基于改进SURF算子的SAR图像弹性配准  

SAR Image Elastic Registration Based on Modified SURF

作　　者：徐颖[1] 周焰[2] 

机构地区：[1]空军预警学院研究生管理大队,武汉430019 [2]空军预警学院四系,武汉430019

出　　处：《武汉理工大学学报》2013年第11期151-156,共6页Journal of Wuhan University of Technology

基　　金：国家自然科学基金(40101019)

摘　　要：针对存在局部几何形变的多波段SAR图像自动配准问题,提出基于改进SURF算子的SAR图像配准算法。对图像采取分块的思想,利用SURF算子提取特征点,利用双向的最小距离和次小距离之比确定匹配特征点对,并通过薄板样条(TPS)函数完成图像的弹性配准。最后,应用文中的配准方法对不同时间获得的两幅多波段SAR图像进行配准实验,并对其配准精度进行了分析,证明了文中的方法具有很好的适应性和配准精度。Aimed at the problems of local geometric deformation of multiband SAR image automatic registration, the modified SURF method is proposed. Adopt the ideas of the partitioning for images, extract the features by using SURF operator,and determine the matching feature point pairs with the ratio of the minimum distance and the second smallest distance. And through the thin plate spline （TPS） function complete elastic registration of images. The registration experiment is made based on two different band SAR images acquired at different times, the registration precision is analyzed. The experimental results show that the proposed method has very good adaptability and accuracy of registration.

关 键 词：SAR图像 弹性配准 SURF算子 薄板样条函数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]