Label analysis

importcom.google.api.gax.rpc.BidiStream ;
importcom.google.cloud.videointelligence.v1p3beta1.LabelAnnotation;
importcom.google.cloud.videointelligence.v1p3beta1.LabelFrame;
importcom.google.cloud.videointelligence.v1p3beta1.StreamingAnnotateVideoRequest;
importcom.google.cloud.videointelligence.v1p3beta1.StreamingAnnotateVideoResponse;
importcom.google.cloud.videointelligence.v1p3beta1.StreamingFeature;
importcom.google.cloud.videointelligence.v1p3beta1.StreamingLabelDetectionConfig;
importcom.google.cloud.videointelligence.v1p3beta1.StreamingVideoAnnotationResults;
importcom.google.cloud.videointelligence.v1p3beta1.StreamingVideoConfig;
importcom.google.cloud.videointelligence.v1p3beta1.StreamingVideoIntelligenceServiceClient;
importcom.google.protobuf.ByteString ;
importio.grpc.StatusRuntimeException;
importjava.io.IOException;
importjava.nio.file.Files;
importjava.nio.file.Path;
importjava.nio.file.Paths;
importjava.util.Arrays;
importjava.util.concurrent.TimeoutException;
class StreamingLabelDetection{
// Perform streaming video label detection
staticvoidstreamingLabelDetection(StringfilePath)
throwsIOException,TimeoutException,StatusRuntimeException{
// String filePath = "path_to_your_video_file";
try(StreamingVideoIntelligenceServiceClientclient=
StreamingVideoIntelligenceServiceClient.create()){
Pathpath=Paths.get(filePath);
byte[]data=Files.readAllBytes(path);
// Set the chunk size to 5MB (recommended less than 10MB).
intchunkSize=5*1024*1024;
intnumChunks=(int)Math.ceil((double)data.length/chunkSize);
StreamingLabelDetectionConfiglabelConfig=
StreamingLabelDetectionConfig.newBuilder().setStationaryCamera(false).build();
StreamingVideoConfigstreamingVideoConfig=
StreamingVideoConfig.newBuilder()
.setFeature(StreamingFeature.STREAMING_LABEL_DETECTION)
.setLabelDetectionConfig(labelConfig)
.build();
BidiStream<StreamingAnnotateVideoRequest,StreamingAnnotateVideoResponse>call=
client.streamingAnnotateVideoCallable().call();
// The first request must **only** contain the audio configuration:
call.send(
StreamingAnnotateVideoRequest.newBuilder().setVideoConfig(streamingVideoConfig).build());
// Subsequent requests must **only** contain the audio data.
// Send the requests in chunks
for(inti=0;i < numChunks;i++){
call.send(
StreamingAnnotateVideoRequest.newBuilder()
.setInputContent(
ByteString .copyFrom (
Arrays.copyOfRange(data,i*chunkSize,i*chunkSize+chunkSize)))
.build());
}
// Tell the service you are done sending data
call.closeSend();
for(StreamingAnnotateVideoResponseresponse:call){
StreamingVideoAnnotationResultsannotationResults=response.getAnnotationResults();
for(LabelAnnotationannotation:annotationResults.getLabelAnnotationsList()){
Stringentity=annotation.getEntity().getDescription ();
// There is only one frame per annotation
LabelFramelabelFrame=annotation.getFrames(0);
doubleoffset=
labelFrame.getTimeOffset().getSeconds()+labelFrame.getTimeOffset().getNanos()/1e9;
floatconfidence=labelFrame.getConfidence();
System.out.format("%fs: %s (%f)\n",offset,entity,confidence);
}
}
}
}
}

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const path = 'Local file to analyze, e.g. ./my-file.mp4';
const{StreamingVideoIntelligenceServiceClient}=
require('@google-cloud/video-intelligence').v1p3beta1;
constfs=require('fs');
// Instantiates a client
constclient=newStreamingVideoIntelligenceServiceClient ();
// Streaming configuration
constconfigRequest={
videoConfig:{
feature:'STREAMING_LABEL_DETECTION',
},
};
constreadStream=fs.createReadStream(path,{
highWaterMark:5*1024*1024,//chunk size set to 5MB (recommended less than 10MB)
encoding:'base64',
});
//Load file content
constchunks=[];
readStream
.on('data',chunk=>{
constrequest={
inputContent:chunk.toString(),
};
chunks.push(request);
})
.on('close',()=>{
// configRequest should be the first in the stream of requests
stream.write(configRequest);
for(leti=0;i < chunks.length;i++){
stream.write(chunks[i]);
}
stream.end();
});
conststream=client.streamingAnnotateVideo().on('data',response=>{
//Gets annotations for video
constannotations=response.annotationResults;
constlabels=annotations.labelAnnotations;
labels.forEach(label=>{
console.log(
`Label ${label.entity.description} occurs at: ${
label.frames[0].timeOffset.seconds||0
}`+`.${(label.frames[0].timeOffset.nanos/1e6).toFixed(0)}s`
);
console.log(` Confidence: ${label.frames[0].confidence}`);
});
});

fromgoogle.cloudimport videointelligence_v1p3beta1 as videointelligence
# path = 'path_to_file'
client = videointelligence.StreamingVideoIntelligenceServiceClient()
# Set streaming config.
config = videointelligence.StreamingVideoConfig(
 feature=(videointelligence.StreamingFeature.STREAMING_LABEL_DETECTION)
)
# config_request should be the first in the stream of requests.
config_request = videointelligence.StreamingAnnotateVideoRequest(
 video_config=config
)
# Set the chunk size to 5MB (recommended less than 10MB).
chunk_size = 5 * 1024 * 1024
# Load file content.
stream = []
with io.open(path, "rb") as video_file:
 while True:
 data = video_file.read(chunk_size)
 if not data:
 break
 stream.append(data)
defstream_generator():
 yield config_request
 for chunk in stream:
 yield videointelligence.StreamingAnnotateVideoRequest(input_content=chunk)
requests = stream_generator()
# streaming_annotate_video returns a generator.
# The default timeout is about 300 seconds.
# To process longer videos it should be set to
# larger than the length (in seconds) of the stream.
responses = client.streaming_annotate_video(requests, timeout=600)
# Each response corresponds to about 1 second of video.
for response in responses:
 # Check for errors.
 if response.error.message:
 print(response.error.message)
 break
 label_annotations = response.annotation_results.label_annotations
 # label_annotations could be empty
 if not label_annotations:
 continue
 for annotation in label_annotations:
 # Each annotation has one frame, which has a timeoffset.
 frame = annotation.frames[0]
 time_offset = (
 frame.time_offset.seconds + frame.time_offset.microseconds / 1e6
 )
 description = annotation.entity.description
 confidence = annotation.frames[0].confidence
 # description is in Unicode
 print(
 "{}s: {} (confidence: {})".format(time_offset, description, confidence)
 )