A survey on player tracking in soccer videos

Abstract There is a growth of demand for automatically analyzing soccer matches and tactics. Since players are the focus of attentions in soccer matches, player tracking is a fundamental element in most soccer video analysis. The aim of player tracking is to extract the trajectories of players, and its input is provided through some preprocessing steps including playfield detection, player detection, player labeling, occlusion handling and player appearance modeling. Soccer player tracking is a complex and challenging task due to difficulties such as blur, illumination change and heavy occlusions. This paper presents the state-of-the-art in preprocessing and processing methods for soccer player tracking. We categorize different approaches, analyze their strengths and weaknesses, review evaluation criteria and conclude future research directions.