Abstract

Yoga promotes physical and mental health but practicing correct posture alignment without expert help isn't easy. To solve these problems, we propose a VR-based yoga posture detection, classification, and correction system in this research. Real-time images of yoga poses were captured using an ESP32-CAM interfaced with Arduino and processed with Python. Mediapipe and OpenCV frameworks are responsible for pose detection and classification. At the same time, angle-based calculations help to detect whether the user has achieved Bridge Pose, Mountain Pose, Downward Dog pose, and Warrior II pose. Real-time voice feedback helps users fine-tune their alignment. This system has combined Blynk software with Unity to build an immersive virtual reality experience where a headset shows off pose animations. Combining AI and VR ensures the solution connects practitioners to expert instruction and correct posture in real time, ultimately enhancing the benefits of yoga as a practice.

Authors

G. Manisha, N.A. Meenakshi, S. Srinithi, Rajalakshmi Murugesan, S.A.R. Sheikh Mastan
Thiagarajar College of Engineering, India

Keywords

Mediapipe, OpenCV, Unity, Angle–Based Pose Recognition, Blynk Integration, Voice Feedback