Title: Application analysis of multi-target tracking algorithm based on BSIC-re ID and spatio-temporal constraints in basketball games

Authors: Mingzhi Ye

Addresses: Physical Culture Institute, West Anhui University, Luan, China

Abstract: With the development of multi-target tracking technology, it has become an important part of ensuring the fairness of basketball games. The traditional multi-target tracking technology has disadvantages such as inaccurate data acquisition and low efficiency. In order to solve these problems, this study effectively combines human key point detection with spatio-temporal constraint recognition technology to design a multi-target tracking modelling algorithm suitable for basketball games. The results show that in the training set, the recognition rate of the modelling method for the basketball player's trajectory is 85.6%; meanwhile, the PR curve area of the modelling method is 0.86, and the selection accuracy is 93.61%, which are better than the comparison method. This indicates that the modelling algorithm is more suitable for multi-target tracking than the existing methods. It aims to provide a new research direction for basketball multi-target tracking technology.

Keywords: basketball match; multi-target tracking; athletes; spatio-temporal constraints; camera.

DOI: 10.1504/IJWMC.2024.140280

International Journal of Wireless and Mobile Computing, 2024 Vol.27 No.2, pp.161 - 172

Received: 22 Sep 2023
Accepted: 28 Jan 2024
Published online: 01 Aug 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article