Dual Tree Complex Wavelet Transform Based Video Object Tracking

Abstract

This paper presents a new method for tracking of an object in video sequence which is based on dual tree complex wavelet transforms. Real valued wavelet transform, mostly used in tracking applications, suffers from lack of shift invariance and have poor directional selectivity. We have used dual tree complex wavelet transform in tracking because it avoids shortcomings of real wavelet transform. In the proposed method, object is tracked in next frames by computing the energy of dual-tree complex wavelet coefficients corresponding to the object area and matching this energy to that of in the neighborhood area. The proposed method is simple and does not require any other parameter except complex wavelet coefficients. Experimental results demonstrate performance of the proposed method. © Springer-Verlag Berlin Heidelberg 2010.