package google.cloud.videointelligence.v1beta1

Get desktop application:
View/edit binary Protocol Buffers messages

Service that implements Google Cloud Video Intelligence API.

• rpc AnnotateVideo (AnnotateVideoRequest, longrunning.Operation)

  video_intelligence.proto:37

  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).

  message AnnotateVideoRequest

  video_intelligence.proto:43

  Video annotation request.

  • string input_uri = 1

    Input video location. Currently, only [Google Cloud Storage](https://cloud.google.com/storage/) URIs are supported, which must be specified in the following format: `gs://bucket-id/object-id` (other URI formats return [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see [Request URIs](/storage/docs/reference-uris). A video URI may include wildcards in `object-id`, and thus identify multiple videos. 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` should be unset.

  • string input_content = 6

    The video data bytes. Encoding: base64. If unset, the input video(s) should be specified via `input_uri`. If set, `input_uri` should be unset.

  • repeated Feature features = 2

    Requested video annotation features.

  • optional VideoContext video_context = 3

    Additional video context and/or feature-specific parameters.

  • string output_uri = 4

    Optional location where the output (in JSON format) should be stored. Currently, only [Google Cloud Storage](https://cloud.google.com/storage/) URIs are supported, which must be specified in the following format: `gs://bucket-id/object-id` (other URI formats return [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see [Request URIs](/storage/docs/reference-uris).

  • string location_id = 5

    Optional cloud region where annotation should take place. Supported cloud regions: `us-east1`, `us-west1`, `europe-west1`, `asia-east1`. If no region is specified, a region will be determined based on video file location.

Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.

• repeated VideoAnnotationProgress annotation_progress = 1

  Progress metadata for all videos specified in `AnnotateVideoRequest`.

Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.

• repeated VideoAnnotationResults annotation_results = 1

  Annotation results for all videos specified in `AnnotateVideoRequest`.

Bounding box.

Used in: FaceLocation

• int32 left = 1

  Left X coordinate.

• int32 right = 2

  Right X coordinate.

• int32 bottom = 3

  Bottom Y coordinate.

• int32 top = 4

  Top Y coordinate.

Face annotation.

Used in: VideoAnnotationResults

• string thumbnail = 1

  Thumbnail of a representative face view (in JPEG format). Encoding: base64.

• repeated VideoSegment segments = 2

  All locations where a face was detected. Faces are detected and tracked on a per-video basis (as opposed to across multiple videos).

• repeated FaceLocation locations = 3

  Face locations at one frame per second.

Face location.

Used in: FaceAnnotation

• optional BoundingBox bounding_box = 1

  Bounding box in a frame.

• int64 time_offset = 2

  Video time offset in microseconds.

Video annotation feature.

Used in: AnnotateVideoRequest

• FEATURE_UNSPECIFIED = 0

  Unspecified.

• LABEL_DETECTION = 1

  Label detection. Detect objects, such as dog or flower.

• FACE_DETECTION = 2

  Human face detection and tracking.

• SHOT_CHANGE_DETECTION = 3

  Shot change detection.

• SAFE_SEARCH_DETECTION = 4

  Safe search detection.

Label annotation.

Used in: VideoAnnotationResults

• string description = 1

  Textual description, e.g. `Fixed-gear bicycle`.

• string language_code = 2

  Language code for `description` in BCP-47 format.

• repeated LabelLocation locations = 3

  Where the label was detected and with what confidence.

Label detection mode.

Used in: VideoContext

• LABEL_DETECTION_MODE_UNSPECIFIED = 0

  Unspecified.

• SHOT_MODE = 1

  Detect shot-level labels.

• FRAME_MODE = 2

  Detect frame-level labels.

• SHOT_AND_FRAME_MODE = 3

  Detect both shot-level and frame-level labels.

Label level (scope).

Used in: LabelLocation

• LABEL_LEVEL_UNSPECIFIED = 0

  Unspecified.

• VIDEO_LEVEL = 1

  Video-level. Corresponds to the whole video.

• SEGMENT_LEVEL = 2

  Segment-level. Corresponds to one of `AnnotateSpec.segments`.

• SHOT_LEVEL = 3

  Shot-level. Corresponds to a single shot (i.e. a series of frames without a major camera position or background change).

• FRAME_LEVEL = 4

  Frame-level. Corresponds to a single video frame.

Label location.

Used in: LabelAnnotation

• optional VideoSegment segment = 1

  Video segment. Set to [-1, -1] for video-level labels. Set to [timestamp, timestamp] for frame-level labels. Otherwise, corresponds to one of `AnnotateSpec.segments` (if specified) or to shot boundaries (if requested).

• float confidence = 2

  Confidence that the label is accurate. Range: [0, 1].

• LabelLevel level = 3

  Label level.

Bucketized representation of likelihood.

Used in: SafeSearchAnnotation

• UNKNOWN = 0

  Unknown likelihood.

• VERY_UNLIKELY = 1

  Very unlikely.

• UNLIKELY = 2

  Unlikely.

• POSSIBLE = 3

  Possible.

• LIKELY = 4

  Likely.

• VERY_LIKELY = 5

  Very likely.

Safe search annotation (based on per-frame visual signals only). If no unsafe content has been detected in a frame, no annotations are present for that frame. If only some types of unsafe content have been detected in a frame, the likelihood is set to `UNKNOWN` for all other types of unsafe content.

Used in: VideoAnnotationResults

• Likelihood adult = 1

  Likelihood of adult content.

• Likelihood spoof = 2

  Likelihood that an obvious modification was made to the original version to make it appear funny or offensive.

• Likelihood medical = 3

  Likelihood of medical content.

• Likelihood violent = 4

  Likelihood of violent content.

• Likelihood racy = 5

  Likelihood of racy content.

• int64 time_offset = 6

  Video time offset in microseconds.

Annotation progress for a single video.

Used in: AnnotateVideoProgress

• string input_uri = 1

  Video file location in [Google Cloud Storage](https://cloud.google.com/storage/).

• int32 progress_percent = 2

  Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.

• optional protobuf.Timestamp start_time = 3

  Time when the request was received.

• optional protobuf.Timestamp update_time = 4

  Time of the most recent update.

Annotation results for a single video.

Used in: AnnotateVideoResponse

• string input_uri = 1

  Video file location in [Google Cloud Storage](https://cloud.google.com/storage/).

• repeated LabelAnnotation label_annotations = 2

  Label annotations. There is exactly one element for each unique label.

• repeated FaceAnnotation face_annotations = 3

  Face annotations. There is exactly one element for each unique face.

• repeated VideoSegment shot_annotations = 4

  Shot annotations. Each shot is represented as a video segment.

• repeated SafeSearchAnnotation safe_search_annotations = 6

  Safe search annotations.

• optional rpc.Status error = 5

  If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.

Video context and/or feature-specific parameters.

Used in: AnnotateVideoRequest

• repeated VideoSegment segments = 1

  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.

• LabelDetectionMode label_detection_mode = 2

  If label detection has been requested, what labels should be detected in addition to video-level labels or segment-level labels. If unspecified, defaults to `SHOT_MODE`.

• bool stationary_camera = 3

  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.

• string label_detection_model = 4

  Model to use for label detection. Supported values: "latest" and "stable" (the default).

• string face_detection_model = 5

  Model to use for face detection. Supported values: "latest" and "stable" (the default).

• string shot_change_detection_model = 6

  Model to use for shot change detection. Supported values: "latest" and "stable" (the default).

• string safe_search_detection_model = 7

  Model to use for safe search detection. Supported values: "latest" and "stable" (the default).

Video segment.

Used in: FaceAnnotation, LabelLocation, VideoAnnotationResults, VideoContext

• int64 start_time_offset = 1

  Start offset in microseconds (inclusive). Unset means 0.

• int64 end_time_offset = 2

  End offset in microseconds (inclusive). Unset means 0.