光电工程, 2010, 37 (11): 121, 网络出版: 2011-01-05
基于仿射不变SIFT特征的SAR图像配准
SAR Image Registration Based on Affine Invariant SIFT Features
摘要
针对SAR (Synthetic Aperture Radar) 图像全自动配准问题,本文提出一种基于仿射不变SIFT (Scale InvariantFeature Transform) 特征的精确配准方法。该方法首先对传统SIFT 方法改进构建具有仿射不变性的SIFT 描述子,并利用该描述子对提取的控制点进行粗匹配,然后由粗匹配点对的尺度比和方位差及其邻域的灰度相似性构建新的相似矩阵,最后利用SVD (Singular Value Decomposition)方法确定精确匹配点对,求出变换参数从而实现图像的精确配准。实验结果表明该方法优于传统的SIFT 方法和SIFT+SVD 方法并且可以达到亚像素的配准精度。
Abstract
Referring to the problems of Synthetic Aperture Radar (SAR) image registration, an approach of SAR image registration based on affine invariant Scale Invariant Feature Transform (SIFT) features is proposed. First, the affine invariant SIFT descriptors are constructed by improving the original SIFT descriptors and the control points are rough matched by using the improved SIFT descriptors. Then, a new proximity matrix is built according to the scale ratio and the difference of orientations among the rough matched points and the similarity of the intensity around the rough matched points. Finally, the exact matching points are determined by using Singular Value Decomposition (SVD) method, and the precise image registration is performed. Experimental results show that the proposed algorithm has a better performance than original SIFT algorithm and SIFT+SVD method, and the accuracy of our algorithm can achieve sub-pixel level.
刘向增, 田铮, 温金环, 武建明, 张朝阳. 基于仿射不变SIFT特征的SAR图像配准[J]. 光电工程, 2010, 37(11): 121. LIU Xiang-zeng, TIAN Zheng, WEN Jin-huan, WU Jian-ming, ZHANG Zhao-yang. SAR Image Registration Based on Affine Invariant SIFT Features[J]. Opto-Electronic Engineering, 2010, 37(11): 121.