Human Pose Estimation

Use Human Pose Estimation to track the position of people in images and video. Build an AI-powered fitness coach, immersive AR experiences, and more.

Custom Training Models for Pose Estimation

You can train a custom model that is compatible with the Pose Estimation API by using Quickstart: Use Fritz AI Studio to Train a Custom Model.

Pre-trained Models

Include our models directly in your app and use them with the API.

Name Example Description Keypoints
Human pose_estimation A model that tracks one or more poses in the scene. Identifies 17 body keypoints. Face: nose, eyes, ears; Torso: shoulders, elbows, wrists; Legs: hips, knees, ankles. View all COCO keypoints

Technical Specifications

Architecture Format(s) Size Input Output Benchmarks
MobileNet backbone Core ML (iOS), TensorFlow Lite (Android) ~5 MB 353x257-pixel image Position of each person and body part detected, Number of people detected, The confidence associated with each detection 20 FPS on iPhone X, 10 FPS on Pixel 2