Crowded scene object tracking in presence of Gaussian White noise using undecimated wavelet features

In this paper, we propose a new noise robust algorithm for object tracking in the crowded video scenes. The algorithm exploits the properties of undecimated wavelet packet transform (UWPT) coefficients and texture analysis to track arbitrary objects. The coefficients of the UWPT of a user-specified region at the reference frame construct a feature vector (FV) for every pixel in that region. Optimal search for the best match of the region in successive frames is then performed by using the generated FVs inside an adaptive search window. Adaptation of the search window is achieved by inter-frame texture analysis to find the direction and speed of the object motion. Noise robustness has been achieved through inherent noise suppression in the FV generation process. Experimental results show a good performance for object tracking in contaminated crowded scenes with Gaussian white noise even in presence of partial occlusion.