In optical image registration, the polynomial regression model generally supposes that the reference control points (RCPs) used as the coefficient matrix is error-free. However, the actual RCPs often inevitably contain errors and RCPs residual errors between different images are not the same. The general least squares method (LS) only considers the error in the observation vector whereas the total least squares method (TLS) takes the errors of both the observation vector and the coefficient matrix into account and assumes that they have the same residual error. In view of this situation, this paper introduces a more reasonable weighted total least squares method (WTLS) for polynomial regression coefficients estimation. Experiments show that the WTLS can estimate the parameters better and significantly improve the image registration accuracy.
李政, 李永树, 楚彬, 唐敏. 基于加权整体最小二乘法的无人机影像配准[J]. 国土资源遥感, 2014, 26(2): 69-73.
LI Zheng, LI Yongshu, CHU Bin, TANG Min. UAV image registration based on the weighted total-least-squares. REMOTE SENSING FOR LAND & RESOURCES, 2014, 26(2): 69-73.
[1] 孙家柄.遥感原理与应用[M].武汉:武汉大学出版社,2009:143-145. Sun J B.Remote sensing principle and application[M].Wuhan:Wuhan University Press,2009:143-145.[2] 梅安新,彭望琭,秦其明,等.遥感导论[M].北京:高等教育出版社,2001:106-112. Mei A X,Peng W L,Qin Q M,et al.Introduction to remote sensing[M].Beijing:Higher Education Press,2001:106-112.[3] 葛咏,梁怡,马江洪,等.遥感影像配准误差传递模型及模拟分析[J].遥感学报,2006,10(3):299-305. Ge Y,Liang Y,Ma J H,et al.Error propagation model for registration of remote sensing image and simulation analysis[J].Journal of Remote Sensing,2006,10(3):299-305.[4] Van Huffel S,Vandewalle.The total least squares and least squares techniques in the presence of errors on all data[J].Siam Journal on Numerical Analysis,1991,25(5):765-769.[5] Schaffrin B,Andreas W.On weighted total least squares adjustment for linear regression [J].Journal of Geodesy,2008,82(6):415-421.[6] Schaffrin B,Felus Y A.On the multivariate total least squares approach to empirical coordinate transformations[J].Journal of Geodesy,2008,82(2):373-383.[7] 陈义,陆珏,郑波.总体最小二乘方法在空间后方交会中的应用[J].武汉大学学报:信息科学版,2008,33(12):1271-1274. Chen Y,Lu Y,Zheng B.Application of total least squares to space resection[J].Geomatics and Information Science of Wuhan Universit,2008,33(12):1271-1274.[8] Cheng C L,Mastrondrdi N,Palge C,et al.Total least squares and errors-in-variables moseling[J].Computational Statistics and Data Analysis,2007,52(2):1076-1079.[9] Schaffrin B.A note on constrained total least-squares estimation [J].Linear Algebra and Its Applications,2006,417(1):245-258.[10] Schaffrin B,Wieser A.On weighted total least squares adjustment for linear regression[J].Journal of Geodesy,2008,82(7):415-421.[11] 黄世存,章文毅,何国金,等.几种不同矩阵算法的遥感图像几何精纠正效果比较[J].国土资源遥感,2005,17(3):18-22,43. Huang S C,Zhang W Y,He G J,et al.A Comparison of remote sensing image rectification effects based on several matrix algorithms[J].Remote Sensing for Land and Resources,2005,17(3):18-22,43.
2014, Vol. 26 
