Design of an Artificial Vision System for Exercise Monitoring in Healthy Aging

Abstract:

This study presents the design and pilot evaluation of a computer vision–based system for monitoring exercise performance in older adults, aiming to reduce frailty-related risks without the need for wearable sensors. Using MediaPipe and OpenCV, the system tracks posture and movement in real time and provides feedback on exercise execution. A pilot test was conducted with 14 volunteers performing seven exercises from the Vivifrail Spanish program (Wheel A). Performance was evaluated using perfomance analysis, yielding recognition rates between 91.06\% and 100\% across exercises. While the system showed high accuracy in detecting posture and repetitions, challenges such as camera positioning, clothing variability, and the absence of validation in the target population remain. These findings demonstrate the feasibility of computer vision for exercise monitoring and support its potential as an accessible tool for fall prevention and functional assessment in older adults. Future work will focus on clinical validation and integration into mobile platforms for home based use. This approach will allow older population to adequately perform exercises from the Vivifrail program, while professionals, as physiotherapists and geriatricians, can monitor their progress remotely, adjusting the program when needed.

• Periodical: Journal of Biomimetics, Biomaterials and Biomedical Engineering (Volume 71)
• Pages: 129-138
• DOI: https://doi.org/10.4028/p-P2KnGL
• Online since: February 2026
• Authors: Karla Miriam Reyes Leiva*, Gloria Zapata, Maryame Heydari, Elena Villalba, Ricardo Imbert
• Keywords: Biomechanics, Computer Vision, Exercise Monitoring, Fall Prevention, Healthy Aging

References

[1] OMS. (2022). Global strategy and action plan on ageing and health. https://www.who.int/publications/i/item/9789241513500

[2] OMS. (2021, abril 26). Falls. https://www.who.int/news-room/fact-sheets/detail/falls

[3] Landi, F., Sieber, C., Fielding, R. A., Rolland, Y., and Guralnik, J. (2018). Nutritional Intervention in Sarcopenia: Report from the International Conference on Frailty and Sarcopenia Research Task Force. The Journal of Frailty & Aging, 7(4), 247-252

DOI: 10.14283/jfa.2017.26

[4] Larsson, L., Degens, H., Li, M., Salviati, L., Lee, Y. il, Thompson, W., Kirkland, J. L., and Sandri, M. (2018). Sarcopenia: Aging-Related Loss of Muscle Mass and Function. Physiological Reviews, 99(1), 427

DOI: 10.1152/physrev.00061.2017

[5] Assi, S., Zhang, W., Carey, J., Deal, J., Huang, A., Oh, E., Martinez-Amezcua, P., Reed, N. (2023). The association of hearing loss with frailty among community-dwelling older adults: Findings from the National Health and Aging Trends Study. The National Health and Aging Trends Study, 23(754)

DOI: 10.1186/s12877-023-04465-1

[6] Y. Li, W. Zhang, H. Ma, F. Chen, D. Sun, X. Cheng, Y. Zheng, Z. Wang, S. Cai. (2023). Posture Detection Based on Kinect and YOLO Technologies. 2023 5th International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI), 205-209

DOI: 10.1109/RICAI60863.2023.10489539

[7] Izquierdo, M. (2017). The Strategy for the Promotion of Health and Quality of Life in the European Union https://vivifrail.com

[8] Ma, B., Yang, J., Wong, F. K. Y., Wong, A. K. C., Ma, T., Meng, J., Zhao, Y., Wang, Y., and Lu, Q. (2023). Artificial intelligence in elderly healthcare: A scoping review. Ageing Research Reviews, 83, 101808

DOI: 10.1016/j.arr.2022.101808

[9] Zahedian-Nasab, N., Jaberi, A., Shirazi, F., and Kavousipor, S. (2021). Effect of virtual reality exercises on balance and fall in elderly people with fall risk: A randomized controlled trial. BMC Geriatrics, 21(1), 509

DOI: 10.1186/s12877-021-02462-w

[10] Villalba, E., de Antonio, A., and Laosa, O. (2022). Computational ecosystem with motivational support and functional assessment for an autonomous exercise program for healthy aging (MOTIVA). Ministry of Science and Innovation.https://ageinglab.ctb.upm.es/en/motiva/

[11] Wang, S., Zhang, J., Zhang, X., Han, X., Chen, J., Hong, Z., Wang, C., and Zhao, H. (2024). Lightweight fall detection system based on Orangepi 5B. Ninth International Symposium on Sensors, Mechatronics, and Automation System (ISSMAS 2023), 12981, 539-544

DOI: 10.1117/12.3015158

[12] Piculell, E., Skär, L., Sanmartin Berglund, J., Anderberg, P., and Bohman, D. (2021). A concept analysis of health communication in a home environment: Perspectives of older persons and their informal caregivers. Scandinavian Journal of Caring Sciences, 35(3), 1006-1024

DOI: 10.1111/scs.12928

[13] Yeh, Shen, W.-C., Ma, C.-W., Yeh, Q.-T., Kuo, C.-W., and Chen, J.-S. (2023). Real-time Human Movement Recognition and Interaction in Virtual Fitness using Image Recognition and Motion Analysis. 2023 12th International Conference on Awareness Science and Technology (iCAST), 242-246

DOI: 10.1109/iCAST57874.2023.10359266

[14] K. Aarthy, and A. A. Nithys. (2023). Yoga Pose Detection and Identification Using MediaPipe and OpenPose Model. 2023 International Conference on Computer Science and Emerging Technologies (CSET), 1-7

DOI: 10.1109/CSET58993.2023.10346786

[15] Wang, C., Ravi, D., Deligianni, F., Berthelot, M., Andreu-Perez, J., Lo, B., and Yang, G.-Z. (2017). Deep Learning for health informatics. IEEE Journal of Biomedical and Health Informatics

DOI: 10.1109/JBHI.2016.2636665

[16] Ullrich, L., Buchholz, M., Dietmayer, K., & Graichen, K. (2025). Expanding the Classical V-Model for the Development of Complex Systems Incorporating AI. arXiv preprint arXiv:2502.13184

DOI: 10.1109/tiv.2024.3434515

[17] Chen, H., & Fan, R. (2025). Improved convolutional neural network for precise exercise posture recognition and intelligent health indicator prediction. Scientific Reports, 15(1), 21309

DOI: 10.1038/s41598-025-01854-x

[18] Kosaraju, D. (2025). Computer Vision for Posture and Gait Analysis in Physical Therapy: Enhancing Motion Assessment Using Deep Learning. International Journal of Artificial Intelligence in Medicine (IJAIMED), 3(1), 33–42

DOI: 10.34218/IJAIMED_03_01_003

[19] Wagh, V., Scott, M. W., & Kraeutner, S. N. (2024). Quantifying Similarities Between MediaPipe and a Known Standard to Address Issues in Tracking 2D Upper Limb Trajectories: Proof of Concept Study. JMIR Formative Research, 8, e56682

DOI: 10.2196/56682

[20] Shang, M., Dedeyne, L., Dupont, J., Vercauteren, L., Amini, N., Lapauw, L., Gielen, E., Verschueren, S., Varon, C., De Raedt, W., & Vanrumste, B. (2024). Otago Exercises Monitoring for Older Adults by a Single IMU and Hierarchical Machine Learning Models. arXiv preprint arXiv:2310.03513.

DOI: 10.1109/tnsre.2024.3355299

[21] García-de-Villa, S., Casillas-Pérez, D., Jiménez-Martín, A., & García-Domínguez, J. J. (2024). Simultaneous exercise recognition and evaluation in prescribed routines: Approach to virtual coaches. arXiv preprint arXiv:2401.12857.

DOI: 10.1016/j.eswa.2022.116990