Extraction of video object with complex motion

摘要

Object segmentation is a problem within the scope of MPEG-4 standardization activities. This paper proposes a novel technique to extract the moving objects in the video sequences. Our approach is based on the integration of mosaic-based temporal segmentation and color-based spatial segmentation. The mosaic representation of video allows us to fully exploit the spatio-temporal information in the video scene to achieve robust segmentation. Compared with the related works which detect motion by the difference of two consecutive frames, our approach uses the information aggregated over a group of frames. Thus, our system is more robust and is able to extract the non-rigid object that has complex motion from one frame to the next.