Title: Recognition method of football players' shooting action based on Bayesian classification

Authors: Xiaofang Zhao

Addresses: Department of Physical Education, Dalian Maritime University, Dalian 116026, China

Abstract: Aiming at the problem of low accuracy and poor real-time performance of existing algorithms in the process of football players' shooting action recognition, a football players' shooting action recognition method based on Bayesian classification is proposed. Firstly, Gaussian mixture model is constructed to extract the characteristics of shooting action. Secondly, the Gaussian parameters are estimated to obtain the optimal state sequence, which provides a basic reference for football players' shooting action recognition. Finally, based on the marking of football players' shooting action behaviour, the recognition of football players' shooting action based on Bayesian classification is realised. Experiments show that the designed Bayesian classification method can accurately identify the shooting action of football players, and has good real-time performance. This shows that the design method can provide basic basis and theoretical guarantee for football players' action recognition, and has certain practical application performance.

Keywords: Bayesian method; motion recognition; football sport; athlete movement.

DOI: 10.1504/IJRIS.2023.128373

International Journal of Reasoning-based Intelligent Systems, 2023 Vol.15 No.1, pp.35 - 40

Received: 22 Feb 2022
Accepted: 27 Apr 2022
Published online: 18 Jan 2023 *