C.: Collaborate Ball and Player Trajectory Extraction

Enormous accessible broadcast soccer videos de-mand an efficient ball and player trajectory extraction framework to represent the tactic semantics for the au-tomatic analysis. Camera motions, noise and blurs in broadcast videos make it difficult to extract the trajec-tories with a single existing object tracking algorithm. In this paper, we propose a novel framework for ball and player trajectory extraction in broadcast soccer videos. The framework generates candidate ball trajec-tories and player trajectory segments, then it searches the optimal ball trajectory with the likelihood ranking and refines player trajectories with MCMC data associ-ation. Instead of extracting ball and player trajectories respectively, our framework employs the motion rela-tionship of the ball and players to build a collaborate scheme to improve the tracking and trajectory refine-ment results. The experimental results show the pro-posed framework is more effective than previous works. 1