As a part of physical education in colleges and universities, fitness game teaching is more and more applied to modern electronic equipment for auxiliary teaching. In order to improve the teaching quality and interestingness of college spinning teaching, a kind of teaching assistant technology of spinning fitness games combined with motion capture was proposed. In the process, kinect 3D depth camera is used for human motion capture, matrix operation is used for coordinate conversion, softmax layer is used for action classification and output classification results, integrated learning is used to supplement and reconstruct motion capture data, and the purpose of multi-person learning is achieved through photon server. The experimental results show that the loss value drops to 0.14 after 100 iterations in the test set. In the calculation accuracy test, the research method maintains 95.1% after 100s in Carnegie Mellon University (CMU) data set, which is higher than other methods. In the round-trip delay test, only 5 wave delay fluctuations occurred in the research method within 60s, and only 1 wave delay fluctuation exceeded 150ms. During the bone extraction test, the study method completed the restoration of 40 joints, and no bone loss occurred. The results show that the research method can more accurately capture the motion of spinning, and can effectively help improve the teaching quality of spinning games.

1. Atlasov B. and Selskiy A., “The State and Prospects of Using Virtual reality Technologies in Sports: A Brief Review,” Russian Journal of Information Technology in Sports Technology, vol. 2, no. 1, pp. 13-21, 2025, DOI: 10.62105/2949-6349-2025-2-1-13-21
2. Carrier B., Creer A., Williams L., Holmes T., and et al., “Validation of Garmin Fenix 3 HR Fitness Tracker Biomechanics and Metabolics (VO2max),” Journal for the Measurement of Physical Behaviour, vol. 3, no. 4, pp. 331-337, 2020. DOI: 10.1123/jmpb.2019-0066
3. Chaccour C., Soorki M., Saad W., Bennis M., and Popovski P., “Can Terahertz Provide High-Rate Reliable Low-Latency Communications for Wireless Vr?,” IEEE Internet of Things Journal, vol. 9 no. 12, pp. 9712-9729, 2022. DOI: 10.1109/JIOT.2022.3142674
4. Dhaya R., “Improved Image Processing Techniques for User Immersion Problem Alleviation in Virtual Reality Environments,” Journal of Innovative Image Processing, vol. 2, no. 2, pp. 77-84, 2020. DOI: 10.36548/jiip.2020.2.002
5. Getuli V., Capone P., and Bruttini A., “Planning, Management and Administration of HS Contents with BIM and VR in Construction: An Implementation Protocol,” Engineering, Construction and Architectural Management, vol. 28, no. 2, pp. 603-623, 2021. DOI: 10.1108/ECAM-11-2019-0647
6. Haghighat P., Prince A., and Jeong H., “Graph Convolutional Networks for Exercise Motion Classification,” in Proceedings of the Human Factors and Ergonomics Society Annual Meeting, Baltimore, pp. 685-689, 2021. DOI: 10.1177/1071181321651255
7. Javaid M. and Haleem A., “Virtual Reality Applications Toward Medical Field,” Clinical Epidemiology and Global Health, vol. 8, no. 2, pp. 600-605, 2020. DOI: 10.1016/j.cegh.2019.12.010
8. Ligorio G., Bergamini E., Truppa L., Guaitolini M., and et al., “A Wearable Magnetometer-Free Motion Capture System: Innovative Solutions for Real-World Applications,” IEEE Sensors Journal, vol. 20, no. 15, pp. 8844-8857, 2020. DOI: 10.1109/JSEN.2020.2983695
9. Long S., He X., and Yao C., “Scene Text Detection and Recognition: The Deep Learning Era,” International Journal of Computer Vision, vol. 129, no. 1, pp. 161-184, 2021. DOI: 10.1007/s11263-020-01369-0
10. Luo H., Li G., Feng Q., Yang Y., and Zuo M., “Virtual Reality in K‐12 and Higher Education: A Systematic Review of the Literature from 2000 to 2019,” Journal of Computer Assisted Learning, vol. 37 no. 3, pp. 887-901, 2021. DOI: 10.1111/jcal.12538
11. MacDowell P., Jaunzems-Fernuk J., Clifford J., Ghani A., and Hoy B., “Virtual Reality in History Education: Instructional Design Considerations for Designing Authentic, Deep, and Meaningful Learning,” Journal of Applied Instructional Design., vol. 14, no. 1, pp. 6-48, 2025, DOI: 10.59668/2033.19032
12. Maihulla A., Yusuf I., and Bala S., “Reliability and Performance Analysis of a Series-Parallel System Using Gumbel-Hougaard Family Copula,” Journal of Computational and Cognitive Engineering, vol. 1, no. 2, pp. 74-82, 2022. DOI: 10.47852/bonviewJCCE2022010101
13. Meng Y., Shen J., Zhang C., and Han J., “Weakly-Supervised Hierarchical Text Classification,” in Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, pp. 6826-6833, 2019. DOI: 10.1609/aaai. v33i01.33016826
14. Mihcin S., “Simultaneous Validation of Wearable Motion Capture System for Lower Body Applications: Over Single Plane Range of Motion (ROM) and Gait Activities,” Biomedical Engineering/Biomedizinische Technik, vol. 67, no. 3, pp. 185-199, 2022. DOI: 10.1515/bmt-2021-0429
15. Minaee S., Kalchbrenner N., Cambria E., Nikzad N., and et al., “Deep Learning-Based Text Classification: A Comprehensive Review,” ACM Computing Surveys (CSUR), vol. 54, no. 3, pp. 1-40, 2021. DOI: 10.1145/3439726
16. Norberg C. and Nordlund M., “A Corpus-Based Study of Lexis in L2 English Textbooks,” Journal of Language Teaching and Research, vol. 9, no. 3, pp. 463-473, 2018. DOI: 10.17507/jltr.0903.03
17. Qiu S., Zhao H., Jiang N., Wu D., and et al., “Sensor Network Oriented Human Motion Capture Via Wearable Intelligent System,” International Journal of Intelligent Systems, vol. 37, no. 2, pp. 1646-1673, 2022. DOI: 10.1002/int.22689
18. Rafi K., Gani M., Hashim N., Rahman M., and Masukujjaman M., “The Influence of 360-Degree VR Videos on Tourism Web Usage Behaviour: The Role of Web Navigability and Visual Interface Design Quality,” Tourism Review, vol. 80, no. 3, pp. 725-741, 2025. DOI: 10.1108/TR-06-2023-0383.
19. Sachan D., Zaheer M., and Salakhutdinov R., “Revisiting Lstm Networks for Semi-Supervised Text Classification Via Mixed Objective Function,” in Proceedings of the Association for the Advancement of Artificial Intelligence AAAI Conference on Artificial Intelligence, Hilton Hawaiian Village, Honolulu, pp. 6940-6948, 2019. DOI:10.1609/aaai. v33i01.33016940
20. Stepanyan I. and Hameed S., “A Neuro Phenotypic Evolution Algorithm for Recognizing Human Motion Type,” The International Arab Journal of Information Technology, vol. 21, no. 6, pp. 1015-1028, 2024. DOI: 10.34028/iajit/21/6/6
21. Trost Z., France C., Anam M., and Shum C., “Virtual Reality Approaches to Pain: Toward a State of the Science,” Pain, vol. 162 no. 2, pp. 325-331, 2021. DOI: 10.1097/j.pain.0000000000002060
22. Wang X., Cheng M., Eaton J., Hsieh C., and Wu S., “Fake Node Attacks on Graph Convolutional Networks,” Journal of Computational and Cognitive Engineering, vol. 1, no. 4, pp. 165-173, 2019. DOI: 10.47852/bonviewJCCE2202321
23. Wright M., Twose D., and Gorter J., “Scootering for Children and Youth is more than Fun: Exploration of a Feasible Approach to Improve function and Fitness,” Pediatric Physical Therapy, vol. 33, no. 4, pp. 218-225, 2021. DOI: 10.1097/PEP.0000000000000829
24. Wu H., Ai C., and Cheng C., “Virtual Reality Experiences, Attachment and Experiential Outcomes in Tourism,” Tourism Review, vol. 75, no. 3, pp. 481-495, 2020. DOI: 10.1108/TR-06-2019-0205
25. Yildirim B., Topalcengiz E., Arikan G., and Timur S., “Using Virtual Reality in the Classroom: Reflections of STEM Teachers on the Use of Teaching and Learning Tools,” Journal of Education in Science Environment and Health, vol. 6, no. 3, pp. 231-245, 2020. DOI: 10.21891/jeseh.711779
26. Zhang J. and Mao H., “WKNN Indoor Positioning Method Based on Spatial Feature Partition and Basketball Motion Capture,” Alexandria engineering journal, vol. 61, no. 1, pp. 125-134, 2022. DOI: 10.1016/j.aej.2021.04.078