An adaptive approach to video tracking

Abstract

A video tracking system based on the principles of optimalizing control is presented. This system is designed such that expensive segmentation procedures are not necessary, and is well suited for fast hardware implementation. At the image received from the camera a perturbation procedure is performed, simulating the variations on the intensity values that would occur if the camera were moved. An index of performance (IP) is evaluated at the results of this perturbation; this IP does not need to detect the position of the tracked object accurately, but rather varies in such a way as to detect the motion of the object with respect to the camera. Algorithms for translation and scaling of the tracking object have been developed using area, centroid, and template matching as indices of performance. Software simulation experiments show that the control law developed yields good results even under variations in background and illumination and under multidimensional motion. >