Research on aerobics action modal recognition algorithm based on fuzzy system and reinforcement learning

  • Fengyi Ke Department of Physical Education, Huazhong Agricultural University, Wuhan 430070, China
  • Qian Zhang School of Materials Science and Engineering, Wuhan Institute of Technology, Wuhan 430070, China
Keywords: fuzzy system; reinforcement learning; aerobics movement recognition; Fuzzy LS-SVM; set empirical modal decomposition
Article ID: 645

Abstract

Nowadays, human movement recognition technology has received a high degree of attention and has been used in a variety of fields such as intelligent security and motion analysis. The traditional action recognition method relies on artificial extraction of features, not only the recognition efficiency is low, and the recognition accuracy is not high, has been unable to meet the requirements of action recognition. The action recognition method based on reinforcement learning can automatically extract features, greatly simplifying the process of manual feature extraction in the traditional method, but at the same time, it also has some defects such as easy to be disturbed by external environment and complicated network training. In view of this situation, this paper takes aerobics action recognition as an example, proposes an action recognition algorithm based on Fuzzy least squares support vector machine, and adopts Fuzzy LS-SVM classification algorithm to realize the classification of actions on the feature set. The results of the study show that the aerobics movement recognition algorithm proposed in this paper has more excellent performance compared to the traditional recognition algorithms.

References

1. Banos O, Damas M, Pomares H. Human act i vi t y recogni ti on based on a sensor weighting hierarchical classifi er[J]. Soft Computing, 2013, 17(2) : 333-343.

2. Wang H, Schmid C. Action recognition with improved trajectories[C]//Proceedings of the IEEE international conference on computer vision. 2013: 3551-3558.

3. Zhou B, Andonian A, Oliva A, et al. Temporal relational reasoning in videos[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 803-818.

4. Kipf T, Fetaya E, Wang K C, et al. Neural relational inference for interacting systems[C]//International conference on machine learning. PMLR, 2018: 2688-2697.

5. Si C, Jing Y, Wang W, et al. Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network[J]. Pattern Recognition, 2020, 107: 107511.

6. Chen Enqing, Fan Junbo. Application Research of Computers,2018,318(4):1277-1280. Chen Enqing, Fan Jian-Bo, et al.Motion Feature Extraction and Recognition based on MIM-LBP [J].

7. Feng Ting. Research on accuracy monitoring of aerobics movement based on image [J]. Modern Electronic Technique, 2018,41 (7) :75-79.

8. Lu Fuxiang. Adaptive Recognition Method of decomposed action images in aerobics based on Feature extraction [J]. Science Technology and Engineering,2019,476(7):153-158.

9. Liu Q. Aerobics posture recognition based on neural network and sensors[J]. Neural Computing and Applications, 2022, 34(5): 3337-3348.

10. Liu Y, Huang Z. Recognition of Aerobics Movement Posture Based on Multisensor Movement Monitoring[C]//International Conference on Advanced Hybrid Information Processing. Cham: Springer International Publishing, 2021: 167-178.

11. Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object

12. detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.2016: 779-788.

13. Kreiss S, Bertoni L, Alahi A. Pifpaf: Composite fields for human pose estimation[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019: 11977-11986.

14. Simonyan K, Zisserman A. Two-stream convolutional networks for action recognition in videos[J].Advances in neural information processing systems, 2014, 27: 568–576.

15. Ullah M, Yamin M M, Mohammed A, et al. Attention-based LSTM network for action recognition in sports[J]. Electronic Imaging, 2021, 33: 1-6.

16. Tejero-de-Pablos A, Nakashima Y, Sato T, et al. Summarization of user-generated sports video by using deep action recognition features[J]. IEEE Transactions on Multimedia, 2018, 20(8): 2000-2011.

17. Martin P E, Benois-Pineau J, Peteri R, et al. Fine grained sport action recognition with Twin spatio-temporal convolutional neural networks: Application to table tennis[J]. Multimedia Tools and Applications, 2020, 79: 20429-20447.

18. Martin P E, Benois-Pineau J, Peteri R, et al. Sport action recognition with siamese spatio-temporal cnns: Application to table tennis[C]//2018 International conference on content-based multimedia indexing (CBMI). IEEE, 2018: 1-6.

Published
2024-11-21
How to Cite
Ke , F., & Zhang , Q. (2024). Research on aerobics action modal recognition algorithm based on fuzzy system and reinforcement learning. Molecular & Cellular Biomechanics, 21(3), 645. https://doi.org/10.62617/mcb645
Section
Article