Sports teaching and training action detection based on deep convolution neural network
Abstract
This study proposes a novel method for detecting errors in physical education teaching and training actions using a deep convolutional neural network (CNN). The architecture incorporates key components such as convolutional layers, pooling layers, and batch normalization to ensure accurate feature extraction and classification of training movements. Input data undergo preprocessing, including resizing and normalization, before being fed into the network. The system effectively reduces errors in detecting incorrect movements during training, achieving an error rate of approximately 0.034%. The experimental results demonstrate that the CNN-based approach outperforms traditional methods in accuracy and efficiency. Additionally, this study provides insights into optimizing sports training methodologies by accurately identifying errors and enabling targeted corrections. These findings highlight the potential of CNN-based systems to enhance physical education and athlete training through advanced motion detection techniques.
References
1. Lu Y, Sun J, Ma S. Moving target detection method based on deep convolution neural network. Journal of system simulation, 2019, 31 (11): 101-106
2. Wang Y, Wang W, Tian S, et al. Human motion recognition based on electrostatic signal. Robot, 2018, 40 (4): 33-40
3. Hu Q, Wang J, Jin G. Research on sequential action detection method based on spatiotemporal information. Microelectronics and computer, 2019, 36 (2): 88-92
4. Shi Y, Sun M, Li Z, et al. Behavior recognition based on motion history image and convolutional neural network. Xiangtan University (Journal of Natural Science),2019,41(2):109-117．
5. Li H, Zhu M. Small target detection algorithm based on deep convolution neural network. Computer engineering and science, 2020, 42 (4): 649-657
6. Yang F, Li J, Li X, et al. Salient object detection algorithm based on multi task deep convolution neural network. Computer applications, 2018, 38 (1): 91-96
7. Jiang L, Li X, Che L. Human motion recognition of UWB radar using two-dimensional wavelet packet decomposition. Journal of electronic measurement and instruments, 2018, 32 (8):74-80．
8. Xu Z, Yin H, Lin J. FMCW radar two person behavior recognition method based on spatial clustering. Journal of Fuzhou University (NATURAL SCIENCE EDITION), 2020, 48(4):445-450．
9. Zhang H, Ye Y, Cai X, et al. Efficient motion recognition algorithm based on human joint points. Computer engineering and design, 2020, 41 (11): 176-182
10. Yu H, Zhi M. human motion recognition based on convolutional neural network. Computer engineering and design, 2019, 40 (4): 1161-1166
11. Chen S, Wei W, He B, et al. Human motion recognition method based on improved deep convolution neural network. Computer application research, 2019, 36(3):945-949．
12. Cheng S, Zhang D. Target detection based on deep convolution neural network. Fujian computer, 2019, 35 (8): 38-40
13. Yu L, Hu J, Yao L. Non standard squat posture detection method based on human skeleton. Computer application, 2019, 39 (5): 1448-1452
14. Dang X, Huang Y, Hao Z, et al. Passive indoor personnel daily behavior detection method based on channel state information. Journal of communications, 2019, 40 (4):164-174．
15. Chen S, Ma Q, Zhao J, et al. Research on methods of motion detection and recognition based on upper limb motion score. Chinese Journal of rehabilitation medicine, 2019, 34(6):707-710．
16. Ba Y, Qi L. Construction of WeChat Mobile Teaching Platform in the Reform of Physical Education Teaching Strategy Based on Deep Neural Network. Mobile Information Systems, 2021, 2021:3532963.
17. Zhang S. Detection of Aerobics Action Based on Convolutional Neural Network. Computational intelligence and neuroscience, 2022, 2022:1857406.DOI:10.1155/2022/1857406.
18. Liu Y, Mei Q, Gan X, et al. Design of action detection system in wrestling match video based on 3D convolutional neural network. International journal of wireless and mobile computing: IJWMC, 2022(1):22.
19. Xiong X, Cao L, Liu Q, et al. Fall Detection Based on Action Structured Method and Cascaded Dilated Graph Convolution Network//International Conference on Multimedia Technology and Enhanced Learning. Springer, Cham, 2022.DOI:10.1007/978-3-031-18123-8_41.
20. Wu Z, Du H. Research on Human Action Feature Detection and Recognition Algorithm Based on Deep Learning. Mobile Information Systems, 2022.DOI:10.1155/2022/4652946.
Copyright (c) 2025 Lihua Liu, Shu Zhang, Bin Lv
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
