AI Visual Recognition Technology in Action Difficulty Grading and Referee Assistant System for Freestyle Roller Skating

Jingxiao Wei

doi:10.71222/pgqvkq58

Authors

Jingxiao Wei School of General Education, Beijing Normal-Hong Kong Baptist University, Zhuhai, China Author

DOI:

https://doi.org/10.71222/pgqvkq58

Keywords:

artificial intelligence, visual recognition, deep learning, sports technology, motion analysis, referee system

Abstract

With the rapid development and increasing global popularity of freestyle roller skating, the traditional difficulty grading and judging model, which relies predominantly on subjective human judgment, is no longer able to meet the stringent needs of the standardized development of the sport. Subjective evaluations often lead to inconsistencies during high-stakes competitions. Consequently, this paper focuses on the innovative application of artificial intelligence (AI) visual recognition technology within this athletic field, aiming to significantly improve the objectivity, accuracy, and fairness of judging by constructing a robust difficulty grading model and an intelligent referee assistant system. First, this study comprehensively explains the underlying AI visual recognition technology architecture and details the freestyle roller skating action judging rules. It designs a comprehensive motion data collection scheme and an advanced feature engineering process to capture the intricate dynamics of the skaters. Furthermore, it constructs and optimizes a sophisticated difficulty grading model based on deep learning algorithms, specifically tailored for complex spatial-temporal movements. On this foundational basis, a comprehensive referee assistant system equipped with real-time monitoring and automated referee assistance functions is developed. Its practical application effectiveness is rigorously evaluated through both computer simulation and actual live competition tests. The empirical results demonstrate that this proposed technical solution will effectively improve the accuracy of complex motion recognition and ensure the high consistency of grading. Ultimately, this research provides a highly feasible approach for the intelligent development of freestyle roller skating. In addition, corresponding strategic solutions are proposed to address the potential technical challenges encountered in the real-world application.

References

1. H. Vila, J. A. Abraldes, N. Rodríguez, and C. Ferragut, "Anthropometric and somatotype characteristics of world class male roller skaters by discipline," The Journal of Sports Medicine and Physical Fitness, vol. 55, no. 7-8, pp. 742-748, 2015.

2. T. Stöggl, E. Müller, and S. Lindinger, "Biomechanical comparison of the double-push technique and the conventional skate skiing technique in cross-country sprint skiing," Journal of Sports Sciences, vol. 26, no. 11, pp. 1225-1233, 2008.

3. G. Bongiorno, G. Sisti, H. Biancuzzi, F. Dal Mas, F. G. Minisini, and L. Miceli, "Training in roller speed skating: proposal of surface electromyography and kinematics data for educational purposes in junior and senior athletes," Sensors, vol. 24, no. 23, p. 7617, 2024.

4. S. Sehgal, A. Chahal, V. Esht, M. M. Alshehri, R. A. Beg, M. A. Shaphe, et al., "Unleashing potential and optimizing adolescent roller skating performance through a structured exercise program–a randomized controlled trial," BMC Sports Science, Medicine and Rehabilitation, vol. 15, no. 1, p. 117, 2023.

5. G. Bongiorno, H. Biancuzzi, F. Dal Mas, G. Fasano, and L. Miceli, "Roller speed skating kinematics and electromyographic analysis: A methodological approach," Sports, vol. 10, no. 12, p. 209, 2022.

6. X. Yang, J. Yan, W. Wang, S. Li, B. Hu, and J. Lin, "Brain-inspired models for visual object recognition: an overview," Artificial Intelligence Review, vol. 55, no. 7, pp. 5263-5311, 2022.

7. B. Hariharan and R. Girshick, "Low-shot visual recognition by shrinking and hallucinating features," in Proceedings of the IEEE International Conference on Computer Vision, pp. 3018-3027, 2017.

8. D. Lowe, Perceptual Organization and Visual Recognition. Springer Science & Business Media, 2012.

9. J. Wang, K. Sun, T. Cheng, B. Jiang, C. Deng, Y. Zhao, et al., "Deep high-resolution representation learning for visual recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 10, pp. 3349-3364, 2020.

10. Y. Zhang, X. S. Wei, B. Zhou, and J. Wu, "Bag of tricks for long-tailed visual recognition with deep convolutional neural networks," in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 4, pp. 3447-3455, May 2021.

11. J. Ren, C. Yu, X. Ma, H. Zhao, and S. Yi, "Balanced meta-softmax for long-tailed visual recognition," Advances in Neural Information Processing Systems, vol. 33, pp. 4175-4186, 2020.

12. P. Dakshinamoorthy, G. Rajaram, S. Garg, P. Murugan, A. Manimaran, and R. Sundar, "Artificial intelligence algorithms for object detection and recognition in video and images," Multimedia Tools and Applications, vol. 84, no. 29, pp. 36089-36106, 2025.

13. O. I. Abiodun, A. Jantan, A. E. Omolara, K. V. Dada, A. M. Umar, O. U. Linus, et al., "Comprehensive review of artificial neural network applications to pattern recognition," IEEE Access, vol. 7, pp. 158820-158846, 2019.

14. J. Donahue, Y. Jia, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, and T. Darrell, "Decaf: A deep convolutional activation feature for generic visual recognition," in International Conference on Machine Learning, pp. 647-655, Jan. 2014.

15. R. K. Painam, D. K. Pathak, V. Jagadish Kumar, A. Bhagyalakshmi, and R. Sharma, "Artificial Intelligence in Image Processing: A New Era of Visual Recognition," in *Proceedings of the 3rd International Conference on Optimization Techniques in the Field of Engineering (ICOFE-2024)*, Nov. 2024.

16. Y. Tian, "Artificial intelligence image recognition method based on convolutional neural network algorithm," IEEE Access, vol. 8, pp. 125731-125744, 2020.

17. W. Chen, "Artificial intelligence recognition simulation of 3D multimedia visual image based on sparse representation algorithm," IEEE Access, vol. 8, pp. 121437-121450, 2020.