A Method for Football Players Detection on the Soccer Field by Integrated Image Processing Techniques

Abstract

The player detection algorithm in a soccer field image is an important step for an offside situation detection. A difficulty of player detection occur when the player is overlap with the crowd of cheering. In this paper, we propose a new method for football player detection on the soccer field by integrated image processing techniques. This method consists of two steps. Firstly, the soccer field area is segmented from the background. This step is used to avoid the error of player detection from overlap problem between player and crowd of cheering. Finally, the process to detect players in the soccer field from Morphological. To test the performance of the proposed method, the images used to test in this research have 150 images from three football matches. The detected players compared with the total players on the field by visual. Detection rate is 85.943% and the accuracy of the player detection process is 76.63%. The result show that the proposed method is satisfactory in order to continue for performance improvement. © 2023 IEEE.