Visually Tracking Football Games Based on TV Broadcasts

This paper describes ASPOGAMO, a visual tracking system that determines the coordinates and trajectories of football players in camera view based on TV broadcasts. To do so, ASPOGAMO solves a complex probabilistic estimation problem that consists of three subproblems that interact in subtle ways: the estimation of the camera direction and zoom factor, the tracking and smoothing of player routes, and the disambiguation of tracked players after occlusions. The paper concentrates on system aspects that make it suitable for operating under unconstrained conditions and in (almost) realtime. We report on results obtained in a public demonstration at RoboCup 2006 where we conducted extensive experiments with real data from live coverage of World Cup 2006 games in Germany.