Abstract
The study aims to solve the problem of tennis picking for players in the training process and realize intelligent tennis picking. An intelligent tennis picking robot is studied to recognize and position tennis balls. First, the tennis recognition algorithm based on HSV (hue, saturation, value) color space is used to identify the tennis ball, and the coordinates of tennis and obstacles are obtained by background difference and OF (optical flow). Second, particle swarm optimization (PSO) that has excellent global planning ability and support vector machine (SVM) that has good obstacle avoidance performance are applicable because there may be some obstacles in tennis courts. Therefore, the traditional PSO and SVM are combined to obtain the optimized PSO. And the simulation comparison experiment is carried out on the Matlab simulation software. Finally, the model is tested and 50 random screenshots of tennis videos collected on the spot, and tennis photos downloaded on the network are tested in the dataset. The results show that the number of tennis balls correctly identified by the proposed algorithm is 248 and that of tennis balls wrongly identified is 8. Its recognition accuracy is 96.88% and the time spent is 9.33 s. The algorithm proposed provides some ideas to solve the problem of tennis picking for tennis players.
Similar content being viewed by others
References
Archana M, Ayyasamy A (2018) Tracking based event detection of singles broadcast tennis video. In: 2018 3rd International conference on communication and electronics systems (ICCES). IEEE, pp 835–838
Arunraj M, Srinivasan A, Juliet AV (2018) Online action recognition from RGB-D cameras based on reduced basis decomposition. J Real Time Image Process 17:1–16
Bai N, Liu N (2021) Deep spatial/temporal-level feature engineering for tennis-based action recognition. Future Gener Comput Syst 125(6):29–31
Bini AA (2019) Image restoration via DOST and total variation regularisation. IET Image Proc 13(3):458–468
Cai J, Tang X (2018) RGB video based tennis action recognition using a deep weighted long short-term memory. arXiv preprint arXiv:1808.00845
Chen C, Liu K, Kehtarnavaz N (2016) Real-time human action recognition based on depth motion maps. J Real Time Image Proc 12(1):155–163
Chen C, Shu Y, Shu KI et al (2018) WiTT: modeling and the evaluation of table tennis actions based on WIFI signals. In: 2018 24th International conference on pattern recognition (ICPR). IEEE, pp 3100–3107
Choi HR, Kim TY (2018) Modified dynamic time warping based on direction similarity for fast gesture recognition. Math Probl Eng 2018:1–9
Fu Z, Shu KI, Zhang H (2019) Ping Pong motion recognition based on smart watch. In: 3rd International conference on mechatronics engineering and information technology (ICMEIT 2019). Atlantis Press
Gao C, Wang L, Xiao Y et al (2018) Infrared small-dim target detection based on Markov random field guided noise modeling. Pattern Recogn 76:463–475
Gao Y, Tebbe J, Krismer J et al (2019) Markerless racket pose detection and stroke classification based on stereo vision for table tennis robots. In: 2019 Third IEEE international conference on robotic computing (IRC). IEEE, pp 189–196
Gu S, Zeng W, Jia Y et al (2019) Intelligent tennis robot based on a deep neural network. Appl Sci 9(18):3746
Harada K, Wan W, Tsuji T et al (2018) Experiments on learning based industrial bin-picking with iterative visual recognition. Ind Robot 45(4):446–457
Hu Z, Lee SH, Lee EJ (2018) Improved DT algorithm based human action features detection. J Korea Multimed Soc 21(4):478–484. (in Korean)
Ji YF, Zhang JW, Shi Z et al (2018) Research on real-time tracking of table tennis ball based on machine learning with low-speed camera. Syst Sci Control Eng 6(1):71–79
Jian Y, Qin C (2021) Design of rolling ball control system based on image recognition. J Phys Confer Ser 1865(4):042037
Lara JPR, Vieira CLR, Misuta MS et al (2018) Validation of a video-based system for automatic tracking of tennis players. Int J Perform Anal Sport 18(1):137–150
Martinez-Castillo C, Astray G, Mejuto JC et al (2020) Random forest, artificial neural network, and support vector machine models for honey classification. eFood 1(1):69–76
Ml A, Hk B, Hjka B (2020) Sparse-view CT reconstruction based on multi-level wavelet convolution neural network. Physica Med 80:352–362
Mochizuki I, Toyoura M, Mao X (2018) Visual attention prediction for images with leading line structure. Vis Comput 34(6–8):1031–1041
Reno V, Mosca N, Marani R et al (2018) Convolutional neural networks based ball detection in tennis games. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 1758–1764
Shimizu T, Hachiuma R, Saito H et al (2019) Prediction of future shot direction using pose and position of tennis player. In: Proceedings of the 2nd international workshop on multimedia content analysis in sports. ACM, pp 59–66
Shorman AA, Faris H, Aljarah I (2020) Unsupervised intelligent system based on one class support vector machine and Grey Wolf optimization for IoT botnet detection. J Ambient Intell Humaniz Comput 11(7):2809–2825
Wang P, Li Z, Hou Y et al (2016) Action recognition based on joint trajectory maps using convolutional neural networks. In: Proceedings of the 24th ACM international conference on multimedia. ACM, pp 102–106
Wei Z (2017) Research on the teaching system of table tennis based on artificial intelligence. In: 2017 Sixth international conference on future generation communication technologies (FGCT). IEEE, pp 1–4
Xu S, Liang L, Ji C (2020) Gesture recognition for human–machine interaction in table tennis video based on deep semantic understanding. Signal Process Image Commun 81:115688
Zhang D, Gao L, Teng T et al (2020) Underwater moving target detection using track-before-detect method with low power and high refresh rate signal. Appl Acoust 174(4):107750
Zhou J, Yang W, Yin Y et al (2021) Improved two-color LIF thermometry for gas–liquid system by optical flow algorithm. Exp Fluids 62(6):1–12
Funding
This research received no external funding.
Author information
Authors and Affiliations
Contributions
All authors listed have made a substantial, direct and intellectual contribution to the work, and approved it for publication.
Corresponding author
Ethics declarations
Conflict of interest
All authors declare that they have no conflict of interest.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Informed consent
Informed consent was obtained from all individual participants included in the study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wang, Z., Zhao, Y. & Bian, C. The analysis of tennis recognition model for human health based on computer vision and particle swarm optimization algorithm. Int J Syst Assur Eng Manag 13 (Suppl 3), 1228–1241 (2022). https://doi.org/10.1007/s13198-022-01673-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13198-022-01673-7