Leveraging OpenCV for Precise Yoga Pose Estimation and Reducing Injury Risks

Jha, Anand (2023) Leveraging OpenCV for Precise Yoga Pose Estimation and Reducing Injury Risks. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (9MB) | Preview
Preview	PDF (Configuration Manual) Download (2MB) | Preview

Abstract

This project aligns yoga practices with AI forefront technology to demonstrate a real-time yoga pose detection system. Using a diverse training set and MediaPipe’s Blazepose model, landmark points were extracted and organized for machine learning. The top-performing model was – XGBoost, which demonstrates better accuracy with the complex spatial relationships observed among different yoga poses. Inclusive and personalized guidance is provided by the system using text-to-speech, visual cues and pose-specific benefits. It is this XGBoost’s 92% accuracy that underlies its performance in seamless pose classification. The system provides real-time feedback about pose correctness, total pose duration and helpful insights. These features include pose analysis, visual overlays, and auditory guidance to meet the needs of different users. This blend of AI-powered pose detection, feedback loop mechanism and inclusive design defines the shift in paradigm towards opening up a yoga experience for all practitioners.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Menghwar, Teerath Kumar UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QP Physiology Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine > Personal Health and Hygiene
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	09 May 2025 09:26
Last Modified:	09 May 2025 09:26
URI:	https://norma.ncirl.ie/id/eprint/7533

Actions (login required)

View Item