Robust watershed segmentation of moving shadows using wavelets

Segmentation of moving objects in a video sequence is a primary mission of many computer vision tasks. However, shadows extracted along with the objects can result in large errors in object localization and recognition. We propose a novel method of moving shadow detection using wavelets and watershed segmentation algorithm, which can effectively separate the cast shadow of moving objects in a scene obtained from a video sequence. The wavelet transform is used to de-noise and enhance edges of foreground image, and to obtain an enhanced version of gradient image. Then, the watershed transform is applied to the gradient image to segment different parts of object including shadows. Finally a post-processing exertion is accommodated to mark segmented parts with chromacity close to the background reference as shadows. Experimental results on two datasets prove the efficiency and robustness of the proposed approach.