Detect text in a local video file

import (
	"context"
	"fmt"
	"io"
	"os"

	video "cloud.google.com/go/videointelligence/apiv1"
	videopb "cloud.google.com/go/videointelligence/apiv1/videointelligencepb"
	"github.com/golang/protobuf/ptypes"
)

// textDetection analyzes a video and extracts the text from the video's audio.
func textDetection(w io.Writer, filename string) error {
	// filename := "../testdata/googlework_short.mp4"

	ctx := context.Background()

	// Creates a client.
	client, err := video.NewClient(ctx)
	if err != nil {
		return fmt.Errorf("video.NewClient: %w", err)
	}
	defer client.Close()

	fileBytes, err := os.ReadFile(filename)
	if err != nil {
		return fmt.Errorf("os.ReadFile: %w", err)
	}

	op, err := client.AnnotateVideo(ctx, &videopb.AnnotateVideoRequest{
		InputContent: fileBytes,
		Features: []videopb.Feature{
			videopb.Feature_TEXT_DETECTION,
		},
	})
	if err != nil {
		return fmt.Errorf("AnnotateVideo: %w", err)
	}

	resp, err := op.Wait(ctx)
	if err != nil {
		return fmt.Errorf("Wait: %w", err)
	}

	// Only one video was processed, so get the first result.
	result := resp.GetAnnotationResults()[0]

	for _, annotation := range result.TextAnnotations {
		fmt.Fprintf(w, "Text: %q\n", annotation.GetText())

		// Get the first text segment.
		segment := annotation.GetSegments()[0]
		start, _ := ptypes.Duration(segment.GetSegment().GetStartTimeOffset())
		end, _ := ptypes.Duration(segment.GetSegment().GetEndTimeOffset())
		fmt.Fprintf(w, "\tSegment: %v to %v\n", start, end)

		fmt.Fprintf(w, "\tConfidence: %f\n", segment.GetConfidence())

		// Show the result for the first frame in this segment.
		frame := segment.GetFrames()[0]
		seconds := float32(frame.GetTimeOffset().GetSeconds())
		nanos := float32(frame.GetTimeOffset().GetNanos())
		fmt.Fprintf(w, "\tTime offset of the first frame: %fs\n", seconds+nanos/1e9)

		fmt.Fprintf(w, "\tRotated bounding box vertices:\n")
		for _, vertex := range frame.GetRotatedBoundingBox().GetVertices() {
			fmt.Fprintf(w, "\t\tVertex x=%f, y=%f\n", vertex.GetX(), vertex.GetY())
		}
	}

	return nil
}

/**
 * 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;
  }
}

// Imports the Google Cloud Video Intelligence library + Node's fs library
const Video = require('@google-cloud/video-intelligence');
const fs = require('fs');
const util = require('util');
// Creates a client
const video = new Video.VideoIntelligenceServiceClient();

/**
 * TODO(developer): Uncomment the following line before running the sample.
 */
// const path = 'Local file to analyze, e.g. ./my-file.mp4';

// Reads a local video file and converts it to base64
const file = await util.promisify(fs.readFile)(path);
const inputContent = file.toString('base64');

const request = {
  inputContent: inputContent,
  features: ['TEXT_DETECTION'],
};
// Detects text in a video
const [operation] = await video.annotateVideo(request);
const results = await operation.promise();
console.log('Waiting for operation to complete...');

// Gets annotations for video
const textAnnotations = results[0].annotationResults[0].textAnnotations;
textAnnotations.forEach(textAnnotation => {
  console.log(`Text ${textAnnotation.text} occurs at:`);
  textAnnotation.segments.forEach(segment => {
    const time = segment.segment;
    if (time.startTimeOffset.seconds === undefined) {
      time.startTimeOffset.seconds = 0;
    }
    if (time.startTimeOffset.nanos === undefined) {
      time.startTimeOffset.nanos = 0;
    }
    if (time.endTimeOffset.seconds === undefined) {
      time.endTimeOffset.seconds = 0;
    }
    if (time.endTimeOffset.nanos === undefined) {
      time.endTimeOffset.nanos = 0;
    }
    console.log(
      `\tStart: ${time.startTimeOffset.seconds || 0}` +
        `.${(time.startTimeOffset.nanos / 1e6).toFixed(0)}s`
    );
    console.log(
      `\tEnd: ${time.endTimeOffset.seconds || 0}.` +
        `${(time.endTimeOffset.nanos / 1e6).toFixed(0)}s`
    );
    console.log(`\tConfidence: ${segment.confidence}`);
    segment.frames.forEach(frame => {
      const timeOffset = frame.timeOffset;
      console.log(
        `Time offset for the frame: ${timeOffset.seconds || 0}` +
          `.${(timeOffset.nanos / 1e6).toFixed(0)}s`
      );
      console.log('Rotated Bounding Box Vertices:');
      frame.rotatedBoundingBox.vertices.forEach(vertex => {
        console.log(`Vertex.x:${vertex.x}, Vertex.y:${vertex.y}`);
      });
    });
  });
});

use Google\Cloud\VideoIntelligence\V1\AnnotateVideoRequest;
use Google\Cloud\VideoIntelligence\V1\Client\VideoIntelligenceServiceClient;
use Google\Cloud\VideoIntelligence\V1\Feature;

/**
 * @param string $path   File path to a video file to analyze
 * @param int $pollingIntervalSeconds
 */
function analyze_text_detection_file(string $path, int $pollingIntervalSeconds = 0)
{
    # Instantiate a client.
    $video = new VideoIntelligenceServiceClient();

    # Read the local video file
    $inputContent = file_get_contents($path);

    # Execute a request.
    $features = [Feature::TEXT_DETECTION];
    $request = (new AnnotateVideoRequest())
        ->setInputContent($inputContent)
        ->setFeatures($features);
    $operation = $video->annotateVideo($request);

    # Wait for the request to complete.
    $operation->pollUntilComplete([
        'pollingIntervalSeconds' => $pollingIntervalSeconds
    ]);

    # Print the results.
    if ($operation->operationSucceeded()) {
        $results = $operation->getResult()->getAnnotationResults()[0];

        # Process video/segment level label annotations
        foreach ($results->getTextAnnotations() as $text) {
            printf('Video text description: %s' . PHP_EOL, $text->getText());
            foreach ($text->getSegments() as $segment) {
                $start = $segment->getSegment()->getStartTimeOffset();
                $end = $segment->getSegment()->getEndTimeOffset();
                printf('  Segment: %ss to %ss' . PHP_EOL,
                    $start->getSeconds() + $start->getNanos() / 1000000000.0,
                    $end->getSeconds() + $end->getNanos() / 1000000000.0);
                printf('  Confidence: %f' . PHP_EOL, $segment->getConfidence());
            }
        }
        print(PHP_EOL);
    } else {
        print_r($operation->getError());
    }
}

import io

from google.cloud import videointelligence

def video_detect_text(path):
    """Detect text in a local video."""
    video_client = videointelligence.VideoIntelligenceServiceClient()
    features = [videointelligence.Feature.TEXT_DETECTION]
    video_context = videointelligence.VideoContext()

    with io.open(path, "rb") as file:
        input_content = file.read()

    operation = video_client.annotate_video(
        request={
            "features": features,
            "input_content": input_content,
            "video_context": video_context,
        }
    )

    print("\nProcessing video for text detection.")
    result = operation.result(timeout=300)

    # The first result is retrieved because a single video was processed.
    annotation_result = result.annotation_results[0]

    for text_annotation in annotation_result.text_annotations:
        print("\nText: {}".format(text_annotation.text))

        # Get the first text segment
        text_segment = text_annotation.segments[0]
        start_time = text_segment.segment.start_time_offset
        end_time = text_segment.segment.end_time_offset
        print(
            "start_time: {}, end_time: {}".format(
                start_time.seconds + start_time.microseconds * 1e-6,
                end_time.seconds + end_time.microseconds * 1e-6,
            )
        )

        print("Confidence: {}".format(text_segment.confidence))

        # Show the result for the first frame in this segment.
        frame = text_segment.frames[0]
        time_offset = frame.time_offset
        print(
            "Time offset for the first frame: {}".format(
                time_offset.seconds + time_offset.microseconds * 1e-6
            )
        )
        print("Rotated Bounding Box Vertices:")
        for vertex in frame.rotated_bounding_box.vertices:
            print("\tVertex.x: {}, Vertex.y: {}".format(vertex.x, vertex.y))