Video

Face Grouping

Detect, track, and group faces across video frames

10K runs

Note: This playground provides simulated output to showcase functionality. No input data is processed or stored on our servers. Use this demo to explore the feature extractor's capabilities before integrating it into your application.

Input

File URL string

Enter a URL to a video file

Upload video

Drag and drop a video file here, or click to browse

Select File

# video_url string

Required

URL pointing to video file. Supported formats: MP4, MOV, AVI. Default: undefined

# min_face_size integer

Minimum face size in pixels to detect. Default: 40

# detection_threshold number

Confidence threshold for face detection (0.0-1.0). Default: 0.7

# similarity_threshold number

Similarity threshold for grouping faces (0.0-1.0). Default: 0.85

# detection_mode string

Detection mode to use. Default: standard

# extract_attributes boolean

Extract facial attributes (age, gender, emotion). Default: true

# extract_landmarks boolean

Extract facial landmarks (eyes, nose, mouth positions). Default: false

# generate_embedding boolean

Generate face embedding for identity matching. Default: true

# crop_faces boolean

Generate cropped face images. Default: true

# frame_sampling integer

Process every Nth frame for performance. Default: 1

Output

{
  "document_id": "doc_abc123",
  "collection_id": "col_xyz789",
  "source_object_id": "obj_def456",
  "person": {
    "id": "person_12345",
    "confidence": 0.94,
    "appearances": [
      {
        "frame_number": 120,
        "timestamp": 4,
        "bounding_box": {
          "x": 125,
          "y": 80,
          "width": 120,
          "height": 150
        },
        "attributes": {
          "age_estimate": 32,
          "gender": "female",
          "emotion": "happy",
          "confidence": 0.89
        }
      }
    ],
    "embedding": {
      "model": "facenet_v2",
      "dimension": 512,
      "vector": [
        0.12,
        0.34
      ],
      "normalized": true
    },
    "first_appearance": 4,
    "last_appearance": 32.5,
    "total_frames": 28,
    "representative_image_url": "https://storage.example.com/faces/person_12345.jpg"
  },
  "video": {
    "filename": "interview.mp4",
    "width": 1920,
    "height": 1080,
    "fps": 30,
    "duration": 180.5
  }
}

Already have embeddings? Skip extraction — search your own vectors with MVS. First 1M vectors free.

Try MVS →