Search in sources :

Example 6 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 7 with VideoAnnotationResults

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

the class LogoDetectionGcs method detectLogoGcs.

public static void detectLogoGcs(String inputUri) throws IOException, ExecutionException, InterruptedException, TimeoutException {
    // 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(300, 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());
            // 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());
                }
            }
            // 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());
            }
        }
    }
}
Also used : Entity(com.google.cloud.videointelligence.v1.Entity) AnnotateVideoRequest(com.google.cloud.videointelligence.v1.AnnotateVideoRequest) Duration(com.google.protobuf.Duration) VideoIntelligenceServiceClient(com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient) AnnotateVideoProgress(com.google.cloud.videointelligence.v1.AnnotateVideoProgress) NormalizedBoundingBox(com.google.cloud.videointelligence.v1.NormalizedBoundingBox) VideoSegment(com.google.cloud.videointelligence.v1.VideoSegment) TimestampedObject(com.google.cloud.videointelligence.v1.TimestampedObject) VideoAnnotationResults(com.google.cloud.videointelligence.v1.VideoAnnotationResults) LogoRecognitionAnnotation(com.google.cloud.videointelligence.v1.LogoRecognitionAnnotation) DetectedAttribute(com.google.cloud.videointelligence.v1.DetectedAttribute) Track(com.google.cloud.videointelligence.v1.Track) AnnotateVideoResponse(com.google.cloud.videointelligence.v1.AnnotateVideoResponse)

Example 8 with VideoAnnotationResults

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

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://cloud-samples-data/video/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 9 with VideoAnnotationResults

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

the class TextDetection method detectTextGcs.

// [END video_detect_text]
// [START video_detect_text_gcs]
/**
 * Detect Text in a video.
 *
 * @param gcsUri the path to the video file to analyze.
 */
public static VideoAnnotationResults detectTextGcs(String gcsUri) throws Exception {
    try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
        // Create the request
        AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputUri(gcsUri).addFeatures(Feature.TEXT_DETECTION).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(300, TimeUnit.SECONDS);
        VideoAnnotationResults results = response.getAnnotationResults(0);
        // Get only the first annotation for demo purposes.
        TextAnnotation annotation = results.getTextAnnotations(0);
        System.out.println("Text: " + annotation.getText());
        // Get the first text segment.
        TextSegment textSegment = annotation.getSegments(0);
        System.out.println("Confidence: " + textSegment.getConfidence());
        // For the text segment display it's time offset
        VideoSegment videoSegment = textSegment.getSegment();
        Duration startTimeOffset = videoSegment.getStartTimeOffset();
        Duration endTimeOffset = videoSegment.getEndTimeOffset();
        // Display the offset times in seconds, 1e9 is part of the formula to convert nanos to seconds
        System.out.println(String.format("Start time: %.2f", startTimeOffset.getSeconds() + startTimeOffset.getNanos() / 1e9));
        System.out.println(String.format("End time: %.2f", endTimeOffset.getSeconds() + endTimeOffset.getNanos() / 1e9));
        // Show the first result for the first frame in the segment.
        TextFrame textFrame = textSegment.getFrames(0);
        Duration timeOffset = textFrame.getTimeOffset();
        System.out.println(String.format("Time offset for the first frame: %.2f", timeOffset.getSeconds() + timeOffset.getNanos() / 1e9));
        // Display the rotated bounding box for where the text is on the frame.
        System.out.println("Rotated Bounding Box Vertices:");
        List<NormalizedVertex> vertices = textFrame.getRotatedBoundingBox().getVerticesList();
        for (NormalizedVertex normalizedVertex : vertices) {
            System.out.println(String.format("\tVertex.x: %.2f, Vertex.y: %.2f", normalizedVertex.getX(), normalizedVertex.getY()));
        }
        return results;
    }
}
Also used : AnnotateVideoRequest(com.google.cloud.videointelligence.v1.AnnotateVideoRequest) Duration(com.google.protobuf.Duration) NormalizedVertex(com.google.cloud.videointelligence.v1.NormalizedVertex) VideoIntelligenceServiceClient(com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient) AnnotateVideoProgress(com.google.cloud.videointelligence.v1.AnnotateVideoProgress) VideoSegment(com.google.cloud.videointelligence.v1.VideoSegment) VideoAnnotationResults(com.google.cloud.videointelligence.v1.VideoAnnotationResults) TextFrame(com.google.cloud.videointelligence.v1.TextFrame) TextSegment(com.google.cloud.videointelligence.v1.TextSegment) TextAnnotation(com.google.cloud.videointelligence.v1.TextAnnotation) AnnotateVideoResponse(com.google.cloud.videointelligence.v1.AnnotateVideoResponse)

Example 10 with VideoAnnotationResults

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

the class TextDetection method detectText.

// [START video_detect_text]
/**
 * Detect text in a video.
 *
 * @param filePath the path to the video file to analyze.
 */
public static VideoAnnotationResults detectText(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.TEXT_DETECTION).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(300, TimeUnit.SECONDS);
        VideoAnnotationResults results = response.getAnnotationResults(0);
        // Get only the first annotation for demo purposes.
        TextAnnotation annotation = results.getTextAnnotations(0);
        System.out.println("Text: " + annotation.getText());
        // Get the first text segment.
        TextSegment textSegment = annotation.getSegments(0);
        System.out.println("Confidence: " + textSegment.getConfidence());
        // For the text segment display it's time offset
        VideoSegment videoSegment = textSegment.getSegment();
        Duration startTimeOffset = videoSegment.getStartTimeOffset();
        Duration endTimeOffset = videoSegment.getEndTimeOffset();
        // Display the offset times in seconds, 1e9 is part of the formula to convert nanos to seconds
        System.out.println(String.format("Start time: %.2f", startTimeOffset.getSeconds() + startTimeOffset.getNanos() / 1e9));
        System.out.println(String.format("End time: %.2f", endTimeOffset.getSeconds() + endTimeOffset.getNanos() / 1e9));
        // Show the first result for the first frame in the segment.
        TextFrame textFrame = textSegment.getFrames(0);
        Duration timeOffset = textFrame.getTimeOffset();
        System.out.println(String.format("Time offset for the first frame: %.2f", timeOffset.getSeconds() + timeOffset.getNanos() / 1e9));
        // Display the rotated bounding box for where the text is on the frame.
        System.out.println("Rotated Bounding Box Vertices:");
        List<NormalizedVertex> vertices = textFrame.getRotatedBoundingBox().getVerticesList();
        for (NormalizedVertex normalizedVertex : vertices) {
            System.out.println(String.format("\tVertex.x: %.2f, Vertex.y: %.2f", normalizedVertex.getX(), normalizedVertex.getY()));
        }
        return results;
    }
}
Also used : Path(java.nio.file.Path) AnnotateVideoRequest(com.google.cloud.videointelligence.v1.AnnotateVideoRequest) Duration(com.google.protobuf.Duration) NormalizedVertex(com.google.cloud.videointelligence.v1.NormalizedVertex) VideoIntelligenceServiceClient(com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient) AnnotateVideoProgress(com.google.cloud.videointelligence.v1.AnnotateVideoProgress) VideoSegment(com.google.cloud.videointelligence.v1.VideoSegment) VideoAnnotationResults(com.google.cloud.videointelligence.v1.VideoAnnotationResults) TextFrame(com.google.cloud.videointelligence.v1.TextFrame) TextSegment(com.google.cloud.videointelligence.v1.TextSegment) TextAnnotation(com.google.cloud.videointelligence.v1.TextAnnotation) 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