Auto-generated Strokes for Motion Segmentation

We propose a new approach to motion segmentation that is based on auto-generated strokes. The novelty of the approach is twofold. First, inspired by recent work of other researchers we formulate the problem as that of interactive segmentation. Instead of inputting the strokes by the user, the strokes in our approach are auto-generated. The second novelty of the paper is formulation in which, unlike in many other motion segmentation algorithms, we do not use complex algorithm which fuses the output of multiple cues to segment foreground objects, a simple and effective maximum hybrid similarity method is presented. The maximum hybrid similarity does not need to set the threshold in advance. Experimental results have shown the superiority of the proposed method in extracting moving objects.