一种基于背景重建和视差图的立体视频对象分割算法  

A Stereo Video Object Segmentation Algorithm Based on Background Reconstruction and Disparity Map

作　　者：王凌云[1] 李朝晖[1] 李冬梅[1] 

机构地区：[1]中国传媒大学信息工程学院,北京100024

出　　处：《中国传媒大学学报（自然科学版）》2013年第5期41-45,共5页Journal of Communication University of China：Science and Technology

摘　　要：提出了一种基于背景重建和视差图的立体视频分割算法,利用背景、视差和边缘等信息进行运动对象分割。该算法首先采用基于块的背景重建方法获取视频序列的背景信息,再利用背景相减法获得运动对象的初步分割结果,然后利用立体匹配获得的视差图对初步分割结果进行修正,最后利用边缘信息和后处理操作获得最终的立体视频运动对象。实验表明,该算法能够有效地从运动背景中将视频运动对象完整地提取出来。A stereo video object segmentation algorithm based on background reconstruction and disparity map is proposed, which utilizes the information of background, disparity and edging features to extract moving objects from video sequences. Firstly, the method of background reconstruction based on blocks is used to obtain the background information of video sequences, then the background subtraction algorithm is adopted to get the initial segmentation results of moving objects. Secondly, the stereo matching is used to get the disparity map which will then be used to modify the initial segmentation results. Finally, the edging information and mathematic morphology post - processing are applied to get the accurate video object. Experimental results demonstrate that the proposed algorithm can successfully extract moving objects from stereo video sequences whose background have other moving objects.

关 键 词：立体视频 背景重建 视差估计 对象分割 

分 类 号：TN911.73[电子电信—通信与信息系统]