Self-Learning Yoga Monitoring System Based on Pose Estimation
“Real-time computer vision pose estimation framework providing biomechanical joint-angle correction and feedback for unassisted yoga practice.”
Project Scope & Details
This project develops an intelligent self-learning yoga monitoring system utilizing multi-keypoint pose estimation. The system tracks 2D/3D human joint landmarks, analyzes real-time biomechanical angles against reference postures, and provides corrective visual and audio feedback to practitioners.
3D Joint Angle Biomechanical Extraction
Calculates real-time angular positions of spine, hips, knees, and shoulders from monocular webcam feeds.
Real-Time Postural Alignment Feedback
Compares practitioner posture against expert biomechanical archetypes, providing visual correction guidance.
Ergonomic Overextension Prevention
Detects hazardous joint hyper-extension and strain risks, ensuring safe home self-practice.
Privacy-Preserving On-Device Processing
Executes 100% of computer vision pose estimation locally in the client browser without external video streaming.
Biomechanical Yoga Pose Estimation Pipeline
A Self Learning Yoga Monitoring System Based on Pose Estimation
Authors: Prahitha Movva, Hemanth Pasupuleti, Himangshu Sarma
- Prahitha Movva
- Hemanth Pasupuleti
- Dr. Himangshu Sarma