A VSS Algorithm Based on Multiple Features for Object Tracking

A variable search space (VSS) approach according to the color feature combined with point feature for object tracking is presented. Mean shift is a well- established and fundamental algorithm that works on the basis of color probability distributions, and is robust to given color targets. As it solely depends upon back projected probabilities, it may miss the targets because of illumination and noise. To overcome the flaw, we proposes VSS algorithm based on the color and robust feature of the detected object. The proposed algorithm can solve the problem that the color of the detected object is similar to the background, and achieve better real-time tracking due to change the search window's size. Experimental work demonstrates that the presented method is robust and computationally effective. Index Terms-Meanshift, Scale Invariant Feature Transform, target tracking, variable search space