Research on Automatic Evaluation Algorithm of Students' Sports Action Standardization Based on Computer Vision

Han Li1 , Yanan Sun2
1 Sports Management College, Kyung Hee University, Yongin-si, Republic of Korea
2 Sports Management College, Xi'an University of Architecture and Technology, Shaanxi, China
International Scientific Technical and Economic Research 2026, Vol. 4, No. 1, pp. 188-199
DOI: 10.71451/ISTAER2609
Received: 2 January 2026; Revised: 20 February 2026; Accepted: 18 March 2026; Published: 24 March 2026
Abstract

Aiming at the problems of strong subjectivity, lack of accuracy and difficulty in large-scale evaluation of students' sports action standardization, this paper proposes an automatic evaluation algorithm based on computer vision. First, a multi-perspective sports action dataset is constructed and an expert scoring system is designed; Secondly, key point sequences are extracted using an improved pose estimation model, and a multi-scale motion representation method is introduced to integrate joint-level, limb-level, and global features; Furthermore, a bias-aware alignment network is proposed to achieve adaptive modeling of spatiotemporal errors; Finally, a multi-task scoring model based on the fusion of GCN and Transformer is constructed to realize the normative classification and regression prediction of actions. The experimental results show that on the self-built data set, the MAE of this method is reduced to 0.318, which represents an improvement of approximately 29.6% over mainstream methods, the classification accuracy is 91.6%, and the correlation coefficient with expert score is 0.94. At the same time, in the cross-scenario test, the performance decreased by only 2.8%, which was significantly better than the comparison method. Ablation experiments and statistical tests validate the effectiveness of each module. The results show that this method has obvious advantages in accuracy, generalization ability and interpretability, and can provide technical support for intelligent physical education teaching and automatic evaluation.

Keywords
Computer vision Sports movement evaluation Attitude estimation Multiscale feature Graph convolution network Action alignment Deep learning
References
  1. Chang, C. J., Putukian, M., Aerni, G., Diamond, A. B., Hong, E. S., Ingram, Y. M., ... & Wolanin, A. T. (2020). Mental health issues and psychological factors in athletes: detection, management, effect on performance, and prevention: American medical society for sports medicine position statement. Clinical Journal of Sport Medicine, 30(2), e61-e87. DOI: 10.1136/bjsports-2019-101583
  2. Jo, K. H., Lee, S. M., So, W. Y., & Lee, E. J. (2023). Mediating effect of sports safety awareness between sports activity habits and the intention to complete safety education among Korean adolescents. In Healthcare (Vol. 11, No. 13, p. 1891). MDPI. DOI: 10.3390/healthcare11131891
  3. Potop, V., Manolachi, V., Mihailescu, L. E., Manolachi, V., & Kulbayev, A. (2022). Knowledge of the fundamentals necessary for the scientific research activity in the field of Physical Education and Sports Science. Journal of Physical Education and Sport, 22(8), 1922-1926. DOI: 10.7752/jpes.2022.08243
  4. Hsia, L. H., Hwang, G. J., Lin, Y. N., & Hwang, J. P. (2025). Artificial intelligence-supported physical education during the pandemic: a physical skill auto-assessment and feedback approach based on a reflection-promoting mechanism. Educational Technology Research and Development, 73(3), 1429-1450. DOI: 10.1007/s11423-025-10452-7
  5. Usmani, U. A., Aziz, I. A., Jaafar, J., & Watada, J. (2024). Deep learning for anomaly detection in time-series data: An analysis of techniques, review of applications, and guidelines for future research. IEEE Access, 12, 174564-174590. DOI: 10.1109/ACCESS.2024.3495819
  6. Middlehurst, M., Schäfer, P., & Bagnall, A. (2024). Bake off redux: a review and experimental evaluation of recent time series classification algorithms. Data Mining and Knowledge Discovery, 38(4), 1958-2031. DOI: 10.1007/s10618-024-01022-1
  7. Zheng, C., Wu, W., Chen, C., Yang, T., Zhu, S., Shen, J., ... & Shah, M. (2023). Deep learning-based human pose estimation: A survey. ACM Computing Surveys, 56(1), 1-37. DOI: 10.1145/3603618
  8. Lan, G., Wu, Y., Hu, F., & Hao, Q. (2022). Vision-based human pose estimation via deep learning: A survey. IEEE Transactions on Human-Machine Systems, 53(1), 253-268. DOI: 10.1109/TPAMI.2008.106
  9. Zhang, X., Zhou, Z., Han, Y., Meng, H., Yang, M., & Rajasegarar, S. (2023). Deep learning-based real-time 3D human pose estimation. Engineering Applications of Artificial Intelligence, 119, 105813. DOI: 10.5281/zenodo.17880888
  10. Hussain, A., Hussain, T., Ullah, W., & Baik, S. W. (2022). Vision transformer and deep sequence learning for human activity recognition in surveillance videos. Computational Intelligence and Neuroscience, 2022(1), 3454167. DOI: 10.1155/2022/3454167
  11. Li, J., Liu, X., Zhang, W., Zhang, M., Song, J., & Sebe, N. (2020). Spatio-temporal attention networks for action recognition and detection. IEEE Transactions on Multimedia, 22(11), 2990-3001. DOI: 10.1109/TMM.2020.2965434
  12. Huang, Y., Zhao, H., Zhou, Y., Riedel, T., & Beigl, M. (2023). Standardizing Your Training Process for Human Activity Recognition Models–A Comprehensive Review in the Tunable Factors. In International Conference on Mobile and Ubiquitous Systems: Computing, Networking, and Services (pp. 15-27). Cham: Springer Nature Switzerland. DOI: 10.1007/978-3-031-63992-0_2
  13. Pareek, P., & Thakkar, A. (2021). A survey on video-based human action recognition: recent updates, datasets, challenges, and applications. Artificial Intelligence Review, 54(3), 2259-2322. DOI: 10.1007/s10462-020-09904-8
  14. Ohlendorf, D., Avaniadi, I., Adjami, F., Christian, W., Doerry, C., Fay, V., ... & Maurer-Grubinger, C. (2023). Standard values of the upper body posture in healthy adults with special regard to age, sex and BMI. Scientific Reports, 13(1), 873. DOI: 10.1038/s41598-023-27976-8
  15. Tao, W., Du, B., Li, B., He, W., & Sun, H. J. (2020). Body-posture recognition by undergraduate students majoring in physical education and other disciplines. Frontiers in Psychology, 11, 505543. DOI: 10.3389/fpsyg.2020.505543
  16. Liu, Y., Zhou, G., He, W., Zhu, H., & Cui, Y. (2025). DE-HRNet: Detail enhanced high-resolution network for human pose estimation. PLoS One, 20(9), e0325540. DOI: 10.1371/journal.pone.0325540
  17. Wang, Y., Wang, R., Shi, H., & Liu, D. (2024). MS-HRNet: multi-scale high-resolution network for human pose estimation. The Journal of Supercomputing, 80(12), 17269-17291. DOI: 10.1007/s11227-024-06125-6
  18. Guo, X., Li, C., Luo, Z., & Cao, D. (2024). Identification of track irregularities with the multi-sensor acceleration measurements of vehicle dynamic responses. Vehicle System Dynamics, 62(4), 906-931. DOI: 10.1080/00423114.2023.2200193
  19. Zhu, J., Zhang, Z., Liu, R., Ren, M., & Ma, G. (2025). Multiscale Modeling and Reconstruction of Joint Motion: Finite Element Optimization Based on Particle Swarm Algorithm. IEEE Access. DOI: 10.1109/ACCESS.2025.3553469
  20. Yang, D., Shaw, T., & Tsai, T. J. (2022). A study of parallelizable alternatives to dynamic time warping for aligning long sequences. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 30, 2117-2127. DOI: 10.1109/TASLP.2022.3180673
  21. Liu, Y., Zhang, Y. A., Zeng, M., & Zhao, J. (2024). A novel distance measure based on dynamic time warping to improve time series classification. Information Sciences, 656, 119921. DOI: 10.1016/j.ins.2023.119921
  22. Kraprayoon, J., Pham, A., & Tsai, T. J. (2024). Improving the robustness of DTW to global time warping conditions in audio synchronization. Applied Sciences, 14(4), 1459. DOI: 10.3390/app14041459
  23. Laughlin, D. E., & Massalski, T. B. (2021). Construction of equilibrium phase diagrams: Some errors to be avoided. Progress in Materials Science, 120, 100715. DOI: 10.1016/j.pmatsci.2020.100715
  24. Reyad, M., Sarhan, A. M., & Arafa, M. (2023). A modified Adam algorithm for deep neural network optimization. Neural Computing and Applications, 35(23), 17095-17112. DOI: 10.1007/s00521-023-08568-z
  25. Yi, D., Ahn, J., & Ji, S. (2020). An effective optimization method for machine learning based on ADAM. Applied Sciences, 10(3), 1073. DOI: 10.3390/app10031073
  26. Robeson, S. M., & Willmott, C. J. (2023). Decomposition of the mean absolute error (MAE) into systematic and unsystematic components. PLoS One, 18(2), e0279774. DOI: 10.1371/journal.pone.0279774
  27. Warneke, K., Siegel, S. D., Afonso, J., & Wallot, S. (2025). What the mean absolute percentage error (MAPE) should adopt from Bland–Altman analyses. German Journal of Exercise and Sport Research, 1-8. DOI: 10.1007/s12662-025-01084-3
  28. Hodson, T. O. (2022). Root mean square error (RMSE) or mean absolute error (MAE): When to use them or not. Geoscientific Model Development Discussions, 2022, 1-10. DOI: 10.5194/gmd-15-5481-2022
  29. Sun, Z., Wang, G., Li, P., Wang, H., Zhang, M., & Liang, X. (2024). An improved random forest based on the classification accuracy and correlation measurement of decision trees. Expert Systems with Applications, 237, 121549. DOI: 10.1016/j.eswa.2023.121549
  30. DeVries, Z., Locke, E., Hoda, M., Moravek, D., Phan, K., Stratton, A., ... & Phan, P. (2021). Using a national surgical database to predict complications following posterior lumbar surgery and comparing the area under the curve and F1-score for the assessment of prognostic capability. The Spine Journal, 21(7), 1135-1142. DOI: 10.1016/j.spinee.2021.02.007
  31. Pan, S., Liu, Z., Han, Y., Zhang, D., Zhao, X., Li, J., & Wang, K. (2024). Using the Pearson's correlation coefficient as the sole metric to measure the accuracy of quantitative trait prediction: is it sufficient?. Frontiers in Plant Science, 15, 1480463. DOI: 10.3389/fpls.2024.1480463
  32. Ma, X., Yuan, J., Chen, Y. W., Tong, R., & Lin, L. (2022). Attention-based cross-layer domain alignment for unsupervised domain adaptation. Neurocomputing, 499, 1-10. DOI: 10.1016/j.neucom.2022.04.086
  33. Yang, C., Dong, Y., Du, B., & Zhang, L. (2022). Attention-based dynamic alignment and dynamic distribution adaptation for remote sensing cross-domain scene classification. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-13. DOI: 10.1109/TGRS.2022.3225589
  34. Aljarbouh, A., Yarygina, I., Mohamed, A. P., Bystrova, N., & Tsarev, R. (2024). Evaluating the Effectiveness of an Online Trainer: A Paired T-Test Analysis. In International Workshop Hybrid methods of modeling and optimization in complex systems (pp. 338-347). Cham: Springer Nature Switzerland. DOI: 10.1007/978-3-031-95649-2_29
  35. Uddin, S., & Lu, H. (2024). Confirming the statistically significant superiority of tree-based machine learning algorithms over their counterparts for tabular data. PLoS One, 19(4), e0301541. DOI: 10.1093/ecco-jcc/jjaf231.1458