Annotate a video by using the command line

This page shows how to make a Video Intelligence API request with curl for projects that you own.

You can follow the steps on this page or try this quickstart as a Google Cloud Training lab.

Try it with a lab

Before you begin

  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.

    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.

  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.

    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.

  16. Install the Google Cloud CLI.
  17. To initialize the gcloud CLI, run the following command:

    gcloud init

Make an Annotate Video Request

gcloud

Use the gcloud CLI to call the detect-labels command on the path of the video to be analyzed.

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

Command-line

  1. Use curl to make a POST request to the videos:annotate method, using the gcloud auth application-default print-access-token command to paste in an access token to your service account:

    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. The Video Intelligence API creates an operation to process your request. The response includes the operation name:

    {
      "name": "projects/PROJECT_NUMBER/locations/LOCATION_ID/operations/OPERATION_ID"
    }
    
  3. You can request information on the operation by calling the v1.operations endpoint, replacing OPERATION_NAME in the example below with the name returned in the previous step:

     curl -X GET \
       -H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
       https://videointelligence.googleapis.com/v1/OPERATION_NAME
    
  4. You'll see information related to your operation. If the operation has completed, a done field is included and set to 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,
     ...
    }
    

After giving the request some time (about a minute, typically), the same request returns annotation results:

{
  "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
              }
            ]
          }
        ]
      }
    ]
  }
}
   

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

Clean up

To avoid unnecessary Google Cloud charges, use the Google Cloud console to delete your project if you do not need it.

What's next