基于分级策略和改进相位相关的SAR影像配准  

SAR Image Registration Based on Classification Strategy and Improved Phase Correlation

作　　者：何伟 徐卓揆[1,2] 刘佳斌[1] HE Wei;XU Zhuokui;LIU Jiabin(School of Traffic and Transportation Engineering,Changsha University of Science and Technology,Changsha 410114,China;Engineering Laboratory of Spatial Information Technology of Highway Geological Disaster Early Warning in Hunan Province,Changsha University of Science and Technology,Changsha 410114,China)

机构地区：[1]长沙理工大学交通运输工程学院,湖南长沙410114 [2]长沙理工大学公路地质灾变预警空间信息技术湖南省工程实验室,湖南长沙410114

出　　处：《地理空间信息》2022年第3期72-76,共5页Geospatial Information

基　　金：长沙理工大学公路地质灾变预警空间信息技术湖南省工程实验室开放基金资助项目(kfj180602)。

摘　　要：传统SAR影像自动配准方法往往存在大量重复运算或需要精确初值,特别是在亚像素配准时,大量重采样运算更不可避免;而传统相位相关亚像素配准方法用于SAR影像配准的可靠性和精度较差,大范围配准时更忽略了局部偏移量的不一致。鉴于此,采用分级配准策略,在全局粗配准后分块进行精配准,即先利用传统相位相关法完成局部整像素配准,再利用改进的相位相关法迭代完成局部亚像素配准。在局部亚像素配准时改进了传统相位相关亚像素配准方法,以相关峰为测度,通过曲线拟合并改正偏移量来迭代求取亚像素偏移值。通过控制点的二次多项式拟合均方根误差和精配准后控制点平均相关系数分析配准精度,进行了验证实验。结果表明,在低相关区域,该配准方法得到的结果在精度上接近实相关法、优于复相关法,且明显提高了运算效率。Traditional SAR image automatic registration methods often have a large number of repeated operations or require accurate initial val-ues.A large number of resampling operations are inevitable in subpixel registration.The traditional subpixel phase correlation registration meth-od used in SAR image registration also has poor reliability and accuracy,and the inconsistency of local shifts is ignored when registering in a large range.We adopted a hierarchical registration strategy.After the global roughly registering,we divided the image into many parts for pixel and subpixel registration.We improved the subpixel registration method for local registration by taking the coherent peak as a measure and itera-tively obtaining subpixel shift value by curve fitting and correcting shifts.We used root mean square error of quadratic polynomial fitting and av-erage correlation coefficient of control points to analyze registration accuracy.Finally,we used two ENVISAT ASAR Single Look Complex data for verification experiments.The results show that in the low correlation area,the registration results of the proposed method are close to the real correlation method,and superior to the complex correlation method.This method obviously improves operation efficiency.

关 键 词：SAR 分级配准 亚像素 相位相关 

分 类 号：P228[天文地球—大地测量学与测量工程]