极化SAR影像分类方法研究
|
摘要
为了充分发挥多极化、全极化SAR影像相对于单极化SAR影像具有更多信息量的优势,更好地进行极化SAR影像分类,本文针对利用现有极化分类算法得到的分类结果精度低、实用性差的不足,重点围绕提高精度和增强实用性这两方面的内容展开研究,提出了行之有效的改进算法及其处理流程,在此基础上研制了极化SAR分类软件模块,主要研究成果如下:
1.发展了自适应窗口的极化Lee滤波,去除相干斑噪声的同时较好地保留了边缘信息,有效地消除了相干斑噪声对后续的分类和分类后处理的影响;
2.鉴于使用单一特征无法获得令人满意的分类结果的问题,本文实现了利用GLCM和SVM的多尺度极化SAR影像分类方法,即提取光谱、纹理、极化特征的基础上应用SVM进行极化SAR影像分类;
3.针对目前基于像素的极化SAR影像分类精度不高、分类结果“椒盐”现象较严重的现状,本文构建了一种面向对象极化SAR影像监督分类算法;
4.对于地形起伏较大地区SAR影像阴影和水体较较难区分的难题,本文设计了一种实用化的基于DEM与面向对象技术的SAR影像阴影和水体区分方法;
5.采用Visual C++6.0实现了上述几种算法,研制了极化SAR分类代码,并将其嵌入到CASM ImageInfo?软件中形成了极化SAR分类模块。
Aim at the deficiency of the existing polarimetric SAR classification algorithm that the classification precision is low and the practicality is restricted and take advantage of multi- polarimetric or quad-polarimetric SAR data that has much more information, the paper is focused on raising classification precision and enhancing classification practicality, bringes up the feasible polarimetric SAR classification improvement algorithm and technology process, and then developes the polarimetric SAR classification module. The main research is as follows:
1. Lee filter is evolved based on adaptive window, it eliminates speckle noise and preserves edge at the same time, and avoids the influence of the speckle noise in future process.
2. Because of the unsatisfactory classification result using single characteristic, the multi-scale polarimetric SAR classification algorithm was realized by using GLCM and SVM, applies SVM to polarimetric SAR classification on the basis of extracting spectrum、texture、polarimetric characteristic.
3. Aim at the low precision and great mount of pepper and salt in polarimetric SAR classification result, a new object-oriented polarimetric SAR supervised classification algorithm is constructed.
4. Because it is difficult to make difference between shadow and water in mountain area, the algorithm of distinguishing water from shadow based on DEM data and object-oriented method is designed;
5. The above algorithms are realized based on the Visual C++6.0, the polarimetric SAR classification code is developed, and the polarimetric SAR classification module is embeded into the CASM ImageInfo? software.
1.发展了自适应窗口的极化Lee滤波,去除相干斑噪声的同时较好地保留了边缘信息,有效地消除了相干斑噪声对后续的分类和分类后处理的影响;
2.鉴于使用单一特征无法获得令人满意的分类结果的问题,本文实现了利用GLCM和SVM的多尺度极化SAR影像分类方法,即提取光谱、纹理、极化特征的基础上应用SVM进行极化SAR影像分类;
3.针对目前基于像素的极化SAR影像分类精度不高、分类结果“椒盐”现象较严重的现状,本文构建了一种面向对象极化SAR影像监督分类算法;
4.对于地形起伏较大地区SAR影像阴影和水体较较难区分的难题,本文设计了一种实用化的基于DEM与面向对象技术的SAR影像阴影和水体区分方法;
5.采用Visual C++6.0实现了上述几种算法,研制了极化SAR分类代码,并将其嵌入到CASM ImageInfo?软件中形成了极化SAR分类模块。
Aim at the deficiency of the existing polarimetric SAR classification algorithm that the classification precision is low and the practicality is restricted and take advantage of multi- polarimetric or quad-polarimetric SAR data that has much more information, the paper is focused on raising classification precision and enhancing classification practicality, bringes up the feasible polarimetric SAR classification improvement algorithm and technology process, and then developes the polarimetric SAR classification module. The main research is as follows:
1. Lee filter is evolved based on adaptive window, it eliminates speckle noise and preserves edge at the same time, and avoids the influence of the speckle noise in future process.
2. Because of the unsatisfactory classification result using single characteristic, the multi-scale polarimetric SAR classification algorithm was realized by using GLCM and SVM, applies SVM to polarimetric SAR classification on the basis of extracting spectrum、texture、polarimetric characteristic.
3. Aim at the low precision and great mount of pepper and salt in polarimetric SAR classification result, a new object-oriented polarimetric SAR supervised classification algorithm is constructed.
4. Because it is difficult to make difference between shadow and water in mountain area, the algorithm of distinguishing water from shadow based on DEM data and object-oriented method is designed;
5. The above algorithms are realized based on the Visual C++6.0, the polarimetric SAR classification code is developed, and the polarimetric SAR classification module is embeded into the CASM ImageInfo? software.
引文
[1] Sinclair G.The Transmission and Reception of Elliptical Polarized Wave.Proc.IRE, 1950.
[2] Kennaugh E.M.Polarization Properties of Radar Reflections[D].Columbus:The Ohio State University,1952.
[3] Graves C.D. Radar Polarization Power Scattering Matrix [J] .Proc.IRE,1956,44(5)248-252.
[4] Huynen J.R..Phenomenological Theory of Radar Targets[D],Ph.D.Dissertation.1970.
[5] Pottier E..On Dr.J.R.Huynen's main contributions in the development of polarimetric radar techniques and how the Radar Targets Phenomenological Concept'becomes a theory [J].Proceedings of SPIE,1992,1748:72-85.
[6] Van Zyl J..Unsupervised classification of scattering behavior using radar polarimetry data[J].IEEE Trans.Geosci.Remote Sensing,1989,27(1):36-45.
[7] Yoshio Yamaguchi,Toshifumi Moriyama,Motoi Ishido,and Hiroyoshi Yamada. Four Component Scattering Model for Polarimetric SAR Image Decomposition.IEEE Trans. on Geoscience and Remote Ssnsing,2005,43(8):1699-1706.
[8] Cloude S R,Pottier E.An entropy based classification scheme for land applications of polarimetric SAR.IEEE Trans.Geosci.Remote Sensing,1997,35:68–78.
[9] Cloude S R,Pottier E.A review of target decomposition theorems in radar polarimetry. IEEE Trans.Geosci.Remote Sensing,1996,34:498–518.
[10] Kong J.A.,Swartz A.A..Identification of Terrain Cover Using the Optimal Terrain Classifier,J., Electronmagn.Waves Applicat.,1988,2:171-194.
[11] Lee J.S.,Grunes M.R.,Kwok R..Classification of Multi-look Polarimetric SAR Imagery Based on Complex Wishart Distribution[J].Int.J.Remote Sensing, 1994, 15(11):2299-2311.
[12] Lee J.S.,Grunes M.R.,Ainsworth T.L.,et al.Unsupervised classification using polarimetric decomposition and the complex Wishart classifier[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(5):2249-2258.
[13] Pottier E.,Lee J.S..Unsupervised classification scheme of polsar images based on the complex wishart distribution and the H/A/a polarimetric decomposition theorem[C].Presented at EUSAR2000.Munich:2000.
[14]陈劲松,邵芸,李震.基于目标分解理论的全极化SAR图像神经网络分类方法[J].中国图象图形学报,2005,9(5):552-556.
[15]刘秀清,杨汝良.基于全极化SAR非监督分类的迭代分类方法.电子学报,2004,32(12) :1982-1986.
[16]吴永辉等.基于支持向量机的极化SAR图像分类.现代雷达,2007,29(6):57-60.
[17]吴永辉等.基于Wishart分布和MRF的多视全极化SAR图像分割.电子学报, 2007, 35(12):2302-2306.
[18]李晓玮,种劲松基于目标相干散射特性的极化SAR图像分解分类方法.遥感技术与应用,2007,22(3):443-448.
[19]刘保利.有效的SAR图像多尺度分类算法.计算机工程与设计.2008,29(6): 1364 - 1366.
[20]王超等.全极化合成孔径雷达图像处理[M].科学出版社:北京,2008.
[21]焦李成等.智能SAR图像处理与解译[M].科学出版社:北京,2008.
[22]舒宁.微波遥感原理[M].武汉大学出版社:武汉,2003.
[23] http://earth.esa.int/polsarpro.
[24] http://www.ccrs.nrcan.gc.ca/index_e.php.
[25]付毓生等.极化雷达增强理论[M].电子工业出版社:北京,2008.
[26]何钰等.基于偏微分方程的去噪方法[J].测绘科学技术学报.2007,24(4):284-286.
[27] Perona P, Malik J.Scale-Space andEdgeDetectionUsingAnisotropic Diffusion[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1990, 12(7): 629-639.
[28] Lee J S.Digital image enhancement and noise filtering by use of local statistics.IEEE Trans. On Pattern Analysis and Machine Intelligence, March, 1980, PAMI–2(2): 165-168.
[29] Lee J S,Grunes M R and Mango S A.Speckle reduction in multipolarization and multifrequency SAR imagery.IEEE Trans.Geosci.Remote sensing,1991,29:535-544.
[30] Lee J S,Mitchell R Grunes and Gianfranco de Grandi.Polarimetric SAR specklefiltering and its implication for classification.IEEE Trans.Geosci.Remote sensing, 1999,37:2363-2373.
[31] J.-M.Park,W.J.Song and W.A.Pearlman.Speckle filtering of SAR images based on adaptive windowing. IEE Proc.-Vis. Image Signal Proccss, Vol. 146, No. 4, August 1999 pp.191-197.
[32] LEE. J.S.‘Speckle analysis and smoothing of synthetic aperture radarimages’, Computer Graph. Image Process.,1981, 17, pp. 24-32.
[33] PORCELLO, L.J., MASSEY, N.G., INNES, R.B., and MARKS, J.M.:‘Speckle reduction in synthetic-aperture radars’, J Opt. Soc. Am., 1976,66,11,pp. 1305-1311.
[34] C.F.Yanasse, A.C.Frery,et al.On the use of multi-look amplitude K-distribution for SAR image analysis. International Geoscience and Remote Sensing Symposium, pp.8~12,1994.
[35] L.M.Novak, and M.C.Burl. Optimal speckle reduction in polarimetric SAR imagery. IEEE Trans.Aerosp.Electron.Syst., Vol.26,No.2,pp.293-305,1990.
[36] L.M.Novak, and M.C.Burl, and W.W.Iving.Optimal polarimetric processing for enhanced target detection .IEEE trans. Aerosp.Electron.Syst., Vol.29, No.1, pp.234~243,1993.
[37]梅安新等.遥感导论[M].高等教育出版社:北京,2008.
[38] H.Derin and H.Ellion,Modeling and segmentation of noisy and textured images using Gibbs random fields,Transon Pattern Anal Machine Intell,1983,9(l):33-553.
[39] P.A.Kelly,H.Derin,and K.D.Hart.Adaptive segmentation of speckled images using a hierarchical random field model, IEEE trans on Acoust, Speech, Signal Processing.1987, 36(10):1624-1641.
[40] S.Lakshmanan and H.Derin, Simultaneous parameter estimate and segmentation of Gibbs random fields using simulated annealing, IEEE Trans on Pattern Anal Machine Intell. 1988.8:799-813.
[41] S. R. Cloude and E. Pottier,“A review of target decomposition theorems in radar polarimetry,”IEEE Trans. Geosci. Remote Sensing, vol. 34, pp. 498–518, Mar. 1996.
[42] Haralick R M, Shanmugam K, Dinstein I. Textural features for imageclassification[J]. IEEE Transactions on Systems, Man and Cybernetics, 1973, 3(6): 610-621.
[43] HARALICK R, SHANMUGAM M K. Textural Features for Image[J]. IEEE, 1983, 3(6): 610-621.
[44]王耀南等.计算机图像处理与识别技术[M].高等教育出版社,2001.06.
[45]邓乃扬等.数据挖掘中的新方法-支持向量机[M].科学出版社,2004,06.
[46] Nello Cristianini. An Introduction to Support Vector Machines and Other Kernel- based Learning Methods[M].Cambridge University Press,2000,06.
[47]李国正等.支持向量机导论[M].电子工业出版社,2004,03.
[48]何德平等.支持向量机在遥感影像处理中的应用[J].城市勘测,2006,03.
[49]明冬萍,骆剑承,周成虎等.高分辨率遥感影像信息提取及块状基元特征提取研究[J].数据采集与处理,2005,20 (1):34-39.
[50] BAATZ M, SCHAPE A. Object -Oriented and Multi - Scale Image Analysis in Semantic Networks[R].Proc. of the 2nd International Symposium on Operationalization of Remote Sensing. Enschede: ITC ,1999.
[51]曹宝等.面向对象方法在SPOT5遥感图像分类中的应用—以北京市海淀区为例[J].地理与地理信息科学, 2006.3.
[52]求是科技.Visual C++数字图像处理典型算法及实现[M].北京:人民邮电出版社,2006.
[53]彭祥龙,张扬等.马尔可夫随机场在SAR图像处理中的应用[J],2002,08,05.
[54] S.Z.Li, Markov Random Field Modeling in Computer Vision, Springer, Tokyo, 1995.
[55] B.C.K.Tso and P. M. Mather,“Classification of multi-resource remote sensing imagery using a genetic algorithm and markov random fields,”IEEE Trans. on Geoscience and Remote Sensing, vol.37,no.3, pp.1255–1260,May 1999.
[56] F. Yang and T. Jiang,“Pixel-based image segmentation with markov random fields,”IEEE Trans. on Image Processing, vol.12, no.12, pp.1552–1559,Dec.2003.
[57]Y.Dong,Member,IEEE,A.K.Milne,Member,IEEE,andB.C.Forster,Member,IEEE.Segmentation and Classification of Vegetated Areas Using Polarimetric SAR Image Data. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, VOL. 39, NO.2, pp.321-328,FEBRUARY. 2001.
[58] S.R.Cloude and E. Pottier,“A review of target decomposition theorems in radar polarimetry,”IEEE Trans. Geosci. Remote Sensing, vol. 34, pp. 498–518, Mar. 1996.
[59]吴永辉等.基于Wishart分布和MRF的多视全极化SAR影像分割.电子学报,2007.12.
[60]李晓玮等.基于目标相干散射特性的极化SAR图像分解分类方法[J].遥感技术与应用, 2007,6.
[61]刘秀清等.基于全极化SAR非监督分类的迭代分类方法.电子学报,2004,12.
[62]舒宁.雷达遥感原理[M].北京:测绘出版社, 2000.
[63]郭华东.雷达对地观测理论与应用[M].北京:科学出版社, 2000.12.
[64]朱俊杰等.基于纹理与成像知识的高分辨率SAR图像水体检测.
[65]杨存建等.基于DEM的SAR图像洪水水体的提取[J].自然灾害学报, 2002,11(3).
[66] http://www.gdal.org.
[2] Kennaugh E.M.Polarization Properties of Radar Reflections[D].Columbus:The Ohio State University,1952.
[3] Graves C.D. Radar Polarization Power Scattering Matrix [J] .Proc.IRE,1956,44(5)248-252.
[4] Huynen J.R..Phenomenological Theory of Radar Targets[D],Ph.D.Dissertation.1970.
[5] Pottier E..On Dr.J.R.Huynen's main contributions in the development of polarimetric radar techniques and how the Radar Targets Phenomenological Concept'becomes a theory [J].Proceedings of SPIE,1992,1748:72-85.
[6] Van Zyl J..Unsupervised classification of scattering behavior using radar polarimetry data[J].IEEE Trans.Geosci.Remote Sensing,1989,27(1):36-45.
[7] Yoshio Yamaguchi,Toshifumi Moriyama,Motoi Ishido,and Hiroyoshi Yamada. Four Component Scattering Model for Polarimetric SAR Image Decomposition.IEEE Trans. on Geoscience and Remote Ssnsing,2005,43(8):1699-1706.
[8] Cloude S R,Pottier E.An entropy based classification scheme for land applications of polarimetric SAR.IEEE Trans.Geosci.Remote Sensing,1997,35:68–78.
[9] Cloude S R,Pottier E.A review of target decomposition theorems in radar polarimetry. IEEE Trans.Geosci.Remote Sensing,1996,34:498–518.
[10] Kong J.A.,Swartz A.A..Identification of Terrain Cover Using the Optimal Terrain Classifier,J., Electronmagn.Waves Applicat.,1988,2:171-194.
[11] Lee J.S.,Grunes M.R.,Kwok R..Classification of Multi-look Polarimetric SAR Imagery Based on Complex Wishart Distribution[J].Int.J.Remote Sensing, 1994, 15(11):2299-2311.
[12] Lee J.S.,Grunes M.R.,Ainsworth T.L.,et al.Unsupervised classification using polarimetric decomposition and the complex Wishart classifier[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(5):2249-2258.
[13] Pottier E.,Lee J.S..Unsupervised classification scheme of polsar images based on the complex wishart distribution and the H/A/a polarimetric decomposition theorem[C].Presented at EUSAR2000.Munich:2000.
[14]陈劲松,邵芸,李震.基于目标分解理论的全极化SAR图像神经网络分类方法[J].中国图象图形学报,2005,9(5):552-556.
[15]刘秀清,杨汝良.基于全极化SAR非监督分类的迭代分类方法.电子学报,2004,32(12) :1982-1986.
[16]吴永辉等.基于支持向量机的极化SAR图像分类.现代雷达,2007,29(6):57-60.
[17]吴永辉等.基于Wishart分布和MRF的多视全极化SAR图像分割.电子学报, 2007, 35(12):2302-2306.
[18]李晓玮,种劲松基于目标相干散射特性的极化SAR图像分解分类方法.遥感技术与应用,2007,22(3):443-448.
[19]刘保利.有效的SAR图像多尺度分类算法.计算机工程与设计.2008,29(6): 1364 - 1366.
[20]王超等.全极化合成孔径雷达图像处理[M].科学出版社:北京,2008.
[21]焦李成等.智能SAR图像处理与解译[M].科学出版社:北京,2008.
[22]舒宁.微波遥感原理[M].武汉大学出版社:武汉,2003.
[23] http://earth.esa.int/polsarpro.
[24] http://www.ccrs.nrcan.gc.ca/index_e.php.
[25]付毓生等.极化雷达增强理论[M].电子工业出版社:北京,2008.
[26]何钰等.基于偏微分方程的去噪方法[J].测绘科学技术学报.2007,24(4):284-286.
[27] Perona P, Malik J.Scale-Space andEdgeDetectionUsingAnisotropic Diffusion[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1990, 12(7): 629-639.
[28] Lee J S.Digital image enhancement and noise filtering by use of local statistics.IEEE Trans. On Pattern Analysis and Machine Intelligence, March, 1980, PAMI–2(2): 165-168.
[29] Lee J S,Grunes M R and Mango S A.Speckle reduction in multipolarization and multifrequency SAR imagery.IEEE Trans.Geosci.Remote sensing,1991,29:535-544.
[30] Lee J S,Mitchell R Grunes and Gianfranco de Grandi.Polarimetric SAR specklefiltering and its implication for classification.IEEE Trans.Geosci.Remote sensing, 1999,37:2363-2373.
[31] J.-M.Park,W.J.Song and W.A.Pearlman.Speckle filtering of SAR images based on adaptive windowing. IEE Proc.-Vis. Image Signal Proccss, Vol. 146, No. 4, August 1999 pp.191-197.
[32] LEE. J.S.‘Speckle analysis and smoothing of synthetic aperture radarimages’, Computer Graph. Image Process.,1981, 17, pp. 24-32.
[33] PORCELLO, L.J., MASSEY, N.G., INNES, R.B., and MARKS, J.M.:‘Speckle reduction in synthetic-aperture radars’, J Opt. Soc. Am., 1976,66,11,pp. 1305-1311.
[34] C.F.Yanasse, A.C.Frery,et al.On the use of multi-look amplitude K-distribution for SAR image analysis. International Geoscience and Remote Sensing Symposium, pp.8~12,1994.
[35] L.M.Novak, and M.C.Burl. Optimal speckle reduction in polarimetric SAR imagery. IEEE Trans.Aerosp.Electron.Syst., Vol.26,No.2,pp.293-305,1990.
[36] L.M.Novak, and M.C.Burl, and W.W.Iving.Optimal polarimetric processing for enhanced target detection .IEEE trans. Aerosp.Electron.Syst., Vol.29, No.1, pp.234~243,1993.
[37]梅安新等.遥感导论[M].高等教育出版社:北京,2008.
[38] H.Derin and H.Ellion,Modeling and segmentation of noisy and textured images using Gibbs random fields,Transon Pattern Anal Machine Intell,1983,9(l):33-553.
[39] P.A.Kelly,H.Derin,and K.D.Hart.Adaptive segmentation of speckled images using a hierarchical random field model, IEEE trans on Acoust, Speech, Signal Processing.1987, 36(10):1624-1641.
[40] S.Lakshmanan and H.Derin, Simultaneous parameter estimate and segmentation of Gibbs random fields using simulated annealing, IEEE Trans on Pattern Anal Machine Intell. 1988.8:799-813.
[41] S. R. Cloude and E. Pottier,“A review of target decomposition theorems in radar polarimetry,”IEEE Trans. Geosci. Remote Sensing, vol. 34, pp. 498–518, Mar. 1996.
[42] Haralick R M, Shanmugam K, Dinstein I. Textural features for imageclassification[J]. IEEE Transactions on Systems, Man and Cybernetics, 1973, 3(6): 610-621.
[43] HARALICK R, SHANMUGAM M K. Textural Features for Image[J]. IEEE, 1983, 3(6): 610-621.
[44]王耀南等.计算机图像处理与识别技术[M].高等教育出版社,2001.06.
[45]邓乃扬等.数据挖掘中的新方法-支持向量机[M].科学出版社,2004,06.
[46] Nello Cristianini. An Introduction to Support Vector Machines and Other Kernel- based Learning Methods[M].Cambridge University Press,2000,06.
[47]李国正等.支持向量机导论[M].电子工业出版社,2004,03.
[48]何德平等.支持向量机在遥感影像处理中的应用[J].城市勘测,2006,03.
[49]明冬萍,骆剑承,周成虎等.高分辨率遥感影像信息提取及块状基元特征提取研究[J].数据采集与处理,2005,20 (1):34-39.
[50] BAATZ M, SCHAPE A. Object -Oriented and Multi - Scale Image Analysis in Semantic Networks[R].Proc. of the 2nd International Symposium on Operationalization of Remote Sensing. Enschede: ITC ,1999.
[51]曹宝等.面向对象方法在SPOT5遥感图像分类中的应用—以北京市海淀区为例[J].地理与地理信息科学, 2006.3.
[52]求是科技.Visual C++数字图像处理典型算法及实现[M].北京:人民邮电出版社,2006.
[53]彭祥龙,张扬等.马尔可夫随机场在SAR图像处理中的应用[J],2002,08,05.
[54] S.Z.Li, Markov Random Field Modeling in Computer Vision, Springer, Tokyo, 1995.
[55] B.C.K.Tso and P. M. Mather,“Classification of multi-resource remote sensing imagery using a genetic algorithm and markov random fields,”IEEE Trans. on Geoscience and Remote Sensing, vol.37,no.3, pp.1255–1260,May 1999.
[56] F. Yang and T. Jiang,“Pixel-based image segmentation with markov random fields,”IEEE Trans. on Image Processing, vol.12, no.12, pp.1552–1559,Dec.2003.
[57]Y.Dong,Member,IEEE,A.K.Milne,Member,IEEE,andB.C.Forster,Member,IEEE.Segmentation and Classification of Vegetated Areas Using Polarimetric SAR Image Data. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, VOL. 39, NO.2, pp.321-328,FEBRUARY. 2001.
[58] S.R.Cloude and E. Pottier,“A review of target decomposition theorems in radar polarimetry,”IEEE Trans. Geosci. Remote Sensing, vol. 34, pp. 498–518, Mar. 1996.
[59]吴永辉等.基于Wishart分布和MRF的多视全极化SAR影像分割.电子学报,2007.12.
[60]李晓玮等.基于目标相干散射特性的极化SAR图像分解分类方法[J].遥感技术与应用, 2007,6.
[61]刘秀清等.基于全极化SAR非监督分类的迭代分类方法.电子学报,2004,12.
[62]舒宁.雷达遥感原理[M].北京:测绘出版社, 2000.
[63]郭华东.雷达对地观测理论与应用[M].北京:科学出版社, 2000.12.
[64]朱俊杰等.基于纹理与成像知识的高分辨率SAR图像水体检测.
[65]杨存建等.基于DEM的SAR图像洪水水体的提取[J].自然灾害学报, 2002,11(3).
[66] http://www.gdal.org.