Class VideoObjectTrackingPredictionResult (0.1.1)

VideoObjectTrackingPredictionResult(
    mapping=None, *, ignore_unknown_fields=False, **kwargs
)

Prediction output format for Video Object Tracking.

Attributes

Name Description
segment_start_time google.protobuf.timestamp_pb2.Timestamp
The beginning, inclusive, of the video's time segment in which the current identifications happens.
segment_end_time google.protobuf.timestamp_pb2.Timestamp
The end, inclusive, of the video's time segment in which the current identifications happen. Particularly, if the end is the same as the start, it means the identifications happen on a specific video frame.
objects MutableSequence[google.cloud.visionai_v1.types.VideoObjectTrackingPredictionResult.DetectedObject]
All of the objects detected in the specified time range.

Classes

BoundingBox

BoundingBox(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Boundingbox for detected object. I.e. the rectangle over the video frame pinpointing the found AnnotationSpec. The coordinates are relative to the frame size, and the point 0,0 is in the top left of the frame.

DetectedObject

DetectedObject(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Each DetectedObject is one particular identification of an object specified with the AnnotationSpec id and display_name, the bounding box, the associated confidence score and the corresponding track_id.