Recognize logos in a Cloud Storage file

import (
	"context"
	"fmt"
	"io"
	"time"

	video "cloud.google.com/go/videointelligence/apiv1"
	videopb "cloud.google.com/go/videointelligence/apiv1/videointelligencepb"
	"github.com/golang/protobuf/ptypes"
)

// logoDetectionGCS analyzes a video and extracts logos with their bounding boxes.
func logoDetectionGCS(w io.Writer, gcsURI string) error {
	// gcsURI := "gs://cloud-samples-data/video/googlework_tiny.mp4"

	ctx := context.Background()

	// Creates a client.
	client, err := video.NewClient(ctx)
	if err != nil {
		return fmt.Errorf("video.NewClient: %w", err)
	}
	defer client.Close()

	ctx, cancel := context.WithTimeout(ctx, time.Second*180)
	defer cancel()

	op, err := client.AnnotateVideo(ctx, &videopb.AnnotateVideoRequest{
		InputUri: gcsURI,
		Features: []videopb.Feature{
			videopb.Feature_LOGO_RECOGNITION,
		},
	})
	if err != nil {
		return fmt.Errorf("AnnotateVideo: %w", err)
	}

	resp, err := op.Wait(ctx)
	if err != nil {
		return fmt.Errorf("Wait: %w", err)
	}

	// Only one video was processed, so get the first result.
	result := resp.GetAnnotationResults()[0]

	// Annotations for list of logos detected, tracked and recognized in video.
	for _, annotation := range result.LogoRecognitionAnnotations {
		fmt.Fprintf(w, "Description: %q\n", annotation.Entity.GetDescription())
		// Opaque entity ID. Some IDs may be available in Google Knowledge
		// Graph Search API (https://developers.google.com/knowledge-graph/).
		if len(annotation.Entity.EntityId) > 0 {
			fmt.Fprintf(w, "\tEntity ID: %q\n", annotation.Entity.GetEntityId())
		}

		// All logo tracks where the recognized logo appears. Each track
		// corresponds to one logo instance appearing in consecutive frames.
		for _, track := range annotation.Tracks {
			// Video segment of a track.
			segment := track.GetSegment()
			start, _ := ptypes.Duration(segment.GetStartTimeOffset())
			end, _ := ptypes.Duration(segment.GetEndTimeOffset())
			fmt.Fprintf(w, "\tSegment: %v to %v\n", start, end)
			fmt.Fprintf(w, "\tConfidence: %f\n", track.GetConfidence())

			// The object with timestamp and attributes per frame in the track.
			for _, timestampedObject := range track.TimestampedObjects {
				// Normalized Bounding box in a frame, where the object is
				// located.
				box := timestampedObject.GetNormalizedBoundingBox()
				fmt.Fprintf(w, "\tBounding box position:\n")
				fmt.Fprintf(w, "\t\tleft  : %f\n", box.GetLeft())
				fmt.Fprintf(w, "\t\ttop   : %f\n", box.GetTop())
				fmt.Fprintf(w, "\t\tright : %f\n", box.GetRight())
				fmt.Fprintf(w, "\t\tbottom: %f\n", box.GetBottom())

				// Optional. The attributes of the object in the bounding box.
				for _, attribute := range timestampedObject.Attributes {
					fmt.Fprintf(w, "\t\t\tName: %q\n", attribute.GetName())
					fmt.Fprintf(w, "\t\t\tConfidence: %f\n", attribute.GetConfidence())
					fmt.Fprintf(w, "\t\t\tValue: %q\n", attribute.GetValue())
				}
			}

			// Optional. Attributes in the track level.
			for _, trackAttribute := range track.Attributes {
				fmt.Fprintf(w, "\t\tName: %q\n", trackAttribute.GetName())
				fmt.Fprintf(w, "\t\tConfidence: %f\n", trackAttribute.GetConfidence())
				fmt.Fprintf(w, "\t\tValue: %q\n", trackAttribute.GetValue())
			}
		}

		// All video segments where the recognized logo appears. There might be
		// multiple instances of the same logo class appearing in one VideoSegment.
		for _, segment := range annotation.Segments {
			start, _ := ptypes.Duration(segment.GetStartTimeOffset())
			end, _ := ptypes.Duration(segment.GetEndTimeOffset())
			fmt.Fprintf(w, "\tSegment: %v to %v\n", start, end)
		}
	}

	return nil
}

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.videointelligence.v1.AnnotateVideoProgress;
import com.google.cloud.videointelligence.v1.AnnotateVideoRequest;
import com.google.cloud.videointelligence.v1.AnnotateVideoResponse;
import com.google.cloud.videointelligence.v1.DetectedAttribute;
import com.google.cloud.videointelligence.v1.Entity;
import com.google.cloud.videointelligence.v1.Feature;
import com.google.cloud.videointelligence.v1.LogoRecognitionAnnotation;
import com.google.cloud.videointelligence.v1.NormalizedBoundingBox;
import com.google.cloud.videointelligence.v1.TimestampedObject;
import com.google.cloud.videointelligence.v1.Track;
import com.google.cloud.videointelligence.v1.VideoAnnotationResults;
import com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient;
import com.google.cloud.videointelligence.v1.VideoSegment;
import com.google.protobuf.Duration;
import java.io.IOException;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;

public class LogoDetectionGcs {

  public static void detectLogoGcs() throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String gcsUri = "gs://YOUR_BUCKET_ID/path/to/your/video.mp4";
    detectLogoGcs(gcsUri);
  }

  public static void detectLogoGcs(String inputUri)
      throws IOException, ExecutionException, InterruptedException, TimeoutException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
      // Create the request
      AnnotateVideoRequest request =
          AnnotateVideoRequest.newBuilder()
              .setInputUri(inputUri)
              .addFeatures(Feature.LOGO_RECOGNITION)
              .build();

      // asynchronously perform object tracking on videos
      OperationFuture<AnnotateVideoResponse, AnnotateVideoProgress> future =
          client.annotateVideoAsync(request);

      System.out.println("Waiting for operation to complete...");
      // The first result is retrieved because a single video was processed.
      AnnotateVideoResponse response = future.get(600, TimeUnit.SECONDS);
      VideoAnnotationResults annotationResult = response.getAnnotationResults(0);

      // Annotations for list of logos detected, tracked and recognized in video.
      for (LogoRecognitionAnnotation logoRecognitionAnnotation :
          annotationResult.getLogoRecognitionAnnotationsList()) {
        Entity entity = logoRecognitionAnnotation.getEntity();
        // Opaque entity ID. Some IDs may be available in
        // [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).
        System.out.printf("Entity Id : %s\n", entity.getEntityId());
        System.out.printf("Description : %s\n", entity.getDescription());
        // All logo tracks where the recognized logo appears. Each track corresponds to one logo
        // instance appearing in consecutive frames.
        for (Track track : logoRecognitionAnnotation.getTracksList()) {

          // Video segment of a track.
          Duration startTimeOffset = track.getSegment().getStartTimeOffset();
          System.out.printf(
              "\n\tStart Time Offset: %s.%s\n",
              startTimeOffset.getSeconds(), startTimeOffset.getNanos());
          Duration endTimeOffset = track.getSegment().getEndTimeOffset();
          System.out.printf(
              "\tEnd Time Offset: %s.%s\n", endTimeOffset.getSeconds(), endTimeOffset.getNanos());
          System.out.printf("\tConfidence: %s\n", track.getConfidence());

          // The object with timestamp and attributes per frame in the track.
          for (TimestampedObject timestampedObject : track.getTimestampedObjectsList()) {

            // Normalized Bounding box in a frame, where the object is located.
            NormalizedBoundingBox normalizedBoundingBox =
                timestampedObject.getNormalizedBoundingBox();
            System.out.printf("\n\t\tLeft: %s\n", normalizedBoundingBox.getLeft());
            System.out.printf("\t\tTop: %s\n", normalizedBoundingBox.getTop());
            System.out.printf("\t\tRight: %s\n", normalizedBoundingBox.getRight());
            System.out.printf("\t\tBottom: %s\n", normalizedBoundingBox.getBottom());

            // Optional. The attributes of the object in the bounding box.
            for (DetectedAttribute attribute : timestampedObject.getAttributesList()) {
              System.out.printf("\n\t\t\tName: %s\n", attribute.getName());
              System.out.printf("\t\t\tConfidence: %s\n", attribute.getConfidence());
              System.out.printf("\t\t\tValue: %s\n", attribute.getValue());
            }
          }

          // Optional. Attributes in the track level.
          for (DetectedAttribute trackAttribute : track.getAttributesList()) {
            System.out.printf("\n\t\tName : %s\n", trackAttribute.getName());
            System.out.printf("\t\tConfidence : %s\n", trackAttribute.getConfidence());
            System.out.printf("\t\tValue : %s\n", trackAttribute.getValue());
          }
        }

        // All video segments where the recognized logo appears. There might be multiple instances
        // of the same logo class appearing in one VideoSegment.
        for (VideoSegment segment : logoRecognitionAnnotation.getSegmentsList()) {
          System.out.printf(
              "\n\tStart Time Offset : %s.%s\n",
              segment.getStartTimeOffset().getSeconds(), segment.getStartTimeOffset().getNanos());
          System.out.printf(
              "\tEnd Time Offset : %s.%s\n",
              segment.getEndTimeOffset().getSeconds(), segment.getEndTimeOffset().getNanos());
        }
      }
    }
  }
}

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const inputUri = 'gs://cloud-samples-data/video/googlework_short.mp4';

// Imports the Google Cloud client libraries
const Video = require('@google-cloud/video-intelligence');

// Instantiates a client
const client = new Video.VideoIntelligenceServiceClient();

// Performs asynchronous video annotation for logo recognition on a file hosted in GCS.
async function detectLogoGcs() {
  // Build the request with the input uri and logo recognition feature.
  const request = {
    inputUri: inputUri,
    features: ['LOGO_RECOGNITION'],
  };

  // Make the asynchronous request
  const [operation] = await client.annotateVideo(request);

  // Wait for the results
  const [response] = await operation.promise();

  // Get the first response, since we sent only one video.
  const annotationResult = response.annotationResults[0];
  for (const logoRecognitionAnnotation of annotationResult.logoRecognitionAnnotations) {
    const entity = logoRecognitionAnnotation.entity;
    // Opaque entity ID. Some IDs may be available in
    // [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).
    console.log(`Entity Id: ${entity.entityId}`);
    console.log(`Description: ${entity.description}`);

    // All logo tracks where the recognized logo appears.
    // Each track corresponds to one logo instance appearing in consecutive frames.
    for (const track of logoRecognitionAnnotation.tracks) {
      console.log(
        `\n\tStart Time Offset: ${track.segment.startTimeOffset.seconds}.${track.segment.startTimeOffset.nanos}`
      );
      console.log(
        `\tEnd Time Offset: ${track.segment.endTimeOffset.seconds}.${track.segment.endTimeOffset.nanos}`
      );
      console.log(`\tConfidence: ${track.confidence}`);

      // The object with timestamp and attributes per frame in the track.
      for (const timestampedObject of track.timestampedObjects) {
        // Normalized Bounding box in a frame, where the object is located.
        const normalizedBoundingBox = timestampedObject.normalizedBoundingBox;
        console.log(`\n\t\tLeft: ${normalizedBoundingBox.left}`);
        console.log(`\t\tTop: ${normalizedBoundingBox.top}`);
        console.log(`\t\tRight: ${normalizedBoundingBox.right}`);
        console.log(`\t\tBottom: ${normalizedBoundingBox.bottom}`);
        // Optional. The attributes of the object in the bounding box.
        for (const attribute of timestampedObject.attributes) {
          console.log(`\n\t\t\tName: ${attribute.name}`);
          console.log(`\t\t\tConfidence: ${attribute.confidence}`);
          console.log(`\t\t\tValue: ${attribute.value}`);
        }
      }

      // Optional. Attributes in the track level.
      for (const trackAttribute of track.attributes) {
        console.log(`\n\t\tName: ${trackAttribute.name}`);
        console.log(`\t\tConfidence: ${trackAttribute.confidence}`);
        console.log(`\t\tValue: ${trackAttribute.value}`);
      }
    }

    // All video segments where the recognized logo appears.
    // There might be multiple instances of the same logo class appearing in one VideoSegment.
    for (const segment of logoRecognitionAnnotation.segments) {
      console.log(
        `\n\tStart Time Offset: ${segment.startTimeOffset.seconds}.${segment.startTimeOffset.nanos}`
      );
      console.log(
        `\tEnd Time Offset: ${segment.endTimeOffset.seconds}.${segment.endTimeOffset.nanos}`
      );
    }
  }
}

detectLogoGcs();

from google.cloud import videointelligence


def detect_logo_gcs(input_uri="gs://YOUR_BUCKET_ID/path/to/your/file.mp4"):
    client = videointelligence.VideoIntelligenceServiceClient()

    features = [videointelligence.Feature.LOGO_RECOGNITION]

    operation = client.annotate_video(
        request={"features": features, "input_uri": input_uri}
    )

    print("Waiting for operation to complete...")
    response = operation.result()

    # Get the first response, since we sent only one video.
    annotation_result = response.annotation_results[0]

    # Annotations for list of logos detected, tracked and recognized in video.
    for logo_recognition_annotation in annotation_result.logo_recognition_annotations:
        entity = logo_recognition_annotation.entity

        # Opaque entity ID. Some IDs may be available in [Google Knowledge Graph
        # Search API](https://developers.google.com/knowledge-graph/).
        print("Entity Id : {}".format(entity.entity_id))

        print("Description : {}".format(entity.description))

        # All logo tracks where the recognized logo appears. Each track corresponds
        # to one logo instance appearing in consecutive frames.
        for track in logo_recognition_annotation.tracks:
            # Video segment of a track.
            print(
                "\n\tStart Time Offset : {}.{}".format(
                    track.segment.start_time_offset.seconds,
                    track.segment.start_time_offset.microseconds * 1000,
                )
            )
            print(
                "\tEnd Time Offset : {}.{}".format(
                    track.segment.end_time_offset.seconds,
                    track.segment.end_time_offset.microseconds * 1000,
                )
            )
            print("\tConfidence : {}".format(track.confidence))

            # The object with timestamp and attributes per frame in the track.
            for timestamped_object in track.timestamped_objects:
                # Normalized Bounding box in a frame, where the object is located.
                normalized_bounding_box = timestamped_object.normalized_bounding_box
                print("\n\t\tLeft : {}".format(normalized_bounding_box.left))
                print("\t\tTop : {}".format(normalized_bounding_box.top))
                print("\t\tRight : {}".format(normalized_bounding_box.right))
                print("\t\tBottom : {}".format(normalized_bounding_box.bottom))

                # Optional. The attributes of the object in the bounding box.
                for attribute in timestamped_object.attributes:
                    print("\n\t\t\tName : {}".format(attribute.name))
                    print("\t\t\tConfidence : {}".format(attribute.confidence))
                    print("\t\t\tValue : {}".format(attribute.value))

            # Optional. Attributes in the track level.
            for track_attribute in track.attributes:
                print("\n\t\tName : {}".format(track_attribute.name))
                print("\t\tConfidence : {}".format(track_attribute.confidence))
                print("\t\tValue : {}".format(track_attribute.value))

        # All video segments where the recognized logo appears. There might be
        # multiple instances of the same logo class appearing in one VideoSegment.
        for segment in logo_recognition_annotation.segments:
            print(
                "\n\tStart Time Offset : {}.{}".format(
                    segment.start_time_offset.seconds,
                    segment.start_time_offset.microseconds * 1000,
                )
            )
            print(
                "\tEnd Time Offset : {}.{}".format(
                    segment.end_time_offset.seconds,
                    segment.end_time_offset.microseconds * 1000,
                )
            )