A real-time tracking algorithm for estimating the positions, motions and dimensions of unknown objects in image sequences is presented. Processing is based on the dynamic model of the motion imaging situation and on Kalman filter theory. Experimental results on synthetic and real images demonstrate the applicability of the algorithm to surveillance systems.
A real-time approach to 3D object tracking in complex scenes
C. S. Regazzoni;G. L. Foresti
1994-01-01
Abstract
A real-time tracking algorithm for estimating the positions, motions and dimensions of unknown objects in image sequences is presented. Processing is based on the dynamic model of the motion imaging situation and on Kalman filter theory. Experimental results on synthetic and real images demonstrate the applicability of the algorithm to surveillance systems.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
