基于秩3约束的遮挡点恢复方法  

Occlusion recovery method based on rank 3

作　　者：刘侍刚[1] 彭亚丽[2] 徐秋平[1] 王琳娟[1] 

机构地区：[1]陕西师范大学计算机科学学院,西安710062 [2]西安电子科技大学计算机学院,西安710071

出　　处：《仪器仪表学报》2008年第12期2622-2625,共4页Chinese Journal of Scientific Instrument

基　　金：国家自然科学基金(60805016);中国博士后科学基金(20080430201)资助项目

摘　　要：提出了一种基于秩3约束的遮挡点恢复方法,该方法利用所有图像点组成一个秩3的矩阵,并利用该特性构造一个投影矩阵,利用该投影矩阵求得遮挡点,再用求得的遮挡点代替图像中的遮挡点,经过多次迭代,最后求得遮挡点的真实图像位置。该方法的优点是将所有的图像及图像点都平等地看待,模拟实验和真实实验表明,该方法具有鲁棒性好、收敛性好及误差小等优点。An occlusion recovery method based on rank 3 is presented in the paper. All of the image points compose a matrix with rank 3, with which a projective matrix is constructed and is used to find all the occlusions. At the same time, the obtained occlusions are used to substitute for the old occlusions in the image. Through iterations, the real positions of the occlusions can be found. The innovation of the algorithm is that all the images and all the image points are treated uniformly. The experiments with both simulation and real data show that the algorithm is effieient, robust, and has good convergence property and small error.

关 键 词：秩3 遮挡点 线性迭代 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]