A DCT-Based Video Object Segmentation Algorithm for Rainy Situation Using Change Detection

This paper proposes a DCT-based moving object extraction algorithm which is focused on rainy condition by change detection method. The DCT kchniqzle is used to decrease the rainy efect in order to construct a reliable background model. Then, we use change detection to classzfj, pixeb in video frame into the foregro~lnd region or background region so as to acquire an initial object mask. Besides, reflection eflect can be removed from initial object mask through edge detection and bounding box match. Finally, a post-processing is used lo refine the boundary of moving object by connect component labeling and morphological operation. Experimental results show lhat the proposed algorithm can provide a safisfactory segmentation resztlt in rainy situations.