Annoter une vidéo à l'aide de la ligne de commande

Annoter une vidéo à l'aide de la ligne de commande

Cette page explique comment envoyer une requête à l'API Video Intelligence avec curl pour les projets dont vous êtes propriétaire.

Vous pouvez suivre les étapes décrites sur cette page ou essayer ce démarrage rapide en tant qu'atelier de formation Google Cloud.

Essayer avec un atelier

Avant de commencer

1. Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

2. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

   Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

   Go to project selector

3. Make sure that billing is enabled for your Google Cloud project.

4. Enable the required API.

   Enable the API

5. Create a service account:

   1. In the Google Cloud console, go to the Create service account page.

      Go to Create service account
   2. Select your project.

   3. In the Service account name field, enter a name. The Google Cloud console fills in the Service account ID field based on this name.

      In the Service account description field, enter a description. For example, Service account for quickstart.

   4. Click Create and continue.

   5. Click Done to finish creating the service account.

      Do not close your browser window. You will use it in the next step.

6. Create a service account key:

   1. In the Google Cloud console, click the email address for the service account that you created.
   2. Click Keys.
   3. Click Add key, and then click Create new key.
   4. Click Create. A JSON key file is downloaded to your computer.
   5. Click Close.

7. Set the environment variable GOOGLE_APPLICATION_CREDENTIALS to the path of the JSON file that contains your credentials. This variable applies only to your current shell session, so if you open a new session, set the variable again.

   Example: Linux or macOS

   export GOOGLE_APPLICATION_CREDENTIALS="KEY_PATH"

   Replace KEY_PATH with the path of the JSON file that contains your credentials.

   For example:

   export GOOGLE_APPLICATION_CREDENTIALS="/home/user/Downloads/service-account-file.json"

   Example: Windows

   For PowerShell:

   $env:GOOGLE_APPLICATION_CREDENTIALS="KEY_PATH"

   Replace KEY_PATH with the path of the JSON file that contains your credentials.

   For example:

   $env:GOOGLE_APPLICATION_CREDENTIALS="C:\Users\username\Downloads\service-account-file.json"

   For command prompt:

   set GOOGLE_APPLICATION_CREDENTIALS=KEY_PATH

   Replace KEY_PATH with the path of the JSON file that contains your credentials.

8. Install the Google Cloud CLI.

9. To initialize the gcloud CLI, run the following command:

   gcloud init

10. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

    Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

    Go to project selector

11. Make sure that billing is enabled for your Google Cloud project.

12. Enable the required API.

    Enable the API

13. Create a service account:

    1. In the Google Cloud console, go to the Create service account page.

       Go to Create service account
    2. Select your project.

    3. In the Service account name field, enter a name. The Google Cloud console fills in the Service account ID field based on this name.

       In the Service account description field, enter a description. For example, Service account for quickstart.

    4. Click Create and continue.

    5. Click Done to finish creating the service account.

       Do not close your browser window. You will use it in the next step.

14. Create a service account key:

    1. In the Google Cloud console, click the email address for the service account that you created.
    2. Click Keys.
    3. Click Add key, and then click Create new key.
    4. Click Create. A JSON key file is downloaded to your computer.
    5. Click Close.

15. Set the environment variable GOOGLE_APPLICATION_CREDENTIALS to the path of the JSON file that contains your credentials. This variable applies only to your current shell session, so if you open a new session, set the variable again.

    Example: Linux or macOS

    export GOOGLE_APPLICATION_CREDENTIALS="KEY_PATH"

    Replace KEY_PATH with the path of the JSON file that contains your credentials.

    For example:

    export GOOGLE_APPLICATION_CREDENTIALS="/home/user/Downloads/service-account-file.json"

    Example: Windows

    For PowerShell:

    $env:GOOGLE_APPLICATION_CREDENTIALS="KEY_PATH"

    Replace KEY_PATH with the path of the JSON file that contains your credentials.

    For example:

    $env:GOOGLE_APPLICATION_CREDENTIALS="C:\Users\username\Downloads\service-account-file.json"

    For command prompt:

    set GOOGLE_APPLICATION_CREDENTIALS=KEY_PATH

    Replace KEY_PATH with the path of the JSON file that contains your credentials.

16. Install the Google Cloud CLI.

17. To initialize the gcloud CLI, run the following command:

    gcloud init

Effectuer une requête d'annotation vidéo

gcloud

Utiliser la gcloud CLI pour appeler la commande detect-labels sur le chemin de la vidéo à analyser.

gcloud ml video detect-labels gs://YOUR_BUCKET/YOUR_OBJECT

Ligne de commande

1. Utilisez curl pour envoyer une requête POST à la méthode videos:annotate à l'aide de la commande gcloud auth application-default print-access-token pour coller un jeton d'accès dans votre compte de service :

   curl -X POST \
     -H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
     -H "Content-Type: application/json; charset=utf-8" \
     --data '{"inputUri":"gs://YOUR_BUCKET/YOUR_OBJECT","features":["LABEL_DETECTION"]}'\
     "https://videointelligence.googleapis.com/v1/videos:annotate"

2. L'API Video Intelligence crée une opération qui traite votre requête. La réponse inclut le nom de l'opération :

   {
     "name": "projects/PROJECT_NUMBER/locations/LOCATION_ID/operations/OPERATION_ID"
   }

3. Vous pouvez demander des informations sur l'opération en appelant le point de terminaison v1.operations. Pour ce faire, utilisez l'exemple de code ci-dessous en remplaçant OPERATION_NAME par la valeur "name" (nom) renvoyée à l'étape précédente :

    curl -X GET \
      -H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
      https://videointelligence.googleapis.com/v1/OPERATION_NAME

4. Vous obtenez des informations associées à votre opération. Si celle-ci est terminée, un champ done est ajouté et défini sur true :

   {
     "name": "projects/PROJECT_NUMBER/locations/LOCATION_ID/operations/OPERATION_ID",
     "metadata": {
     "@type": "type.googleapis.com/google.cloud.videointelligence.v1.AnnotateVideoProgress",
       "annotationProgress": [
         {
           "inputUri": "/YOUR_BUCKET/YOUR_OBJECT",
           "progressPercent": 100,
           "startTime": "2020-04-01T22:13:17.978847Z",
           "updateTime": "2020-04-01T22:13:29.576004Z"
         }
       ]
     },
     "done": true,
    ...
   }

Au bout d'un certain temps (une minute, en général), la requête renvoie les résultats d'annotation :

{
  "name": "projects/PROJECT_NUMBER/locations/LOCATION_ID/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.videointelligence.v1.AnnotateVideoProgress",
    "annotationProgress": [
      {
        "inputUri": "YOUR_BUCKET/YOUR_OBJECT",
        "progressPercent": 100,
        "startTime": "2020-04-01T22:13:17.978847Z",
        "updateTime": "2020-04-01T22:13:29.576004Z"
      }
    ]
  },
  "done": true,
  "response": {
    "@type": "type.googleapis.com/google.cloud.videointelligence.v1.AnnotateVideoResponse",
    "annotationResults": [
      {
        "inputUri": "/YOUR_BUCKET/YOUR_OBJECT",
        "segmentLabelAnnotations": [
          {
            "entity": {
              "entityId": "/m/07bsy",
              "description": "transport",
              "languageCode": "en-US"
            },
            "segments": [
              {
                "segment": {
                  "startTimeOffset": "0s",
                  "endTimeOffset": "38.757872s"
                },
                "confidence": 0.81231534
              }
            ]
          },
         {
          "entity": {
              "entityId": "/m/01n32",
              "description": "city",
              "languageCode": "en-US"
            },
            "categoryEntities": [
              {
                "entityId": "/m/043rvww",
                "description": "geographical feature",
                "languageCode": "en-US"
              }
            ],
            "segments": [
              {
                "segment": {
                  "startTimeOffset": "0s",
                  "endTimeOffset": "38.757872s"
                },
                "confidence": 0.3942462
              }
            ]
          },
          ...
          {
            "entity": {
              "entityId": "/m/06gfj",
              "description": "road",
              "languageCode": "en-US"
            },
            "segments": [
              {
                "segment": {
                  "startTimeOffset": "0s",
                  "endTimeOffset": "38.757872s"
                },
                "confidence": 0.86698604
              }
            ]
          }
        ]
      }
    ]
  }
}
   

Félicitations ! Vous avez envoyé votre première requête à l'API Video Intelligence.

Effectuer un nettoyage

Pour éviter d'encourir des frais inutiles liés à Google Cloud, supprimez votre projet à l'aide de Google Cloud Console si vous n'en avez plus besoin.

Étape suivante

• Suivez les guides pratiques.
• Découvrez les exemples et tutoriels.
• Consultez la documentation de référence sur l'API pour en savoir plus sur tous les appels d'API.