Discrete particle swarm optimization for player trajectory extraction in soccer broadcast videos

Broadcasted soccer videos demand automatic semantic representation for event and tactic analyses. Player tracking is an important step which can be further processed and analyzed by sport experts to evaluate player or team performance. A novel scheme for player tracking in soccer broadcast videos is proposed in this research. Following player detection using Adaboost, player labeling, occlusion handling and mosaic construction, player tracking is formulated as an optimization problem allowing player trajectories to be extracted using Particle Swarm Optimization (PSO). PSO is an optimization method inspired by the ocking behavior of birds, which was originally customized for continuous function value optimization. In this paper, a new application of discrete particle swarm optimization for player tracking in soccer videos is proposed. Updating equations for the particle swarm optimization algorithm are modied based on problem characteristics and discrete variables to extract the player trajectory. Experimental results show that the modied PSO is promising in solving soccer player tracking problems.