Search in sources :

Example 41 with VideoAnnotationResults

use of com.google.cloud.videointelligence.v1p2beta1.VideoAnnotationResults in project java-video-intelligence by googleapis.

the class TrackObjects method trackObjects.

// [START video_object_tracking]
/**
 * Track objects in a video.
 *
 * @param filePath the path to the video file to analyze.
 */
public static VideoAnnotationResults trackObjects(String filePath) throws Exception {
    try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
        // Read file
        Path path = Paths.get(filePath);
        byte[] data = Files.readAllBytes(path);
        // Create the request
        AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputContent(ByteString.copyFrom(data)).addFeatures(Feature.OBJECT_TRACKING).setLocationId("us-east1").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(450, TimeUnit.SECONDS);
        VideoAnnotationResults results = response.getAnnotationResults(0);
        // Get only the first annotation for demo purposes.
        ObjectTrackingAnnotation annotation = results.getObjectAnnotations(0);
        System.out.println("Confidence: " + annotation.getConfidence());
        if (annotation.hasEntity()) {
            Entity entity = annotation.getEntity();
            System.out.println("Entity description: " + entity.getDescription());
            System.out.println("Entity id:: " + entity.getEntityId());
        }
        if (annotation.hasSegment()) {
            VideoSegment videoSegment = annotation.getSegment();
            Duration startTimeOffset = videoSegment.getStartTimeOffset();
            Duration endTimeOffset = videoSegment.getEndTimeOffset();
            // Display the segment time in seconds, 1e9 converts nanos to seconds
            System.out.println(String.format("Segment: %.2fs to %.2fs", startTimeOffset.getSeconds() + startTimeOffset.getNanos() / 1e9, endTimeOffset.getSeconds() + endTimeOffset.getNanos() / 1e9));
        }
        // Here we print only the bounding box of the first frame in this segment.
        ObjectTrackingFrame frame = annotation.getFrames(0);
        // Display the offset time in seconds, 1e9 converts nanos to seconds
        Duration timeOffset = frame.getTimeOffset();
        System.out.println(String.format("Time offset of the first frame: %.2fs", timeOffset.getSeconds() + timeOffset.getNanos() / 1e9));
        // Display the bounding box of the detected object
        NormalizedBoundingBox normalizedBoundingBox = frame.getNormalizedBoundingBox();
        System.out.println("Bounding box position:");
        System.out.println("\tleft: " + normalizedBoundingBox.getLeft());
        System.out.println("\ttop: " + normalizedBoundingBox.getTop());
        System.out.println("\tright: " + normalizedBoundingBox.getRight());
        System.out.println("\tbottom: " + normalizedBoundingBox.getBottom());
        return results;
    }
}
Also used : Path(java.nio.file.Path) Entity(com.google.cloud.videointelligence.v1.Entity) ObjectTrackingAnnotation(com.google.cloud.videointelligence.v1.ObjectTrackingAnnotation) AnnotateVideoRequest(com.google.cloud.videointelligence.v1.AnnotateVideoRequest) Duration(com.google.protobuf.Duration) VideoIntelligenceServiceClient(com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient) ObjectTrackingFrame(com.google.cloud.videointelligence.v1.ObjectTrackingFrame) AnnotateVideoProgress(com.google.cloud.videointelligence.v1.AnnotateVideoProgress) NormalizedBoundingBox(com.google.cloud.videointelligence.v1.NormalizedBoundingBox) VideoSegment(com.google.cloud.videointelligence.v1.VideoSegment) VideoAnnotationResults(com.google.cloud.videointelligence.v1.VideoAnnotationResults) AnnotateVideoResponse(com.google.cloud.videointelligence.v1.AnnotateVideoResponse)

Example 42 with VideoAnnotationResults

use of com.google.cloud.videointelligence.v1p2beta1.VideoAnnotationResults in project java-video-intelligence by googleapis.

the class Detect method analyzeLabelsFile.

/**
 * Performs label analysis on the video at the provided file path.
 *
 * @param filePath the path to the video file to analyze.
 */
public static void analyzeLabelsFile(String filePath) throws Exception {
    // Instantiate a com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient
    try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
        // Read file and encode into Base64
        Path path = Paths.get(filePath);
        byte[] data = Files.readAllBytes(path);
        AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputContent(ByteString.copyFrom(data)).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:%.2f\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:%.2f\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 video_analyze_labels]
}
Also used : VideoIntelligenceServiceClient(com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient) Path(java.nio.file.Path) 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 43 with VideoAnnotationResults

use of com.google.cloud.videointelligence.v1p2beta1.VideoAnnotationResults in project java-video-intelligence by googleapis.

the class Detect method analyzeShots.

/**
 * Performs shot analysis on the video at the provided Cloud Storage path.
 *
 * @param gcsUri the path to the video file to analyze.
 */
public static void analyzeShots(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.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);
            }
        }
    }
// [END video_analyze_shots]
}
Also used : VideoIntelligenceServiceClient(com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient) AnnotateVideoProgress(com.google.cloud.videointelligence.v1.AnnotateVideoProgress) VideoSegment(com.google.cloud.videointelligence.v1.VideoSegment) AnnotateVideoRequest(com.google.cloud.videointelligence.v1.AnnotateVideoRequest) VideoAnnotationResults(com.google.cloud.videointelligence.v1.VideoAnnotationResults) AnnotateVideoResponse(com.google.cloud.videointelligence.v1.AnnotateVideoResponse)

Example 44 with VideoAnnotationResults

use of com.google.cloud.videointelligence.v1p2beta1.VideoAnnotationResults in project java-video-intelligence by googleapis.

the class Detect method speechTranscription.

/**
 * Transcribe speech from a video stored on GCS.
 *
 * @param gcsUri the path to the video file to analyze.
 */
public static void speechTranscription(String gcsUri) throws Exception {
    // Instantiate a com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient
    try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
        // Set the language code
        SpeechTranscriptionConfig config = SpeechTranscriptionConfig.newBuilder().setLanguageCode("en-US").setEnableAutomaticPunctuation(true).build();
        // Set the video context with the above configuration
        VideoContext context = VideoContext.newBuilder().setSpeechTranscriptionConfig(config).build();
        // Create the request
        AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputUri(gcsUri).addFeatures(Feature.SPEECH_TRANSCRIPTION).setVideoContext(context).build();
        // asynchronously perform speech transcription on videos
        OperationFuture<AnnotateVideoResponse, AnnotateVideoProgress> response = client.annotateVideoAsync(request);
        System.out.println("Waiting for operation to complete...");
        // Display the results
        for (VideoAnnotationResults results : response.get(600, TimeUnit.SECONDS).getAnnotationResultsList()) {
            for (SpeechTranscription speechTranscription : results.getSpeechTranscriptionsList()) {
                try {
                    // Print the transcription
                    if (speechTranscription.getAlternativesCount() > 0) {
                        SpeechRecognitionAlternative alternative = speechTranscription.getAlternatives(0);
                        System.out.printf("Transcript: %s\n", alternative.getTranscript());
                        System.out.printf("Confidence: %.2f\n", alternative.getConfidence());
                        System.out.println("Word level information:");
                        for (WordInfo wordInfo : alternative.getWordsList()) {
                            double startTime = wordInfo.getStartTime().getSeconds() + wordInfo.getStartTime().getNanos() / 1e9;
                            double endTime = wordInfo.getEndTime().getSeconds() + wordInfo.getEndTime().getNanos() / 1e9;
                            System.out.printf("\t%4.2fs - %4.2fs: %s\n", startTime, endTime, wordInfo.getWord());
                        }
                    } else {
                        System.out.println("No transcription found");
                    }
                } catch (IndexOutOfBoundsException ioe) {
                    System.out.println("Could not retrieve frame: " + ioe.getMessage());
                }
            }
        }
    }
// [END video_speech_transcription_gcs]
}
Also used : AnnotateVideoRequest(com.google.cloud.videointelligence.v1.AnnotateVideoRequest) VideoContext(com.google.cloud.videointelligence.v1.VideoContext) VideoIntelligenceServiceClient(com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient) AnnotateVideoProgress(com.google.cloud.videointelligence.v1.AnnotateVideoProgress) SpeechRecognitionAlternative(com.google.cloud.videointelligence.v1.SpeechRecognitionAlternative) SpeechTranscriptionConfig(com.google.cloud.videointelligence.v1.SpeechTranscriptionConfig) VideoAnnotationResults(com.google.cloud.videointelligence.v1.VideoAnnotationResults) SpeechTranscription(com.google.cloud.videointelligence.v1.SpeechTranscription) WordInfo(com.google.cloud.videointelligence.v1.WordInfo) AnnotateVideoResponse(com.google.cloud.videointelligence.v1.AnnotateVideoResponse)

Example 45 with VideoAnnotationResults

use of com.google.cloud.videointelligence.v1p2beta1.VideoAnnotationResults in project java-video-intelligence by googleapis.

the class DetectFaces method detectFaces.

// Detects faces in a video stored in a local file using the Cloud Video Intelligence API.
public static void detectFaces(String localFilePath) throws Exception {
    try (VideoIntelligenceServiceClient videoIntelligenceServiceClient = VideoIntelligenceServiceClient.create()) {
        // Reads a local video file and converts it to base64.
        Path path = Paths.get(localFilePath);
        byte[] data = Files.readAllBytes(path);
        ByteString inputContent = ByteString.copyFrom(data);
        FaceDetectionConfig faceDetectionConfig = FaceDetectionConfig.newBuilder().setIncludeBoundingBoxes(true).setIncludeAttributes(true).build();
        VideoContext videoContext = VideoContext.newBuilder().setFaceDetectionConfig(faceDetectionConfig).build();
        AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputContent(inputContent).addFeatures(Feature.FACE_DETECTION).setVideoContext(videoContext).build();
        // Detects faces in a video
        OperationFuture<AnnotateVideoResponse, AnnotateVideoProgress> future = videoIntelligenceServiceClient.annotateVideoAsync(request);
        System.out.println("Waiting for operation to complete...");
        AnnotateVideoResponse response = future.get();
        // Gets annotations for video
        VideoAnnotationResults annotationResult = response.getAnnotationResultsList().get(0);
        // Annotations for list of faces detected, tracked and recognized in video.
        for (FaceDetectionAnnotation faceDetectionAnnotation : annotationResult.getFaceDetectionAnnotationsList()) {
            System.out.print("Face detected:\n");
            for (Track track : faceDetectionAnnotation.getTracksList()) {
                VideoSegment segment = track.getSegment();
                System.out.printf("\tStart: %d.%.0fs\n", segment.getStartTimeOffset().getSeconds(), segment.getStartTimeOffset().getNanos() / 1e6);
                System.out.printf("\tEnd: %d.%.0fs\n", segment.getEndTimeOffset().getSeconds(), segment.getEndTimeOffset().getNanos() / 1e6);
                // Each segment includes timestamped objects that
                // include characteristics of the face detected.
                TimestampedObject firstTimestampedObject = track.getTimestampedObjects(0);
                for (DetectedAttribute attribute : firstTimestampedObject.getAttributesList()) {
                    // Attributes include glasses, headwear, smiling, direction of gaze
                    System.out.printf("\tAttribute %s: %s %s\n", attribute.getName(), attribute.getValue(), attribute.getConfidence());
                }
            }
        }
    }
}
Also used : Path(java.nio.file.Path) FaceDetectionAnnotation(com.google.cloud.videointelligence.v1.FaceDetectionAnnotation) AnnotateVideoRequest(com.google.cloud.videointelligence.v1.AnnotateVideoRequest) ByteString(com.google.protobuf.ByteString) VideoContext(com.google.cloud.videointelligence.v1.VideoContext) VideoIntelligenceServiceClient(com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient) AnnotateVideoProgress(com.google.cloud.videointelligence.v1.AnnotateVideoProgress) VideoSegment(com.google.cloud.videointelligence.v1.VideoSegment) TimestampedObject(com.google.cloud.videointelligence.v1.TimestampedObject) VideoAnnotationResults(com.google.cloud.videointelligence.v1.VideoAnnotationResults) FaceDetectionConfig(com.google.cloud.videointelligence.v1.FaceDetectionConfig) DetectedAttribute(com.google.cloud.videointelligence.v1.DetectedAttribute) Track(com.google.cloud.videointelligence.v1.Track) AnnotateVideoResponse(com.google.cloud.videointelligence.v1.AnnotateVideoResponse)

Aggregations

VideoAnnotationResults (com.google.cloud.videointelligence.v1.VideoAnnotationResults)44 AnnotateVideoResponse (com.google.cloud.videointelligence.v1.AnnotateVideoResponse)34 AnnotateVideoProgress (com.google.cloud.videointelligence.v1.AnnotateVideoProgress)33 AnnotateVideoRequest (com.google.cloud.videointelligence.v1.AnnotateVideoRequest)33 VideoIntelligenceServiceClient (com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient)33 VideoSegment (com.google.cloud.videointelligence.v1.VideoSegment)19 Duration (com.google.protobuf.Duration)18 Entity (com.google.cloud.videointelligence.v1.Entity)17 Path (java.nio.file.Path)14 Test (org.junit.Test)14 VideoContext (com.google.cloud.videointelligence.v1.VideoContext)10 LabelAnnotation (com.google.cloud.videointelligence.v1.LabelAnnotation)9 LabelSegment (com.google.cloud.videointelligence.v1.LabelSegment)9 DetectedAttribute (com.google.cloud.videointelligence.v1.DetectedAttribute)8 NormalizedBoundingBox (com.google.cloud.videointelligence.v1.NormalizedBoundingBox)8 TextAnnotation (com.google.cloud.videointelligence.v1.TextAnnotation)8 TimestampedObject (com.google.cloud.videointelligence.v1.TimestampedObject)8 Track (com.google.cloud.videointelligence.v1.Track)8 VideoAnnotationResults (com.google.cloud.videointelligence.v1p2beta1.VideoAnnotationResults)8 AnnotateVideoResponse (com.google.cloud.videointelligence.v1p1beta1.AnnotateVideoResponse)5