Search in sources :

Example 1 with AnnotateVideoRequest

use of com.google.cloud.videointelligence.v1p1beta1.AnnotateVideoRequest in project java-docs-samples by GoogleCloudPlatform.

the class Detect method analyzeFacesBoundingBoxes.

// [START video_face_bounding_boxes]
/**
 * Detects faces' bounding boxes on the video at the provided Cloud Storage path.
 *
 * @param gcsUri the path to the video file to analyze.
 */
public static void analyzeFacesBoundingBoxes(String gcsUri) throws Exception {
    // Instantiate a com.google.cloud.videointelligence.v1p1beta1.VideoIntelligenceServiceClient
    try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
        // Set the configuration to include bounding boxes
        FaceConfig config = FaceConfig.newBuilder().setIncludeBoundingBoxes(true).build();
        // Set the video context with the above configuration
        VideoContext context = VideoContext.newBuilder().setFaceDetectionConfig(config).build();
        // Create the request
        AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputUri(gcsUri).addFeatures(Feature.FACE_DETECTION).setVideoContext(context).build();
        // asynchronously perform facial analysis on videos
        OperationFuture<AnnotateVideoResponse, AnnotateVideoProgress> response = client.annotateVideoAsync(request);
        System.out.println("Waiting for operation to complete...");
        boolean faceFound = false;
        // Display the results
        for (VideoAnnotationResults results : response.get(900, TimeUnit.SECONDS).getAnnotationResultsList()) {
            int faceCount = 0;
            // Display the results for each face
            for (FaceDetectionAnnotation faceAnnotation : results.getFaceDetectionAnnotationsList()) {
                faceFound = true;
                System.out.println("\nFace: " + ++faceCount);
                // Each FaceDetectionAnnotation has only one segment.
                for (FaceSegment segment : faceAnnotation.getSegmentsList()) {
                    double startTime = segment.getSegment().getStartTimeOffset().getSeconds() + segment.getSegment().getStartTimeOffset().getNanos() / 1e9;
                    double endTime = segment.getSegment().getEndTimeOffset().getSeconds() + segment.getSegment().getEndTimeOffset().getNanos() / 1e9;
                    System.out.printf("Segment location: %.3fs to %.3f\n", startTime, endTime);
                }
                // There are typically many frames for each face,
                try {
                    // Here we process only the first frame.
                    if (faceAnnotation.getFramesCount() > 0) {
                        // get the first frame
                        FaceDetectionFrame frame = faceAnnotation.getFrames(0);
                        double timeOffset = frame.getTimeOffset().getSeconds() + frame.getTimeOffset().getNanos() / 1e9;
                        System.out.printf("First frame time offset: %.3fs\n", timeOffset);
                        // print info on the first normalized bounding box
                        NormalizedBoundingBox box = frame.getAttributes(0).getNormalizedBoundingBox();
                        System.out.printf("\tLeft: %.3f\n", box.getLeft());
                        System.out.printf("\tTop: %.3f\n", box.getTop());
                        System.out.printf("\tBottom: %.3f\n", box.getBottom());
                        System.out.printf("\tRight: %.3f\n", box.getRight());
                    } else {
                        System.out.println("No frames found in annotation");
                    }
                } catch (IndexOutOfBoundsException ioe) {
                    System.out.println("Could not retrieve frame: " + ioe.getMessage());
                }
            }
        }
        if (!faceFound) {
            System.out.println("No faces detected in " + gcsUri);
        }
    }
}
Also used : FaceDetectionAnnotation(com.google.cloud.videointelligence.v1p1beta1.FaceDetectionAnnotation) AnnotateVideoRequest(com.google.cloud.videointelligence.v1p1beta1.AnnotateVideoRequest) VideoContext(com.google.cloud.videointelligence.v1p1beta1.VideoContext) FaceDetectionFrame(com.google.cloud.videointelligence.v1p1beta1.FaceDetectionFrame) FaceConfig(com.google.cloud.videointelligence.v1p1beta1.FaceConfig) VideoIntelligenceServiceClient(com.google.cloud.videointelligence.v1p1beta1.VideoIntelligenceServiceClient) AnnotateVideoProgress(com.google.cloud.videointelligence.v1p1beta1.AnnotateVideoProgress) FaceSegment(com.google.cloud.videointelligence.v1p1beta1.FaceSegment) NormalizedBoundingBox(com.google.cloud.videointelligence.v1p1beta1.NormalizedBoundingBox) VideoAnnotationResults(com.google.cloud.videointelligence.v1p1beta1.VideoAnnotationResults) AnnotateVideoResponse(com.google.cloud.videointelligence.v1p1beta1.AnnotateVideoResponse)

Example 2 with AnnotateVideoRequest

use of com.google.cloud.videointelligence.v1p1beta1.AnnotateVideoRequest in project java-docs-samples by GoogleCloudPlatform.

the class Detect method analyzeLabels.

/**
 * Performs label analysis on the video at the provided Cloud Storage path.
 *
 * @param gcsUri the path to the video file to analyze.
 */
public static void analyzeLabels(String gcsUri) throws Exception {
    // 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.LABEL_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...");
        for (VideoAnnotationResults results : response.get().getAnnotationResultsList()) {
            // process video / segment level label annotations
            System.out.println("Locations: ");
            for (LabelAnnotation labelAnnotation : results.getSegmentLabelAnnotationsList()) {
                System.out.println("Video label: " + labelAnnotation.getEntity().getDescription());
                // categories
                for (Entity categoryEntity : labelAnnotation.getCategoryEntitiesList()) {
                    System.out.println("Video label category: " + categoryEntity.getDescription());
                }
                // segments
                for (LabelSegment segment : labelAnnotation.getSegmentsList()) {
                    double startTime = segment.getSegment().getStartTimeOffset().getSeconds() + segment.getSegment().getStartTimeOffset().getNanos() / 1e9;
                    double endTime = segment.getSegment().getEndTimeOffset().getSeconds() + segment.getSegment().getEndTimeOffset().getNanos() / 1e9;
                    System.out.printf("Segment location: %.3f:%.3f\n", startTime, endTime);
                    System.out.println("Confidence: " + segment.getConfidence());
                }
            }
            // process shot label annotations
            for (LabelAnnotation labelAnnotation : results.getShotLabelAnnotationsList()) {
                System.out.println("Shot label: " + labelAnnotation.getEntity().getDescription());
                // categories
                for (Entity categoryEntity : labelAnnotation.getCategoryEntitiesList()) {
                    System.out.println("Shot label category: " + categoryEntity.getDescription());
                }
                // segments
                for (LabelSegment segment : labelAnnotation.getSegmentsList()) {
                    double startTime = segment.getSegment().getStartTimeOffset().getSeconds() + segment.getSegment().getStartTimeOffset().getNanos() / 1e9;
                    double endTime = segment.getSegment().getEndTimeOffset().getSeconds() + segment.getSegment().getEndTimeOffset().getNanos() / 1e9;
                    System.out.printf("Segment location: %.3f:%.3f\n", startTime, endTime);
                    System.out.println("Confidence: " + segment.getConfidence());
                }
            }
            // process frame label annotations
            for (LabelAnnotation labelAnnotation : results.getFrameLabelAnnotationsList()) {
                System.out.println("Frame label: " + labelAnnotation.getEntity().getDescription());
                // categories
                for (Entity categoryEntity : labelAnnotation.getCategoryEntitiesList()) {
                    System.out.println("Frame label category: " + categoryEntity.getDescription());
                }
                // segments
                for (LabelSegment segment : labelAnnotation.getSegmentsList()) {
                    double startTime = segment.getSegment().getStartTimeOffset().getSeconds() + segment.getSegment().getStartTimeOffset().getNanos() / 1e9;
                    double endTime = segment.getSegment().getEndTimeOffset().getSeconds() + segment.getSegment().getEndTimeOffset().getNanos() / 1e9;
                    System.out.printf("Segment location: %.3f:%.2f\n", startTime, endTime);
                    System.out.println("Confidence: " + segment.getConfidence());
                }
            }
        }
    }
// [END detect_labels_gcs]
}
Also used : VideoIntelligenceServiceClient(com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient) AnnotateVideoProgress(com.google.cloud.videointelligence.v1.AnnotateVideoProgress) Entity(com.google.cloud.videointelligence.v1.Entity) LabelSegment(com.google.cloud.videointelligence.v1.LabelSegment) AnnotateVideoRequest(com.google.cloud.videointelligence.v1.AnnotateVideoRequest) VideoAnnotationResults(com.google.cloud.videointelligence.v1.VideoAnnotationResults) LabelAnnotation(com.google.cloud.videointelligence.v1.LabelAnnotation) AnnotateVideoResponse(com.google.cloud.videointelligence.v1.AnnotateVideoResponse)

Example 3 with AnnotateVideoRequest

use of com.google.cloud.videointelligence.v1p1beta1.AnnotateVideoRequest in project java-docs-samples by GoogleCloudPlatform.

the class QuickstartSample method main.

/**
 * Demonstrates using the video intelligence client to detect labels in a video file.
 */
public static void main(String[] args) throws Exception {
    // Instantiate a video intelligence client
    try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
        // The Google Cloud Storage path to the video to annotate.
        String gcsUri = "gs://demomaker/cat.mp4";
        // Create an operation that will contain the response when the operation completes.
        AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputUri(gcsUri).addFeatures(Feature.LABEL_DETECTION).build();
        OperationFuture<AnnotateVideoResponse, AnnotateVideoProgress> response = client.annotateVideoAsync(request);
        System.out.println("Waiting for operation to complete...");
        List<VideoAnnotationResults> results = response.get().getAnnotationResultsList();
        if (results.isEmpty()) {
            System.out.println("No labels detected in " + gcsUri);
            return;
        }
        for (VideoAnnotationResults result : results) {
            System.out.println("Labels:");
            // get video segment label annotations
            for (LabelAnnotation annotation : result.getSegmentLabelAnnotationsList()) {
                System.out.println("Video label description : " + annotation.getEntity().getDescription());
                // categories
                for (Entity categoryEntity : annotation.getCategoryEntitiesList()) {
                    System.out.println("Label Category description : " + categoryEntity.getDescription());
                }
                // segments
                for (LabelSegment segment : annotation.getSegmentsList()) {
                    double startTime = segment.getSegment().getStartTimeOffset().getSeconds() + segment.getSegment().getStartTimeOffset().getNanos() / 1e9;
                    double endTime = segment.getSegment().getEndTimeOffset().getSeconds() + segment.getSegment().getEndTimeOffset().getNanos() / 1e9;
                    System.out.printf("Segment location : %.3f:%.3f\n", startTime, endTime);
                    System.out.println("Confidence : " + segment.getConfidence());
                }
            }
        }
    }
}
Also used : VideoIntelligenceServiceClient(com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient) AnnotateVideoProgress(com.google.cloud.videointelligence.v1.AnnotateVideoProgress) Entity(com.google.cloud.videointelligence.v1.Entity) LabelSegment(com.google.cloud.videointelligence.v1.LabelSegment) AnnotateVideoRequest(com.google.cloud.videointelligence.v1.AnnotateVideoRequest) VideoAnnotationResults(com.google.cloud.videointelligence.v1.VideoAnnotationResults) LabelAnnotation(com.google.cloud.videointelligence.v1.LabelAnnotation) AnnotateVideoResponse(com.google.cloud.videointelligence.v1.AnnotateVideoResponse)

Example 4 with AnnotateVideoRequest

use of com.google.cloud.videointelligence.v1p1beta1.AnnotateVideoRequest in project google-cloud-java by GoogleCloudPlatform.

the class VideoIntelligenceServiceClientTest method annotateVideoTest.

@Test
@SuppressWarnings("all")
public void annotateVideoTest() throws Exception {
    AnnotateVideoResponse expectedResponse = AnnotateVideoResponse.newBuilder().build();
    Operation resultOperation = Operation.newBuilder().setName("annotateVideoTest").setDone(true).setResponse(Any.pack(expectedResponse)).build();
    mockVideoIntelligenceService.addResponse(resultOperation);
    String inputUri = "inputUri1707300727";
    List<Feature> features = new ArrayList<>();
    VideoContext videoContext = VideoContext.newBuilder().build();
    String outputUri = "outputUri-1273518802";
    String locationId = "locationId552319461";
    AnnotateVideoResponse actualResponse = client.annotateVideoAsync(inputUri, features, videoContext, outputUri, locationId).get();
    Assert.assertEquals(expectedResponse, actualResponse);
    List<GeneratedMessageV3> actualRequests = mockVideoIntelligenceService.getRequests();
    Assert.assertEquals(1, actualRequests.size());
    AnnotateVideoRequest actualRequest = (AnnotateVideoRequest) actualRequests.get(0);
    Assert.assertEquals(inputUri, actualRequest.getInputUri());
    Assert.assertEquals(features, actualRequest.getFeaturesList());
    Assert.assertEquals(videoContext, actualRequest.getVideoContext());
    Assert.assertEquals(outputUri, actualRequest.getOutputUri());
    Assert.assertEquals(locationId, actualRequest.getLocationId());
}
Also used : AnnotateVideoRequest(com.google.cloud.videointelligence.v1beta1.AnnotateVideoRequest) ArrayList(java.util.ArrayList) VideoContext(com.google.cloud.videointelligence.v1beta1.VideoContext) Operation(com.google.longrunning.Operation) Feature(com.google.cloud.videointelligence.v1beta1.Feature) GeneratedMessageV3(com.google.protobuf.GeneratedMessageV3) AnnotateVideoResponse(com.google.cloud.videointelligence.v1beta1.AnnotateVideoResponse) Test(org.junit.Test)

Example 5 with AnnotateVideoRequest

use of com.google.cloud.videointelligence.v1p1beta1.AnnotateVideoRequest in project java-docs-samples by GoogleCloudPlatform.

the class Detect method analyzeFaceEmotions.

// [END video_face_bounding_boxes]
// [START video_face_emotions]
/**
 * Analyze faces' emotions over frames on the video at the provided Cloud Storage path.
 *
 * @param gcsUri the path to the video file to analyze.
 */
public static void analyzeFaceEmotions(String gcsUri) throws Exception {
    // Instantiate a com.google.cloud.videointelligence.v1p1beta1.VideoIntelligenceServiceClient
    try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
        // Set the configuration to include bounding boxes
        FaceConfig config = FaceConfig.newBuilder().setIncludeEmotions(true).build();
        // Set the video context with the above configuration
        VideoContext context = VideoContext.newBuilder().setFaceDetectionConfig(config).build();
        // Create the request
        AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputUri(gcsUri).addFeatures(Feature.FACE_DETECTION).setVideoContext(context).build();
        // asynchronously perform facial analysis on videos
        OperationFuture<AnnotateVideoResponse, AnnotateVideoProgress> response = client.annotateVideoAsync(request);
        System.out.println("Waiting for operation to complete...");
        boolean faceFound = false;
        // Display the results
        for (VideoAnnotationResults results : response.get(600, TimeUnit.SECONDS).getAnnotationResultsList()) {
            int faceCount = 0;
            // Display the results for each face
            for (FaceDetectionAnnotation faceAnnotation : results.getFaceDetectionAnnotationsList()) {
                faceFound = true;
                System.out.println("\nFace: " + ++faceCount);
                // Each FaceDetectionAnnotation has only one segment.
                for (FaceSegment segment : faceAnnotation.getSegmentsList()) {
                    double startTime = segment.getSegment().getStartTimeOffset().getSeconds() + segment.getSegment().getStartTimeOffset().getNanos() / 1e9;
                    double endTime = segment.getSegment().getEndTimeOffset().getSeconds() + segment.getSegment().getEndTimeOffset().getNanos() / 1e9;
                    System.out.printf("Segment location: %.3fs to %.3f\n", startTime, endTime);
                }
                try {
                    // Print each frame's highest emotion
                    for (FaceDetectionFrame frame : faceAnnotation.getFramesList()) {
                        double timeOffset = frame.getTimeOffset().getSeconds() + frame.getTimeOffset().getNanos() / 1e9;
                        float highestScore = 0.0f;
                        String emotion = "";
                        // Get the highest scoring emotion for the current frame
                        for (EmotionAttribute emotionAttribute : frame.getAttributes(0).getEmotionsList()) {
                            if (emotionAttribute.getScore() > highestScore) {
                                highestScore = emotionAttribute.getScore();
                                emotion = emotionAttribute.getEmotion().name();
                            }
                        }
                        System.out.printf("\t%4.2fs: %14s %4.3f\n", timeOffset, emotion, highestScore);
                    }
                } catch (IndexOutOfBoundsException ioe) {
                    System.out.println("Could not retrieve frame: " + ioe.getMessage());
                }
            }
        }
        if (!faceFound) {
            System.out.println("No faces detected in " + gcsUri);
        }
    }
}
Also used : FaceDetectionAnnotation(com.google.cloud.videointelligence.v1p1beta1.FaceDetectionAnnotation) AnnotateVideoRequest(com.google.cloud.videointelligence.v1p1beta1.AnnotateVideoRequest) VideoContext(com.google.cloud.videointelligence.v1p1beta1.VideoContext) FaceDetectionFrame(com.google.cloud.videointelligence.v1p1beta1.FaceDetectionFrame) FaceConfig(com.google.cloud.videointelligence.v1p1beta1.FaceConfig) VideoIntelligenceServiceClient(com.google.cloud.videointelligence.v1p1beta1.VideoIntelligenceServiceClient) AnnotateVideoProgress(com.google.cloud.videointelligence.v1p1beta1.AnnotateVideoProgress) FaceSegment(com.google.cloud.videointelligence.v1p1beta1.FaceSegment) EmotionAttribute(com.google.cloud.videointelligence.v1p1beta1.EmotionAttribute) VideoAnnotationResults(com.google.cloud.videointelligence.v1p1beta1.VideoAnnotationResults) AnnotateVideoResponse(com.google.cloud.videointelligence.v1p1beta1.AnnotateVideoResponse)

Aggregations

AnnotateVideoProgress (com.google.cloud.videointelligence.v1.AnnotateVideoProgress)6 AnnotateVideoRequest (com.google.cloud.videointelligence.v1.AnnotateVideoRequest)6 AnnotateVideoResponse (com.google.cloud.videointelligence.v1.AnnotateVideoResponse)6 VideoAnnotationResults (com.google.cloud.videointelligence.v1.VideoAnnotationResults)5 VideoIntelligenceServiceClient (com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient)5 Entity (com.google.cloud.videointelligence.v1.Entity)3 LabelAnnotation (com.google.cloud.videointelligence.v1.LabelAnnotation)3 LabelSegment (com.google.cloud.videointelligence.v1.LabelSegment)3 AnnotateVideoProgress (com.google.cloud.videointelligence.v1p1beta1.AnnotateVideoProgress)3 AnnotateVideoRequest (com.google.cloud.videointelligence.v1p1beta1.AnnotateVideoRequest)3 AnnotateVideoResponse (com.google.cloud.videointelligence.v1p1beta1.AnnotateVideoResponse)3 VideoAnnotationResults (com.google.cloud.videointelligence.v1p1beta1.VideoAnnotationResults)3 VideoContext (com.google.cloud.videointelligence.v1p1beta1.VideoContext)3 VideoIntelligenceServiceClient (com.google.cloud.videointelligence.v1p1beta1.VideoIntelligenceServiceClient)3 FaceConfig (com.google.cloud.videointelligence.v1p1beta1.FaceConfig)2 FaceDetectionAnnotation (com.google.cloud.videointelligence.v1p1beta1.FaceDetectionAnnotation)2 FaceDetectionFrame (com.google.cloud.videointelligence.v1p1beta1.FaceDetectionFrame)2 FaceSegment (com.google.cloud.videointelligence.v1p1beta1.FaceSegment)2 ExplicitContentFrame (com.google.cloud.videointelligence.v1.ExplicitContentFrame)1 VideoSegment (com.google.cloud.videointelligence.v1.VideoSegment)1