By default, the Video Intelligence API examines a video, or video segments, by frame.
That is, each complete picture in the series that forms the video is examined.
You can also have Video Intelligence annotate a video, or video segment,
according to each shot that it detects in the input video.

*Shot change detection* annotates a video with video segments that are generated
when detecting abrupt shot changes in the video. In the output annotation, the
beginning frame of each video segment indicates an abrupt shot change (i.e.,
the frames before and after that frame are visually different).

To detect shot changes in a video, call the
[`annotate`](https://docs.cloud.google.com/video-intelligence/docs/reference/rest/v1/videos/annotate.md.txt)
method and specify
[`SHOT_CHANGE_DETECTION`](https://docs.cloud.google.com/video-intelligence/docs/reference/rest/v1/videos.md.txt#Feature)
in the `features` field.

Check out the [Video Intelligence API visualizer](https://zackakil.github.io/video-intelligence-api-visualiser/#Shot%20Detection) to see this feature in action.

For examples, see
[Analyzing Videos for Shot Changes](https://docs.cloud.google.com/video-intelligence/docs/analyze-shots.md.txt) and
the [Shot Change Detection Tutorial](https://docs.cloud.google.com/video-intelligence/docs/shot_detection).