COMPUTER VISION TECHNOLOGIES FOR HUMAN POSE ESTIMATION IN EXERCISE: ACCURACY AND PRACTICALITY
DOI:
https://doi.org/10.17770/sie2024vol2.7842Keywords:
accuracy, balance test, computer vision, pose estimation, studentAbstract
Information technologies are increasingly being integrated into all aspects of human life. Over the past few years, the use of machine learning models for human pose detection has significantly increased. As the realms of technology and physical activity converge, understanding the potential of these innovations becomes imperative for refining exercise monitoring systems. The aim of the research - evaluate the accuracy and viability of employing modern computer vision technologies in the identification of human pose during physical exercises. The study employed a combination of machine learning methods, video analysis, a review of scientific literature, and methods from mathematical statistics. The precision evaluation of contemporary machine learning models was conducted on a prepared dataset, comprising annotated images featuring students executing a body balance test with the camera positioned directly towards the subjects. The obtained data showed that both MediaPipe and OpenPose models proficiently recognize key anatomical landmarks during the conducted test. The MediaPipe model demonstrates a lower percentage of deviation from manual annotation compared to OpenPose for most key points: the mean deviation exceeds the threshold for 11 out of 15 key points and 7 out of 18 key points, as defined by the OpenPose and MediaPipe models, respectively. The most significant deviations are noticeable in the detection of points corresponding to the foot and wrist. The derived conclusions underscore the models can address only a portion of the tasks set. Essentially, this raises scepticism regarding the practical application of contemporary machine learning methods for human pose estimation without additional refinement.
Downloads
References
Andriluka, M., Pishchulin, L., Gehler, P., & Schiele, B. (2014). 2d human pose estimation: New benchmark and state of the art analysis. In Proceedings of the IEEE Conference on computer Vision and Pattern Recognition (pp. 3686-3693).
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.
Beddiar, D. R., Nini, B., Sabokrou, M., & Hadid, A. (2020). Vision-based human activity recognition: a survey. Multimedia Tools and Applications, 79(41-42), 30509-30555.
Blythman, R., Saxena, M., Tierney, G. J., Richter, C., Smolic, A., & Simms, C. (2022). Assessment of deep learning pose estimates for sports collision tracking. Journal of sports sciences, 40(17), 1885-1900.
Bogle Thorbahn, L. D., & Newton, R. A. (1996). Use of the Berg Balance Test to predict falls in elderly persons. Physical therapy, 76(6), 576-583.
Bohannon, R. W., Larkin, P. A., Cook, A. C., Gear, J., & Singer, J. (1984). Decrease in timed balance test scores with aging. Physical therapy, 64(7), 1067-1070.
Cao, Z., Simon, T., Wei, S. E., & Sheikh, Y. (2017). Realtime multi-person 2d pose estimation using part affinity fields. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7291-7299).
Carlson, J. A., Liu, B., Sallis, J. F., Hipp, J. A., Staggs, V. S., Kerr, J., ... & Vasconcelos, N. M. (2020). Automated high-frequency observations of physical activity using computer vision. Medicine and science in sports and exercise, 52(9), 2029.
Channa, A., Popescu, N., Skibinska, J., & Burget, R. (2021). The rise of wearable devices during the COVID-19 pandemic: A systematic review. Sensors, 21(17), 5787.
Chung, J. L., Ong, L. Y., & Leow, M. C. (2022). Comparative analysis of skeleton-based human pose estimation. Future Internet, 14(12), 380.
Cioppa, A., Deliege, A., Huda, N. U., Gade, R., Van Droogenbroeck, M., & Moeslund, T. B. (2020). Multimodal and multiview distillation for real-time player detection on a football field. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops (pp. 880-881).
Citraro, L., Márquez-Neila, P., Savare, S., Jayaram, V., Dubout, C., Renaut, F., ... & Fua, P. (2020). Real-time camera pose estimation for sports fields. Machine Vision and Applications, 31, 1-13.
Cook, G., Burton, L., Hoogenboom, B. J., & Voight, M. (2014). Functional movement screening: The use of fundamental movements as an assessment of function‐part 1. International journal of sports physical therapy, 9(3), 396.
CVAT. Computer vision annotation tool (CVAT). https://github.com/opencv/cvat
Dindorf, C., Bartaguiz, E., Gassmann, F., & Fröhlich, M. (2022). Conceptual structure and current trends in Artificial Intelligence, Machine Learning, and Deep Learning research in sports: A bibliometric review. International Journal of Environmental Research and Public Health, 20(1), 173.
Hellsten, T., Karlsson, J., Shamsuzzaman, M., & Pulkkis, G. (2021). The potential of computer vision-based marker-less human motion analysis for rehabilitation. Rehabilitation Process and Outcome, 10, 11795727211022330.
Hutagalung, A. P., Akhmad, I., & Irfan, M. (2023). Development of Test and Measurement Tools Standing Stork Test Android Based. Kinestetik: Jurnal Ilmiah Pendidikan Jasmani, 7(2), 293-304.
Kale, S., Kulkarni, N., Kumbhkarn, S., Khuspe, A., & Kharde, S. (2023). Posture Detection and Comparison of Different Physical Exercises Based on Deep Learning Using Media Pipe, Opencv. International Journal of Scientific Research in Engineering and Management, 07(04), 1-29.
Kaupuzs, A., Larins, V., & Rizakova, L. (2016, May). Effects of Vestibular Exercises on Postural Balance for Children. In SOCIETY. INTEGRATION. EDUCATION. Proceedings of the International Scientific Conference (Vol. 3, pp. 453-463).
Khanal, S. R., Paulino, D., Sampaio, J., Barroso, J., Reis, A., & Filipe, V. (2022). A Review on Computer Vision Technology for Physical Exercise Monitoring. Algorithms, 15(12), 444.
Kim, J. W., Choi, J. Y., Ha, E. J., & Choi, J. H. (2023). Human pose estimation using mediapipe pose and optimization method based on a humanoid model. Applied Sciences, 13(4), 2700.
Kranti Panta, B. P. T. (2015). A study to associate the Flamingo Test and the Stork Test in measuring static balance on healthy adults. Foot Ankle Online J, 8(4).
Latyshev, M., Latyshev, S., Kaupuzs, A., Kvasnytsya, O., Tropin, Y., Kvasnytsya, I., & Prystynskyi, V. (2020, May). Cadets and juniors success: how important is it for sports careers in free-style wrestling?. In Society. integration. education. Proceedings of the International Scientific Conference (Vol. 6, pp. 282-291).
Latyshev, M., Shandrygos, V., Tropin, Y., Polianychko, O., Deineko, A., Lakhtadyr, O., & Mozoliuk, O. (2021). Age distribution of wrestlers participating in the world championships. Acta Kinesiologica, (15), 138-143.
Lengkana, A. S., Rahman, A. A., Alif, M. N., Mulya, G., Priana, A., & Hermawan, D. B. (2020). Static and dynamic balance learning in primary school students. International Journal of Human Movement and Sports Sciences, 8(6), 469-476.
Li, Y. C., Chang, C. T., Cheng, C. C., & Huang, Y. L. (2021, April). Baseball Swing Pose Estimation Using OpenPose. In 2021 IEEE International Conference on Robotics, Automation and Artificial Intelligence (RAAI) (pp. 6-9). IEEE.
Mahmood, H. A. (2023). Automated Body Postures Assessment from Still Images Using Mediapipe. Journal of Optimization and Decision Making, 2(2), 240-246.
Pardos, A., Tziomaka, M., Menychtas, A. & Maglogiannis, I. (2022). Automated Posture Analysis for the Assessment of Sports Exercises. In Proceedings of the 12th Hellenic Conference on Artificial Intelligence, 1-9. DOI:10.1145/3549737.3549784.
Rafi, U., Leibe, B., Gall, J., & Kostrikov, I. (2016, September). An Efficient Convolutional Network for Human Pose Estimation. In BMVC (Vol. 1, p. 2).
Rahmadani, A., Dewantara, B. S. B., & Sari, D. M. (2022, August). Human Pose Estimation for Fitness Exercise Movement Correction. In 2022 International Electronics Symposium (IES) (pp. 484-490). IEEE.
Robertson, D. G. E., Caldwell, G. E., Hamill, J., Kamen, G., & Whittlesey, S. (2013). Research methods in biomechanics. Human kinetics.
Sainani, K. L., Borg, D. N., Caldwell, A. R., Butson, M. L., Tenan, M. S., Vickers, A. J., ... & Bargary, N. (2020). Call to increase statistical collaboration in sports science, sport and exercise medicine and sports physiotherapy. British journal of sports medicine.
Thomas, G., Gade, R., Moeslund, T. B., Carr, P., & Hilton, A. (2017). Computer vision for sports: Current applications and research topics. Computer Vision and Image Understanding, 159, 3-18.
Wang, J., Qiu, K., Peng, H., Fu, J., & Zhu, J. (2019, October). Ai coach: Deep human pose estimation and analysis for personalized athletic training assistance. In Proceedings of the 27th ACM international conference on multimedia (pp. 374-382). https://doi.org/10.1145/3343031.3350910
Weinberg, M. D., & Gould, D. (2019). Foundations of sport and exercise psychology (7th ed.). Champaign, IL, USA: Human Kinetics.
Zhu, L. (2021). Computer vision-driven evaluation system for assisted decision-making in sports training. Wireless Communications and Mobile Computing, 2021, 1-7.
