Recognition method of tennis swing based on time series convolution network
Abstract
Tennis swings vary widely in type, and accurately identifying these motion patterns is crucial for swing analysis. With advancements in artificial intelligence, recent studies have achieved significant progress in human activity recognition through machine learning and sensor technologies. However, research specifically on tennis swing recognition remains relatively nascent, with limited exploration in this domain. This study focuses on recognizing tennis swing motions using a time-series convolution network, employing sensors to gather essential motion data. The MPU9250 sensor captures the intricate nuances of human movement, which often displays complexity and individual variation. Key challenges include effectively extracting features of tennis swings, designing suitable classifiers for recognition, and enhancing classifier generalization across different individuals. Addressing these challenges, this study introduces a temporal sensing network for swing recognition based on causal and dilated convolution techniques. The network effectively captures the temporal characteristics of swings, achieving a 94.73% recognition rate. Additionally, a comparative analysis between the sequential convolution network and traditional machine learning algorithms is conducted, providing insights into their performance and processing workflows.
References
1. Khanam S, Sharif M, Cheng X, et al. Suspicious action recognition in surveillance based on handcrafted and deep learning methods: A survey of the state of the art. Computers and Electrical Engineering, 2024, 120(PC):109811-109811.
2. Wu X. Application of intelligent trajectory analysis based on new spectral imaging technology in basketball match motion recognition. Optical and Quantum Electronics, 2023, 56(3).
3. Yawen P, Yi N. Dance video motion recognition based on computer vision and image processing. Applied Artificial Intelligence, 2023, 37(1).
4. Zhonghua S, Tianyi W, Meng D. Combining channel-wise joint attention and temporal attention in graph convolutional networks for skeleton-based action recognition. Signal, Image and Video Processing, 2022, 17(5):2481-2488.
5. Shehzad F, Khan M, Asfand M, et al. Two-stream deep learning architecture-based human action recognition. Computers, Materials & Continua, 2022, 74(3):5931-5949.
6. Kau, L. A Multi-Scale Human Action Recognition Method Based on Laplacian Pyramid Depth Motion Images. In Proceedings of the 2020 ACM Multimedia Asia Conference (MMAsia ‘20), pp. 33-38. ACM, 2020
7. Kalantarian H., Sarrafzadeh M. An Indoor Human Action Recognition Method Based on Spatial Location Information. Proceedings of the 2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops), 2015:1-6.
8. Jin X, Tang P, Houet T, et al. Sequence Image Interpolation via Separable Convolution Network. Remote Sensing, 2021, 13(2):296.
9. Harry J. Time series models with univariate margins in the convolution-closed infinitely divisible class. Journal of Applied Probability, 2020, 53(1):43-18.
10. Kourogi M, Ishikawa T, Kurata T. A Method of Pedestrian Dead Reckoning Using Action Recognition. IEEEION Position, Location and Navigation Symposium. IEEE, 2019, 83(5):62-73.
11. Charalampous K, Gasteratos A. On-line deep learning method for action recognition. Pattern Analysis & Applications, 2016, 19(2):337-354.
12. Charalampous K, Gasteratos A. On-line deep learning method for action recognition. Pattern Analysis & Applications, 2021, 44(10):33-38.
13. Moussa MM, Hamayed E, Fayek MB, EL Nemr HA. An enhanced method for human action recognition. Journal of Advanced Research, 2015, 6(2):163-169.
14. Vajda T. Action recognition based on Fast Dynamic-Time warping method5th International Conference on Intelligent Computer Communication and Processing. IEEE, 2021, 1043(2):022032 12pp.
15. Zhang J, Liu Z. A Method of Abnormal Action Recognition in Variable Scenarios. Journal of Image and Graphics, 2009, 14(10):2097-2101.
16. Pei X, Fan H, Tang Y. Action recognition method of spatio-temporal feature fusion deep learning network. Infrared and Laser Engineering, 2015, 47(2):203007.
17. Estevam V, Laroca R, Menotti D, et al. Tell me what you see: A zero-shot action recognition method based on natural language descriptions. Multimedia Tools and Applications, 2021, 83: 28147-28173.
18. Dong X, Tan L, Zhou L, et al. An Action Recognition Method Based on Deformable Convolution Network. Journal of Physics Conference Series, 2021, 11(10):15-23.
19. Choi Y., Tang J., Jang S., Kim S. User Customizable Hit Action Recognition Method Using Kinect. Journal of Korea Multimedia Society, 2015, 18(4):557-565
20. He W, Liu B, Xiao Y. Multi-View Action Recognition Method Based on Regularized Extreme Learning Machine. 2017 IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC), Guangzhou, China, 2017, pp. 854-857.
21. Lu Y, Li Y, Yang S, et al. A Human Action Recognition Method Based on Tchebichef Moment Invariants and Temporal Templates. 2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics, Nanchang, China, 2012, pp. 76-79.
22. Liu Z, Miao Z, Huo Y. A realtime human action recognition method based on single view key poses in sports video. 6th International Conference on Wireless, Mobile and Multi-Media (ICWMMN 2015), Beijing, 2015, pp. 210-213.
23. Jin X. SEMG Action Recognition Method Based on WPKPCA and SVM. Application of Electronic Technique, 2017, 43(2):1532-1538.
24. Guo M., Wang Z. A Feature Extraction Method for Human Action Recognition Using Body-Worn Inertial Sensors. Proceedings of the 2015 IEEE International Conference on Computer Supported Cooperative Work in Design (CSCWD), 2015:576-581.
25. Ruan R.Q., Liu X.Q., Wu X. Action Recognition Method for Multi-Joint Industrial Robots Based on End-Arm Vibration and BP Neural Network. Proceedings of the 2021 6th International Conference on Control and Robotics Engineering (ICCRE), 2021:971-976.
26. Kim H Y, Song Y K, Cho J S. Fight Action Recognition Method using AI Deep Learning. Journal of Institute of Control Robotics and Systems, 2021, 27(7):482-489.
27. Wang L., Zhang J., Pfab C., et al. A Temporal–Spatial Attention-Based Action Recognition Method for Intelligent Fault Diagnosis. ISA Transactions, 2021, 111:319-328.
28. Qiao Y., Zhou L., Wang Y., et al. Action Recognition Method and Apparatus. Chinese Patent CN101200349A, 2008.
29. Zhang S., Wang J., Liang Z., et al. Action Recognition Method, Apparatus and Device and Storage Medium. European Patent EP3907653A1, 2021.
30. Feng J., Zhang L. Research of Human Action Recognition Method Based on Random Dropout Convolutional Neural Network. Journal of Test and Measurement Technology, 2011, 58(3):346-357.
Copyright (c) 2025 Bo Huang
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
