With the continuous development of economy, people have more and more choices for recreation and leisure, and tennis has become one of the chosen sports, especially in recent years, the booming development of tennis in China has driven a large number of people to contact tennis. In tennis, the serve occupies a crucial position, so this paper aims to use deep learning technology to study the path of tennis serve images, detect the moving objects from the images, extract the key parts of the action, obtain the relevant information during the movement, conduct a multi-level and scientific study of the serve action, and provide a basis for tennis serve training. This paper proposes to conduct experiments on tennis serve technology using literature method, video observation, comparative analysis and deep learning technology to investigate the serve position, serve action and serve route of sportsmen, and the experimental results show that the height of the ball leaving the hand should maintain a ratio of 0.98 to the height, the instantaneous speed of the ball leaving the hand should reach 4.79m/s, and the minimum angle of the elbow joint in holding the racket should be best maintained at 41°or so, and the angle of the racket-holding elbow joint at the time of action acceptance should preferably be around 112°.

Yule Cai, Jie Guan, Jie Cai. Simulation Analysis of Optimal Modeling of Tennis Serve Image Path Based on Deep Learning. Frontiers in Sport Research (2024) Vol. 6, Issue 5: 157-164. https://doi.org/10.25236/FSR.2024.060525.

[1] Parunchaya, Jamkrajang, Mark, et al. How Do Tennis Players Control Their Balance During The Serve?[J]. ISBS Proceedings Archive, 2017, 35(1):54-55.

[2] Campbell A, Straker L, Whiteside D, et al. Lumbar Mechanics in Tennis Groundstrokes: Differences in Elite Adolescent Players With and Without Low Back Pain [J]. Journal of Applied Biomechanics, 2016, 32(1):32-39.

[3] Reno V, Mosca N, Nitti M, et al. A technology platform for automatic high-level tennis game analysis [J]. Computer Vision and Image Understanding, 2017, 159(jun.):164-175.

[4] Kovalchik S A, Albert J. A multilevel Bayesian approach for modeling the time-to-serve in professional tennis[J]. Journal of Quantitative Analysis in Sports, 2017, 13(2):49-62.

[5] G, Torres-Luque, J, et al. Serve profile of male and female professional tennis players at the 2015 Roland Garros Grand Slam tournament[J]. German Journal of Exercise and Sport Research, 2019, 49(3):319–324.

[6] Krause L M, Buszard T, Reid M, et al. Assessment of elite junior tennis serve and return practice: A cross-sectional observation[J]. Journal of Sports Sciences, 2019, 37(1):1-8.

[7] Connolly, Molly. Differences In Tennis Serve Kinematics Between Elite Adolescent Male And Female Players[J]. ISBS Proceedings Archive, 2019, 37(1):106-108.

[8] Garry, Robinson, Ian, et al. Radar speed gun true velocity measurements of sports-balls in flight: application to tennis[J]. Physica Scripta, 2016, 91(2):23008-23009.

[9] Yaghoobi A, Bakhshi-Jooybari M, Gorji A, et al. Application of adaptive neuro fuzzy inference system and genetic algorithm for pressure path optimization in sheet hydroforming process[J]. International Journal of Advanced Manufacturing Technology, 2016, 86(9-12):1-11.

[10] Liu M, F Zhang, Ma Y, et al. Evacuation path optimization based on quantum ant colony algorithm[J]. Advanced Engineering Informatics, 2016, 30(3):259-267.

[11] Benoit, Gillet, Mickael, et al. Kinematics Of Shoulder Joints During Tennis Serve In Young Female Athletes: Influence Of History Of Shoulder Pain[J]. ISBS Proceedings Archive, 2017, 35(1): 160-162.

[12] Raap M, Meyer-Nieberg S, Pickl S, et al. Aerial Vehicle Search-Path Optimization: A Novel Method for Emergency Operations[J]. Journal of Optimization Theory and Applications, 2017, 172(3):1-19.

[13] Lisa, M, Edwards, et al. Hope Measurement in Mexican American Youth[J]. Hispanic Journal of Behavioral Sciences, 2016, 29(2):1-13.

[14] Zawadzki P. Es más difícil anticipar el saque de tenistas zurdos? Un enfoque descriptivo de los indicios perceptivos [J]. Revista de Psicología del Deporte, 2016, 25(1):27-33.

[15] Chatard J C, Mujika I, Goiriena J J, et al. Screening young athletes for prevention of sudden cardiac death: Practical recommendations for sports physicians[J]. Scandinavian Journal of Medicine & Science in Sports, 2016, 26(4):362-374.

[16] Chen H, Zhang Y. Dynamic Path Optimization in Sharing Mode to Relieve Urban Traffic Congestion [J]. Discrete Dynamics in Nature and Society, 2021, 2021(7):1-16.

[17] MG Kapteyn, Pretorius J, Willcox K E. A probabilistic graphical model foundation for enabling predictive digital twins at scale[J]. Nature Computational Science, 2021, 1(5):1-11.

[18] Buss M K. City serves up a new tennis court[J]. Public works, 2017, 148(4):40-42.

[19] Connolly M, Middleton K, Spence G, et al. Effects of Lumbar Spine Abnormality and Serve Types on Lumbar Kinematics in Elite Adolescent Tennis Players[J]. Sports Medicine - Open, 2021, 7(1):1-10.

[20] Lane B, Sherratt P, Xiao H, et al. Characterisation of ball degradation events in professional tennis[J]. Sports Engineering, 2017, 20(3):1-13.

[21] Ilya B, Ne A, Rfa C, et al. Vibration-Damping technology in tennis racquets: Effects on vibration transfer to the arm, muscle fatigue and tennis performance – Science Direct [J]. Sports Medicine and Health Science, 2019, 1(1):49-58.

[22] Morel M, Achard C, Kulpa R, et al. Automatic evaluation of sports motion: A generic computation of spatial and temporal errors[J]. Image & Vision Computing, 2017, 64(aug.):67-78.

[23] Prinzel L, Pope A T, Palsson O S, et al. Method and Apparatus for Performance Optimization Through Physical Perturbation of Task Elements[J]. Nasa Tech Briefs, 2016, 40(11):58-59.

[24] Florea A, Lobov A, Lanz M. Emotions-aware Digital Twins For Manufacturing[J]. Procedia Manufacturing, 2020, 51(3):605-612. 

[25] Tao F, Qi Q, Wang L, et al. Digital Twins and Cyber–Physical Systems toward Smart Manufacturing and Industry 4.0: Correlation and Comparison[J]. Engineering, 2019, 5(4):653-661.