ANALYSIS OF TRAINING MOVEMENTS USING COMPUTER VISION AND EVALUATION OF THEIR EFFECTIVENESS
Keywords:
computer vision, posture assessment, fitness exercises, real-time assessment, movement analysis, MediaPipe, feedback systems.Abstract
The study employed analytical review, systematic analysis, and comparative synthesis to examine current approaches to human posture assessment, movement analysis, remote exercise monitoring, and real-time feedback systems. The reviewed sources made it possible to identify a four-level framework for real-time fitness exercise assessment. This framework includes determining body support points, extracting kinematic characteristics, assessing movement phases and overall performance quality, and delivering interpretable feedback to the user. The analysis further demonstrated that integrating geometric, temporal, and qualitative characteristics significantly improves the reliability and robustness of such assessment systems. The scientific novelty of the study lies in presenting the fitness exercise assessment process not as a collection of isolated algorithms, but as a unified and interconnected digital analytical cycle in which each stage supports the next. The practical significance of the proposed approaches is determined by their potential application in home-based workouts, online fitness platforms, continuous fitness monitoring systems, and the initial stages of rehabilitation and recovery programs.
References
Badiola-Bengoa, A., & Mendez-Zorrilla, A. (2021). A systematic review of the application of camera-based human pose estimation in the field of sport and physical exercise. Sensors, 21(18), 5996. https://doi.org/10.3390/s21185996
Cao, Z., Simon, T., Wei, S.-E., & Sheikh, Y. (2017). Realtime multi-person 2D pose estimation using part affinity fields. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 7291–7299. https://doi.org/10.1109/CVPR.2017.143
Ekambaram, D., & Ponnusamy, V. (2024). Real-time monitoring and assessment of rehabilitation exercises for low back pain through interactive dashboard pose analysis using Streamlit: A pilot study. Electronics, 13(18), 3782. https://doi.org/10.3390/electronics13183782
Gao, Z., Chen, J., Liu, Y., Jin, Y., & Tian, D. (2025). A systematic survey on human pose estimation: Upstream and downstream tasks, approaches, lightweight models, and prospects. Artificial Intelligence Review, 58, 68. https://doi.org/10.1007/s10462-024-11060-2
Heo, S., Choi, T., & Choi, W. (2026). Clinical validation of an on-device AI-driven real-time human pose estimation and exercise prescription program: Prospective single-arm quasi-experimental study. Healthcare, 14(4), 482. https://doi.org/10.3390/healthcare14040482
Hoang, M. L. (2024). Human pose estimation for rehabilitation by computer vision (pp. 110–128). https://doi.org/10.2174/9789815313055124010008
Kotte, H., Daiber, F., Kravčík, M., & Duong-Trung, N. (2024). FitSight: Tracking and feedback engine for personalized fitness training. Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization, 223–231. https://doi.org/10.1145/3627043.3659547
Naseer, A., Raza, A., Afzal, H., Smerat, A., Fitriyani, N. L., Gu, Y., & Syafrudin, M. (2025). Human pose estimation in physiotherapy fitness exercise correction using novel transfer learning approach. PeerJ Computer Science, 11, e2854. https://doi.org/10.7717/peerj-cs.2854
Rehabilitation Training Evaluation and Correction System Based on BlazePose. (2022). https://doi.org/10.1109/ECICE55674.2022.10042886
Samanta, A., Kotte, H., Handwerk, P., Mat Sanusi, K. A., Geisen, M., Kravčík, M., & Duong-Trung, N. (2024). IMPECT-POSE: A complete front-end and back-end architecture for pose tracking and feedback. Adjunct Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization, 142–147. https://doi.org/10.1145/3631700.3664865
Sideridou, M., Kouidi, E., Hatzitaki, V., & Chouvarda, I. (2024). Towards automating personal exercise assessment and guidance with affordable mobile technology. https://doi.org/10.3390/s24072037
Stenum, J., Cherry-Allen, K. M., Pyles, C. O., Reetzke, R. D., Vignos, M. F., & Roemmich, R. T. (2021). Applications of pose estimation in human health and performance across the lifespan. Sensors, 21(21), 7315. https://doi.org/10.3390/s21217315
Tharatipyakul, A., Srikaewsiew, T., & Pongnumkul, S. (2024). Deep learning-based human body pose estimation in providing feedback for physical movement: A review. Heliyon, 10, e36589. https://doi.org/10.1016/j.heliyon.2024.e36589
Wang, J., & Zhang, Y. (2023). Design of real-time movement guidance system based on Blazepose on mobile terminal. Academic Journal of Science and Technology, 4(3), 162–164. https://doi.org/10.54097/ajst.v4i3.5050
Woo, Y., & Jeong, H. (2025). Exercise assessment based on human pose estimation and relative phase for real-time remote exercise system. IEEE Access, 13, 53203–53213. https://doi.org/10.1109/ACCESS.2025.3551834
Yang, H., Wang, Y., & Shi, Y. (2022). Rehabilitation training evaluation and correction system based on BlazePose. 27–30. https://doi.org/10.1109/ECICE55674.2022.10042886
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Yassawi Journal of Engineering Science
This work is licensed under a Creative Commons Attribution 4.0 International License.
