Google Cloud Video Intelligence

import os
from google.cloud import videointelligence_v1 as videointelligence

# Set GOOGLE_APPLICATION_CREDENTIALS environment variable or ensure gcloud is authenticated.
# For local development, run `gcloud auth application-default login`.
# os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = 'path/to/your/key.json'

def analyze_video_labels(gcs_uri):
    """Detects labels in the video specified by the GCS URI."""
    client = videointelligence.VideoIntelligenceServiceClient()
    features = [videointelligence.Feature.LABEL_DETECTION]

    # Optional: Configure label detection mode for more granular control
    config = videointelligence.LabelDetectionConfig(
        label_detection_mode=videointelligence.LabelDetectionMode.SHOT_AND_FRAME_MODE,
        stationary_camera=False # Set to True if analyzing footage from a stationary camera
    )
    video_context = videointelligence.VideoContext(label_detection_config=config)

    print(f'Processing video for label annotations: {gcs_uri}')
    operation = client.annotate_video(
        request={
            "input_uri": gcs_uri,
            "features": features,
            "video_context": video_context
        }
    )

    # Long-running operations must be waited for.
    print('\nWaiting for operation to complete...')
    result = operation.result(timeout=600)  # Adjust timeout as needed (in seconds)

    print('\nFinished processing.')
    # First result is retrieved because a single video is processed
    annotation_result = result.annotation_results[0]

    for i, shot_label in enumerate(annotation_result.shot_label_annotations):
        print(f'Video shot label: {shot_label.entity.description} ({shot_label.entity.entity_id})')
        for segment in shot_label.segments:
            start_time = (segment.segment.start_time_offset.seconds + 
                          segment.segment.start_time_offset.nanos / 1e9)
            end_time = (segment.segment.end_time_offset.seconds + 
                        segment.segment.end_time_offset.nanos / 1e9)
            print(f'\tSegment: {start_time:.1f}s to {end_time:.1f}s (confidence: {segment.confidence:.2f})')

    for i, frame_label in enumerate(annotation_result.frame_label_annotations):
        print(f'Video frame label: {frame_label.entity.description} ({frame_label.entity.entity_id})')
        for frame in frame_label.frames:
            time_offset = (frame.time_offset.seconds + 
                           frame.time_offset.nanos / 1e9)
            print(f'\tFrame: {time_offset:.1f}s (confidence: {frame.confidence:.2f})')

if __name__ == '__main__':
    # Replace with your GCS video URI
    # Public sample video from Google Cloud documentation
    video_uri = "gs://cloud-samples-data/video/chicago.mp4"
    analyze_video_labels(video_uri)