Quickstart: Using Client Libraries

This page shows you how to get started with the Cloud Video Intelligence API in your favorite programming language using the Google Cloud Client Libraries.

Before you begin

  1. Accede a tu Cuenta de Google.

    Si todavía no tienes una cuenta, regístrate para obtener una nueva.

  2. Selecciona o crea un proyecto de GCP.

    Ir a la página Administrar recursos

  3. Comprueba que la facturación esté habilitada en tu proyecto.

    Descubre cómo puedes habilitar la facturación

  4. Habilita las Cloud Video Intelligence API necesarias.

    Habilita las API

  5. Configura la autenticación:
    1. En GCP Console, ve a la página Crear clave de la cuenta de servicio.

      Ir a la página Crear clave de la cuenta de servicio
    2. Desde la lista desplegable de la Cuenta de servicio, selecciona Nueva cuenta de servicio.
    3. En el campo Nombre de cuenta de servicio, ingresa un nombre.
    4. En la lista desplegable Función, selecciona Proyecto > Propietario.

      Nota: El campo Función autoriza tu cuenta de servicio para acceder a los recursos. Puedes ver y cambiar este campo luego con GCP Console. Si desarrollas una aplicación de producción, especifica permisos más detallados que Proyecto > Propietario. Para obtener más información, consulta Cómo otorgar funciones a las cuentas de servicio.
    5. Haz clic en Crear. Se descargará un archivo JSON a tu computadora que contiene tus descargas de claves.
  6. Configura la variable de entorno GOOGLE_APPLICATION_CREDENTIALS con la ruta de acceso al archivo JSON que contiene la clave de tu cuenta de servicio. Esta variable solo se aplica a tu sesión actual de shell. Por lo tanto, si abres una sesión nueva, deberás volver a configurar la variable.

Install the client library

C#

For more on setting up your C# development environment, refer to the C# Development Environment Setup Guide.
Install-Package Google.Cloud.VideoIntelligence.V1 -Pre

Go

go get -u cloud.google.com/go/videointelligence/apiv1

Java

For more on setting up your Java development environment, refer to the Java Development Environment Setup Guide. Si usas Maven, agrega lo siguiente a tu archivo pom.xml:
<dependency>
  <groupId>com.google.cloud</groupId>
  <artifactId>google-cloud-video-intelligence</artifactId>
  <version>0.79.0-beta</version>
</dependency>
Si usas Gradle, agrega lo siguiente a tus dependencias:
compile 'com.google.cloud:google-cloud-video-intelligence:0.79.0-beta'
Si usas SBT, agrega lo siguiente a tus dependencias:
libraryDependencies += "com.google.cloud" % "google-cloud-video-intelligence" % "0.79.0-beta"

Si usas IntelliJ o Eclipse, puedes agregar bibliotecas cliente a tu proyecto mediante los siguientes complementos IDE:

Los complementos brindan funcionalidades adicionales, como administración de claves para las cuentas de servicio. Consulta la documentación de cada complemento para obtener más detalles.

Node.js

For more on setting up your Node.js development environment, refer to the Node.js Development Environment Setup Guide.
npm install --save @google-cloud/video-intelligence

PHP

composer require google/cloud-videointelligence

Python

For more on setting up your Python development environment, refer to the Python Development Environment Setup Guide.
pip install --upgrade google-cloud-videointelligence

Ruby

For more on setting up your Ruby development environment, refer to the Ruby Development Environment Setup Guide.
gem install google-cloud-video_intelligence

Label detection

Now you can use the Video Intelligence to request information from a video or video segment, such as label detection. Run the following code to perform your first video label detection request:

C#


using Google.Cloud.VideoIntelligence.V1;
using System;

namespace GoogleCloudSamples.VideoIntelligence
{
    public class QuickStart
    {
        public static void Main(string[] args)
        {
            var client = VideoIntelligenceServiceClient.Create();
            var request = new AnnotateVideoRequest()
            {
                InputUri = @"gs://cloud-samples-data/video/cat.mp4",
                Features = { Feature.LabelDetection }
            };
            var op = client.AnnotateVideo(request).PollUntilCompleted();
            foreach (var result in op.Result.AnnotationResults)
            {
                foreach (var annotation in result.SegmentLabelAnnotations)
                {
                    Console.WriteLine($"Video label: {annotation.Entity.Description}");
                    foreach (var entity in annotation.CategoryEntities)
                    {
                        Console.WriteLine($"Video label category: {entity.Description}");
                    }
                    foreach (var segment in annotation.Segments)
                    {
                        Console.Write("Segment location: ");
                        Console.Write(segment.Segment.StartTimeOffset);
                        Console.Write(":");
                        Console.WriteLine(segment.Segment.EndTimeOffset);
                        System.Console.WriteLine($"Confidence: {segment.Confidence}");
                    }
                }
            }
        }
    }
}

Go


// Sample video_quickstart uses the Google Cloud Video Intelligence API to label a video.
package main

import (
	"context"
	"fmt"
	"log"

	"github.com/golang/protobuf/ptypes"

	video "cloud.google.com/go/videointelligence/apiv1"
	videopb "google.golang.org/genproto/googleapis/cloud/videointelligence/v1"
)

func main() {
	ctx := context.Background()

	// Creates a client.
	client, err := video.NewClient(ctx)
	if err != nil {
		log.Fatalf("Failed to create client: %v", err)
	}

	op, err := client.AnnotateVideo(ctx, &videopb.AnnotateVideoRequest{
		InputUri: "gs://cloud-samples-data/video/cat.mp4",
		Features: []videopb.Feature{
			videopb.Feature_LABEL_DETECTION,
		},
	})
	if err != nil {
		log.Fatalf("Failed to start annotation job: %v", err)
	}

	resp, err := op.Wait(ctx)
	if err != nil {
		log.Fatalf("Failed to annotate: %v", err)
	}

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

	for _, annotation := range result.SegmentLabelAnnotations {
		fmt.Printf("Description: %s\n", annotation.Entity.Description)

		for _, category := range annotation.CategoryEntities {
			fmt.Printf("\tCategory: %s\n", category.Description)
		}

		for _, segment := range annotation.Segments {
			start, _ := ptypes.Duration(segment.Segment.StartTimeOffset)
			end, _ := ptypes.Duration(segment.Segment.EndTimeOffset)
			fmt.Printf("\tSegment: %s to %s\n", start, end)
			fmt.Printf("\tConfidence: %v\n", segment.Confidence)
		}
	}
}

Java


import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.videointelligence.v1.AnnotateVideoProgress;
import com.google.cloud.videointelligence.v1.AnnotateVideoRequest;
import com.google.cloud.videointelligence.v1.AnnotateVideoResponse;
import com.google.cloud.videointelligence.v1.Entity;
import com.google.cloud.videointelligence.v1.Feature;
import com.google.cloud.videointelligence.v1.LabelAnnotation;
import com.google.cloud.videointelligence.v1.LabelSegment;
import com.google.cloud.videointelligence.v1.VideoAnnotationResults;
import com.google.cloud.videointelligence.v1.VideoIntelligenceServiceClient;
import java.util.List;

public class QuickstartSample {

  /**
   * 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());
          }
        }
      }
    }
  }
}

Node.js

// Imports the Google Cloud Video Intelligence library
const videoIntelligence = require('@google-cloud/video-intelligence');

// Creates a client
const client = new videoIntelligence.VideoIntelligenceServiceClient();

// The GCS uri of the video to analyze
const gcsUri = 'gs://nodejs-docs-samples-video/quickstart_short.mp4';

// Construct request
const request = {
  inputUri: gcsUri,
  features: ['LABEL_DETECTION'],
};

// Execute request
const [operation] = await client.annotateVideo(request);

console.log(
  'Waiting for operation to complete... (this may take a few minutes)'
);

const [operationResult] = await operation.promise();

// Gets annotations for video
const annotations = operationResult.annotationResults[0];

// Gets labels for video from its annotations
const labels = annotations.segmentLabelAnnotations;
labels.forEach(label => {
  console.log(`Label ${label.entity.description} occurs at:`);
  label.segments.forEach(segment => {
    segment = segment.segment;
    if (segment.startTimeOffset.seconds === undefined) {
      segment.startTimeOffset.seconds = 0;
    }
    if (segment.startTimeOffset.nanos === undefined) {
      segment.startTimeOffset.nanos = 0;
    }
    if (segment.endTimeOffset.seconds === undefined) {
      segment.endTimeOffset.seconds = 0;
    }
    if (segment.endTimeOffset.nanos === undefined) {
      segment.endTimeOffset.nanos = 0;
    }
    console.log(
      `\tStart: ${segment.startTimeOffset.seconds}` +
        `.${(segment.startTimeOffset.nanos / 1e6).toFixed(0)}s`
    );
    console.log(
      `\tEnd: ${segment.endTimeOffset.seconds}.` +
        `${(segment.endTimeOffset.nanos / 1e6).toFixed(0)}s`
    );
  });
});

PHP

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

# Instantiate a client.
$video = new VideoIntelligenceServiceClient();

# Execute a request.
$options = [
    'inputUri' => 'gs://cloud-samples-data/video/cat.mp4',
    'features' => [Feature::LABEL_DETECTION]
];
$operation = $video->annotateVideo($options);

# Wait for the request to complete.
$operation->pollUntilComplete();

# Print the result.
if ($operation->operationSucceeded()) {
    $results = $operation->getResult()->getAnnotationResults()[0];
    # Process video/segment level label annotations
    foreach ($results->getSegmentLabelAnnotations() as $label) {
        printf('Video label description: %s' . PHP_EOL, $label->getEntity()->getDescription());
        foreach ($label->getCategoryEntities() as $categoryEntity) {
            printf('  Category: %s' . PHP_EOL, $categoryEntity->getDescription());
        }
        foreach ($label->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, $segment->getConfidence());
        }
    }
} else {
    print_r($operation->getError());
}

Python

from google.cloud import videointelligence

video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.enums.Feature.LABEL_DETECTION]
operation = video_client.annotate_video(
    'gs://cloud-samples-data/video/cat.mp4', features=features)
print('\nProcessing video for label annotations:')

result = operation.result(timeout=120)
print('\nFinished processing.')

# first result is retrieved because a single video was processed
segment_labels = result.annotation_results[0].segment_label_annotations
for i, segment_label in enumerate(segment_labels):
    print('Video label description: {}'.format(
        segment_label.entity.description))
    for category_entity in segment_label.category_entities:
        print('\tLabel category description: {}'.format(
            category_entity.description))

    for i, segment in enumerate(segment_label.segments):
        start_time = (segment.segment.start_time_offset.seconds +
                      segment.segment.start_time_offset.nanos / 1e9)
        end_time = (segment.segment.end_time_offset.seconds +
                    segment.segment.end_time_offset.nanos / 1e9)
        positions = '{}s to {}s'.format(start_time, end_time)
        confidence = segment.confidence
        print('\tSegment {}: {}'.format(i, positions))
        print('\tConfidence: {}'.format(confidence))
    print('\n')

Ruby

require "google/cloud/video_intelligence"

video_client = Google::Cloud::VideoIntelligence.new
features     = [:LABEL_DETECTION]
path         = "gs://cloud-samples-data/video/cat.mp4"

# Register a callback during the method call
operation = video_client.annotate_video input_uri: path, features: features do |operation|
  raise operation.results.message? if operation.error?
  puts "Finished Processing."

  labels = operation.results.annotation_results.first.segment_label_annotations

  labels.each do |label|
    puts "Label description: #{label.entity.description}"

    label.category_entities.each do |category_entity|
      puts "Label category description: #{category_entity.description}"
    end

    label.segments.each do |segment|
      start_time = (segment.segment.start_time_offset.seconds +
                     segment.segment.start_time_offset.nanos / 1e9)
      end_time =   (segment.segment.end_time_offset.seconds +
                     segment.segment.end_time_offset.nanos / 1e9)

      puts "Segment: #{start_time} to #{end_time}"
      puts "Confidence: #{segment.confidence}"
    end
  end
end

puts "Processing video for label annotations:"
operation.wait_until_done!

Congratulations! You've sent your first request to Video Intelligence.

How did it go?

Clean up

To avoid incurring charges to your Google Cloud Platform account for the resources used in this quickstart:

  • Use the GCP Console to delete your project if you do not need it.

What's next

Find out more about our Cloud Video Intelligence API Client Libraries.

¿Te ha resultado útil esta página? Enviar comentarios:

Enviar comentarios sobre...

Cloud Video Intelligence API