纹理特征向量与最大化熵法相结合的SAR影像非监督变化检测

庄会富; 邓喀中; 范洪冬

doi:10.11947/j.AGCS.2016.20150022

测绘学报 >

2016 , Vol. 45 >Issue 3: 339 - 346

DOI: https://doi.org/10.11947/j.AGCS.2016.20150022

摄影测量学与遥感

纹理特征向量与最大化熵法相结合的SAR影像非监督变化检测

庄会富 ,
邓喀中 ,
范洪冬

展开

中国矿业大学国土环境与灾害监测国家测绘地理信息局重点实验室, 江苏徐州 221116

庄会富(1990-),男,博士生,研究方向为遥感影像融合与解译。

收稿日期: 2015-01-12

修回日期: 2015-08-04

网络出版日期: 2016-03-25

基金资助

测绘地理信息公益性行业科研专项经费项目(201412016);国家自然科学基金(41272389);江苏省基础研究计划(自然科学基金)青年基金(BK20130174)

收起

SAR Images Unsupervised Change Detection Based on Combination of Texture Feature Vector with Maximum Entropy Principle

ZHUANG Huifu ,
DENG Kazhong ,
FAN Hongdong

Expand

China University of Mining and Technology, Key Laboratory for Land Environment and Disaster Monitoring of SBSM, Xuzhou 221116, China

Received date: 2015-01-12

Revised date: 2015-08-04

Online published: 2016-03-25

Supported by

Research and Special Funding of Mapping Geographic Information Public Service Sectors(No.201412016);The National Natural Science Foundation of China(No.41272389);Project Supported by the Basic Research Project of Jiangsu Province(Natural Science Foundation)(No.BK20130174)

Fold

摘要

合成孔径雷达(SAR)影像具有明显的斑点噪声,在变化检测中,一般需要考虑空间邻域信息。本文结合SAR影像丰富的纹理信息,提出一种考虑空间邻域信息的高分辨率SAR影像非监督变化检测方法,用基于灰度共生矩阵(GLCM)的32维纹理特征向量构造差异影像。通过最大化熵法自动选取阈值,对精度指标随窗口大小的变化进行回归分析,得到适合于变化检测的窗口为11×11。试验表明,本文方法优于马尔科夫随机场法,可以减小斑点噪声的影响,有效提高高分辨率SAR影像变化检测的精度。

关键词： 灰度共生矩阵; 纹理特征向量; 最大化熵法; SAR; 变化检测

本文引用格式

庄会富 , 邓喀中 , 范洪冬 . 纹理特征向量与最大化熵法相结合的SAR影像非监督变化检测[J]. 测绘学报, 2016 , 45(3) : 339 -346 . DOI: 10.11947/j.AGCS.2016.20150022

Abstract

Generally, spatial-contextual information would be used in change detection because there is significant speckle noise in synthetic aperture radar(SAR) images. In this paper, using the rich texture information of SAR images, an unsupervised change detection approach to high-resolution SAR images based on texture feature vector and maximum entropy principle is proposed. The difference image is generated by using the 32-dimensional texture feature vector of gray-level co-occurrence matrix(GLCM). And the automatic threshold is obtained by maximum entropy principle. In this method, the appropriate window size to change detection is 11×11 according to the regression analysis of window size and precision index. The experimental results show that the proposed approach is better could both reduce the influence of speckle noise and improve the detection accuracy of high-resolution SAR image effectively; and it is better than Markov random field.

Key words： GLCM; texture feature vector; maximum entropy principle; SAR; change detection

参考文献

[1] HACHICHA S, CHAABANE F. On the SAR Change Detection Review and Optimal Decision[J]. International Journal of Remote Sensing, 2014, 35(5):1693-1714.
[2] MARINO A, HAJNSEK I. A Change Detector Based on an Optimization with Polarimetric SAR Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(8):4781-4798.
[3] AGHABABAEE H, AMINI J, TZENG Y C. Improving Change Detection Methods of SAR Images Using Fractals[J]. Scientia Iranica, 2013, 20(1):15-22.
[4] AGHABABAEE H, AMINI J, TZENG Y C, et al. Unsupervised Change Detection on SAR Images Using a New Fractal-based Measure[J]. Photogrammetrie-Fernerkundung-Geoinformation, 2013(3):209-220.
[5] XIONG Boli, CHEN J M, KUANG Gangyao. A Change Detection Measure Based on a Likelihood Ratio and Statistical Properties of SAR Intensity Images[J]. Remote Sensing Letters, 2012, 3(3):267-275.
[6] 郝洪美, 张永红, 石海燕, 等. 统计假设检验方法在全极化SAR变化检测中的应用[J]. 遥感学报, 2012, 16(3):520-532. HAO Hongmei, ZHANG Yonghong, SHI Haiyan, et al. Application of Test Statistic Method in Fully Polarimetric SAR Change Detection[J]. Journal of Remote Sensing, 2012, 16(3):520-532.
[7] AGHABABAEE H, TZENG Y C, AMINI J. Swarm Intelligence and Fractals in Dual-pol Synthetic Aperture Radar Image Change Detection[J]. Journal of Applied Remote Sensing, 2012, 6(1):63596-63596.
[8] 黄世奇, 刘代志, 胡明星, 等. 基于小波变换的多时相SAR图像变化检测技术[J]. 测绘学报, 2010, 39(2):180-186. HUANG Shiqi,LIU Daizhi,HU Mingxing,et al.Multi-temporal SAR Image Change Detection Technique Based on Wavelet Transform[J]. Acta Geodaetica et Cartographica Sinica, 2010, 39(2):180-186.
[9] 高丛珊, 张红, 王超, 等. 广义Gamma模型及自适应KI阈值分割的SAR图像变化检测[J]. 遥感学报, 2010, 14(4):710-724. GAO Congshan, ZHANG Hong, WANG Chao, et al. SAR Change Detection Based on Generalized Gamma Distribution Divergence and Auto-threshold Segmentation[J]. Journal of Remote Sensing, 2010, 14(4):710-724.
[10] 胡召玲. 广义高斯模型及KI双阈值法的SAR图像非监督变化检测[J]. 测绘学报, 2013, 42(1):116-122. HU Zhaoling. An Unsupervised Change Detection Approach Based on KI Dual Thresholds under the Generalized Gauss Model Assumption in SAR Images[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42(1):116-122.
[11] 韩春明,郭华东,王长林.SAR图像斑点噪声抑制的本质[J]. 遥感学报, 2002, 6(6):470-474. HAN Chunming, GUO Huadong, WANG Changlin. The Essence of SAR Image Speckle Suppression[J]. Journal of Remote Sensing, 2002, 6(6):470-474.
[12] MOSER G,SERPICO S B.Unsupervised Change Detection from Multichannel SAR Data by Markovian Data Fusion[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(7):2114-2128.
[13] WANG Guangxue, HUANG Xiaotao, ZHOU Zhimin, et al. A New SAR Image Change Detection Algorithm Based on Texture Feature[C]//Proceedings of the 3rd International Asia-Pacific Conference on Synthetic Aperture Radar. Seoul, Korea:IEEE, 2011.
[14] GONG Maoguo,LI Yu,JIAO Licheng,et al.SAR Change Detection Based on Intensity and Texture Changes[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 93:123-135.
[15] 陈志鹏, 邓鹏, 种劲松, 等. 纹理特征在SAR图像变化检测中的应用[J]. 遥感技术与应用, 2002, 17(3):162-166. CHEN Zhipeng, DENG Peng, CHONG Jinsong, et al. Application of Textural Features to Change Detection in SAR Image[J]. Remote Sensing Technology and Application, 2002, 17(3):162-166.
[16] BAZI Y, BRUZZONE L, MELGANI F. An Unsupervised Approach Based on the Generalized Gaussian Model to Automatic Change Detection in Multitemporal SAR Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(4):874-887.
[17] WONG A K C, SAHOO P K. A Gray-level Threshold Selection Method Based on Maximum Entropy Principle[J]. IEEE Transactions on Systems, Man and Cybernetics, 1989, 19(4):866-871.
[18] KAPUR J N, SAHOO P K, WONG A K C. A New Method for Gray-level Picture Thresholding Using the Entropy of the Histogram[J]. Computer Vision, Graphics and Image Processing, 1985, 29(3):273-285.
[19] 刘丽, 匡纲要. 图像纹理特征提取方法综述[J]. 中国图象图形学报, 2009, 14(4):622-635. LIU Li, KUANG Gangyao. Overview of Image Textural Feature Extraction Methods[J]. Journal of Image and Graphics, 2009, 14(4):622-635.
[20] TUCERYAN M, JAIN A K. Texture Analysis[M]//CHEN C H, PAU L F, WANG P S P. The Handbook of Pattern Recognition and Computer Vision.[S.l.]:World Scientific Publishing Co., 1998:207-248.
[21] HARALICK R M, SHANMUGAM K, DINSTEIN I H. Textural Features for Image Classification[J]. IEEE Transactions on Systems, Man and Cybernetics, 1973, SMC-3(6):610-621.
[22] RÉNYI A. On Measures of Entropy and Information[C]//Proceedings of the Fourth Berkeley Symposium on Mathematical Statistics and Probability. Berkeley:University of California Press, 1961.
[23] KAPUR J N, KESAVAN H K. Entropy Optimization Principles with Applications[M]. Boston:Academic Press, 1992.
[24] 贾伟洁, 张继贤, 杨景辉, 等. 基于滤波的SAR影像去噪方法分析[J]. 微计算机信息, 2012, 28(6):24-26. JIA Weijie, ZHANG Jixian, YANG Jinghui, et al. The Analysis of Noise Reduction for SAR Image Based on Filters[J]. Microcomputer Information, 2012, 28(6):24-26.
[25] LOWE D G. Distinctive Image Features From Scale-invariant Keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献