Automatic registration of multi-source images for extraction of earthquake damage information
YANG Dehe1, CHEN Yijin1, YANG Xi1, LYU Jingguo2, ZHANG Zixin1, ZHANG Shuai1
1. China University of Mining and Technology (Beijing), College of Geoscience and Surveying Engineering, Beijing 100083, China;
2. Beijing University of Civil Engineering and Architecture, Beijing 100044, China
In order to extract the information of earthquake damage from multi-source images, the authors explored a high-accuracy algorithm of automatic image registration. Firstly, It uses Moravec operator to extract feature points and uses random sample consensus (random sample consensus, RANSAC)algorithm to reject mismatching points. Secondly, it makes a log-polar transformation according to the feature points to obtain the rotated angles and the scaled factors of the reference image and the image to be registered. After compensating coefficients of the rotated angles and the scaled factors, it uses an algorithm of sub-pixel level and phase-correlated to calculate the offset between the images and uses the interpolation algorithm to resample the registration image. At last, the images before and after the earthquake are processed as classification targets. They are used to classify and extract the earthquake damage information based on the features. The results show that the designed algorithm in this paper is of the high robustness and registration precision, and is more suitable to the registration of multi-source remote sensing images. The information of earthquake damage can be better applied to the assessment of the earthquake damage than before.
[1] 吴金鹿,陈绍炜,孙磊.一种基于互相关匹配的空域目标提取方法[J].科学技术与工程,2011,11(32):7948-7951. Wu J L,Chen S W,Sun L.An airspace object extraction method based on cross-correlation matching[J].Science Technology and Engineering,2011,11(32):7948-7951.[2] 林茂.基于改进的曲线傅里叶变换图像配准研究[J].计算机仿真,2011,28(10):265-268. Lin M.Improved digital image contour curve Fourier descriptor algorithm[J].Computer Simulation,2011,28(10):265-268.[3] 詹毅.基于泰勒展开式的图像插值方法[J].计算机工程,2012,38(13):202-204. Zhan Y.Image interpolation method based on Tyler expansion[J].Computer Engineering,2012,38(13):202-204.[4] 张晓芬.基于偏微分方程的图像配准技术研究[D].河北:华北电力大学,2009:32-39. Zhang X F.Research on image registration technique based on PDE’s[D].Hebei:North China Electric Power University,2009:32-39.[5] 程有娥.基于角点特征和最大互信息的图像配准[J].计算机系统应用,2012,21(6):186-190. Cheng Y E.Image registration based on mutual information and corner points[J].Computer Systems and Applications,2012,21(6):186-190.[6] 刘晓龙,李英成.基于多源遥感影像融合的影像匹配技术[J].测绘科学,2007,32(3):59-61. Liu X L,Li Y C.Image matching based on multi-source remote-sensing image fusion[J].Science of Surveying and Mapping,2007,32(3):59-61.[7] 周剑军,欧阳宁,张彤,等.基于RANSAC的图像拼接方法[J].计算机工程与设计,2009,30(24):5692-5694. Zhou J J,Ouyang N,Zhang T,et al.Image mosaic method based on RANSAC[J].Computer Engineering and Design,2009,30(24):5692-5694.[8] 雷凯,刘艳滢,王延杰,等.基于特征点的对数极坐标变换图像配准算法[J].光学技术,2007,32(3):435-437. Lei K,Liu Y Y,Wang Y J,et al.Log polar transformation based on feature points for image registration[J].Optical Technique,2007,32(3):435-437.[9] 刘卫光,崔江涛,周利华.插值和相位相关的图像亚像素配准方法[J].计算机辅助设计与图形学学报,2005,17(6):1273-1277. Liu W G,Cui J T,Zhou L H.Subpixel registration based on interpolation and extension phase correlation[J].Journal of Computer-aided Design and Computer Graphics,2005,17(6):1273-1277.[10] 贾永红.数字图像处理[M].武汉:武汉大学出版社,2003:182-186. Jia Y H.Digital image processing[M].Wuhan:Wuhan University Press,2003:182-186.