ASSESSMENT OF BIOMECHANICAL PARAMETERS OF PHYSICAL EXERCISES BASED ON COMPUTER VISION

Currently, increasing the effectiveness of the training process, reducing the risk of injuries, and personalizing training and education are key challenges in the fields of sports and physical education. In this context, research focused on the automated analysis and evaluation of physical exercises using artificial intelligence (AI) and computer vision technologies is rapidly developing. These technologies enable real-time tracking of human movement and accurate determination of biomechanical parameters.

This paper presents the development of an intelligent computer vision – based fitness assistant designed to recognize physical activity, analyze exercise execution techniques, and provide users with real-time feedback. The proposed system is implemented using deep learning methods based on the Ultralytics YOLO architecture and the OpenCV library. The system detects key body landmarks and joints, analyzes their spatial positions, evaluates the correctness of exercise execution, counts repetitions, and determines performance metrics.

During the study, a dataset of video recordings containing various exercise movements was collected, preprocessed, and annotated. Deep neural network models were trained, and their accuracy and performance were evaluated. In addition, biomechanical modeling was applied to calculate loads on individual body segments and to generate corrective recommendations aimed at improving movement quality.

Experimental results demonstrate that the proposed system achieves high accuracy in exercise recognition and operates efficiently in real time. The developed software solution can be used by individuals training at home, athletes, coaches, and physical education professionals as an additional tool for monitoring and optimizing the training process. The research findings confirm the promising potential for widespread application of artificial intelligence and computer vision technologies in the fields of fitness and sports.

1. Moeslund T.B., Thomas G., Hilton A. Computer Vision in Sports. Advances in Computer Vision and Pattern Recognition. https://link.springer.com/book/10.1007/978-3-319-09396-3#bibliographicinformation (date of access: 17.04.2024). (In English).

2. Naik B.T. A Comprehensive Review of Computer Vision in Sports: Open Issues / B.T. Naik, M.F. Hashmi, N.D. Bokde // Future Trends and Research Directions. Applied Sciences. – 2022. – vol. 12, issue 9. https://doi.org/10.3390/app12094429. (In English).

3. Smith J., Johnson M. Exploring the applications of computer vision in sports. https://www.ultralytics.com/blog/exploring-the-applications-of-computer-vision-in-sports (date of access: 17.01.2026). (In English).

4. AI-FIT COACH – Revolutionizing Personal Fitness with Pose Detection, Correction and Smart Guidance / K. Lakshmi Joshitha et al. // International Conference on Communication, Computing and Internet of Things, Chennai, India. – 2024. – R. 1-5. https://doi.org/10.1109/IC3IoT60841.2024.10550400. (In English).

5. Lakshay Gupta Virtual Fitness Trainer using Artificial Intelligence / Lakshay Gupta, Shrey Gurbuxani, Kapil Madan // Proceedings of the 2024 Sixteenth International Conference on Contemporary Computing. – 2024. – R. 226-233. https://doi.org/10.1145/3675888.3676056. (In English).

6. Empowering the Sports Scientist with Artificial Intelligence in Training, Performance, and Health Management / Nuno Mateus et al. // Sensors. – 2025. – vol. 25, № 1. – R. 1-12. https://doi.org/10.3390/s25010139. (In English).

7. Enhanced Gym Performance Prediction using Machine Learning: A Comprehensive Model for Personalized Fitness / R. Babitha Lincy et al. // 3rd International Conference on Automation, Computing and Renewable Systems, Pudukkottai, India. – 2024. – R. 1396-1400. https://doi.org/10.1109/ICACRS62842.2024.10841763. (In English).

8. Vel'mozhko N.I. Razrabotka algoritma raspoznavaniya fizicheskikh uprazhnenii / N.I. Vel'mozhko, A.A. Boiko // Fizika i radioehlektronika v meditsine i ehkologii: trudy XIV Mezhdunarodnoi nauchnoi konferentsii. Kn. 2. – Vladimir, 2020. – S. 94-99. (In Russian).

9. Germanov K.V. Analiz primeneniya komp'yuternogo zreniya v sporte / K.V. Germanov, T.V. Krasnoperova, A.A. Germanova // Uchenye zapiski universiteta imeni P. F. Lesgafta. – 2023. – № 9 (223). – S. 100–105. (In Russian).

10. Terekhin A.D. Sistema otsenivaniya sportivnykh uprazhnenii po neirosetevomu analizu videoryada / A.D. Terekhin, O.R. Il'yalov, A.V. Stepanov // Prikladnaya matematika i voprosy upravleniya. – 2022. – № 1. – S. 75-86. (In Russian).

11. Analiz podkhodov, metodov i reshenii dlya detektirovaniya pozy cheloveka. Vybor instrumenta dlya zadachi opredeleniya ehmotsional'nogo sostoyaniya cheloveka po ego poze / Yu.V. Kiselev i dr. // Sovremennye naukoemkie tekhnologii. – 2023. – № 6. – S. 41-47. (In Russian).

12. Sivtsov I.V. Revolyutsiya iskusstvennogo intellekta v sportivnom turizme: ehffektivnost', bezopasnost' i personalizatsiya / I.V. Sivtsov // Problemy i perspektivy razvitiya sportivnogo orientirovaniya i aktivnykh vidov turizma: materialy III Vserossiiskoi nauchno-prakticheskoi konferentsii s mezhdunarodnym uchastiem. – Smolensk: Izd-vo SGUS, 2024. – S. 222-224. (In Russian).

13. Kobernik P.S. Ispol'zovanie iskusstvennogo intellekta v sfere sporta dlya optimizatsii raboty fitnes-prilozhenii / P.S. Kobernik // Molodoi uchenyi. – 2024. – № 15(514). – S. 453-454. (In Russian).

14. Kulakov P.A. Osobennosti razrabotki komp'yuternykh obuchayushchikh trenazherov v Unity 3D / P.A. Kulakov, A.S. Eremin // Izvestiya Tul'skogo gosudarstvennogo universiteta. Tekhnicheskie nauki. – 2024. – № 1. – S. 177-181. (In Russian).

15. Mednikova E.V. Perspektivy primeneniya prilozhenii s iskusstvennym intellektom v fizicheskoi kul'ture / E.V. Mednikova, E.S. Kotlyarov, M.V. Popova // Studencheskii sport: innovatsii, tekhnologii i tsifrovaya transformatsiya: materialy I Vserossiiskoi nauchno-prakticheskoi konferentsii (Kaliningrad, 30-31 marta 2023 g.). – Kaliningrad: Izd-vo BFU im. I. Kanta, 2023. – S. 153-156. (In Russian).

16. Raspoznavanie aktivnosti cheloveka po videodannym / A.V. Pyataeva i dr. // International Journal of Advanced Studies. – 2022. – T. 12, № 4. – S. 96-110. (In Russian).

17. Shrainer B.A. Innovatsionnye podkhody v organizatsii zanyatii fizicheskoi kul'turoi s primeneniem komp'yuternykh tekhnologii / B.A. Shrainer, K.M. Zhomin // Vestnik pedagogicheskikh innovatsii. – 2023. – № 4(72). – S. 77-85. (In Russian).

18. Konopko E.A. Obrazovanie i iskusstvennyi intellekt: vozmozhnosti, ogranicheniya i perspektivy / E.A. Konopko, M.G. Sidin // Studencheskaya nauka dlya razvitiya informatsionnogo obshchestva: materialy KhV Vserossiiskoi nauchno-tekhnicheskoi konferentsii s priglasheniem zarubezhnykh uchenykh. – Stavropol': Izd-vo SKFU, 2024. – S. 37-42. (In Russian).