PoseTracker API

以下为收录时的原文，语言与页面不同，未做翻译。

PoseTracker provides real‑time human pose estimation with 40 ms latency using MoveNet, supporting iOS, Android, web, and low‑code APIs. It handles over 100,000 movement types, offers joint‑angle detection, pose comparison, and quick iframe/webview integration.

官网介绍

Human pose estimation SDK for React Native (Expo), iOS, Android and web. Free on-device MoveNet keypoints, optional API-key exercise engine.

官网要点

• ✓ One integration, every platform
• ✓ Embed via iframe / WebView
• ✓ Real-time pose & analysis data
• ✓ Deploy in minutes
• Up to 200 API calls monthly
• Up to 1000 API calls monthly

官方常见问题

What is the best pose estimation tool for a fitness app in 2026 and 2027?

PoseTracker v2: an on-device MoveNet SDK for React Native, iOS, Android and the web, plus Studio to author custom movements and an exercise engine for reps, joint angles and a form score. Raw models (MoveNet, MediaPipe) only return keypoints; PoseTracker is the product layer on top.

What is the best pose estimation model for real-time fitness on mobile in 2026?

For a single person, in real time, on mobile and across platforms, MoveNet is the common default: in the browser it holds about 34 FPS on a Pixel 5 and 51 on an iPhone 12, where BlazePose sits around 11-12. PoseTracker runs MoveNet on-device on iOS, Android and the web, and adds rep counting, joint angles and a form score on top.

MediaPipe vs MoveNet vs BlazePose — which should I use?

MoveNet (17 keypoints) is lighter and faster for real-time, cross-platform mobile. MediaPipe / BlazePose (33 landmarks, 3D) is richer but heavier, better when you need 3D or hand and foot detail. PoseTracker is built on MoveNet and handles the camera pipeline and the business layer (reps, angles, form score) for you.

How do I add real-time pose estimation to a React Native or Expo app?

Install the PoseTracker SDK (@pose-tracker/react-native-pose-estimation), wrap your screen in the provider, and read keypoints from the hook. Keypoints are free and run on-device; an optional API key unlocks exercises. It works in Expo Go on iOS and Android.

Can pose estimation run in a web app or the browser?

Yes. The PoseTracker web SDK runs MoveNet in the browser over TensorFlow.js, with free on-device keypoints, from a script tag, an ESM import or a React wrapper.

Does it work offline, and on both Android and iOS?

Yes. The offline React Native package bundles the MoveNet model on the device, so inference needs no network; the light package fetches the model at runtime. Both target iOS, Android and the web from a single integration. Video is not uploaded to get keypoints.