High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Yog-Guru: AI based Human Pose Detection, Correction & Visualization

Author(s):

Shravani Madiwale , Dr. D.Y Patil Institute of Engineering, Management and Research, Akurdi; Shifa Dewani, Dr. D.Y Patil Institute of Engineering, Management and Research, Akurdi; Priyanshu Deore, Dr. D.Y Patil Institute of Engineering, Management and Research, Akurdi; Shreyash Murumkar, Dr. D.Y Patil Institute of Engineering, Management and Research, Akurdi; Mr. Jitendra Garud, Dr. D.Y Patil Institute of Engineering, Management and Research, Akurdi

Keywords:

Machine Learning, Artificial Intelligence, Posenet, KNN, Tensorfow, Mediapipe, Computer Vision, Speech Recognition, Yoga Pose Detection, K-Mean Clustering, Deep Learning, Pose Alignment, Data Visualization

Abstract

Yoga is an intricate postured type of exercise originated in ancient India, that has acquired popularity worldwide for its various health benefits, including spiritual, physical, and mental well-being Yoga but, improper poses may cause injuries and slow progress. This project takes advantage of the strength of Machine learning, KNN and TensorFlow to overcome this issue. We present an AI enhanced system that detects and aligns yoga poses in real-time. Users can select from a set of yoga poses, view step-by-step guidelines, and trigger the system. Once the proper pose is obtained, 17 body points become green. triggering a timer with alarm- sound-like functionality. If the posture becomes improper, the sound and timer stop, giving direct feedback. This project seeks to improve the safety of yoga practice, offer real-time instruction, and monitor progress, enabling a better and more enjoyable experience with yoga.

Other Details

Paper ID: IJSRDV13I20071
Published in: Volume : 13, Issue : 2
Publication Date: 01/05/2025
Page(s): 106-111

Article Preview

Download Article