The Biomechanical Analysis on the Tennis Batting Angle Selection Under Deep Learning

Abstract

The objective is to study the impacts of batting strength and angle of tennis players on batting results based on deep learning (DL) image processing technology. A real-time evaluation algorithm of human motion is constructed based on the camera video image and convolution neural network (CNN), and the selection of joint angles in volley training of tennis players is analyzed from the perspective of biomechanics. Gaussian Mixture Model (GMM), Visual Background Extractor (VIBE), and Optical Flow (OF) are introduced for simulation and comparison. Then, the proposed algorithm is applied to the volley experiments in areas A, B, and C of 6 tennis players (denoted by P1, P2, P3, P4, P5, and P6). The results show that the processing frame rate and batting and follow-up similarity score of the proposed algorithm based on the camera video image and CNN are significantly higher than those of GMM, VIBE, and OF. The return success rates of P1 in different areas are the highest, which are 75.46%, 75.62%, and 68.94%, respectively; while those of P6 are the lowest (19.55%, 17.46%, and 21.65%, respectively). The left ankle angle of P6 is much greater than that of P1, the angle of P1 is significantly lower than that of P3, P4, P5, and P6. The batting speed of P1 is significantly slower than that of P3, P4, P5, and P6, which is not much different from that of the left knee joint. The angles of the subjects' right forearm ring, left lower leg ring, and left thigh ring is obvious. Additionally, the displacement of the left foot of P1 and P6 in area A is 0.916m and 0.548m, respectively. Therefore, in the volley preparation stage, the left ankle angle (103-108°) is greater than that of the right ankle (98-103°); the tennis batting speed should be basically the same as that of the left knee joint to lower the gravity center of player. Thus, the proposed algorithm outperforms other algorithms in the volley experiment of tennis players.INDEX TERMS Convolutional neural networks; monocular camera video image; real-time evaluation algorithm of human motion; volley experiment of tennis; biomechanics

Applications of Machine Learning to Optimize Tennis Performance: A Systematic Review

“…The following studies were considered to have high-quality (low risk of bias) [37][38][39][40][41][42][43][44][45][46][47][48][49][50][51][52]. Studies [53][54][55][56][57][58][59] were considered to have low quality (high risk of bias).…”

“…Eight studies [40,41,46,49,51,52,57,59] used ML techniques to analyze spatial and tactical factors. The studies encompassed a wide range of participant numbers.…”

“…The studies encompassed a wide range of participant numbers. Zhang [59] analyzed 120 matches to evaluate tactical performance, while Li et al [57] focused on a smaller group of just 6 players to study the impacts of batting strength. The data used for analysis were equally varied.…”

“…Zhang [59] delved into match data, analyzing details such as serve type, shot selection, and player positioning. In contrast, Li et al [57] focused on kinematic variables, and Rosker and Rosker [46] examined player movement patterns during serves and returns.…”

“…The variety of ML algorithms employed further underscores the versatility of this approach. Backpropagation neural networks [59] and convolutional neural networks [57] were used for tasks such as evaluating tactical performance and classifying groundstroke stances. Random forests [41,46] were utilized for tasks such as movement pattern classification and point-winning prediction.…”