Basketball player identification by jersey and number recognition

Abstract

We are interested in the problem of automatically tracking and identifying players in sports video. While there are many automatic multi-target tracking methods, in sports video, it is difficult to track multiple players due to frequent occlusions, quick motion of players and camera, and camera position. We propose tracking method that associates tracklets of a same player using results of player number recognition. To deal with frequent occlusions, we detect human region by level set method and then estimates if it is occluded group region or unconcluded individual one. This Thesis paper gives a brief description about each paper/technology in the field of ―Player Detection and Mapping Techniques in Sport Videos. Recognition of players in pictures of sporting events is an approachable but tough task. In the case of an NBA game, this task can be accomplished by compartmentalizing the job. By characterizing jersey color with MAP detection, isolating the jerseys and numbers, and using template matching, we can make a max-effort algorithm that identify as many players as possible.