Guidelines for LCS 2001 Paper Submissions

This paper proposes a novel two-stage method for motion segmentation under stationary background conditions. First motion vectors are extracted using an attention based method. Then a region growing technique is applied to these vectors to obtain motion segmentation and completes motion segmentation with region matching. The algorithm is tested on various video data and experimental results show that the proposed approach can extract detailed motion information from non-rigid objects such as moving people.