Colour Object Tracking without Shadow

In video object tracking, shadows are commonly present for general lighting environments and present a confounding factor for correct object tracking. Tracking the real object instead of a compound object with shadow is a challenging problem. Therefore object tracking results based on traditional schemes usually result in a combination of the object and its shadow. In this paper, we present a new method for tracking objects with shadows based on an illumination invariant colour space and gradient vector flow snake model for reliable object tracking in video environment. Experimental results show that the proposed method can track the real object even if there is strong shadow influence.