I know how to trigger a video intelligence request for object tracking / object detection with Google Cloud as following :
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.enums.Feature.OBJECT_TRACKING]
operation = video_client.annotate_video(gs_video_path, features=features)
How can I trigger the same function for brand detection, scene detection, OCR, speech recognition and celebrity recognition ?
To trigger the same function for brand detection (LOGO_RECOGNITION?), scene detection (SHOT_CHANGE_DETECTION?), TEXT_DETECTION and SPEECH_TRANSCRIPTION, you can replace OBJECT_TRACKING by, respectively, LOGO_RECOGNITION, SHOT_CHANGE_DETECTION, TEXT_DETECTION or SPEECH_TRANSCRIPTION.
Reference:
Available client libraries (For example, Python for the v1p3beta1)
Celebrity recognition is a restricted access feature. It is intended for use by media & entertainment companies or their approved partners on professionally-produced media.
You can find more details in the Celebrity recognition documentation on how to request access.
