Detecting shot changes

Shot change analysis detects shot changes in a video.

This section demonstrates a few ways to analyze a video for shot changes.

Here is an example of performing video analysis for shot changes on a file located in Google Cloud Storage.

Looking for something more in-depth? Check out our detailed Python tutorial.

REST & CMD LINE

Send video annotation request

The following shows how to send a POST request to the videos:annotate method. The example uses the access token for a service account set up for the project using the Cloud SDK. For instructions on installing the Cloud SDK, setting up a project with a service account, and obtaining an access token, see the Video Intelligence API Quickstart.

Before using any of the request data below, make the following replacements:

  • input-uri: a Cloud Storage bucket that contains the file you want to annotate, including the file name. Must start with gs://.

HTTP method and URL: 

POST https://videointelligence.googleapis.com/v1/videos:annotate

Request JSON body: 

{
    "inputUri": "input-uri",
    "features": ["SHOT_CHANGE_DETECTION"]
}

To send your request, expand one of these options:

You should receive a JSON response similar to the following:

If the response is successful, the Video Intelligence API returns the name for your operation. The above shows an example of such a response, where project-name is the name of your project and operation-id is the ID of the long running operation created for the request.

  • project-number: the number of your project
  • location-id: the Cloud region where annotation should take place. Supported cloud regions are: us-east1, us-west1, europe-west1, asia-east1. If no region is specified, a region will be determined based on video file location.
  • operation-id: the ID of the long running operation created for the request and provided in the response when you started the operation, for example 12345....

Get annotation results

To retrieve the result of the operation, make a GET request, using the operation name returned from the call to videos:annotate, as shown in the following example.

Before using any of the request data below, make the following replacements:

  • operation-name: the name of the operation as returned by Video Intelligence API. The operation name has the format projects/project-number/locations/location-id/operations/operation-id

HTTP method and URL: 

GET https://videointelligence.googleapis.com/v1/operation-name

To send your request, expand one of these options:

You should receive a JSON response similar to the following:

Shot detection annotations are returned as a shotAnnotations list. Note: The done field is only returned when its value is True. It's not included in responses for which the operation has not completed.

C#

public static object AnalyzeShotsGcs(string uri)
{
    var client = VideoIntelligenceServiceClient.Create();
    var request = new AnnotateVideoRequest()
    {
        InputUri = uri,
        Features = { Feature.ShotChangeDetection }
    };
    var op = client.AnnotateVideo(request).PollUntilCompleted();
    foreach (var result in op.Result.AnnotationResults)
    {
        foreach (var annotation in result.ShotAnnotations)
        {
            Console.Out.WriteLine("Start Time Offset: {0}\tEnd Time Offset: {1}",
                annotation.StartTimeOffset, annotation.EndTimeOffset);
        }
    }
    return 0;
}

Go


func shotChangeURI(w io.Writer, file string) error {
	ctx := context.Background()
	client, err := video.NewClient(ctx)
	if err != nil {
		return err
	}

	op, err := client.AnnotateVideo(ctx, &videopb.AnnotateVideoRequest{
		Features: []videopb.Feature{
			videopb.Feature_SHOT_CHANGE_DETECTION,
		},
		InputUri: file,
	})
	if err != nil {
		return err
	}
	resp, err := op.Wait(ctx)
	if err != nil {
		return err
	}

	// A single video was processed. Get the first result.
	result := resp.AnnotationResults[0].ShotAnnotations

	for _, shot := range result {
		start, _ := ptypes.Duration(shot.StartTimeOffset)
		end, _ := ptypes.Duration(shot.EndTimeOffset)

		fmt.Fprintf(w, "Shot: %s to %s\n", start, end)
	}

	return nil
}

Java

// Instantiate a com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient
try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
  // Provide path to file hosted on GCS as "gs://bucket-name/..."
  AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder()
      .setInputUri(gcsUri)
      .addFeatures(Feature.SHOT_CHANGE_DETECTION)
      .build();

  // Create an operation that will contain the response when the operation completes.
  OperationFuture<AnnotateVideoResponse, AnnotateVideoProgress> response =
      client.annotateVideoAsync(request);

  System.out.println("Waiting for operation to complete...");
  // Print detected shot changes and their location ranges in the analyzed video.
  for (VideoAnnotationResults result : response.get().getAnnotationResultsList()) {
    if (result.getShotAnnotationsCount() > 0) {
      System.out.println("Shots: ");
      for (VideoSegment segment : result.getShotAnnotationsList()) {
        double startTime = segment.getStartTimeOffset().getSeconds()
            + segment.getStartTimeOffset().getNanos() / 1e9;
        double endTime = segment.getEndTimeOffset().getSeconds()
            + segment.getEndTimeOffset().getNanos() / 1e9;
        System.out.printf("Location: %.3f:%.3f\n", startTime, endTime);
      }
    } else {
      System.out.println("No shot changes detected in " + gcsUri);
    }
  }
}

Node.js

// Imports the Google Cloud Video Intelligence library
const video = require('@google-cloud/video-intelligence').v1;

// Creates a client
const client = new video.VideoIntelligenceServiceClient();

/**
 * TODO(developer): Uncomment the following line before running the sample.
 */
// const gcsUri = 'GCS URI of file to analyze, e.g. gs://my-bucket/my-video.mp4';

const request = {
  inputUri: gcsUri,
  features: ['SHOT_CHANGE_DETECTION'],
};

// Detects camera shot changes
const [operation] = await client.annotateVideo(request);
console.log('Waiting for operation to complete...');
const [operationResult] = await operation.promise();
// Gets shot changes
const shotChanges = operationResult.annotationResults[0].shotAnnotations;
console.log('Shot changes:');

if (shotChanges.length === 1) {
  console.log('The entire video is one shot.');
} else {
  shotChanges.forEach((shot, shotIdx) => {
    console.log(`Scene ${shotIdx} occurs from:`);
    if (shot.startTimeOffset === undefined) {
      shot.startTimeOffset = {};
    }
    if (shot.endTimeOffset === undefined) {
      shot.endTimeOffset = {};
    }
    if (shot.startTimeOffset.seconds === undefined) {
      shot.startTimeOffset.seconds = 0;
    }
    if (shot.startTimeOffset.nanos === undefined) {
      shot.startTimeOffset.nanos = 0;
    }
    if (shot.endTimeOffset.seconds === undefined) {
      shot.endTimeOffset.seconds = 0;
    }
    if (shot.endTimeOffset.nanos === undefined) {
      shot.endTimeOffset.nanos = 0;
    }
    console.log(
      `\tStart: ${shot.startTimeOffset.seconds}` +
        `.${(shot.startTimeOffset.nanos / 1e6).toFixed(0)}s`
    );
    console.log(
      `\tEnd: ${shot.endTimeOffset.seconds}.` +
        `${(shot.endTimeOffset.nanos / 1e6).toFixed(0)}s`
    );
  });
}

Python

For more information on installing and using the Cloud Video Intelligence API Client Library for Python, refer to Cloud Video Intelligence API Client Libraries. 
""" Detects camera shot changes. """
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.enums.Feature.SHOT_CHANGE_DETECTION]
operation = video_client.annotate_video(input_uri=path, features=features)
print("\nProcessing video for shot change annotations:")

result = operation.result(timeout=90)
print("\nFinished processing.")

# first result is retrieved because a single video was processed
for i, shot in enumerate(result.annotation_results[0].shot_annotations):
    start_time = shot.start_time_offset.seconds + shot.start_time_offset.nanos / 1e9
    end_time = shot.end_time_offset.seconds + shot.end_time_offset.nanos / 1e9
    print("\tShot {}: {} to {}".format(i, start_time, end_time))

PHP

use Google\Cloud\VideoIntelligence\V1\VideoIntelligenceServiceClient;
use Google\Cloud\VideoIntelligence\V1\Feature;

/** Uncomment and populate these variables in your code */
// $uri = 'The cloud storage object to analyze (gs://your-bucket-name/your-object-name)';
// $options = [];

# Instantiate a client.
$video = new VideoIntelligenceServiceClient();

# Execute a request.
$operation = $video->annotateVideo([
    'inputUri' => $uri,
    'features' => [Feature::SHOT_CHANGE_DETECTION]
]);

# Wait for the request to complete.
$operation->pollUntilComplete($options);

# Print the result.
if ($operation->operationSucceeded()) {
    $results = $operation->getResult()->getAnnotationResults()[0];
    foreach ($results->getShotAnnotations() as $shot) {
        $start = $shot->getStartTimeOffset();
        $end = $shot->getEndTimeOffset();
        printf('Shot: %ss to %ss' . PHP_EOL,
            $start->getSeconds() + $start->getNanos()/1000000000.0,
            $end->getSeconds() + $end->getNanos()/1000000000.0);
    }
} else {
    print_r($operation->getError());
}

Ruby

# path = "Path to a video file on Google Cloud Storage: gs://bucket/video.mp4"

require "google/cloud/video_intelligence"

video = Google::Cloud::VideoIntelligence.video_intelligence_service

# Register a callback during the method call
operation = video.annotate_video features: [:SHOT_CHANGE_DETECTION], input_uri: path

puts "Processing video for shot change annotations:"
operation.wait_until_done!

raise operation.results.message? if operation.error?
puts "Finished processing."

# first result is retrieved because a single video was processed
annotation_result = operation.results.annotation_results.first
print_annotations annotation_result