International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AI-Based Real-Time Exercise Posture Detection and Corrective Feedback System |
|---|---|
| ABSTRACT | Realtime exercise tracking and Feedback system is developed to monitor, analyze, and evaluate physical workout activities using computer vision and machine learning techniques. The system records live video and automatically detects human body keypoints using pose estimation algorithms. Based on these extracted skeletal features, the system identifies the type of exercise being performed and evaluates posture, movement accuracy, and repetition count. A set of predefined criteria is used to filter out incorrect poses and give meaningful responses to the user. The proposed system offers real-time corrective suggestions to prevent injuries and enhance workout efficiency. This feedback mechanism allows users to improve their form without the requirement for human supervision. The system aims to deliver an interactive, automated fitness assistant capable of tracking exercises, analyzing performance, and providing instant, personalized guidance for a safer and more effective workout experience. |
| AUTHOR | DR. CHETANA PRAKASH, VAISHNAVI M NAIK, MAMATA MEDUR, THIMMESH M V Professor, Dept. of Computer Science & Design, Bapuji Institute of Engineering and Technology, Davangere, Karnataka, India UG Student, Dept. of Computer Science & Design, Bapuji Institute of Engineering and Technology, Davangere, Karnataka, India |
| VOLUME | 177 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1312050 |
| pdf/50_AI-Based Real-Time Exercise Posture Detection and Corrective Feedback System.pdf | |
| KEYWORDS | |
| References | [1] Y. Z. Wang, X. Li, M. Zhang, "Real-time Human Pose Estimation for Fitness Applications," IEEE Transactions on Multimedia, 2020. [2] P. Gupta, R. Singh, H. Kumar, "AI-Based Exercise Form Correction Using Pose Estimation," International Conference on Computer Vision and Pattern Recognition (CVPR), 2021. [3] J. Choi, D. Lee, S. Park, "Exercise Classification and Feedback System Using Computer Vision," Journal of Machine Learning Research (JMLR), 2022. [4] S. Kumar, T. S. Lai, M. Tiwari, "Pose Net: Real-time Human Pose Estimation for Fitness and Rehabilitation," ACM Transactions on Graphics (TOG), 2021. [5] L. Zheng, H. Gao, Z. Yang, "Computer Vision for Exercise Recognition and Feedback," IEEE Transactions on Multimedia, 2020. [6] A. R. Nahar, P. Ghosh, J. A. Soni, "Deep Learning for Exercise Tracking Using Pose Estimation," International Conference on Machine Learning and Applications (ICMLA), 2023. [7] X. Liu, R. Shen, Q. Li, "Real-Time Fitness Monitoring Using Pose Estimation and Feedback," Journal of Artificial Intelligence Research, 2021. [8] M. Zhang, S. P. Lee, L. Yang, "Virtual Coaching Using AI and Computer Vision for Exercise Improvement," ACM Transactions on Computer-Human Interaction (TOCHI), 2022. |
