use of com.google.cloud.videointelligence.v1p2beta1.AnnotateVideoRequest in project java-video-intelligence by googleapis.
the class TrackObjects method trackObjectsGcs.
// [END video_object_tracking_beta]
// [START video_object_tracking_gcs_beta]
/**
* Track objects in a video.
*
* @param gcsUri the path to the video file to analyze.
*/
public static VideoAnnotationResults trackObjectsGcs(String gcsUri) throws Exception {
try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
// Create the request
AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputUri(gcsUri).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;
}
}
use of com.google.cloud.videointelligence.v1p2beta1.AnnotateVideoRequest 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]
}
use of com.google.cloud.videointelligence.v1p2beta1.AnnotateVideoRequest in project java-video-intelligence by googleapis.
the class DetectLogo method detectLogo.
public static void detectLogo(String localFilePath) throws IOException, ExecutionException, InterruptedException {
// the "close" method on the client to safely clean up any remaining background resources.
try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
// Read the files contents
Path path = Paths.get(localFilePath);
byte[] data = Files.readAllBytes(path);
ByteString inputContent = ByteString.copyFrom(data);
// Build the request with the inputContent and set the Feature
AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputContent(inputContent).addFeatures(Feature.LOGO_RECOGNITION).build();
// Make the asynchronous request
AnnotateVideoResponse response = client.annotateVideoAsync(request).get();
// Get the first response, since we sent only one video.
VideoAnnotationResults annotationResult = response.getAnnotationResultsList().get(0);
// Annotations for list of logos detected, tracked and recognized in the 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.
VideoSegment segment = track.getSegment();
Duration segmentStartTimeOffset = segment.getStartTimeOffset();
System.out.printf("\n\tStart Time Offset: %s.%s\n", segmentStartTimeOffset.getSeconds(), segmentStartTimeOffset.getNanos());
Duration segmentEndTimeOffset = segment.getEndTimeOffset();
System.out.printf("\tEnd Time Offset: %s.%s\n", segmentEndTimeOffset.getSeconds(), segmentEndTimeOffset.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 logoRecognitionAnnotationSegment : logoRecognitionAnnotation.getSegmentsList()) {
Duration logoRecognitionAnnotationSegmentStartTimeOffset = logoRecognitionAnnotationSegment.getStartTimeOffset();
System.out.printf("\n\tStart Time Offset : %s.%s\n", logoRecognitionAnnotationSegmentStartTimeOffset.getSeconds(), logoRecognitionAnnotationSegmentStartTimeOffset.getNanos());
Duration logoRecognitionAnnotationSegmentEndTimeOffset = logoRecognitionAnnotationSegment.getEndTimeOffset();
System.out.printf("\tEnd Time Offset : %s.%s\n", logoRecognitionAnnotationSegmentEndTimeOffset.getSeconds(), logoRecognitionAnnotationSegmentEndTimeOffset.getNanos());
}
}
}
}
use of com.google.cloud.videointelligence.v1p2beta1.AnnotateVideoRequest in project java-video-intelligence by googleapis.
the class DetectLogoGcs method detectLogoGcs.
public static void detectLogoGcs(String inputUri) throws IOException, ExecutionException, InterruptedException {
// the "close" method on the client to safely clean up any remaining background resources.
try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
// Build the request with the inputUri and set the Feature
AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputUri(inputUri).addFeatures(Feature.LOGO_RECOGNITION).build();
// Make the asynchronous request
AnnotateVideoResponse response = client.annotateVideoAsync(request).get();
// Get the first response, since we sent only one video.
VideoAnnotationResults annotationResult = response.getAnnotationResultsList().get(0);
// Annotations for list of logos detected, tracked and recognized in the 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.
VideoSegment segment = track.getSegment();
Duration segmentStartTimeOffset = segment.getStartTimeOffset();
System.out.printf("\n\tStart Time Offset: %s.%s\n", segmentStartTimeOffset.getSeconds(), segmentStartTimeOffset.getNanos());
Duration segmentEndTimeOffset = segment.getEndTimeOffset();
System.out.printf("\tEnd Time Offset: %s.%s\n", segmentEndTimeOffset.getSeconds(), segmentEndTimeOffset.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 logoRecognitionAnnotationSegment : logoRecognitionAnnotation.getSegmentsList()) {
Duration logoRecognitionAnnotationSegmentStartTimeOffset = logoRecognitionAnnotationSegment.getStartTimeOffset();
System.out.printf("\n\tStart Time Offset : %s.%s\n", logoRecognitionAnnotationSegmentStartTimeOffset.getSeconds(), logoRecognitionAnnotationSegmentStartTimeOffset.getNanos());
Duration logoRecognitionAnnotationSegmentEndTimeOffset = logoRecognitionAnnotationSegment.getEndTimeOffset();
System.out.printf("\tEnd Time Offset : %s.%s\n", logoRecognitionAnnotationSegmentEndTimeOffset.getSeconds(), logoRecognitionAnnotationSegmentEndTimeOffset.getNanos());
}
}
}
}
use of com.google.cloud.videointelligence.v1p2beta1.AnnotateVideoRequest in project java-video-intelligence by googleapis.
the class LogoDetection method detectLogo.
public static void detectLogo(String filePath) throws IOException, ExecutionException, InterruptedException, TimeoutException {
// the "close" method on the client to safely clean up any remaining background resources.
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.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());
}
}
}
}
Aggregations