A algorithm research for stereo video object segmentation and 3-D reconstruction

摘要

Stereo video object segmentation is a critical technology of the new generation of video coding, video retrieval, Internet and other emerging interactive multimedia field. This paper puts forward a redundant wavelet transform based stereo video object segmentation algorithm. First, the algorithm obtains the disparity map by redundant wavelet transform and then uses the disparity map to do video object segmentation. For the moving objects in the stereo video sequence, the algorithm uses the redundant wavelet transform to extract the motion region. Experimental results show that the algorithm can not only segment the overlapping objects, but also can segment the stationary objects and moving objects at the same time with better accuracy and robustness. According to depth map, the visible scene surface is represented with a para-metrically deformable, spatially adaptive, wireframe model.