Automatic video editing: Original tracking method applied to basketball players in video sequences

Abstract

The main task here is to track several basketball players during a game and to be able to retrieve their whole trajectories at the end. The final application is to get some statistics about each players and to identify some special events like free throw or to determine when a counterattack is going to happen. The originality of the solution states in the way the tracking is performed: instead of studying the close environment of each player, all the players are detected on each frame then we are using specific informations like background, speed vector, color or distance between players to link player’s positions and create the whole trajectories. We will compare our results with a benchmark of algorithms to see that our solution is quite efficient in term of tracking and speed.