PoseTracker supports two simple integration modes.
Both modes use the same tracking engine, the same outputs, and the same message format.
1️⃣ Real-time tracking (camera / webcam)
PoseTracker analyzes movements live from the device camera.
Typical use cases:
fitness coaching
real-time rep counting (like counting squats)
posture feedback
live movement analysis
Endpoint:
Your app opens the URL in an iframe or WebView and PoseTracker processes the camera stream directly.
2️⃣ Uploaded video or image analysis
PoseTracker analyzes a video or image uploaded by the user.
Typical use cases:
analyzing workout recordings
generating skeleton videos
extracting keypoints
offline rep counting
Endpoint:
The user uploads a file and PoseTracker processes it directly in the browser.
Same Outputs in Both Modes
Both integration modes return the same type of events and developer outputs, including:
repetition counter
form score
progression
keypoints
angles
recommendations
Your application receives these events through postMessage / WebView bridge.
🆕 Reference Movement Comparison 🆕
PoseTracker now supports reference movement tracking.
Developers can create a reference movement in the PoseTracker dashboard using a short video containing one ideal repetition of a movement.
PoseTracker analyzes this video and generates the movement signature.
This reference can then be used to:
detect repetitions of the same movement
measure similarity to the reference
score each repetition
The reference can be used with both real-time tracking and uploaded video analysis.
Example:
or
When using a reference movement, PoseTracker compares the user's movement to the reference and returns similarity scores.
⚠️ reference cannot be combined with exercise.
How PoseTracker Works
1️⃣ Your application opens the PoseTracker URL in a WebView or iframe
2️⃣ PoseTracker runs pose estimation locally on end-user device
3️⃣ PoseTracker detects movements and computes results
4️⃣ PoseTracker sends structured messages to your application
