Biomechanical analysis and optimization of sports action training in virtual reality (VR) environment
Abstract
Over the past years, virtual reality (VR) has become much more popular. VR combines several technologies to provide an immersive digital environment. This environment allows users to engage and react to their actions, creating a virtual world where users feel more present. In biomechanical analysis, researchers analyze the physical characteristics of biological tissues and model the relationship between tissue form and function. Utilizing VR headsets, motion-tracking apparatus, and realistic virtual worlds that simulate actual sports situations are all part of virtual sports training. VR lacks realism, which can be related to the absence of sensory input, making it unsuitable for training fine motor skills. The research aims to perform biomechanical analysis and optimize sports action training inside a VR setting. A mountain gazelle optimizer fine-tuned adjustable convolution neural network (MGO-ACNN) is proposed to examine the joint angle selections utilized by sports action. In this study, human motion image data are utilized to capture various angles of the training action. The data was preprocessed using a Wiener Filter (WF) for the obtained data. Analyzing spatial frequency and orientation in images for feature extraction is accomplished using the Gabor Filter (GF). This approach incorporates VR simulations to provide a more regulated and immersive setting for joint angle analysis during sports training. The proposed method is implemented using Python software. The result demonstrated by the proposed method significantly outperforms the existing algorithms. The performance parameters for accuracy (99.73%), precision (99.75%), recall (99.73%), and F1-score (99.72%) are assessed in this study. The VR experiments indicate that optimal sports preparation involves a sports action while maintaining a batting speed consistent with the joint to lower the center of gravity. This research highlights the more effective, personalized sports training system, leveraging VR to simulate real-world conditions while providing detailed biomechanical insights.
References
1. Yan, H., 2022. Construction and Application of Virtual Reality‐Based Sports Rehabilitation Training Program. Occupational Therapy International, 2022(1), p.4364360.
2. Talha, M., 2022. Research on the use of 3D modeling and motion capture technologies for making sports training easier. Revista de Psicología del Deporte (Journal of Sport Psychology), 31(3), pp.1-10.
3. Pastel, S., Petri, K., Bürger, D., Marschal, H., Chen, C.H. and Witte, K., 2022. Influence of body visualization in VR during the execution of motoric tasks in different age groups. Plos one, 17(1), p.e0263112.
4. Yuan, R., Zhang, Z., Song, P., Zhang, J. and Qin, L., 2020. Construction of virtual video scene and its visualization during sports training. IEEE Access, 8, pp.124999-125012.
5. Liu, H., Wang, Z., Mousas, C. and Kao, D., 2020, November. Virtual reality racket sports: Virtual drills for exercise and training. In 2020 IEEE International Symposium on Mixed and Augmented Reality (ISMAR) (pp. 566-576). IEEE.
6. Verheul, J., Nedergaard, N.J., Vanrenterghem, J. and Robinson, M.A., 2020. Measuring biomechanical loads in team sports–from lab to field. Science and Medicine in Football, 4(3), pp.246-252.
7. Ozawa, Y., Uchiyama, S., Ogawara, K., Kanosue, K. and Yamada, H., 2021. Biomechanical analysis of volleyball overhead pass. Sports biomechanics.
8. Trasolini, N.A., Nicholson, K.F., Mylott, J., Bullock, G.S., Hulburt, T.C. and Waterman, B.R., 2022. Biomechanical analysis of the throwing athlete and its impact on return to sport. Arthroscopy, Sports Medicine, and Rehabilitation, 4(1), pp.e83-e91.
9. Sarwar, M.A., Lin, Y.C., Daraghmi, Y.A., Tsì-Uí, İ.K. and Li, Y.L., 2023. Skeleton Based Keyframe Detection Framework for Sports Action Analysis: Badminton Smash Case. IEEE Access, 11, pp.90891-90900.
10. Mastorakis, S., Skiadopoulos, A., Shannigrahi, S., Likens, A., Nour, B. and Stergiou, N., 2021. Networking and computing in biomechanical research: Challenges and directions. IEEE Communications Magazine, 59(6), pp.103-109.
11. Maskeliūnas, R., Damaševičius, R., Blažauskas, T., Canbulut, C., Adomavičienė, A. and Griškevičius, J., 2023. BiomacVR: A virtual reality-based system for precise human posture and motion analysis in rehabilitation exercises using depth sensors. Electronics, 12(2), p.339.
12. Chen, J., Samuel, R.D.J. and Poovendran, P., 2021. LSTM with a bio-inspired algorithm for action recognition in sports videos. Image and Vision Computing, 112, p.104214.
13. Ahir, K., Govani, K., Gajera, R. and Shah, M., 2020. Application on virtual reality for enhanced education learning, military training, and sports. Augmented Human Research, 5, pp.1-9.
14. Serpush, F. and Rezaei, M., 2021. Complex human action recognition using a hierarchical feature reduction and deep learning-based method. SN Computer Science, 2(2), p.94.
15. Ji, R., 2020. Research on basketball shooting action based on image feature extraction and machine learning. IEEE Access, 8, pp.138743-138751.
16. Liu, J., 2021. Convolutional neural network-based human movement recognition algorithm in sports analysis. Frontiers in Psychology, 12, p.663359.
17. Aresta, S., Bortone, I., Bottiglione, F., Di Noia, T., Di Sciascio, E., Lofù, D., Musci, M., Narducci, F., Pazienza, A., Sardone, R. and Sorino, P., 2022. Combining biomechanical features and machine learning approaches to identify fencers ‘ levels for training support. Applied Sciences, 12(23), p.12350.
18. Yan, S., Chen, J. and Huang, H., 2022. Biomechanical Analysis of Martial Arts Movements Based on Improved PSO Optimized Neural Network. Mobile Information Systems, 2022(1), p.8189426.
19. Pajak, G., Krutz, P., Patalas-Maliszewska, J., Rehm, M., Pajak, I. and Dix, M., 2022. An approach to sport activity recognition based on an inertial sensor and deep learning. Sensors and Actuators A: Physical, 345, p.113773.
20. Calderón-Díaz, M., Silvestre Aguirre, R., Vásconez, J.P., Yáñez, R., Roby, M., Querales, M. and Salas, R., 2023. Explainable Machine Learning Techniques to Predict Muscle Injuries in Professional Soccer Players through Biomechanical Analysis. Sensors, 24(1), p.119.
21. Chakravarty, S., Kumar, A., Hales, M., David Johnson, J., and Xie, Y., 2024. Machine Learning and Computer Visualization for Monocular Biomechanical Analysis. Wireless Personal Communications, pp.1-14.
22. Lloyd, D., 2021. The future of in-field sports biomechanics: Wearables plus modeling compute real-time in vivo tissue loading to prevent and repair musculoskeletal injuries. Sports Biomechanics, pp.1-29.
23. Ghezelbash, F., Eskandari, A.H., Robert-Lachaine, X., Cao, S., Pesteie, M., Qiao, Z., Shirazi-Adl, A. and Larivière, C., 2024. Machine learning applications in spine biomechanics. Journal of Biomechanics, 166, p.111967.
24. https://www.kaggle.com/datasets/pypiahmad/realistic-action-recognition-ucf50-dataset/data
25. Nunes Rodrigues, A.C., Santos Pereira, A., Sousa Mendes, R.M., Araújo, A.G., Santos Couceiro, M. and Figueiredo, A.J., 2020. Using artificial intelligence for pattern recognition in a sports context. Sensors, 20(11), p.3040.
26. Lyu, L. and Huang, Y., 2024. Sports activity (SA) recognition is based on error-correcting output codes (ECOC) and convolutional neural networks (CNN). Heliyon, 10(6).
Copyright (c) 2024 Jianfeng Deng
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright on all articles published in this journal is retained by the author(s), while the author(s) grant the publisher as the original publisher to publish the article.
Articles published in this journal are licensed under a Creative Commons Attribution 4.0 International, which means they can be shared, adapted and distributed provided that the original published version is cited.
Submit a Paper
