基于边缘与SURF算子的SAR与可见光图像配准方法

纪利娥; 杨风暴; 王志社; 陈磊

doi:doi:10.5768/jao201334.0502007

应用光学, 2013, 34 (5): 809, 网络出版: 2013-12-04

基于边缘与SURF算子的SAR与可见光图像配准方法

SAR and visible image registration method　based on edge and SURF algorithm

论文大纲

纪利娥 ^*杨风暴王志社陈磊

作者单位

中北大学信息与通信工程学院, 山西太原 030051

图像配准 SAR与可见光图像 RANSAC算法 SURF特征 Canny算子 image registration SAR and visible images RANSAC algorithm SURF Canny operator

摘要

鉴于SAR(synthetic aperture radar)与可见光图像的成像机理存在很大差别, 使得其同名特征的提取和配准十分困难, 但在某些情况下, 这两类图像的边缘存在一定的相关性。提出一种基于边缘与SURF(speed-up robust feature)算子的图像配准方法。通过适当预处理增强图像间的共性, 采用综合性能比较好的Canny算子提取两幅图像共有的边缘特征, 在边缘图像的基础上提取SURF特征; 通过比值提纯法进行特征点粗匹配, RANSAC(random sample consensus)算法剔除误匹配点, 计算仿射变换模型从而实现SAR与可见光图像的自动配准。实验结果表明: 该算法的正确匹配率为100%, 均方根误差为0.852个像素, 配准精度达到亚像素水平。

Abstract

Due to the prominent difference of the imaging mechanism between visible and synthetic aperture radar (SAR) images, it is very difficult to extract common features and register, but in some cases, the edges of these two kinds of images have some certain correlation. According to the above problem, an image registration algorithm based on edge and speed-up robust feature (SURF) is proposed. Firstly, the similarity of these two images is enhanced through appropriately preprocessing, the common edge features are extracted by Canny operator which has good performance, and the SURFs are extracted from the edges of the images; then the features matching is done by the ratio purification method, the random sample consensus (RANSAC) algorithm is applied to remove the false matching points, and the affine transformation model is calculated to realize image automatic registration of SAR and visible image. Experimental results demonstrate that the correct matching probability of the proposed algorithm is 100% and the root mean square error is 0.852 pixel, moreover, the registration accuracy can achieve sub-pixel level,which proves the validity of the algorithm.

参考文献

[1] ZITOVA B, FLUSSET J. Image registration methods: a survey[J]. Image and Vision Computing, 2003(21): 977-1000.

[2] 杨敏.结合形态学梯度互信息和多分辨率寻优的图像配准新方法[J].自动化学报,2008,34(3): 246-250.

YANG Min.A novel image regiatration method combining morphological gradient mutual information with multiresolution optimizer[J].Acta automatica sinica, 2008,34(3): 246-250.(in Chinese with an English abstract)

[3] KELLER Y,AVERBUCH A.Multisensor image registration via implictic similarity[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(5): 794-801.

[4] KIM Y S, LEE J H,RA J B.Multisensor image registration based on intensity and edge orientation information[J].Pattern Recognition,2008,41: 3356-3365.

[5] DARE P,DOWMAN I.An improved model for automatic feature based registration of SAR and SPOT image[J].Journal of Photogrammetry & Remote Sensing,2001,56(1): 13-28.

[6] LI Hui,MANJUNATH B S.A countour-based approach to multisensor image registration[J].IEEE Transactions on Image Processing,1995,4(3): 320-334.

[7] YU Xiang-yu,GUO Li-hua.Image registration by contour matching using tangent angle histogram[J].IEEE Congress on Image and Signal Processing,2008,4(4): 746-749.

[8] FLORENCE T,HENRI M.Detection of linear features in SAR images: Application to road network extraction[J].IEEE Transactions on Geosciences and Remote sensing,1993,15: 850-863.

[9] 张登荣,俞乐,蔡志刚.基于面特征的光学与SAR影像自动匹配方法[J].中国矿业大学学报,2007,11(6): 843-847.

ZAHGN Deng-rong,YU Le,CAI Zhi-gang.A region featur based automatic matching for optical and sar images[J].Journal of China University of Mining & Technology, 2007,11(6): 843-847.(in Chinese with an English abstract)

[10] CANNY J.A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(6): 679-698.

[11] HERBERT B, ANDREAS E, TINNE T, et al. Speeded-up robust feature[J]. Computer Vision and Image Understanding, 2008, 110(3): 346-359.

[12] FISCHLER M A, BOLLES R C. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6): 381-395.

[13] 李孟君.基于隐含相似性的光学和SAR图像配准研究[D].长沙: 国防科学技术大学,2008.

LI Meng-jun.Study on registration for sar and optical image via implicit similarity[D].Changsha: National University of Defense Technology, 2008.(in Chinese)

纪利娥, 杨风暴, 王志社, 陈磊. 基于边缘与SURF算子的SAR与可见光图像配准方法[J]. 应用光学, 2013, 34(5): 809. JI Li-e, YANG Feng-bao, WANG Zhi-she, CHEN Lei. SAR and visible image registration method　based on edge and SURF algorithm[J]. Journal of Applied Optics, 2013, 34(5): 809.

基于边缘与SURF算子的SAR与可见光图像配准方法

关于本站 Cookie 的使用提示

全站搜索

基于边缘与SURF算子的SAR与可见光图像配准方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索