复杂环境下基于信息融合的视频实时抠像算法-计算机工程与应用.PDF

208 2016 ，52（22 ） Computer Engineering and Applications 计算机工程与应用 复杂环境下基于信息融合的视频实时抠像算法 1 2 1 邓 爽 ，李磊民 ，黄玉清 1 2 1 DENG Shuang , LI Leimin , HUANG Yuqing 1.西南科技大学 信息工程学院，四川 绵阳 621000 2.西南科技大学 国防科技学院，四川 绵阳 621000 1.School of Information Engineering, Southwest University of Science and Technology, Mianyang, Sichuan 621000, China 2.School of National Defence Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan 621000, China DENG Shuang, LI Leimin, HUANG Yuqing. Real time automatic video matting algorithm based on information fusion in complex environment. Computer Engineering and Applications, 2016, 52 （22 ）：208-211. Abstract ：The problem of an object which is similar to the background texture or the boundary which is unclear in the image segmentation cannot be solved easily by the traditional video matting algorithm. In order to solve this problem, this paper proposes a real-time automatic algorithm of video matting based on information fusion of visual sensor and laser radar. The algorithm obtains the deep information from the original LIDAR point cloud data, which is used as prior knowl- edge to the improvement of spectral matting. It can simultaneously create a region of interest depth matting Laplacian matrix （DML ）. Finally, the matting is gotten by cluster optimal iterative algorithm, and steerable filters is used to post-pro- cessing. Compared with the traditional algorithm of information fusion depth and no other information fusion algorithm, experiments in this paper show that the algorithm reduces the over-segmentation rate and improves the efficiency, and that the edge information of the matting object is more plump and smooth. Key words ：complex scenes; point cloud processing; depth information; spectral matting 摘 要：针对复杂场景下传统的视频抠像算法对目标物体与背景纹理相似或边界不清晰的图像分割困难的问题，提出 了一种基于视觉传感器和激光雷达信息相融合的视频实时抠像算法。该算法从原始激光雷