes": { "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox" } }, "timeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_FaceFrame", "type": "object", "deprecated": true, "description": "Deprecated. No effect." }, "GoogleCloudVideointelligenceV1p1beta1_SpeechContext": { "properties": { "phrases": { "items": { "type": "string" }, "description": "Optional. A list of strings containing words and phrases \"hints\" so that the speech recognition is more likely to recognize them. This can be used to improve the accuracy for specific words and phrases, for example, if specific commands are typically spoken by the user. This can also be used to add additional words to the vocabulary of the recognizer. See [usage limits](https://cloud.google.com/speech/limits#content).", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_SpeechContext", "description": "Provides \"hints\" to the speech recognizer to favor specific words and phrases in the results.", "type": "object" }, "GoogleCloudVideointelligenceV1_FaceAnnotation": { "properties": { "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1_FaceFrame" }, "description": "All video frames where a face was detected.", "type": "array" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1_FaceSegment" }, "description": "All video segments where a face was detected.", "type": "array" }, "thumbnail": { "format": "byte", "description": "Thumbnail of a representative face view (in JPEG format).", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1_FaceAnnotation", "type": "object", "deprecated": true, "description": "Deprecated. No effect." }, "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionAnnotation": { "id": "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionAnnotation", "description": "Person detection annotation per video.", "type": "object", "properties": { "tracks": { "description": "The detected tracks of a person.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_Track" } }, "version": { "description": "Feature version.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p3beta1_Track": { "id": "GoogleCloudVideointelligenceV1p3beta1_Track", "description": "A track of an object instance.", "type": "object", "properties": { "segment": { "description": "Video segment of a track.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "timestampedObjects": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_TimestampedObject" }, "description": "The object with timestamp and attributes per frame in the track.", "type": "array" }, "attributes": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute" }, "description": "Optional. Attributes in the track level.", "type": "array" }, "confidence": { "format": "float", "description": "Optional. The confidence score of the tracked object.", "type": "number" } } }, "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute": { "id": "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute", "description": "A generic detected attribute represented by name in string format.", "type": "object", "properties": { "value": { "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.", "type": "string" }, "name": { "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.", "type": "string" }, "confidence": { "description": "Detected attribute confidence. Range [0, 1].", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1p3beta1_Entity": { "properties": { "languageCode": { "description": "Language code for `description` in BCP-47 format.", "type": "string" }, "entityId": { "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).", "type": "string" }, "description": { "description": "Textual description, e.g., `Fixed-gear bicycle`.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_Entity", "description": "Detected entity from video analysis.", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_TextSegment": { "id": "GoogleCloudVideointelligenceV1p2beta1_TextSegment", "description": "Video segment level annotation results for text detection.", "type": "object", "properties": { "segment": { "description": "Video segment where a text snippet was detected.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" }, "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextFrame" }, "description": "Information related to the frames where OCR detected text appears.", "type": "array" }, "confidence": { "format": "float", "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", "type": "number" } } }, "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoResponse": { "properties": { "annotationResults": { "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults" } } }, "id": "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoResponse", "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex": { "id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex", "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", "type": "object", "properties": { "x": { "format": "float", "description": "X coordinate.", "type": "number" }, "y": { "description": "Y coordinate.", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1_AnnotateVideoResponse": { "id": "GoogleCloudVideointelligenceV1_AnnotateVideoResponse", "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "type": "object", "properties": { "annotationResults": { "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_VideoAnnotationResults" } } } }, "GoogleCloudVideointelligenceV1p2beta1_LogoRecognitionAnnotation": { "properties": { "tracks": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_Track" }, "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", "type": "array" }, "entity": { "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity" }, "segments": { "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" } } }, "id": "GoogleCloudVideointelligenceV1p2beta1_LogoRecognitionAnnotation", "description": "Annotation corresponding to one detected, tracked and recognized logo class.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults": { "properties": { "faceDetectionAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation" }, "description": "Face detection annotations.", "type": "array" }, "textAnnotations": { "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_TextAnnotation" } }, "error": { "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.", "$ref": "GoogleRpc_Status" }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "segmentPresenceLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" }, "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "type": "array" }, "shotAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" }, "description": "Shot annotations. Each shot is represented as a video segment.", "type": "array" }, "segmentLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" }, "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", "type": "array" }, "explicitAnnotation": { "description": "Explicit content annotation.", "$ref": "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation" }, "speechTranscriptions": { "description": "Speech transcription.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_SpeechTranscription" } }, "frameLabelAnnotations": { "description": "Label annotations on frame level. There is exactly one element for each unique label.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" } }, "logoRecognitionAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation" }, "description": "Annotations for list of logos detected, tracked and recognized in video.", "type": "array" }, "shotLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" }, "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", "type": "array" }, "shotPresenceLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation" }, "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "type": "array" }, "faceAnnotations": { "deprecated": true, "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_FaceAnnotation" }, "description": "Deprecated. Please use `face_detection_annotations` instead.", "type": "array" }, "objectAnnotations": { "description": "Annotations for list of objects detected and tracked in video.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation" } }, "segment": { "description": "Video segment on which the annotation is run.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" }, "personDetectionAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation" }, "description": "Person detection annotations.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults", "description": "Annotation results for a single video.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute": { "id": "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute", "description": "A generic detected attribute represented by name in string format.", "type": "object", "properties": { "value": { "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.", "type": "string" }, "name": { "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.", "type": "string" }, "confidence": { "format": "float", "description": "Detected attribute confidence. Range [0, 1].", "type": "number" } } }, "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionAnnotation": { "id": "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionAnnotation", "description": "Face detection annotation.", "type": "object", "properties": { "tracks": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_Track" }, "description": "The face tracks with attributes.", "type": "array" }, "thumbnail": { "description": "The thumbnail of a person's face.", "type": "string", "format": "byte" }, "version": { "description": "Feature version.", "type": "string" } } }, "GoogleCloudVideointelligenceV1beta2_DetectedLandmark": { "id": "GoogleCloudVideointelligenceV1beta2_DetectedLandmark", "description": "A generic detected landmark represented by name in string format and a 2D location.", "type": "object", "properties": { "name": { "description": "The name of this landmark, for example, left_hand, right_shoulder.", "type": "string" }, "point": { "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1.", "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex" }, "confidence": { "format": "float", "description": "The confidence score of the detected landmark. Range [0, 1].", "type": "number" } } }, "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress": { "id": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress", "description": "Annotation progress for a single video.", "type": "object", "properties": { "startTime": { "description": "Time when the request was received.", "type": "string", "format": "google-datetime" }, "progressPercent": { "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.", "type": "integer", "format": "int32" }, "segment": { "description": "Specifies which segment is being tracked if the request contains more than one segment.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" }, "exportStatus": { "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request.", "$ref": "GoogleCloudVideointelligenceV1beta2_ExportToOutputUriStatus" }, "feature": { "description": "Specifies which feature is being tracked if the request contains more than one feature.", "type": "string", "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Person detection." ], "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "PERSON_DETECTION" ] }, "updateTime": { "format": "google-datetime", "description": "Time of the most recent update.", "type": "string" }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" } } }, "GoogleCloudVideointelligenceV1p3beta1_LabelFrame": { "id": "GoogleCloudVideointelligenceV1p3beta1_LabelFrame", "description": "Video frame level annotation results for label detection.", "type": "object", "properties": { "timeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string" }, "confidence": { "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1beta2_FaceFrame": { "deprecated": true, "description": "Deprecated. No effect.", "properties": { "normalizedBoundingBoxes": { "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox" } }, "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string", "format": "google-duration" } }, "id": "GoogleCloudVideointelligenceV1beta2_FaceFrame", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_Track": { "id": "GoogleCloudVideointelligenceV1p1beta1_Track", "description": "A track of an object instance.", "type": "object", "properties": { "segment": { "description": "Video segment of a track.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" }, "timestampedObjects": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_TimestampedObject" }, "description": "The object with timestamp and attributes per frame in the track.", "type": "array" }, "attributes": { "description": "Optional. Attributes in the track level.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute" } }, "confidence": { "description": "Optional. The confidence score of the tracked object.", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionConfig": { "id": "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionConfig", "description": "Config for PERSON_DETECTION.", "type": "object", "properties": { "includeAttributes": { "description": "Whether to enable person attributes detection, such as cloth color (black, blue, etc), type (coat, dress, etc), pattern (plain, floral, etc), hair, etc. Ignored if 'include_bounding_boxes' is set to false.", "type": "boolean" }, "includeBoundingBoxes": { "description": "Whether bounding boxes are included in the person detection annotation output.", "type": "boolean" }, "includePoseLandmarks": { "description": "Whether to enable pose landmarks detection. Ignored if 'include_bounding_boxes' is set to false.", "type": "boolean" } } }, "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation": { "properties": { "segment": { "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" }, "trackId": { "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.", "type": "string", "format": "int64" }, "entity": { "description": "Entity to specify the object category that this track is labeled as.", "$ref": "GoogleCloudVideointelligenceV1beta2_Entity" }, "confidence": { "description": "Object category's labeling confidence of this track.", "type": "number", "format": "float" }, "version": { "description": "Feature version.", "type": "string" }, "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame" }, "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation", "description": "Annotations corresponding to one tracked object.", "type": "object" }, "GoogleCloudVideointelligenceV1_ObjectTrackingFrame": { "properties": { "normalizedBoundingBox": { "description": "The normalized bounding box location of this object track for the frame.", "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox" }, "timeOffset": { "description": "The timestamp of the frame in microseconds.", "type": "string", "format": "google-duration" } }, "id": "GoogleCloudVideointelligenceV1_ObjectTrackingFrame", "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation": { "id": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation", "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", "type": "object", "properties": { "frames": { "description": "All video frames where explicit content was detected.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame" } }, "version": { "description": "Feature version.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame": { "properties": { "timeOffset": { "description": "The timestamp of the frame in microseconds.", "type": "string", "format": "google-duration" }, "normalizedBoundingBox": { "description": "The normalized bounding box location of this object track for the frame.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame", "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox": { "properties": { "right": { "format": "float", "description": "Right X coordinate.", "type": "number" }, "left": { "description": "Left X coordinate.", "type": "number", "format": "float" }, "top": { "description": "Top Y coordinate.", "type": "number", "format": "float" }, "bottom": { "description": "Bottom Y coordinate.", "type": "number", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox", "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].", "type": "object" }, "GoogleCloudVideointelligenceV1_NormalizedVertex": { "properties": { "x": { "format": "float", "description": "X coordinate.", "type": "number" }, "y": { "format": "float", "description": "Y coordinate.", "type": "number" } }, "id": "GoogleCloudVideointelligenceV1_NormalizedVertex", "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_DetectedLandmark": { "properties": { "name": { "description": "The name of this landmark, for example, left_hand, right_shoulder.", "type": "string" }, "point": { "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex" }, "confidence": { "description": "The confidence score of the detected landmark. Range [0, 1].", "type": "number", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_DetectedLandmark", "description": "A generic detected landmark represented by name in string format and a 2D location.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame": { "id": "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame", "description": "Video frame level annotation results for explicit content.", "type": "object", "properties": { "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string", "format": "google-duration" }, "pornographyLikelihood": { "enumDescriptions": [ "Unspecified likelihood.", "Very unlikely.", "Unlikely.", "Possible.", "Likely.", "Very likely." ], "enum": [ "LIKELIHOOD_UNSPECIFIED", "VERY_UNLIKELY", "UNLIKELY", "POSSIBLE", "LIKELY", "VERY_LIKELY" ], "description": "Likelihood of the pornography content..", "type": "string" } } }, "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation": { "id": "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation", "description": "Annotations corresponding to one tracked object.", "type": "object", "properties": { "version": { "description": "Feature version.", "type": "string" }, "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1_ObjectTrackingFrame" }, "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", "type": "array" }, "segment": { "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears.", "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" }, "trackId": { "format": "int64", "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.", "type": "string" }, "entity": { "description": "Entity to specify the object category that this track is labeled as.", "$ref": "GoogleCloudVideointelligenceV1_Entity" }, "confidence": { "description": "Object category's labeling confidence of this track.", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox": { "properties": { "left": { "format": "float", "description": "Left X coordinate.", "type": "number" }, "top": { "format": "float", "description": "Top Y coordinate.", "type": "number" }, "bottom": { "description": "Bottom Y coordinate.", "type": "number", "format": "float" }, "right": { "description": "Right X coordinate.", "type": "number", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox", "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoProgress": { "properties": { "annotationProgress": { "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress" } } }, "id": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoProgress", "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "type": "object" }, "GoogleCloudVideointelligenceV1_WordInfo": { "properties": { "endTime": { "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "type": "string", "format": "google-duration" }, "word": { "description": "The word corresponding to this set of information.", "type": "string" }, "speakerLabel": { "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.", "readOnly": true, "type": "string" }, "speakerTag": { "format": "int32", "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", "readOnly": true, "type": "integer" }, "startTime": { "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "type": "string", "format": "google-duration" }, "confidence": { "format": "float", "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "readOnly": true, "type": "number" } }, "id": "GoogleCloudVideointelligenceV1_WordInfo", "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation": { "properties": { "tracks": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_Track" }, "description": "The face tracks with attributes.", "type": "array" }, "thumbnail": { "description": "The thumbnail of a person's face.", "type": "string", "format": "byte" }, "version": { "description": "Feature version.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation", "description": "Face detection annotation.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscriptionConfig": { "id": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscriptionConfig", "description": "Config for SPEECH_TRANSCRIPTION.", "type": "object", "properties": { "speechContexts": { "description": "Optional. A means to provide context to assist the speech recognition.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechContext" } }, "enableSpeakerDiarization": { "description": "Optional. If 'true', enables speaker detection for each recognized word in the top alternative of the recognition result using a speaker_tag provided in the WordInfo. Note: When this is true, we send all the words from the beginning of the audio for the top alternative in every consecutive response. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time.", "type": "boolean" }, "enableWordConfidence": { "description": "Optional. If `true`, the top result includes a list of words and the confidence for those words. If `false`, no word-level confidence information is returned. The default is `false`.", "type": "boolean" }, "filterProfanity": { "description": "Optional. If set to `true`, the server will attempt to filter out profanities, replacing all but the initial character in each filtered word with asterisks, e.g. \"f***\". If set to `false` or omitted, profanities won't be filtered out.", "type": "boolean" }, "enableAutomaticPunctuation": { "description": "Optional. If 'true', adds punctuation to recognition result hypotheses. This feature is only available in select languages. Setting this for requests in other languages has no effect at all. The default 'false' value does not add punctuation to result hypotheses. NOTE: \"This is currently offered as an experimental service, complimentary to all users. In the future this may be exclusively available as a premium feature.\"", "type": "boolean" }, "maxAlternatives": { "description": "Optional. Maximum number of recognition hypotheses to be returned. Specifically, the maximum number of `SpeechRecognitionAlternative` messages within each `SpeechTranscription`. The server may return fewer than `max_alternatives`. Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of one. If omitted, will return a maximum of one.", "type": "integer", "format": "int32" }, "audioOutputUriPrefix": { "description": "Optional. Legacy field. This field must be a Cloud Storage URI prefix. (e.g., `gs://bucket/path/`).", "type": "string" }, "languageCode": { "description": "Required. *Required* The language of the supplied audio as a [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. Example: \"en-US\". See [Language Support](https://cloud.google.com/speech/docs/languages) for a list of the currently supported language codes.", "type": "string" }, "diarizationSpeakerCount": { "format": "int32", "description": "Optional. If set, specifies the estimated number of speakers in the conversation. If not set, defaults to '2'. Ignored unless enable_speaker_diarization is set to true.", "type": "integer" }, "audioTracks": { "items": { "type": "integer", "format": "int32" }, "description": "Optional. For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two tracks. Default: track 0.", "type": "array" } } }, "GoogleCloudVideointelligenceV1p1beta1_LabelFrame": { "properties": { "timeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string" }, "confidence": { "format": "float", "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_LabelFrame", "description": "Video frame level annotation results for label detection.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_TextSegment": { "id": "GoogleCloudVideointelligenceV1beta2_TextSegment", "description": "Video segment level annotation results for text detection.", "type": "object", "properties": { "segment": { "description": "Video segment where a text snippet was detected.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" }, "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_TextFrame" }, "description": "Information related to the frames where OCR detected text appears.", "type": "array" }, "confidence": { "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1p3beta1_StreamingVideoAnnotationResults": { "properties": { "shotAnnotations": { "description": "Shot annotation results. Each shot is represented as a video segment.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" } }, "labelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation" }, "description": "Label annotation results.", "type": "array" }, "frameTimestamp": { "format": "google-duration", "description": "Timestamp of the processed frame in microseconds.", "type": "string" }, "objectAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation" }, "description": "Object tracking results.", "type": "array" }, "explicitAnnotation": { "description": "Explicit content annotation results.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_StreamingVideoAnnotationResults", "description": "Streaming annotation results corresponding to a portion of the video that is currently being processed. Only ONE type of annotation will be specified in the response.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionAnnotation": { "id": "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionAnnotation", "description": "Face detection annotation.", "type": "object", "properties": { "tracks": { "description": "The face tracks with attributes.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_Track" } }, "thumbnail": { "format": "byte", "description": "The thumbnail of a person's face.", "type": "string" }, "version": { "description": "Feature version.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p3beta1_FaceSegment": { "id": "GoogleCloudVideointelligenceV1p3beta1_FaceSegment", "description": "Video segment level annotation results for face detection.", "type": "object", "properties": { "segment": { "description": "Video segment where a face was detected.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" } } }, "GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation": { "properties": { "entity": { "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.", "$ref": "GoogleCloudVideointelligenceV1beta2_Entity" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" }, "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.", "type": "array" }, "tracks": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_Track" }, "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation", "description": "Annotation corresponding to one detected, tracked and recognized logo class.", "type": "object" }, "GoogleCloudVideointelligenceV1_ExplicitContentFrame": { "id": "GoogleCloudVideointelligenceV1_ExplicitContentFrame", "description": "Video frame level annotation results for explicit content.", "type": "object", "properties": { "timeOffset": { "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string", "format": "google-duration" }, "pornographyLikelihood": { "description": "Likelihood of the pornography content..", "type": "string", "enumDescriptions": [ "Unspecified likelihood.", "Very unlikely.", "Unlikely.", "Possible.", "Likely.", "Very likely." ], "enum": [ "LIKELIHOOD_UNSPECIFIED", "VERY_UNLIKELY", "UNLIKELY", "POSSIBLE", "LIKELY", "VERY_LIKELY" ] } } }, "GoogleCloudVideointelligenceV1p3beta1_LogoRecognitionAnnotation": { "id": "GoogleCloudVideointelligenceV1p3beta1_LogoRecognitionAnnotation", "description": "Annotation corresponding to one detected, tracked and recognized logo class.", "type": "object", "properties": { "entity": { "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity" }, "segments": { "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" } }, "tracks": { "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track" } } } }, "GoogleCloudVideointelligenceV1beta2_ExportToOutputUriStatus": { "properties": { "status": { "description": "Output only. Only set if state is FAILED.", "readOnly": true, "$ref": "GoogleRpc_Status" }, "state": { "type": "string", "enumDescriptions": [ "Default value.", "Export succeeded.", "Export failed." ], "enum": [ "STATE_UNSPECIFIED", "SUCCEEDED", "FAILED" ], "description": "Output only. State of the `output_uri` export.", "readOnly": true } }, "id": "GoogleCloudVideointelligenceV1beta2_ExportToOutputUriStatus", "description": "Status of exporting annotation response to user specified `output_uri`.", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox": { "id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox", "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].", "type": "object", "properties": { "right": { "description": "Right X coordinate.", "type": "number", "format": "float" }, "left": { "format": "float", "description": "Left X coordinate.", "type": "number" }, "top": { "format": "float", "description": "Top Y coordinate.", "type": "number" }, "bottom": { "format": "float", "description": "Bottom Y coordinate.", "type": "number" } } }, "GoogleCloudVideointelligenceV1p3beta1_CelebrityRecognitionAnnotation": { "id": "GoogleCloudVideointelligenceV1p3beta1_CelebrityRecognitionAnnotation", "description": "Celebrity recognition annotation per video.", "type": "object", "properties": { "version": { "description": "Feature version.", "type": "string" }, "celebrityTracks": { "description": "The tracks detected from the input video, including recognized celebrities and other detected faces in the video.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_CelebrityTrack" } } } }, "GoogleCloudVideointelligenceV1_TextSegment": { "id": "GoogleCloudVideointelligenceV1_TextSegment", "description": "Video segment level annotation results for text detection.", "type": "object", "properties": { "frames": { "description": "Information related to the frames where OCR detected text appears.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_TextFrame" } }, "confidence": { "format": "float", "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", "type": "number" }, "segment": { "description": "Video segment where a text snippet was detected.", "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" } } }, "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoRequest": { "properties": { "inputUri": { "description": "Input video location. Currently, only [Cloud Storage](https://cloud.google.com/storage/) URIs are supported. URIs must be specified in the following format: `gs://bucket-id/object-id` (other URI formats return google.rpc.Code.INVALID_ARGUMENT). For more information, see [Request URIs](https://cloud.google.com/storage/docs/request-endpoints). To identify multiple videos, a video URI may include wildcards in the `object-id`. Supported wildcards: '*' to match 0 or more characters; '?' to match 1 character. If unset, the input video should be embedded in the request as `input_content`. If set, `input_content` must be unset.", "type": "string" }, "inputContent": { "description": "The video data bytes. If unset, the input video(s) should be specified via the `input_uri`. If set, `input_uri` must be unset.", "type": "string", "format": "byte" }, "locationId": { "description": "Optional. Cloud region where annotation should take place. Supported cloud regions are: `us-east1`, `us-west1`, `europe-west1`, `asia-east1`. If no region is specified, the region will be determined based on video file location.", "type": "string" }, "videoContext": { "description": "Additional video context and/or feature-specific parameters.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoContext" }, "outputUri": { "description": "Optional. Location where the output (in JSON format) should be stored. Currently, only [Cloud Storage](https://cloud.google.com/storage/) URIs are supported. These must be specified in the following format: `gs://bucket-id/object-id` (other URI formats return google.rpc.Code.INVALID_ARGUMENT). For more information, see [Request URIs](https://cloud.google.com/storage/docs/request-endpoints).", "type": "string" }, "features": { "items": { "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "PERSON_DETECTION" ], "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Person detection." ], "type": "string" }, "description": "Required. Requested video annotation features.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoRequest", "description": "Video annotation request.", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation": { "properties": { "version": { "description": "Feature version.", "type": "string" }, "frames": { "description": "All video frames where a label was detected.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelFrame" } }, "categoryEntities": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity" }, "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", "type": "array" }, "entity": { "description": "Detected entity.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelSegment" }, "description": "All video segments where a label was detected.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation", "description": "Label annotation.", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress": { "properties": { "feature": { "enumDescriptions": [ "Unspecified.", "Label detection. Detect objects, such as dog or flower.", "Shot change detection.", "Explicit content detection.", "Human face detection.", "Speech transcription.", "OCR text detection and tracking.", "Object detection and tracking.", "Logo detection, tracking, and recognition.", "Person detection." ], "enum": [ "FEATURE_UNSPECIFIED", "LABEL_DETECTION", "SHOT_CHANGE_DETECTION", "EXPLICIT_CONTENT_DETECTION", "FACE_DETECTION", "SPEECH_TRANSCRIPTION", "TEXT_DETECTION", "OBJECT_TRACKING", "LOGO_RECOGNITION", "PERSON_DETECTION" ], "description": "Specifies which feature is being tracked if the request contains more than one feature.", "type": "string" }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "updateTime": { "format": "google-datetime", "description": "Time of the most recent update.", "type": "string" }, "startTime": { "format": "google-datetime", "description": "Time when the request was received.", "type": "string" }, "progressPercent": { "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.", "type": "integer", "format": "int32" }, "segment": { "description": "Specifies which segment is being tracked if the request contains more than one segment.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" }, "exportStatus": { "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_ExportToOutputUriStatus" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress", "description": "Annotation progress for a single video.", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_TextFrame": { "id": "GoogleCloudVideointelligenceV1p2beta1_TextFrame", "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", "type": "object", "properties": { "rotatedBoundingBox": { "description": "Bounding polygon of the detected text for this frame.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly" }, "timeOffset": { "description": "Timestamp of this frame.", "type": "string", "format": "google-duration" } } }, "GoogleCloudVideointelligenceV1p1beta1_LabelDetectionConfig": { "id": "GoogleCloudVideointelligenceV1p1beta1_LabelDetectionConfig", "description": "Config for LABEL_DETECTION.", "type": "object", "properties": { "frameConfidenceThreshold": { "description": "The confidence threshold we perform filtering on the labels from frame-level detection. If not set, it is set to 0.4 by default. The valid range for this threshold is [0.1, 0.9]. Any value set outside of this range will be clipped. Note: For best results, follow the default threshold. We will update the default threshold everytime when we release a new model.", "type": "number", "format": "float" }, "labelDetectionMode": { "description": "What labels should be detected with LABEL_DETECTION, in addition to video-level labels or segment-level labels. If unspecified, defaults to `SHOT_MODE`.", "type": "string", "enumDescriptions": [ "Unspecified.", "Detect shot-level labels.", "Detect frame-level labels.", "Detect both shot-level and frame-level labels." ], "enum": [ "LABEL_DETECTION_MODE_UNSPECIFIED", "SHOT_MODE", "FRAME_MODE", "SHOT_AND_FRAME_MODE" ] }, "videoConfidenceThreshold": { "format": "float", "description": "The confidence threshold we perform filtering on the labels from video-level and shot-level detections. If not set, it's set to 0.3 by default. The valid range for this threshold is [0.1, 0.9]. Any value set outside of this range will be clipped. Note: For best results, follow the default threshold. We will update the default threshold everytime when we release a new model.", "type": "number" }, "stationaryCamera": { "description": "Whether the video has been shot from a stationary (i.e., non-moving) camera. When set to true, might improve detection accuracy for moving objects. Should be used with `SHOT_AND_FRAME_MODE` enabled.", "type": "boolean" }, "model": { "description": "Model to use for label detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".", "type": "string" } } }, "GoogleCloudVideointelligenceV1_Track": { "properties": { "confidence": { "format": "float", "description": "Optional. The confidence score of the tracked object.", "type": "number" }, "segment": { "description": "Video segment of a track.", "$ref": "GoogleCloudVideointelligenceV1_VideoSegment" }, "timestampedObjects": { "description": "The object with timestamp and attributes per frame in the track.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_TimestampedObject" } }, "attributes": { "items": { "$ref": "GoogleCloudVideointelligenceV1_DetectedAttribute" }, "description": "Optional. Attributes in the track level.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1_Track", "description": "A track of an object instance.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults": { "properties": { "frameLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" }, "description": "Label annotations on frame level. There is exactly one element for each unique label.", "type": "array" }, "logoRecognitionAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LogoRecognitionAnnotation" }, "description": "Annotations for list of logos detected, tracked and recognized in video.", "type": "array" }, "segmentLabelAnnotations": { "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" } }, "explicitAnnotation": { "description": "Explicit content annotation.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation" }, "speechTranscriptions": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription" }, "description": "Speech transcription.", "type": "array" }, "shotAnnotations": { "description": "Shot annotations. Each shot is represented as a video segment.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" } }, "textAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation" }, "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.", "type": "array" }, "error": { "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.", "$ref": "GoogleRpc_Status" }, "segmentPresenceLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" }, "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "type": "array" }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "faceDetectionAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionAnnotation" }, "description": "Face detection annotations.", "type": "array" }, "personDetectionAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionAnnotation" }, "description": "Person detection annotations.", "type": "array" }, "segment": { "description": "Video segment on which the annotation is run.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" }, "shotPresenceLabelAnnotations": { "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" } }, "faceAnnotations": { "deprecated": true, "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceAnnotation" }, "description": "Deprecated. Please use `face_detection_annotations` instead.", "type": "array" }, "objectAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation" }, "description": "Annotations for list of objects detected and tracked in video.", "type": "array" }, "shotLabelAnnotations": { "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation" } } }, "id": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults", "description": "Annotation results for a single video.", "type": "object" }, "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults": { "properties": { "frameLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" }, "description": "Label annotations on frame level. There is exactly one element for each unique label.", "type": "array" }, "logoRecognitionAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LogoRecognitionAnnotation" }, "description": "Annotations for list of logos detected, tracked and recognized in video.", "type": "array" }, "segmentLabelAnnotations": { "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" } }, "explicitAnnotation": { "description": "Explicit content annotation.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation" }, "speechTranscriptions": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription" }, "description": "Speech transcription.", "type": "array" }, "shotAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" }, "description": "Shot annotations. Each shot is represented as a video segment.", "type": "array" }, "segmentPresenceLabelAnnotations": { "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" } }, "inputUri": { "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).", "type": "string" }, "textAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation" }, "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.", "type": "array" }, "error": { "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.", "$ref": "GoogleRpc_Status" }, "faceDetectionAnnotations": { "description": "Face detection annotations.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionAnnotation" } }, "personDetectionAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionAnnotation" }, "description": "Person detection annotations.", "type": "array" }, "segment": { "description": "Video segment on which the annotation is run.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" }, "objectAnnotations": { "description": "Annotations for list of objects detected and tracked in video.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation" } }, "shotPresenceLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" }, "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.", "type": "array" }, "faceAnnotations": { "description": "Deprecated. Please use `face_detection_annotations` instead.", "type": "array", "deprecated": true, "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceAnnotation" } }, "shotLabelAnnotations": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation" }, "description": "Topical label annotations on shot level. There is exactly one element for each unique label.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults", "description": "Annotation results for a single video.", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_RecognizedCelebrity": { "id": "GoogleCloudVideointelligenceV1p3beta1_RecognizedCelebrity", "description": "The recognized celebrity with confidence score.", "type": "object", "properties": { "celebrity": { "description": "The recognized celebrity.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_Celebrity" }, "confidence": { "format": "float", "description": "Recognition confidence. Range [0, 1].", "type": "number" } } }, "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionConfig": { "properties": { "model": { "description": "Model to use for face detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".", "type": "string" }, "includeAttributes": { "description": "Whether to enable face attributes detection, such as glasses, dark_glasses, mouth_open etc. Ignored if 'include_bounding_boxes' is set to false.", "type": "boolean" }, "includeBoundingBoxes": { "description": "Whether bounding boxes are included in the face annotation output.", "type": "boolean" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionConfig", "description": "Config for FACE_DETECTION.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_FaceAnnotation": { "properties": { "segments": { "description": "All video segments where a face was detected.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceSegment" } }, "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceFrame" }, "description": "All video frames where a face was detected.", "type": "array" }, "thumbnail": { "format": "byte", "description": "Thumbnail of a representative face view (in JPEG format).", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_FaceAnnotation", "type": "object", "description": "Deprecated. No effect.", "deprecated": true }, "GoogleCloudVideointelligenceV1p1beta1_ExportToOutputUriStatus": { "id": "GoogleCloudVideointelligenceV1p1beta1_ExportToOutputUriStatus", "description": "Status of exporting annotation response to user specified `output_uri`.", "type": "object", "properties": { "state": { "enum": [ "STATE_UNSPECIFIED", "SUCCEEDED", "FAILED" ], "enumDescriptions": [ "Default value.", "Export succeeded.", "Export failed." ], "description": "Output only. State of the `output_uri` export.", "readOnly": true, "type": "string" }, "status": { "description": "Output only. Only set if state is FAILED.", "readOnly": true, "$ref": "GoogleRpc_Status" } } }, "GoogleCloudVideointelligenceV1beta2_TextFrame": { "id": "GoogleCloudVideointelligenceV1beta2_TextFrame", "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.", "type": "object", "properties": { "rotatedBoundingBox": { "description": "Bounding polygon of the detected text for this frame.", "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly" }, "timeOffset": { "description": "Timestamp of this frame.", "type": "string", "format": "google-duration" } } }, "GoogleCloudVideointelligenceV1p1beta1_TimestampedObject": { "id": "GoogleCloudVideointelligenceV1p1beta1_TimestampedObject", "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.", "type": "object", "properties": { "timeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.", "type": "string" }, "attributes": { "description": "Optional. The attributes of the object in the bounding box.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute" } }, "landmarks": { "description": "Optional. The detected landmarks.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_DetectedLandmark" } }, "normalizedBoundingBox": { "description": "Normalized Bounding box in a frame, where the object is located.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox" } } }, "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingFrame": { "properties": { "normalizedBoundingBox": { "description": "The normalized bounding box location of this object track for the frame.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox" }, "timeOffset": { "format": "google-duration", "description": "The timestamp of the frame in microseconds.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingFrame", "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingConfig": { "id": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingConfig", "description": "Config for OBJECT_TRACKING.", "type": "object", "properties": { "model": { "description": "Model to use for object tracking. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".", "type": "string" } } }, "GoogleCloudVideointelligenceV1_LabelAnnotation": { "properties": { "version": { "description": "Feature version.", "type": "string" }, "frames": { "description": "All video frames where a label was detected.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelFrame" } }, "categoryEntities": { "items": { "$ref": "GoogleCloudVideointelligenceV1_Entity" }, "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.", "type": "array" }, "entity": { "description": "Detected entity.", "$ref": "GoogleCloudVideointelligenceV1_Entity" }, "segments": { "description": "All video segments where a label was detected.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_LabelSegment" } } }, "id": "GoogleCloudVideointelligenceV1_LabelAnnotation", "description": "Label annotation.", "type": "object" }, "GoogleRpc_Status": { "id": "GoogleRpc_Status", "description": "The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors).", "type": "object", "properties": { "code": { "format": "int32", "description": "The status code, which should be an enum value of google.rpc.Code.", "type": "integer" }, "message": { "description": "A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.", "type": "string" }, "details": { "items": { "type": "object", "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." } }, "description": "A list of messages that carry the error details. There is a common set of message types for APIs to use.", "type": "array" } } }, "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation": { "properties": { "frames": { "description": "All video frames where explicit content was detected.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_ExplicitContentFrame" } }, "version": { "description": "Feature version.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation", "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation": { "properties": { "frames": { "description": "All video frames where explicit content was detected.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame" } }, "version": { "description": "Feature version.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation", "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox": { "id": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox", "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].", "type": "object", "properties": { "right": { "format": "float", "description": "Right X coordinate.", "type": "number" }, "left": { "format": "float", "description": "Left X coordinate.", "type": "number" }, "top": { "format": "float", "description": "Top Y coordinate.", "type": "number" }, "bottom": { "format": "float", "description": "Bottom Y coordinate.", "type": "number" } } }, "GoogleCloudVideointelligenceV1beta2_DetectedAttribute": { "properties": { "value": { "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.", "type": "string" }, "name": { "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.", "type": "string" }, "confidence": { "description": "Detected attribute confidence. Range [0, 1].", "type": "number", "format": "float" } }, "id": "GoogleCloudVideointelligenceV1beta2_DetectedAttribute", "description": "A generic detected attribute represented by name in string format.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionAnnotation": { "id": "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionAnnotation", "description": "Person detection annotation per video.", "type": "object", "properties": { "tracks": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_Track" }, "description": "The detected tracks of a person.", "type": "array" }, "version": { "description": "Feature version.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation": { "properties": { "frames": { "description": "All video frames where explicit content was detected.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentFrame" } }, "version": { "description": "Feature version.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation", "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_Entity": { "id": "GoogleCloudVideointelligenceV1beta2_Entity", "description": "Detected entity from video analysis.", "type": "object", "properties": { "entityId": { "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).", "type": "string" }, "description": { "description": "Textual description, e.g., `Fixed-gear bicycle`.", "type": "string" }, "languageCode": { "description": "Language code for `description` in BCP-47 format.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p1beta1_Entity": { "id": "GoogleCloudVideointelligenceV1p1beta1_Entity", "description": "Detected entity from video analysis.", "type": "object", "properties": { "languageCode": { "description": "Language code for `description` in BCP-47 format.", "type": "string" }, "description": { "description": "Textual description, e.g., `Fixed-gear bicycle`.", "type": "string" }, "entityId": { "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).", "type": "string" } } }, "GoogleCloudVideointelligenceV1p2beta1_WordInfo": { "properties": { "speakerTag": { "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", "readOnly": true, "type": "integer", "format": "int32" }, "confidence": { "format": "float", "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "readOnly": true, "type": "number" }, "startTime": { "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "type": "string", "format": "google-duration" }, "word": { "description": "The word corresponding to this set of information.", "type": "string" }, "endTime": { "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "type": "string", "format": "google-duration" }, "speakerLabel": { "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.", "readOnly": true, "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_WordInfo", "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscription": { "properties": { "alternatives": { "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_SpeechRecognitionAlternative" } }, "languageCode": { "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.", "readOnly": true, "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscription", "description": "A speech recognition result corresponding to a portion of the audio.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_VideoSegment": { "id": "GoogleCloudVideointelligenceV1beta2_VideoSegment", "description": "Video segment.", "type": "object", "properties": { "startTimeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).", "type": "string" }, "endTimeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).", "type": "string" } } }, "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription": { "properties": { "alternatives": { "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative" }, "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.", "type": "array" }, "languageCode": { "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.", "readOnly": true, "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription", "description": "A speech recognition result corresponding to a portion of the audio.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_WordInfo": { "id": "GoogleCloudVideointelligenceV1p1beta1_WordInfo", "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.", "type": "object", "properties": { "speakerLabel": { "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.", "readOnly": true, "type": "string" }, "endTime": { "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "type": "string", "format": "google-duration" }, "word": { "description": "The word corresponding to this set of information.", "type": "string" }, "startTime": { "format": "google-duration", "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "type": "string" }, "confidence": { "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "readOnly": true, "type": "number", "format": "float" }, "speakerTag": { "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", "readOnly": true, "type": "integer", "format": "int32" } } }, "GoogleCloudVideointelligenceV1p3beta1_WordInfo": { "id": "GoogleCloudVideointelligenceV1p3beta1_WordInfo", "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.", "type": "object", "properties": { "word": { "description": "The word corresponding to this set of information.", "type": "string" }, "endTime": { "format": "google-duration", "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "type": "string" }, "speakerLabel": { "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.", "readOnly": true, "type": "string" }, "speakerTag": { "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.", "readOnly": true, "type": "integer", "format": "int32" }, "confidence": { "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "readOnly": true, "type": "number", "format": "float" }, "startTime": { "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.", "type": "string", "format": "google-duration" } } }, "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute": { "id": "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute", "description": "A generic detected attribute represented by name in string format.", "type": "object", "properties": { "name": { "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document.", "type": "string" }, "confidence": { "description": "Detected attribute confidence. Range [0, 1].", "type": "number", "format": "float" }, "value": { "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.", "type": "string" } } }, "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoProgress": { "id": "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoProgress", "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", "type": "object", "properties": { "annotationProgress": { "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationProgress" }, "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.", "type": "array" } } }, "GoogleCloudVideointelligenceV1p1beta1_VideoSegment": { "id": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment", "description": "Video segment.", "type": "object", "properties": { "startTimeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).", "type": "string" }, "endTimeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).", "type": "string" } } }, "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation": { "properties": { "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame" }, "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.", "type": "array" }, "version": { "description": "Feature version.", "type": "string" }, "trackId": { "format": "int64", "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.", "type": "string" }, "entity": { "description": "Entity to specify the object category that this track is labeled as.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity" }, "confidence": { "format": "float", "description": "Object category's labeling confidence of this track.", "type": "number" }, "segment": { "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation", "description": "Annotations corresponding to one tracked object.", "type": "object" }, "GoogleCloudVideointelligenceV1p1beta1_VideoContext": { "properties": { "objectTrackingConfig": { "description": "Config for OBJECT_TRACKING.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingConfig" }, "textDetectionConfig": { "description": "Config for TEXT_DETECTION.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextDetectionConfig" }, "speechTranscriptionConfig": { "description": "Config for SPEECH_TRANSCRIPTION.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscriptionConfig" }, "personDetectionConfig": { "description": "Config for PERSON_DETECTION.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionConfig" }, "labelDetectionConfig": { "description": "Config for LABEL_DETECTION.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelDetectionConfig" }, "shotChangeDetectionConfig": { "description": "Config for SHOT_CHANGE_DETECTION.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_ShotChangeDetectionConfig" }, "segments": { "description": "Video segments to annotate. The segments may overlap and are not required to be contiguous or span the whole video. If unspecified, each video is treated as a single segment.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment" } }, "explicitContentDetectionConfig": { "description": "Config for EXPLICIT_CONTENT_DETECTION.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentDetectionConfig" }, "faceDetectionConfig": { "description": "Config for FACE_DETECTION.", "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionConfig" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_VideoContext", "description": "Video context and/or feature-specific parameters.", "type": "object" }, "GoogleLongrunning_Operation": { "id": "GoogleLongrunning_Operation", "description": "This resource represents a long-running operation that is the result of a network API call.", "type": "object", "properties": { "name": { "description": "The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.", "type": "string" }, "error": { "description": "The error result of the operation in case of failure or cancellation.", "$ref": "GoogleRpc_Status" }, "metadata": { "description": "Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.", "type": "object", "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." } }, "done": { "description": "If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.", "type": "boolean" }, "response": { "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." }, "description": "The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.", "type": "object" } } }, "GoogleCloudVideointelligenceV1beta2_LabelSegment": { "id": "GoogleCloudVideointelligenceV1beta2_LabelSegment", "description": "Video segment level annotation results for label detection.", "type": "object", "properties": { "segment": { "description": "Video segment where a label was detected.", "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment" }, "confidence": { "format": "float", "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number" } } }, "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly": { "id": "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly", "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.", "type": "object", "properties": { "vertices": { "description": "Normalized vertices of the bounding polygon.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1_NormalizedVertex" } } } }, "GoogleCloudVideointelligenceV1p2beta1_LabelSegment": { "id": "GoogleCloudVideointelligenceV1p2beta1_LabelSegment", "description": "Video segment level annotation results for label detection.", "type": "object", "properties": { "segment": { "description": "Video segment where a label was detected.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" }, "confidence": { "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1p2beta1_Track": { "id": "GoogleCloudVideointelligenceV1p2beta1_Track", "description": "A track of an object instance.", "type": "object", "properties": { "segment": { "description": "Video segment of a track.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment" }, "timestampedObjects": { "description": "The object with timestamp and attributes per frame in the track.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_TimestampedObject" } }, "attributes": { "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute" }, "description": "Optional. Attributes in the track level.", "type": "array" }, "confidence": { "description": "Optional. The confidence score of the tracked object.", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation": { "properties": { "segments": { "description": "All video segments where OCR detected text appears.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextSegment" } }, "text": { "description": "The detected text.", "type": "string" }, "version": { "description": "Feature version.", "type": "string" } }, "id": "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation", "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.", "type": "object" }, "GoogleCloudVideointelligenceV1beta2_FaceAnnotation": { "properties": { "thumbnail": { "format": "byte", "description": "Thumbnail of a representative face view (in JPEG format).", "type": "string" }, "frames": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_FaceFrame" }, "description": "All video frames where a face was detected.", "type": "array" }, "segments": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_FaceSegment" }, "description": "All video segments where a face was detected.", "type": "array" } }, "id": "GoogleCloudVideointelligenceV1beta2_FaceAnnotation", "type": "object", "description": "Deprecated. No effect.", "deprecated": true }, "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative": { "id": "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative", "description": "Alternative hypotheses (a.k.a. n-best list).", "type": "object", "properties": { "words": { "items": { "$ref": "GoogleCloudVideointelligenceV1beta2_WordInfo" }, "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.", "readOnly": true, "type": "array" }, "transcript": { "description": "Transcript text representing the words that the user spoke.", "type": "string" }, "confidence": { "format": "float", "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.", "readOnly": true, "type": "number" } } }, "GoogleCloudVideointelligenceV1p3beta1_TextSegment": { "id": "GoogleCloudVideointelligenceV1p3beta1_TextSegment", "description": "Video segment level annotation results for text detection.", "type": "object", "properties": { "segment": { "description": "Video segment where a text snippet was detected.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "frames": { "description": "Information related to the frames where OCR detected text appears.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextFrame" } }, "confidence": { "format": "float", "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.", "type": "number" } } }, "GoogleCloudVideointelligenceV1p3beta1_LabelSegment": { "id": "GoogleCloudVideointelligenceV1p3beta1_LabelSegment", "description": "Video segment level annotation results for label detection.", "type": "object", "properties": { "segment": { "description": "Video segment where a label was detected.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment" }, "confidence": { "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1p2beta1_LabelFrame": { "id": "GoogleCloudVideointelligenceV1p2beta1_LabelFrame", "description": "Video frame level annotation results for label detection.", "type": "object", "properties": { "timeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.", "type": "string" }, "confidence": { "description": "Confidence that the label is accurate. Range: [0, 1].", "type": "number", "format": "float" } } }, "GoogleCloudVideointelligenceV1p2beta1_TimestampedObject": { "properties": { "timeOffset": { "format": "google-duration", "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.", "type": "string" }, "attributes": { "description": "Optional. The attributes of the object in the bounding box.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute" } }, "landmarks": { "description": "Optional. The detected landmarks.", "type": "array", "items": { "$ref": "GoogleCloudVideointelligenceV1p2beta1_DetectedLandmark" } }, "normalizedBoundingBox": { "description": "Normalized Bounding box in a frame, where the object is located.", "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox" } }, "id": "GoogleCloudVideointelligenceV1p2beta1_TimestampedObject", "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.", "type": "object" }, "GoogleCloudVideointelligenceV1p3beta1_StreamingAnnotateVideoResponse": { "id": "GoogleCloudVideointelligenceV1p3beta1_StreamingAnnotateVideoResponse", "description": "`StreamingAnnotateVideoResponse` is the only message returned to the client by `StreamingAnnotateVideo`. A series of zero or more `StreamingAnnotateVideoResponse` messages are streamed back to the client.", "type": "object", "properties": { "annotationResults": { "description": "Streaming annotation results.", "$ref": "GoogleCloudVideointelligenceV1p3beta1_StreamingVideoAnnotationResults" }, "error": { "description": "If set, returns a google.rpc.Status message that specifies the error for the operation.", "$ref": "GoogleRpc_Status" }, "annotationResultsUri": { "description": "Google Cloud Storage URI that stores annotation results of one streaming session in JSON format. It is the annotation_result_storage_directory from the request followed by '/cloud_project_number-session_id'.", "type": "string" } } } }, "description": "Detects objects, explicit content, and scene changes in videos. It also specifies the region for annotation and transcribes speech to text. Supports both asynchronous API and streaming API.", "fullyEncodeReservedExpansion": true, "discoveryVersion": "v1", "canonicalName": "Cloud Video Intelligence", "basePath": "", "mtlsRootUrl": "https://videointelligence.mtls.googleapis.com/", "ownerName": "Google", "servicePath": "", "version": "v1p1beta1", "icons": { "x32": "http://www.google.com/images/icons/product/search-32.gif", "x16": "http://www.google.com/images/icons/product/search-16.gif" }, "batchPath": "batch", "id": "videointelligence:v1p1beta1", "ownerDomain": "google.com", "kind": "discovery#restDescription", "auth": { "oauth2": { "scopes": { "https://www.googleapis.com/auth/cloud-platform": { "description": "See, edit, configure, and delete your Google Cloud data and see the email address for your Google Account." } } } }, "rootUrl": "https://videointelligence.googleapis.com/", "title": "Cloud Video Intelligence API" }