利用Brushlet变换进行SAR图像变化检测

doi:10.3969/j.issn.1001-2400.2013.06.012

J4 ›› 2013, Vol. 40 ›› Issue (6): 67-73.doi: 10.3969/j.issn.1001-2400.2013.06.012

利用Brushlet变换进行SAR图像变化检测

颜学颖;焦李成;王凌霞

(西安电子科技大学智能感知与图像理解教育部重点实验室，陕西西安 710071)

收稿日期:2012-12-18 出版日期:2013-12-20 发布日期:2014-01-10
通讯作者: 颜学颖
作者简介:颜学颖(1984-)，女，西安电子科技大学博士研究生，E-mail: xyyan@mail.xidian.edu.cn．
基金资助:
国家自然科学基金资助项目(61173092, 61072106，60971128，61077009，60972148，60970066，61003198，61001206，61050110144)；高等学校学科创新引智计划(111计划)资助项目(B07048)；教育部“长江学者和创新团队发展计划”资助项目(IRT1170)

SAR image change detection based on Brushlet transform

YAN Xueying;JIAO Licheng;WANG Lingxia

(Ministry of Education Key Lab. of Intelligent Perception and Image Understanding, Xidian Univ., Xi'an 710071， China)

Received:2012-12-18 Online:2013-12-20 Published:2014-01-10
Contact: YAN Xueying

摘要/Abstract

摘要：

针对传统空域和小波域检测算法的相邻像素间相似特征捕捉性能差、方向分辨率低的问题，提出了一种基于非下采样Brushlet变换和各向异性Gabor窗的二维最大类间方差变化检测方法．将非下采样Brushlet域的各向异性Gabor非线性加权均值计算和空域最小化均方误差的线性组合相结合，来获取相干斑噪声抑制后的均值特征，解决了角分辨率低的问题，获得了各个方向、频率和位置的精确定位；利用二维最大类间方差阈值分割来得到最终的变化检测结果．对真实的SAR图像进行了实验，证明了新方法有着较好的检测结果，并能够很好地保留边缘等细节信息．

关键词: 图像变化检测, Brushlet变换, 各向异性, 阈值分割

Abstract:

The traditional change detection method has a poor accuracy for similarity character capture and low direction-resolution. In this paper, a new 2D-Otsu SAR image change detection method is proposed based on the overcomplete Brushlet transform and Gabor window. This method combines the local anisotropic Gabor weighted nonlinear mean procedure in the overcomplete Brushlet domain and linear combination with the minimum mean squared error in the original domain to obtain mean character after the speckle noise is removed, which resolves the problem of low direction-resolution, and can accurately position the texture of each direction, frequency and position. Finally, change detection is processed by the 2D-Otsu method which combines the mean character and gray-level character. Experiment results show that the new method has a better performance, and can well preserve the detailed information such as the texture and edge.

Key words: image change detection, Brushlet transform, anisotropic, threshold segmentation

中图分类号:

TP751.1

颜学颖;焦李成;王凌霞. 利用Brushlet变换进行SAR图像变化检测[J]. J4, 2013, 40(6): 67-73.

YAN Xueying;JIAO Licheng;WANG Lingxia. SAR image change detection based on Brushlet transform[J]. J4, 2013, 40(6): 67-73.

参考文献

［1］ Wan H L, Jung C, Hou B, et al. Novel Change Detection in SAR Imagery Using Local Connectivity ［J］. IEEE Geoscience and Remote Sensing Letters, 2013, 10(1): 174-178.
［2］辛芳芳, 焦李成, 王桂婷, 等. 利用小波域HMC模型进行遥感图像变化检测［J］. 西安电子科技大学学报, 2012, 39(3): 43-49.
Xin Fangfang, Jiao Licheng, Wang Guiting, et al. Change Detection in Multi-temporal Remote Sensing Images Based on Wavelet-domain Hidden Markov Chain Model ［J］. Journal of Xidian University, 2012, 39(3): 43-49.
［3］ Chen K M, Zhou Z X, Huo C L, et al. A Semisupervised Context-Sensitive Change Detection Technique Via Gaussian Process ［J］. IEEE Geoscience and Remote Sensing Letters, 2013, 10(2): 236-240.
［4］ Wang F, Wu Y, Zhang Q, et al. Unsupervised Change Detection on SAR Images Using Triplet Markov Field Model ［J］. IEEE Geoscience and Remote Sensing Letters, 2013, 10(4): 697-701.
［5］辛芳芳, 焦李成, 王凌霞, 等. 利用改进Fisher分类器进行遥感图像变化检测［J］. 西安电子科技大学学报, 2012, 39(5): 12-17.
Xin Fangfang, Jiao Licheng, Wang Lingxia, et al. Change Detection in Multitemporal Remote Sensing Images Based on Local Mean Dynamic Fisher Discriminant Analysis ［J］. Journal of Xidian University, 2012, 39(5): 12-17.
［6］ Meyer F G, Coifman R. Brushlet: a Tool for Directional Image Analysis and Image Compression ［J］. Applied and Computional Harmonic Analysis, 1997, 4(2): 147-187.
［7］ Li J M, Zhong H, Jiao L C. SAR Image Segmentation Based on Multiresolution GLCP in Overcomplete Brushlet Domain ［C］//Proceedings of IEEE International Conference on Radar. Piscataway: IEEE, 2006: 1-4.
［8］ Blu T, Luisier F. The SURE-LET Approach to Image Denoising ［J］. IEEE Transcations on Image Processing, 2007, 16(11): 2778-2786.
［9］ Zeng W, Zhou L, Jiang X B, et al. Clustering Based Image Denoising Using SURE-LET ［C］//2011 Seventh International Conference on Computational Intelligence and Security. Piscataway: IEEE, 2011: 1303-1307.
［10］ Luisier F, Blu T, Unser M. SURE-LET for Orthonormal Wavelet-Domain Video Denoising ［J］. IEEE Transcations on Circuits and Systems for Video Technology, 2010, 20(6): 913-919.
［11］ Clausi D A, Yue B. Comparing Cooccurrence Probabilities and Markov Random Fields for Texture Analysis of SAR Sea Ice Imagery ［J］. IEEE Transcations on Geoscience and Remote Sensing, 2004, 42(1): 215-228.
［12］ Xu X Y, Xu S Z, Jin L H, et al. Characteristic Analysis of Otsu Threshold and Its Applications ［J］. Pattern Recognition Letters, 2011, 32(7): 956-961.

[1]	王昕,常贵清,池琛琛. 广角SAR各向异性散射目标分离成像[J]. 西安电子科技大学学报, 2021, 48(2): 109-116.
[2]	杨瑞科, 周静. 各向异性大气湍流中涡旋Lommel光束传输特性[J]. 西安电子科技大学学报, 2018, 45(5): 1-6+31.
[3]	冯象初;李晓晖;王卫卫;贾西西. 方向扩散方程修正BM3D图像去噪改进算法[J]. 西安电子科技大学学报, 2017, 44(5): 102-108.
[4]	任宇辉;丁君;郭陈江;邢天璋;王夫蔚. 一种宽带高效反射型超材料极化旋转器[J]. 西安电子科技大学学报, 2017, 44(5): 171-176.
[5]	李林茜;魏兵;杨谦;葛德彪. 二维DGTD方法中UPML吸收边界的实现[J]. 西安电子科技大学学报, 2016, 43(6): 86-90.
[6]	马洪晋;聂玉峰. 一种图像特征增强的各向异性扩散去噪方法[J]. J4, 2015, 42(5): 154-160.
[7]	林涛;韩平丽;刘飞. 利用窄波段像素色比的红外弱小目标检测方法[J]. J4, 2014, 41(4): 58-63+157.
[8]	章为川;水鹏朗;徐国靖. 边缘线上各向异性高斯核信息熵的角点检测[J]. J4, 2013, 40(4): 119-124+129.
[9]	赵丽霞;张鹤鸣;戴显英;宣荣喜. 应变Si/(101)Si_xGe_1-x空穴迁移率[J]. J4, 2013, 40(3): 121-125.
[10]	杨秀红;郭宝龙;严春满. 结构测度约束下基于加权分形的图像修复算法[J]. J4, 2012, 39(6): 84-91.
[11]	王旭东;冯象初;白键. 基于结构张量场拟合的图像恢复方法[J]. J4, 2011, 38(6): 68-74.
[12]	李敏;冯象初. 基于总变分和各向异性扩散方程的图像恢复模型 [J]. J4, 2006, 33(5): 759-762.
[13]	江玲玲;殷海青;冯象初. 基于震动滤波和各向异性扩散的图像增强算法[J]. J4, 2006, 33(3): 476-478.
[14]	姜东焕;冯象初;宋国乡. 基于形态学算子的各向异性扩散方程[J]. J4, 2006, 33(1): 121-124.
[15]	暂时无作者信息. 二维金属凹槽填充各向异性介质时散射的边界元方法:TE情形[J]. J4, 2002, 29(6): 737-741.

利用Brushlet变换进行SAR图像变化检测

SAR image change detection based on Brushlet transform

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10