P.L. Mazzeo, P. Spagnolo, and A. Distante (Italy)
Visual Tracking of Player, Player Detection, real time application, soccer scene analysis
In this paper we present an algorithm to classify and track soccer players in outdoor environment with varying light conditions. We introduce a multi-player-tracking algorithm which is able to detect and track humans in complex situations with varying light conditions, high frame rate, and real time processing. We propose a stochastic approach for foreground people tracking based on the evaluation of the maximum a posteriori probability (MAP). The algorithm evaluates geometrical information on the blob overlapping and requires the feature extraction only to solve blob merge situations. Furthermore we use a classification step to solve the blob merging and splitting situations. Experimental tests have been carried out on soccer image sequences in which some players enter into the camera view and remain for some time.
Important Links:
Go Back
