A Visual Tracking Algorithm for Real Time People Detection
Tiziana D’Orazio, Marco Leo, Paolo Spagnolo, Pier Luigi Mazzeo, Nicola Mosca, Massimiliano Nitti · 2007
In this paper we present a multi-people-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 does not require the feature extraction to track the single object. Experimental tests have been carried out on soccer image sequence in which some players enter into the camera view and remain for some time.