Workout Form Analysis Model
I built a computer vision model that analyzes workout technique using pose estimation. It tracks key body landmarks and checks angles and posture during exercises like squats, lunges, and forward bends. If the form becomes unsafe, the system triggers an alarm sound to warn the user.
Why it matters
Many people train without a coach and rely on online videos. Small posture mistakes can build up and lead to injury. This project focuses on early detection of risky form so users can correct it immediately.
Project overview
A detailed explanation of the whole process of creating this system. It includes codes, screenshots, and descriptions.
Read the articleUsed technology
How it works
- Detects body landmarks with MediaPipe Pose.
- Computes angles (e.g., knee/hip/ankle) and compares them to safe thresholds.
- Uses simple rule-based logic to identify harmful technique.
- Plays an alarm sound when unsafe posture is detected.
Status
The demo version is done.