Automated Sports Player Performance Analysis: A Survey

Document Type : Original Article

Authors

1 Computer Science Department, Faculty of Computers and Information, Helwan University.

2 Computer Science Department, Faculty of Computers and Information, Helwan University

3 HCI-LAB, Department of Computer Science, Faculty of Computers and Artificial Intelligence, Helwan University, Helwan, Egypt

Abstract

Sports can not be said it is a mean for social cohesion by allowing people interaction disregarding their social status, age, etc. only but also it became the entertainment industry from governmental views. Consequently, a large amount of resources has been directed to sports to improve understanding, performance and presentation. Sports video analysis is a popular tool to capture low-level and high-level analysis. Sports analytics have several usage scenarios such as personalized video summary, player statistics and tactical analysis. In order to make the automatic sports video analysis realized, there is a necessity for player identification across sports. Identifying players in sports videos is a major research challenge due to low video resolution per player, camera perspective, the variation of the posture of player, illumination conditions, variety of sports fields and t-shirts. Here, we survey the most significant methods and problem formulations that have been proposed to address the problem of player identification.

Keywords

Main Subjects

Files

Share

How to cite

Statistics