一种基于非线性扩散方程和Hausdorff测度理论的SAR图像与光学图像配准方法

王子路; 李智勇; 粟毅

doi:10.3724/SP.J.1146.2007.01453

一种基于非线性扩散方程和Hausdorff测度理论的SAR图像与光学图像配准方法

doi: 10.3724/SP.J.1146.2007.01453

计量
- 文章访问数: 3852
- HTML全文浏览量: 122
- PDF下载量: 948
- 被引次数: 0
出版历程
- 收稿日期: 2007-09-13
- 修回日期: 2008-02-04
- 刊出日期: 2009-02-19

Matching Optical Image to SAR Image Using Nonlinear Equation and Hausdorff Distance

摘要

摘要: 该文提出了一种新的利用非线性扩散方程与Hausdorff测度的合成孔径雷达(SAR)图像与可见光图像的配准算法。在此算法中，首先利用非线性扩散方程的SAR图像分割算法获得SAR图像与光学二值图像中相对应的闭合区域特征，将闭合区域质心坐标重合后，被提取特征可通过Hausdorff测度与遗传算法对图像进行快速粗匹配。在粗配准的基础上最后使用二值图像的相关度来进行精配准。实验结果表明，本文方法鲁棒性好，配准精度高，能自动完成存在较大坐标平移、角度变换、尺度缩放的待配图像的配准。
- 合成孔径雷达;特征提取;Hausdorff距离;遗传算法;图像配准
Abstract: This paper describes a new method for matching SAR image and optical image. First, regularizing anisotropic heat diffusion equations is used for segmenting closed-boundary regions in SAR image. After superposing the center of mass of closed-boundary regions, Haudorff distance and genetic algorithm are used to determine scaling and rotation parameters respectively. Finally, the affine-transformed result is refined by binary image correlation to achieve high precise registration. Experimental results indicated that this method can perform automatic registration under precision acquirement for images which differ by translation, rotation and scaling.

HTML全文

参考文献(1)

Yosi keller and Amir Averbach. Implicit similarity: A newapproach to multi-sensor image registration. Proceedings ofthe 2003 IEEE Computer Society Conference on ComputerVision and Pattern Recognition(CVPR03). IEEE, 2003:1-6.[2]Yosi Keller. Multisensor image registration via implicitsimilarity[J].IEEE Trans. on Pattern Analysis and MachineIntelligence.2006, 28(5):794-801[3]Dai Xiaolong and Khopram S. Afeature-based imageregistration algorithm using improved chain-coderepresentation combined with invariant moments. IEEETrans. on G.R.S, 1999, 37(5): 2351-2362.[4]于秋则, 程辉. 基于改进Hausdorff 测度和遗传算法的SAR图像与光学图像匹配. 宇航学报, 2005, 27(1): 130-134.Yu Qiu-ze and Chen Hui. Matching SAR image to opticalimage using modified hausdorff distance and geneticalgorithm. Journal of Astronautics, 2005, 27(1): 130-134.[5]Stockman G, Kopstein S, and Benett S. Matching images tomodels for registration and object via clustering[J].IEEE Trans.on Pattern Analysis and Machine Intelligence.1982, 4(3):229-241[6]Weisenseel A and Karl W, et al.. MRF-based algorithms forsegmentation of SAR images. the Processing of the 1998International Conference on Image Processing, IEEE, 1998,Vol. 3: 770-774.[7]高贵. 基于各向异性热扩散方程的SAR 图像分割方法. 信号处理, 2006, 22(1): 105-109.Gao Gui. The segmentation method for SAR image based onthe anisotropic heat diffusion equation. Signal Processing,2006, 22(1): 105-109.[8]Perona P and Malik J. Scale-space and edge detection usinganisotropic diffusion[J].IEEE Trans. on Pattern Analysis andMachine Intelligence.1990, 12(7):629-639[9]Struwe M. Variational Methods. Berlin: Springer_Verlag,1996, chapter 3.[10]王正明, 朱炬波. SAR 图像提高分辨率技术. 科学出版社,2006, 第3 章.[11]Catte F, Lions P L, Morel J M, and Coll T. Image selectivesmoothing and edge detection diffusion II[J].SIAM J. Numer.Anal.1992, 29(1):182-193[12]Teboul S, Blanc-Feraud L, and Aubert G, et al.. Variationalapproach for edge-preserving regularization using coupledPDEs[J].IEEE Trans. on Image Proc.1998, 7(3):387-397[13]Yu Yongjian and Acton S T. Speckle reduction anisotropicdiffusion[J].IEEE Trans. on Image Processing.2002, 11(11):1260-1270[14]Dong-Gyn Sim et al.. Object matching algorithms usingrobust hausdorff distance measures. IEEE Trans. on ImageProcessing, 1999, 8(1): 425-429.

施引文献

资源附件(0)

访问统计