Web-Based Application for Assessment of Physical Exercises using Machine Learning

Rafael Santos; Andrei Sant’anna; Luan Machado; Lucas Santos; Márcio Soussa

doi:10.5753/jis.2026.6417

Authors

Rafael Santos SENAI CIMATEC University https://orcid.org/0009-0005-0401-7314
Andrei Sant’anna SENAI CIMATEC University https://orcid.org/0009-0007-3717-3369
Luan Machado SENAI CIMATEC University https://orcid.org/0009-0006-7634-1452
Lucas Santos SENAI CIMATEC University https://orcid.org/0009-0004-3392-6034
Márcio Soussa SENAI CIMATEC University https://orcid.org/0000-0002-3359-4760

DOI:

https://doi.org/10.5753/jis.2026.6417

Keywords:

Computer Vision, Pose Estimation, Machine Learning, Physical Exercise, Web Application

Abstract

The rise of digital platforms for physical activity in the post-pandemic period has driven the demand for accessible and automated solutions to support and correct exercise performance remotely. Recent advances in computer vision have enabled the development of systems that provide real-time feedback using only conventional cameras, eliminating the need for specialized sensors. Using the Design Science Research (DSR) methodology, a web-based solution for real-time exercise assessment powered by machine learning was developed as an artifact. This work covers the entire development pipeline, including data collection and labeling, training of machine learning models, conversion and optimization for inference in the browser environment, and integration into a fully functional and responsive prototype web application. Furthermore, a modular software design is proposed to support scalability and extensibility, allowing the seamless inclusion of new validation strategies. Results show that all trained models achieved accuracies above 90% and executed efficiently in the browser, with inference times below 5 ms across different devices.

Downloads

Download data is not yet available.

References

Bazarevsky, V., Grishchenko, I., Raveendran, K., Zhu, T., Zhang, F., and Grundmann, M. (2020). Blazepose: On-device real-time body pose tracking.

Dias, V., Mauricio, C., and Peres, F. (2023). Análise e orientação de postura nos exercícios de calistenia usando estimativa de pose humana. In Anais do XX Congresso Latino-Americano de Software Livre e Tecnologias Abertas, pages 154–157, Porto Alegre, RS, Brasil. SBC. DOI: https://doi.org/10.5753/latinoware.2023.236523.

Difini, G. M., Martins, M. G., and Barbosa, J. L. V. (2021). Human pose estimation for training assistance: a systematic literature review. In Proceedings of the Brazilian Symposium on Multimedia and the Web, WebMedia '21, page 189–196, New York, NY, USA. Association for Computing Machinery. DOI: https://doi.org/10.1145/3470482.3479633.

Draelos, R. (2019). Measuring performance: The confusion matrix. Blog post on Glass Box Medicine.

Fong, A. and Otto, M. (2025). Yoga for all. Kaggle Dataset, released under MIT License.

G, A., Anas, M., B, N. K., G, R., and Jituri, V. (2023). Ai fitness trainer using human pose estimation. International Journal of Engineering Research & Technology (IJERT), 11(08). RTCSIT – 2023.

Gonçalves, J., Palhares, J., Soares, V. N. G. J., and Neves, P. A. (2024). Detection and pose adjustment in physical exercises using computer vision techniques: Approaches, challenges and opportunities. Revista de Informática Teórica e Aplicada, 31(1):11–31. DOI: https://doi.org/10.22456/2175-2745.135436.

Han, J., Kamber, M., and Pei, J. (2011). Data Mining: Concepts and Techniques. Morgan Kaufmann, San Francisco, CA, 3 edition.

Ko, Y.-M., Nasridinov, A., and Park, S.-H. (2024). Real-time ai posture correction for powerlifting exercises using yolov5 and mediapipe. IEEE Access, 12:195830–195853. DOI: https://doi.org/10.1109/ACCESS.2024.3516723.

Kwon, Y. and Kim, D. (2022). Real-time workout posture correction using opencv and mediapipe. The Journal of Korean Institute of Information Technology, 20:199–208. DOI: https://doi.org/10.14801/jkiit.2022.20.1.199.

Martinez, J. J. L., Rodríguez-Roiz, J. M., and Cánovas, C. S. (2020). Musculoskeletal injuries secondary to exercise during confinement by the pandemic covid-19. Medicina Clínica (English Edition), 155(5):221–222. DOI: https://doi.org/10.1016/j.medcle.2020.05.013.

Moreira, R., Teixeira, S., Fialho, R., Miranda, A., Lima, L. D. B., Carvalho, M. B., Alves, A. B., Bastos, V. H. V., and Teles, A. S. (2024). Validity analysis of monocular human pose estimation models interfaced with a mobile application for assessing upper limb range of motion. Sensors, 24(24). DOI: https://doi.org/10.3390/s24247983.

Newcombe, R., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A., Kohli, P., Shotton, J., Hodges, S., and Fitzgibbon, A. (2011). Kinectfusion: Real-time dense surface mapping and tracking. pages 127–136. DOI: https://doi.org/10.1109/ISMAR.2011.6092378.

Peffers, K., Tuunanen, T., Rothenberger, M., and Chatterjee, S. (2007). A design science research methodology for information systems research. Journal of Management Information Systems, 24:45–77.

Pires, J., Oliveira, M., Fonseca, B., Ribeiro, M., Giglio, B., and Calzado, A. (2025). Ergonomic assessment using human pose estimation: A real-time approach with yolo and blazepose. In Anais Estendidos do XXV Simpósio Brasileiro de Computação Aplicada à Saúde, pages 293–298, Porto Alegre, RS, Brasil. SBC. DOI: https://doi.org/10.5753/sbcas_estendido.2025.7623.

Rocha, J. Q. S., da Silva, L. S., Pintanel Freitas, M., Mendes Delpino, F., Rombaldi, A. J., de Almeida Paz, I., Schröeder, N., Santos Feter, J., Nascimento da Silva, C., Leal da Cunha, L., Cassuriaga, J., Feter, N., Cozzensa da Silva, M., Pereira Vieira, Y., Lucia Caputo, E., and Fossati Reichert, F. (2024). The use of digital platforms and physical activity practice in a population from southern brazil: Findings from the pampa cohort. Preventive Medicine Reports, 44:102816. DOI: https://doi.org/10.1016/j.pmedr.2024.102816.

Roggio, F., Trovato, B., Sortino, M., and Musumeci, G. (2024). A comprehensive analysis of the machine learning pose estimation models used in human movement and posture analyses: A narrative review. Heliyon, 10(21):e39977. DOI: https://doi.org/10.1016/j.heliyon.2024.e39977.

Schlegel, K., Jiang, L., and Ni, H. (2024). Using joint angles based on the international biomechanical standards for human action recognition and related tasks.

Sugawara, E. K. (2022). Estimativa de postura: Uma abordagem multicâmera para classificação e avaliação de exercícios físicos. Master's thesis, Universidade Federal de Santa Catarina.

Xu, H., Bazavan, E. G., Zanfir, A., Freeman, B., Sukthankar, R., and Sminchisescu, C. (2020). Ghum ghuml: Generative 3d human shape and articulated pose models. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (Oral), pages 6184–6193.

Zheng, C., Wu, W., Chen, C., Yang, T., Zhu, S., Shen, J., Kehtarnavaz, N., and Shah, M. (2023). Deep learning-based human pose estimation: A survey. ACM Computing Surveys, 56(1):1–37. DOI: https://doi.org/10.1145/3603618.