Please wait a minute...
img

官方微信

遥感技术与应用  2014, Vol. 29 Issue (3): 482-488    DOI: 10.11873/j.issn.1004-0323.2014.3.0482
图像与数据处理     
基于非下采样Shearlet和几何结构的遥感图像无监督变化检测
李青松1,覃锡忠1,贾振红1,杨杰2,胡英杰3
(1.新疆大学信息科学与工程学院,新疆 乌鲁木齐830046;
2.上海交通大学图像处理和模式识别研究所,上海200240;
3.新西兰奥克兰理工大学知识工程与开发研究所,新西兰 奥克兰1020)
Unsupervised Change Detection of Remote Sensing Images based on Nonsubsampled Shearlet and Geometrical Structure
Li Qingsong1,Qin Xizhong1,Jia Zhenhong1,Yang Jie2,Raphael Hu3
(1.College of Information Science and Engineering,Xinjiang University,Urumqi 830046,China;
2.Institute of Image Processing and Pattern Recognition,Shanghai Jiao Tong University,Shanghai 200240,China;
3.Knowledge Engineering and Discovery Research Institute,Auckland University of Technology,Auckland 1020,New Zealand)
 全文: PDF(4923 KB)  
摘要:

提出了基于非下采样Shearlet和几何结构的遥感图像无监督变化检测新算法。首先将两幅SAR图像相减取绝对值得到差异图像,然后利用基于非下采样Shearlet自适应贝叶斯阈值去噪算法对差异图像进行去噪处理来减少噪声的影响。最后根据差异图像的局部几何特征和邻域信息构造跨特征矢量,再利用模糊C-means聚类算法对跨特征矢量聚类,聚类的结果为变化类和未变化类即最终的变化检测结果。实验证明:该算法对噪声的抗噪性能平稳而且有效,可以得到较好的检测结果。

关键词: 非下采样Shearlet几何结构模糊C-means聚类遥感图像变化检测    
Abstract:

A novel unsupervised change detection algorithm of remote sensing images based on Nonsubsampled shearlet and Geometrical structure is proposed.Firstly,the difference image is composed of the absolute value of the difference of two remote sensing images.Then denoising algorithm based on Nonsubsampled shearlet adaptive Bayesian threshold is used to deal with the difference image to reduce the influence of noise.Finally,local geometric features and neighborhood information of the difference image are used to construct the cross\|feature vector,and then the cross\|feature vector is clustered by Fuzzy C\|means clustering algorithm.The results of clustering is change class and no change class,which are the final change detection results.Experiments show that Anti\|noise performance of the proposed algorithm is steady and effective and the proposed algorithm can get a better change detection results.

Key words: Nonsubsampled shearlet    Geometrical structure    Fuzzy C-means clustering    Remote sensing images    Change detection
收稿日期: 2013-03-26 出版日期: 2014-06-23
:  TP 751.1  
基金资助:

教育部促进与美大地区科研合作与高层次人才培养项目(20101595)。

通讯作者: 覃锡忠(1964-),男,重庆长寿人,副教授,主要从事移动通信与图像处理研究。Email:qmqqxz@163.com。    
作者简介: 李青松(1986-),男,河南夏邑人,硕士研究生,主要从事图像处理研究。Email:lantiang12@163.com。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
李青松
覃锡忠
贾振红
杨杰
胡英杰

引用本文:

李青松,覃锡忠,贾振红,杨杰,胡英杰. 基于非下采样Shearlet和几何结构的遥感图像无监督变化检测[J]. 遥感技术与应用, 2014, 29(3): 482-488.

Li Qingsong,Qin Xizhong,Jia Zhenhong,Yang Jie,Raphael Hu. Unsupervised Change Detection of Remote Sensing Images based on Nonsubsampled Shearlet and Geometrical Structure. Remote Sensing Technology and Application, 2014, 29(3): 482-488.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2014.3.0482        http://www.rsta.ac.cn/CN/Y2014/V29/I3/482

[1]Radke R J,Andra S,Al-Kofahi O,et al.Image Chang Detection Algorithms:A Systematic Survey[J].IEEE Transactions on Image Process,2005,14(3):294-307.[2]Mishra N S,Ghosh S,Ghosh A.Fuzzy Clustering Algorithms Incorporating Local Information for Change Detection in Remotely Sensed Images[J].Applied Soft Computing,2012,12:2683-2692.

[3]Wang Q L.The Discrete Shearlet Transform:A New Directional Transform and Compactly Supported Shearlet Frames[J].IEEE Transform on Image Processing,2009,19(5):1166-1180.

[4]Glenn E,Demetrio L,Wang Q L.Sparse Directional Image Representation Using the Discrete Shearlet Transform[J].IEEE Signals,System and Computer,2006,10(1):974-978.

[5]Zhang Xiaohua,Chen Jiawei,Meng Hongyun,et al.SAR Image Despeckling based on Non-local Means with Non-subsample Shearlet and Directional Windows[J].Journal of Infrared and Millimeter Waves,2012,31(2):159-165.[张小华,陈佳伟,孟红云,等.基于非下采样Shearlet和方向权值邻域窗的非局部均值SAR图像相干斑抑制[J].红外与毫米波学报,2012,31(2):159-165.]

[6]Hou B,Zhang X H,Bu X M,et al.SAR Image Despeckling based on Nonsubsampled Shearlet Transform[J].IEEE Journal of Selected in Topics in Applied Earth Observations and Remote Sensing,2012,5(3):809-823.

[7]Moser G,Serpico S B.Automatic Parameter Optimization for Support Vector Regression for Land Sea Surfance Temperature Satellite Data[J].International Journal of Remote Sensing,2008,29(16):4823-4838.

[8]Celik T,Kai-Kuang M.Unsupervised Chang Detection for Satellite Images Using Dual-tree Complex Wavelet Transform[J].IEEE Transactions on Geoscience and Remote Sensing,2010,48(3):1199-2010.

[9]Deng J S,Wang K,Deng Y H,et al.PCA-based Land Use Change Detection and Anaylysis Using Multitemporal and Multisensor Satellite Data[J].International Journal of Remote Sensing,2008,29(16):4823-4838.

[10]Zhang X H,Wang L,Jiao L C.An Unsupervised Change Detection based on Clustering Combined with Multiscale and Region Growing[C]//2011 International Workshop on Multi-platform/Muti-sensor Remote Sensing and Mapping,2011:1-4.

[11]Bruzzone L,Prieto D F.An Adaptive Parcel-based Technique for Unsupervised Change Detection[J].International Journal of Remote Sensing,2000,21(4):817-822.

[12]Ghosh S,Mishra N S,Ghosh A.Unsupervised Change Detection of Remotely Sensed Images Using Fuzzy Clustering[C]//International Conference on Advances in Pattern Recognition,2009:385-388.

[13]Mishra N S,Ghosh S,Ghosh A.Fuzzy Clustering Algorithms Incorporating Local  Information for Change Detection in Remotely Sensed Images[J].Applied Soft Computing,2012,12:2683-2692.

[14]elik T.Bayesian Change Detection based on Spatial Sampling and Gaussian Mixture Model[J].Pattern Recognition Letters,2011,32(12):1635-1642.

[15]Koenderink J J,Doorn A J.Representation of Local Geometry in the Visal System[J].Biological Cybemetics,1987,55(6):367-375.

[16]Koenderink J J,Doorn A J.Local Structure of Gaussian Texture[J].IEEE Transactions on Information and Systems,2003,86(7):1165-1171.

[17]Florack L M J.The Syntactical Structure of Scalar Images[D].Holland:University of Utrecht,1993.

[18]Chang Bao,Zhang Gong.An Unsupervised Approach based on Geometrical Structures to Automatic Change Detection in Multitemporal SAR Images[J].Acta Electronica Sinica,2011,39(9):2125-2128.[常宝,张弓.基于几何结构的SAR图像无监督变化检测方法[J].电子学报,2011,39(9):2125-2128.]

[19]Chui M W,Feng Y Q,Wang W,et al.Image Denoising Method with Adaptive Bayes Threshold in Nonsubsampled Contourlet Domain[C]//AASRI Conference on Computational Intelligence and Bioinformatics,2012,(1):512-518.

[20]Celik T.Multiscale Change Detection in  Multitemporal Satellite Images[J].IEEE Geoscience and Remote Sensing Letters,2009,6(4):820-840.

[21]Wu C,Wu Y Q.Multitemporal Images Change Detection Using Nonsubsampled Contourlet Transform and Kernel Fuzzy C-Mean Clustering[C]//International Symposium on Intelligence Information Processing and Trusted Computing,2011:96-99.

[22]Xin Fangfang.Change Detection in Remote Sensing Imagery based on Fisher Classifier and Computational Intelligence[D].Xian:Xidian University,2011.[辛芳芳.基于Fisher分类器和计算智能的遥感图像变化检测[D].西安:西安电子科技大学,2011.]

[1] 秦振涛,杨茹,张靖,杨武年. 基于聚类结构自适应稀疏表示的高光谱遥感图像修复研究[J]. 遥感技术与应用, 2018, 33(2): 212-215.
[2] 姜爱辉,刘国林,陈富龙. 基于PALSAR-1影像的汉函谷关遗迹变化检测研究[J]. 遥感技术与应用, 2017, 32(5): 787-793.
[3] 张祥,陈报章,赵慧,汪磊. 基于时序Sentinel-1A数据的农田土壤水分变化检测分析[J]. 遥感技术与应用, 2017, 32(2): 338-345.
[4] 王俊,秦其明,叶昕,王建华,秦雪彬,杨绣丞. 高分辨率光学遥感图像建筑物提取研究进展[J]. 遥感技术与应用, 2016, 31(4): 653-662.
[5] 张从梅,孙权森,王超,封磊,顾一禾. 基于非局部自相似性的遥感图像稀疏去噪算法[J]. 遥感技术与应用, 2016, 31(4): 739-747.
[6] 张明哲,张红,王超,刘萌,谢镭. 基于超像素分割和多方法融合的SAR 图像变化检测方法[J]. 遥感技术与应用, 2016, 31(3): 481-487.
[7] 赵永光,李传荣,马灵玲,唐伶俐,王宁. 一种遥感图像太阳—观测几何归一化方法[J]. 遥感技术与应用, 2016, 31(2): 260-266.
[8] 肖新耀,许宁,尤红建. 一种基于à trous小波和联合稀疏表示的遥感图像融合方法[J]. 遥感技术与应用, 2015, 30(5): 1021-1026.
[9] 董淑英,晋锐,亢健,李大治. ASAR GM后散时间序列数据估算黑河上游地表土壤水分[J]. 遥感技术与应用, 2015, 30(4): 667-676.
[10] 苏腾飞,李洪玉. 一种两阶段区域生长的遥感图像分割算法[J]. 遥感技术与应用, 2015, 30(3): 476-485.
[11] 侯鹏洋,季艳,高峰,胡蕾. 一种基于SIFT特征的快速逐层遥感图像配准方法[J]. 遥感技术与应用, 2014, 29(5): 873-877.
[12] 吴田军,胡晓东,夏列钢,骆剑承,沈占锋,吴炜. 基于对象级分类的土地覆盖动态变化及趋势分析[J]. 遥感技术与应用, 2014, 29(4): 600-606.
[13] 万智萍. 结合方向小波的多光谱与全色遥感图像融合算法[J]. 遥感技术与应用, 2014, 29(4): 660-668.
[14] 许夙晖,慕晓冬,柯冰,王晓日. 基于遥感影像的军事阵地动态监测技术研究[J]. 遥感技术与应用, 2014, 29(3): 511-516.
[15] 夏朝旭,何政伟,于欢,王东辉,叶娇珑. 面向对象的土地覆被变化检测研究[J]. 遥感技术与应用, 2014, 29(1): 106-113.