一种基于双向匹配融合的合成孔径雷达景象匹配算法

doi:10.3969/j.issn.1000-1093.2019.01.015

兵工学报 ›› 2019, Vol. 40 ›› Issue (1): 124-133.doi: 10.3969/j.issn.1000-1093.2019.01.015

一种基于双向匹配融合的合成孔径雷达景象匹配算法

伍薇, 苏娟

（火箭军工程大学，陕西西安 710025）

收稿日期:2018-02-09 修回日期:2018-02-09 上线日期:2019-03-12
通讯作者: 苏娟（1973—），女，副教授，硕士生导师 E-mail:suj04@mails.tsinghua.edu.cn
作者简介:伍薇（1994—），女，硕士研究生。E-mail: wuw171121@sina.com
基金资助:
国家自然科学基金项目（61302195）

A SAR Scene Matching Algorithm Based on Bi-directional Matching Fusion

WU Wei, SU Juan

（Rocket Force University of Engineering, Xi'an 710025, Shaanxi, China）

Received:2018-02-09 Revised:2018-02-09 Online:2019-03-12

摘要/Abstract

摘要： 针对合成孔径雷达（SAR）图像进行景象匹配时因图像差异和斑点噪声造成误匹配的问题，提出了一种基于双向匹配融合的景象匹配算法。采用变形差异相似性测度进行从实时图到参考图的正向匹配；通过选取参考图中易匹配子区，进行基于相位一致性特征强度互相关的从参考图到实时图的反向匹配；对双向匹配的结果进行融合处理，确定最终的匹配位置。实验结果表明，该算法能克服异源SAR图像间的图像差异对匹配的影响，具有较高的匹配精度和较好的鲁棒性。

关键词: 合成孔径雷达图像, 双向匹配, 变形差异相似性, 相位一致性特征

Abstract: A SAR scene matching algorithm based on bi-directional matching fusion is proposed. The deformable diversity similarity is used to realize the forward matching from the real-time image to the reference image. The subregions which are easy to be matched are chosen in the reference image, and the normalized cross correlation of phase congruency feature is adopted to realize the reverse matching from the reference image to the real-time image. The final matching location is determined by fusing the bi-directional matching results. Experimental results show that the proposed algorithm has high accuracy and strong robustness, which can overcome the influence of image difference on matching. Key

Key words: syntheticapertureradarimage, bi-directionalmatching, deformablediversitysimilarity, phasecongruencyfeature

中图分类号:

TP751

伍薇, 苏娟. 一种基于双向匹配融合的合成孔径雷达景象匹配算法[J]. 兵工学报, 2019, 40(1): 124-133.

WU Wei, SU Juan. A SAR Scene Matching Algorithm Based on Bi-directional Matching Fusion[J]. Acta Armamentarii, 2019, 40(1): 124-133.

参考文献

［1］谢宜壮, 吴琼之, 符蓓蓓, 等. 系统级仿真与验证方法在精确打击武器成像系统中的应用[J]. 兵工学报, 2010, 31(增刊2): 1-4.
XIE Y Z,WU Q Z, FU B B, et al. Application of system simulation and validation method in precise attack weapon imaging system[J]. Acta Armamentarii, 2010, 31(S2):1-4.(in Chinese)
[2］庞海洋, 王岩飞, 张健. 基于合成孔径雷达图像的伪装遮障目标特性建模技术[J]. 兵工学报, 2016, 37(3):559-564.
PANG H Y, WANG Y F, ZHANG J. Modeling technology of camouflages screen target characteristics based on SAR images[J]. Acta Armamentarii, 2016, 37(3):559-564.(in Chinese)
[3］李壮. 异源图像匹配关键技术研究[D]. 长沙: 国防科学技术大学, 2011.
LI Z. Research onkey technologies of multi-sensor images matching[D]. Changsha: National University of Defense Technology, 2011. (in Chinese)
[4］ DELLINGER F, DELON J, GOUSSEAU Y, et al. SAR-SIFT: a sift-like algorithm for SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(1):453-466.
[5］ CHEN T, CHEN L. A union matching method for SAR images based on SIFT and edge strength[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(12):4897-4906.
[6］ XIONG B L, HE Z G, HU C B, et al. A method of acquiring tie points based on closed regions in SAR images[C]∥Proceedings of IEEE International Conference on Geoscience and Remote Sensing. Munich, Germany: IEEE, 2012:2351-2362.
[7］苏娟, 李彬, 王延钊. 一种基于封闭均匀区域的SAR图像配准方法[J]. 电子与信息学报, 2016, 38(12): 3282-3288.
SU J, LI B, WANG Y Z. SAR image registration algorithm based on closed uniform regions[J]. Journal of Electronics and Information Technology, 2016, 38(12): 3282-3288. (in Chinese)
[8］ HELOR Y, HELOR H, DAVID E. Matching by tone mapping: photometric invariant template matching[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(2):317-330.
[9］ DEKEL T, ORON S, RUBINSTEIN M, et al. Best-buddies similarity for robust template matching[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, US: IEEE, 2015:2021-2029.

[10］ YE Y X, SHEN L. HOPC: a novel similarity metric based on geometric structural properties for multi-modal remote sensing image matching[J]. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016, 3(1):9-16.
[11］ YE Y X, SHAN J, BRUZZONE L, et al. Robust registration of multimodal remote sensing images based on structural similarity[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(5): 2941-2958.
[12］ GONG M G, ZHAO S M, JIAO L C, et al. A novel coarse-to-fine scheme for automatic image registration based on SIFT and mutual information[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(7):4328-4338.
[13］ SHECHTMAN E, IRANI M. Matching local self-similarities across images and videos[C]∥Proceeedings of IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, MN, US: IEEE, 2007:1-8.
[14］ TALMI I, MECHREZ R, ZELNIKMANOR L. Template matching with deformable diversity similarity[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Honolulu，HI, US: IEEE,2017:1311-1319.
[15］ FRSTNER W, GlCH E. A fast operator for detection and precise location of distinct points, corners and circular features[C]∥Proceedings of ISPRS Intercommission Workshop on Fast Processing of Photogrammetric Data. Interlaken, Switzerland: IEEE, 1987:281-305.
[16］ MORRONE M C, OWENS R A. Feature detection from local energy[J]. Pattern Recognition Letters, 1987, 6(5):303-313.
[17］ KOVESI P. Image features from phase congruency[J]. Journal of Computer Vision Research, 1999, 1(3):115-116.

第40卷第1期
2019 年1月兵工学报ACTA
ARMAMENTARIIVol.40No.1Jan.2019

[1]	徐英，谷雨，彭冬亮，刘俊，陈华杰. 面向合成孔径雷达图像任意方向舰船检测的改进YOLOv3模型[J]. 兵工学报, 2021, 42(8): 1698-1707.
[2]	李响，苏娟，杨龙. 基于改进YOLOv3的合成孔径雷达图像中建筑物检测算法[J]. 兵工学报, 2020, 41(7): 1347-1359.
[3]	庞海洋，王岩飞，张健. 基于合成孔径雷达图像的伪装遮障目标特性建模技术[J]. 兵工学报, 2016, 37(3): 559-564.
[4]	袁礼海，宋建林，沈涛. 合成孔径雷达围像特征关键度分析与分类算法研究[J]. 兵工学报, 2007, 28(10): 1186-1190.

一种基于双向匹配融合的合成孔径雷达景象匹配算法

A SAR Scene Matching Algorithm Based on Bi-directional Matching Fusion

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价