极化SAR图像分类技术研究
|
摘要
极化SAR是一种先进的遥感信息获取手段。与单极化SAR相比,它通过测量每个分辨单元在不同收发极化组合下的散射特性,更完整地记录了目标后向散射信息,为详尽分析目标散射特性提供了良好的数据支持。极化SAR图像分类是图像解译的重要步骤,分类图既可作为中间结果为边缘提取、目标检测、识别等提供辅助信息,也可作为最终结果直接输出给用户。开展极化SAR图像分类研究对于探索目标散射特性、提高极化SAR系统的应用水平具有重要的理论意义和实用价值。
论文以揭示目标散射机理和提高分类精度为主要目的,系统地研究了极化SAR图像分类方法。
揭示目标散射机理是极化SAR数据分析的重要目的之一,现有这方面研究一般只针对全极化数据。双极化是极化SAR常用的工作模式,为研究双极化SAR对目标散射机理的识别性能,论文对H-α方法进行了修正。推导了双极化H-α平面有效区域的边界,从理论角度研究了双极化SAR对各向同性表面、偶极子和各向同性二面角三种基本散射的识别能力,通过实验分析了双极化SAR对H-α平面有效区域内八种基本散射机理的识别性能,并给出了HH-VV双极化H-α平面的一种可行划分方式。
现有极化SAR图像分类算法大多以像素为基本分类单元。为提高分类精度,论文从改进已有算法和引入发展于其它领域的算法两个角度,对基于像素的分类方法进行了研究。H-α方法是最为著名的极化SAR图像非监督分类方法之一,但其分类图存在地物类别模糊问题。针对该问题,通过结合C-均值算法,提出H-α-CM算法,从而将H-α方法的散射机理分类转化为地物分类。为自动确定迭代次数,定义了分类图像熵,以熵最大作为H-α-CM算法的迭代终止准则,并通过实验分析了该准则的合理性。SVM是一种较新的分类和回归算法,论文研究了它在极化SAR图像分类中的应用。为避免依据经验选择特征导致分类性能不稳定,提出以支持向量个数作为评估指标的NSVFS特征选择算法,并将其用作SVM分类的预处理,从而构成完整的利用SVM进行特征选择和分类的NSSVM算法。实验结果表明该算法对SVM参数的敏感性较低,具有较强的自适应性。最后,以SVM为分类器,定性、定量地比较了全极化、双极化和单极化SAR的分类性能,并从目标散射特性和分类器工作原理的角度阐明了三者性能差异的成因。
基于像素的方法能保持分类图的地物细节,但其性能易受相干斑影响。基于区域的方法在分类过程中考虑像素空间相关性,可有效减弱相干斑的不良影响。MRF是一种常用的描述像素空间相关性的模型,在将MRF引入极化SAR图像分类的过程中,为充分利用数据的统计先验知识和避免拆分协方差矩阵导致信息损失,将MRF与协方差矩阵的Wishart分布结合,提出WMICM算法。随后,针对watershed算法过分割时存在锯齿效应的问题,采用MRF进行过分割,提出MOS-ML算法。WMICM和MOS-ML在分类的不同阶段考虑像素的空间相关性,前者由初始分类和ICM调整两个步骤构成,在第二步中引入相邻像素相关性:后者包括仞始过分割和ML分类,在构造过分割得到的大量子区域的过程中利用像素相关性。由于利用了极化数据的统计先验知识和相邻像素的空间相关性,因此两种算法均具有较高的分类精度,并能获得清晰平滑的分类图。
Polarimetric synthetic aperture radar (SAR) is an advanced instrument for remote sensing. It obtains scattering characteristics of each resolution cell under different combinations of receiving and transmitting polarization, and records back scattering information of targets more completely than single-polarization SAR. It is helpful for analyzing target scattering characteristics. Classification of polarimetric SAR images is an important procedure of image interpretation. The classification map can be used as the middle result for edge extraction, target detection and recognition, etc., and also as the final result output directly to users. Investigation of classification of polarimetric SAR images is of much theoretical and applicable significance in the exploitation of target scattering characteristics, as well as the improvement of the application efficiency of polarimetric SAR systems.
To reveal target scattering mechanisms and improving classification accuracy, classification methods of polarimetric SAR images are investigated in this thesis.
It is very important to reveal target scattering mechanisms in analysis of polarimetric SAR data, nevertheless it is done generally for fully polarimetric data. Dual polarization is a frequently used operational mode of polarimetric SAR systems. In order to investigate performance of scattering mechanism identification of dual-polarization SARs, H-αdecomposition is modified. The boundary of the feasible region in H-αplane for dual-polarization cases is derived. Performance of dual-polarization SARs to distinguish three basic scattering mechanisms from an isotropic surface, a dipole, and an isotropic dihedral is studied theoretically. Performance of dual-polarization SARs to identify the eight scattering mechanisms inside the feasible region in H-αplane is analyzed, and a feasible division of H-αplane for HH-VV dual-polarization SAR is obtained in an experimental manner.
Individual pixels are taken as elements in most classification methods for polarimetric SAR images so far. In order to improve classification accuracy, pixel-based classification methods are investigated by improving an existing method and introducing an algorithm developed in other fields. H-αdecomposition is one of the most famous unsupervised methods for classifying polarimetric SAR images. However, terrain classes are confused in the classification map of H-αdecomposition. Therefore the H-α-CM is proposed by integrating the C-mean algorithm, thus classification of scattering mechanisms is transformed into terrain classification. In this algorithm, to determine the number of iteration automatically, the entropy of a classification map is defined, and maximizing the entropy is taken as the termination criterion, which is demonstrated to be reasonable by experimental results. SVM is a new algorithm for classification and regression. It is used in classification of polarimetric SAR images herein. To avoid instability of classification performance induced by selecting features using experience, the NSVFS is proposed for feature selection, in which the number of support vectors is taken as the estimation index. Then it is used as a preprocess step in SVM classification, thus the NSSVM is constructed to select features and classify images using SVM. It is demonstrated by experiments that this algorithm is not very sensitive to SVM parameters, and has better self-adaptability. Finally, classification performance of full polarization versus dual and single polarization is compared qualitatively and quantitatively using SVM. Causes resulting in performance difference are illuminated by target scattering characteristics and operational mechanism of the classifier.
Terrain details can be preserved in classification maps obtained by pixel-based methods. But performance of these methods is affected by the speckle. It is different for region-based methods. The spatial relation of neighboring pixels is considered in these methods, thus speckle effect is reduced effectively. MRF is a frequently used model for describing the spatial correlation between adjacent pixels. While introducing MRF into classification of polarimetric SAR images, in order to use completely the statistical a priori knowledge of the data and avoid information loss induced by separating the covariance matrix, the WMICM is proposed by integrating MRF and Wishart distribution of the covariance matrix. Then, aiming at the sawtooth effect of the watershed algorithm in over-segmentation, the MOS-ML is proposed using MRF for over-segmentation. The spatial relation of neighboring pixels is considered in different phase of the two algorithms. It is introduced in the second step of the WMICM, which contains initial classification and ICM adjustment, while introduced in the first step of the MOS-ML, containing initial over-segmentation and ML classification. Clear and smooth classification maps and high accuracy are observed using the two algorithms, due to full consideration of the statistical characteristic of polarimetric data and the spatial relation between adjacent pixels.
论文以揭示目标散射机理和提高分类精度为主要目的,系统地研究了极化SAR图像分类方法。
揭示目标散射机理是极化SAR数据分析的重要目的之一,现有这方面研究一般只针对全极化数据。双极化是极化SAR常用的工作模式,为研究双极化SAR对目标散射机理的识别性能,论文对H-α方法进行了修正。推导了双极化H-α平面有效区域的边界,从理论角度研究了双极化SAR对各向同性表面、偶极子和各向同性二面角三种基本散射的识别能力,通过实验分析了双极化SAR对H-α平面有效区域内八种基本散射机理的识别性能,并给出了HH-VV双极化H-α平面的一种可行划分方式。
现有极化SAR图像分类算法大多以像素为基本分类单元。为提高分类精度,论文从改进已有算法和引入发展于其它领域的算法两个角度,对基于像素的分类方法进行了研究。H-α方法是最为著名的极化SAR图像非监督分类方法之一,但其分类图存在地物类别模糊问题。针对该问题,通过结合C-均值算法,提出H-α-CM算法,从而将H-α方法的散射机理分类转化为地物分类。为自动确定迭代次数,定义了分类图像熵,以熵最大作为H-α-CM算法的迭代终止准则,并通过实验分析了该准则的合理性。SVM是一种较新的分类和回归算法,论文研究了它在极化SAR图像分类中的应用。为避免依据经验选择特征导致分类性能不稳定,提出以支持向量个数作为评估指标的NSVFS特征选择算法,并将其用作SVM分类的预处理,从而构成完整的利用SVM进行特征选择和分类的NSSVM算法。实验结果表明该算法对SVM参数的敏感性较低,具有较强的自适应性。最后,以SVM为分类器,定性、定量地比较了全极化、双极化和单极化SAR的分类性能,并从目标散射特性和分类器工作原理的角度阐明了三者性能差异的成因。
基于像素的方法能保持分类图的地物细节,但其性能易受相干斑影响。基于区域的方法在分类过程中考虑像素空间相关性,可有效减弱相干斑的不良影响。MRF是一种常用的描述像素空间相关性的模型,在将MRF引入极化SAR图像分类的过程中,为充分利用数据的统计先验知识和避免拆分协方差矩阵导致信息损失,将MRF与协方差矩阵的Wishart分布结合,提出WMICM算法。随后,针对watershed算法过分割时存在锯齿效应的问题,采用MRF进行过分割,提出MOS-ML算法。WMICM和MOS-ML在分类的不同阶段考虑像素的空间相关性,前者由初始分类和ICM调整两个步骤构成,在第二步中引入相邻像素相关性:后者包括仞始过分割和ML分类,在构造过分割得到的大量子区域的过程中利用像素相关性。由于利用了极化数据的统计先验知识和相邻像素的空间相关性,因此两种算法均具有较高的分类精度,并能获得清晰平滑的分类图。
Polarimetric synthetic aperture radar (SAR) is an advanced instrument for remote sensing. It obtains scattering characteristics of each resolution cell under different combinations of receiving and transmitting polarization, and records back scattering information of targets more completely than single-polarization SAR. It is helpful for analyzing target scattering characteristics. Classification of polarimetric SAR images is an important procedure of image interpretation. The classification map can be used as the middle result for edge extraction, target detection and recognition, etc., and also as the final result output directly to users. Investigation of classification of polarimetric SAR images is of much theoretical and applicable significance in the exploitation of target scattering characteristics, as well as the improvement of the application efficiency of polarimetric SAR systems.
To reveal target scattering mechanisms and improving classification accuracy, classification methods of polarimetric SAR images are investigated in this thesis.
It is very important to reveal target scattering mechanisms in analysis of polarimetric SAR data, nevertheless it is done generally for fully polarimetric data. Dual polarization is a frequently used operational mode of polarimetric SAR systems. In order to investigate performance of scattering mechanism identification of dual-polarization SARs, H-αdecomposition is modified. The boundary of the feasible region in H-αplane for dual-polarization cases is derived. Performance of dual-polarization SARs to distinguish three basic scattering mechanisms from an isotropic surface, a dipole, and an isotropic dihedral is studied theoretically. Performance of dual-polarization SARs to identify the eight scattering mechanisms inside the feasible region in H-αplane is analyzed, and a feasible division of H-αplane for HH-VV dual-polarization SAR is obtained in an experimental manner.
Individual pixels are taken as elements in most classification methods for polarimetric SAR images so far. In order to improve classification accuracy, pixel-based classification methods are investigated by improving an existing method and introducing an algorithm developed in other fields. H-αdecomposition is one of the most famous unsupervised methods for classifying polarimetric SAR images. However, terrain classes are confused in the classification map of H-αdecomposition. Therefore the H-α-CM is proposed by integrating the C-mean algorithm, thus classification of scattering mechanisms is transformed into terrain classification. In this algorithm, to determine the number of iteration automatically, the entropy of a classification map is defined, and maximizing the entropy is taken as the termination criterion, which is demonstrated to be reasonable by experimental results. SVM is a new algorithm for classification and regression. It is used in classification of polarimetric SAR images herein. To avoid instability of classification performance induced by selecting features using experience, the NSVFS is proposed for feature selection, in which the number of support vectors is taken as the estimation index. Then it is used as a preprocess step in SVM classification, thus the NSSVM is constructed to select features and classify images using SVM. It is demonstrated by experiments that this algorithm is not very sensitive to SVM parameters, and has better self-adaptability. Finally, classification performance of full polarization versus dual and single polarization is compared qualitatively and quantitatively using SVM. Causes resulting in performance difference are illuminated by target scattering characteristics and operational mechanism of the classifier.
Terrain details can be preserved in classification maps obtained by pixel-based methods. But performance of these methods is affected by the speckle. It is different for region-based methods. The spatial relation of neighboring pixels is considered in these methods, thus speckle effect is reduced effectively. MRF is a frequently used model for describing the spatial correlation between adjacent pixels. While introducing MRF into classification of polarimetric SAR images, in order to use completely the statistical a priori knowledge of the data and avoid information loss induced by separating the covariance matrix, the WMICM is proposed by integrating MRF and Wishart distribution of the covariance matrix. Then, aiming at the sawtooth effect of the watershed algorithm in over-segmentation, the MOS-ML is proposed using MRF for over-segmentation. The spatial relation of neighboring pixels is considered in different phase of the two algorithms. It is introduced in the second step of the WMICM, which contains initial classification and ICM adjustment, while introduced in the first step of the MOS-ML, containing initial over-segmentation and ML classification. Clear and smooth classification maps and high accuracy are observed using the two algorithms, due to full consideration of the statistical characteristic of polarimetric data and the spatial relation between adjacent pixels.
引文
[1]张澄波.综合孔径雷达原理、系统分析与应用.北京:科学出版社,1989.
[2]张直中.微波成像术.北京:科学出版社,1990.
[3]杨士中.合成孔径雷达.北京:国防工业出版社,1981.
[4]庄钊文,削顺平,王雪松.雷达极化信息处理及其应用.北京:国防工业出版社,1999.
[5]Hubbert J C.A comparison of radar,optic,and specular null polarization theories.IEEE Trans.on Geoscience and Remote Sensing,1994,32(3):658-671.
[6]Zebker H A and van Zyl J J.Imaging radar polarimetry:a review.Proc.IEEE,1991,79(11):1583-1606.
[7]Sinclair G.The transmission and reception of elliptically polarized waves.Proc.IRE,1950,38(2):148-151.
[8]Kennaugh E M.Polarization properties of radar reflections.Master's thesis.Columbus,Ohio,USA:The Ohio State University,March 1952.
[9]Huynen J R.Measurement of the target scattering matrix.Proc.IEEE,1965,53(8):936-946.
[10]Huynen J R.Phenomenological theory of radar targets.Ph.D.dissertation.Delft,The Netherlands:Tech.Univ.Delft,1970.
[11]Touzi R,Boerner W M,Lee J S.et al.A review of polarimetry in the context of synthetic aperture radar:concepts and information extraction.Canadian Journal of Remote Sensing,2004,30(3):380-407.
[12]Poelman A J and Guy J R F.Polarization information utilization in primary radar:an introduction and up-date to activities at SHAPE technical centre.Mathematical and Physical Sciences,1985,143:521-572.
[13]van Zyl J J and Zebker H A.Imaging radar polarization signatures:theory and observation.Radio Science,1987,22:529-543.
[14]Zebker H A,van Zyl J J,and Held D N.Imaging radar polarimetry from wave synthesis.Journal of Geophysical Research,1987,92:683-701.
[15]Chu A,Kim Y J,van Zyl J J,et al.The NASA/JPL AIRSAR integrated processor.Proc.International Geoscience and Remote Sensing Symposium,Washington,USA,July 1998:1908-1910.
[16]van Zyl J J,Carande R,Lou Y L,et al.The NASA/JPL three-frequency polarimetric AIRSAR system.Proc.International Geoscience and Remote Sensing Symposium,Texas,USA,May 1992:649-651.
[17]Kozma A,Nichols A D,Rawson R F.et al.Multifrequency polarimetric SAR for remote sensing.Proc.International Geoscience and Remote Sensing Symposium,Zurich,Switzerland,September 1986:715-720.
[18]Sullivan R,Nichols A,Rawson R,et al.Polarimetric X/L/C-band SAR.Proc.IEEE International Radar Conference,Michigan,USA,April 1988:9-14.
[19]Horn R.The DLR airborne SAR project E-SAR.Proc.International Geoscience and Remote Sensing Symposium,Nebraska,USA,May 1996:1624-1628.
[20]Horn R,Werner M,and Mayr B.Extension of the DLR airborne synthetic aperture radar,E-SAR,to X-band.Proc.International Geoscience and Remote Sensing Symposium,Maryland,USA,May 1990:2047-2049.
[21] Scheiber R, Reigber A, Ulbricht A, et al. Overview of interferometric data acquisition and processing modes of the experimental airborne SAR system of DLR. Proc. International Geoscience and Remote Sensing Symposium, Hamburg, Germany, June 1999: 35-37.
[22] Livingstone C E, Gray A L, Hawkins R K, et al. The CCRS airborne SAR systems: radar for remote sensing research. Canadian Journal of Remote Sensing, 1995, 21 (4): 468-491.
[23] Livingstone C E, Lukowski T I, Rey M T, et al. CCRS/DREO synthetic aperture radar polarimetry - status report. Proc. International Geoscience and Remote Sensing Symposium, Maryland, USA, May 1990: 1671-1674.
[24] Hoffmann K and Fischer P. DOSAR: a multifrequency polarimetric and interferometric airborne SAR-system. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 1708-1710.
[25] Skou N, Granholm J, Woelders K, et al. A high resolution polarimetric L-band SAR - design and first results. Proc. International Geoscience and Remote Sensing Symposium, Florence, Italy, July 1995: 1779-1782.
[26] Christensen E L, Skou N, Dall J, et al. EMISAR: an absolutely calibrated polarimetric L- and C-band SAR. IEEE Trans, on Geoscience and Remote Sensing, 1998, 36 (6): 1852-1865.
[27] Christensen E L and Dall J. EMISAR: a dual-frequency, polarimetric airborne SAR. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 1711-1713.
[28] Sheen D R, Strawitch C M, and Lewis T B. UHF wideband SAR design and preliminary results. Proc. International Geoscience and Remote Sensing Symposium, California, USA, August 1994: 289-291.
[29] Sheen D R, Shackman S J, VandenBerg N L, et al. The P-3 ultra-wideband SAR: description and examples. Proc. IEEE International Radar Conference, Michigan, USA, May 1996: 50-53.
[30] Sheen D R, VandenBerg N L, Shackman S J, et al. P-3 ultra-wideband SAR: description and examples. IEEE Aerospace and Electronic Systems Magazine, 1996: 25-30.
[31] Greidanus H, Hoogeboom P, and Koomen P. First results and status of the PHARUS phased array airborne SAR. Proc. International Geoscience and Remote Sensing Symposium, Nebraska, USA, May 1996: 1633-1635.
[32] Hoogeboom P, Snoeij P, Koomen P J, et al. The PHARUS project, results of the definition study including the SAR testbed PHARS. IEEE Trans. on Geoscience and Remote Sensing, 1992, 30 (4): 723-735.
[33] Uratsuka S, Satake M, Kobayashi T, et al. High-resolution dual-bands interferometric and polarimetric airborne SAR (Pi-SAR) and its applications. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 1720-1722.
[34] Uratsuka S, Moriyama T, Umehara T, et al. Disastrous environment after earthquake observed by airborne SAR (Pi-SAR). Proc. International Geoscience and Remote Sensing Symposium, Seoul, Korea, July 2005: 4081-4083.
[35] Wang H P, Ouchi K, Watanabe M, et al. In search of the statistical properties of high-resolution polarimetric SAR data for the measurements of forest biomass beyond the RCS saturation limits. IEEE Geoscience and Remote Sensing Letters, 2006, 3 (4): 495-499.
[36] Dubois-Fernandez P, Cantalloube H, and Dupuis X. Clutter statistical analysis for high resolution SAR data. Proc. International Geoscience and Remote Sensing Symposium, Alaska, USA, September 2004: 1781-1783.
[37] Dubois-Fernandez P, du Plessis O R, le Coz D, et al. The ONERA RAMSES SAR system. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 1723-1725.
[38] Dreuillet P, Paillou P, Cantalloube H, et al. P band data collection and investigations utilizing the RAMSES SAR facility. Proc. International Geoscience and Remote Sensing Symposium, Toulouse, France, July 2003: 4262-4264.
[39] Schimpf H, Essen H, Boehmsdorff S, et al. MEMPHIS - a fully polarimetric experimental radar. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 1714-1716.
[40] Essen H, Fuchs H H, and Pagels A. Remote sensing of the sea surface by millimeterwave SAR. Proc. SPIE Conference on Remote Sensing of the Ocean, Sea Ice, and Large Water Regions, vol. 6360, September 2006: 63600N-63601-63608.
[41] Jordan R L, Huneycutt B L, and Werner M. The SIR-C/X-SAR synthetic aperture radar system. Proc. IEEE, 1991, 79 (6): 827-838.
[42] Jordan R L, Huneycutt B L, and Werner M. The SIR-C/X-SAR synthetic aperture radar system. IEEE Trans. on Geoscience and Remote Sensing, 1995, 33 (4): 829-839.
[43] Hawkins R K, Touzi R, Wolfe J, et al. ASAR AP mode performance and applications potential. Proc. International Geoscience and Remote Sensing Symposium, Toulouse, France, July 2003: 1115-1117.
[44] Kimura H and Ito N. ALOS PALSAR: The Japanese second-generation spaceborne SAR and its applications. Proc. SPIE Conference on Microwave Remote Sensing of the Atmosphere and Environment II, vol. 4152, December 2000: 110-119.
[45] http://alos.jaxa.jp/index-e.html.
[46] http://www.jaxa.jp/about/index e.html.
[47] http://www. jaxa.jp/projects/rockets/h2a/index_e.html.
[48] Schulz-Stellenfleth J, Lehner S, and Horstmann J. Use of TerraSAR-X for oceanography. Proc. International Geoscience and Remote Sensing Symposium, Seoul, Korea, July 2005: 4886-4889.
[49] Stangl M, Werninghaus R, Schweizer B, et al. TerraSAR-X technologies and first results. IEE Proc. Radar Sonar Navigation, 2006, 153 (2): 86-95.
[50] http://www.RADARSAT2.info.
[51] 刘永坦. 雷达成像技术. 哈尔滨: 哈尔滨工业大学出版社, 1999.
[52] Cloude S R and Pottier E. An entropy based classification scheme for land applications of polarimetric SAR. IEEE Trans. on Geoscience and Remote Sensing, 1997, 35 (1): 68-78.
[53] Baronti S, Macelloni G, Paloscia S, et al. Analysis of an automatic method for surface classification using multifrequency multipolarization SAR data. Proc. International Geoscience and Remote Sensing Symposium, Florence, Italy, July 1995: 973-975.
[54] Ferrazzoli P, Paloscia S, Pampaloni P, et al. The potential of multifrequency polarimetric SAR in assessing agricultural and arboreous biomass. IEEE Trans. on Geoscience and Remote Sensing, 1997, 35 (1): 5-17.
[55] Ferrazzoli P, Guerriero L, and Schiavon G. Experimental and model investigation on radar classification capability. IEEE Trans. on Geoscience and Remote Sensing, 1999, 37 (2): 960-968.
[56] Fujita M and Tamura D. Land use classification of SIR-C imagery based on a published database of multi-polarization backscattering. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 1956-1958.
[57] Du L J and Grunes M R. Unsupervised segmentation of multi-polarization SAR images based on amplitude and texture characteristics. Proc. International Geoscience and Remote Sensing Symposium, Honolulu, Hawaii, USA, July 2000: 1122-1124.
[58] Chen K S, Huang W P, Tsay D H, et al. Classification of multifrequency polarimetric SAR imagery using a dynamic learning neural network. IEEE Trans. on Geoscience and Remote Sensing, 1996, 34 (3): 814-820.
[59] Tzeng Y C and Chen K S. A fuzzy neural network to SAR image classification. IEEE Trans. on Geoscience and Remote Sensing, 1998, 36 (1): 301-307.
[60] Frate F D, Schiavon G, Solimini D, et al. Crop classification using multiconfiguration C-band SAR data. IEEE Trans. on Geoscience and Remote Sensing, 2003, 41 (7): 1611-1619.
[61] Benz U C. Supervised fuzzy analysis of single- and multichannel SAR data. IEEE Trans. on Geoscience and Remote Sensing, 1999, 37 (2): 1023-1037.
[62] Fukuda S and Hirosawa H. Support vector machine classification of land cover: application to polarimetric SAR data. Proc. International Geoscience and Remote Sensing Symposium, Sydney, Australia, July 2001: 187-189.
[63] Fukuda S, Katagiri R, and Hirosawa H. Unsupervised approach for polarimetric SAR image classification using support vector machines. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 2599-2601.
[64] Pellizzeri T M and Lombardo P. Model-based processing of multifrequency polarimetric SAR images of urban areas. Proc. GRSS/ISPRS Joint Workshop on Data Fusion and Remote Sensing over Urban Areas, May 2003: 47-51.
[65] Lombardo P. Optimal classification of polarimetric SAR images using segmentation. Proc. IEEE International Radar Conference, Long Beach, California, April 2002: 8-13.
[66] Treitz P M, Filho O R, Howarth P J, et al. Textural processing of multi-polarization SAR for agricultural crop classification. Proc. International Geoscience and Remote Sensing Symposium, Lincoln, Nebraska, USA, May 1996: 1986-1988.
[67] Lee J S. Feature classification using multi-look polarimetric SAR imagery. Proc. International Geoscience and Remote Sensing Symposium, Houston, Texas, USA, May 1992: 77-79.
[68] Skriver H, Svendsen M T, Nielsen F, et al. Crop classification by polarimetric SAR. Proc. International Geoscience and Remote Sensing Symposium, Hamburg, Germany, June 1999: 2333-2335.
[69] Scheuchl B and Cumming I G. Potential of RADARSAT-2 for sea ice classification. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 2185-2187.
[70]Lee J S,Grunes M R,Ainsworth T L,et al.Quantitative comparison of classification capability:fully-polarimetric versus partially polarimetric SAR.Proc.International Geoscience and Remote Sensing Symposium,Honolulu,Hawaii,USA,July 2000:1101-1103.
[71]Lee J S,Grunes M R,and Pottier E.Quantitative comparison of classification capability:fully polarimetric versus dual and single-polarization SAR.IEEE Trans.on Geoscience and Remote Sensing,2001,39(11):2343-2351.
[72]Liu G Q,Huang S J,Torre A,et al.Bayesian classification of multi-look polarimetric SAR images with a generalized multiplicative speckle model.Proc.SPIE Conference on Algorithms for Synthetic Aperture Radar Imagery Ⅳ,vol.3070,July 1997:398-405.
[73]刘国庆,熊红,黄顺吉等.多视极化合成孔径雷达图象的分类和极化通道优化.电子科学学刊,1998,20(1):56-61.
[74]Tran T N,Wehrens R,and Hoekman D H.Initialization of Markov Random Field clustering of large polarimetric SAR images.Proc.International Geoscience and Remote Sensing Symposium,Anchorage,Alaska,USA,September 2004:714-717.
[75]Tran T N,Wehrens R,Hoekman D H,et al.Initialization of Markov random field clustering of large remote sensing images.IEEE Trans.on Geoscience and Remote Sensing,2005,43(8):1912-1919.
[76]Frery A C,Correia A H,and Freitas C C.Multifrequency full polarimetric SAR classification with multiple sources of statistical evidence.Proc.International Geoscience and Remote Sensing Symposium,Denver,Colorado,USA,July 2006:4195-4197.
[77]Freitas C C,Frery A C,and Correia A H.The polarimetric G distribution for SAR data analysis.Environmetrics,2005,16(1):13-31.
[78]Hara Y,Atkins R G,Yueh S H,et al.Application of neural networks to radar image classification.IEEE Trans.on Geoscience and Remote Sensing,1994,32(1):100-109.
[79]Hara Y,Atkins R G,Shin R T,et al.Application of neural networks for sea ice classification in polarimetric SAR images.IEEE Trans.on Geoscience and Remote Sensing,1995,33(3):740-748.
[80]Chen C T,Chen K S,and Lee J S.The use of fully polarimetric information for the fuzzy neural classification of SAR images.IEEE Trans.on Geoscience and Remote Sensing,2003,41(9):2089-2100.
[81]Du L,Lee J S,and Mango S A.Fuzzy classification of Earth terrain covers using multi-look polarimetric SAR image data.Proc.International Geoscience and Remote Sensing Symposium,Tokyo,Japan,August 1993:1602-1604.
[82]Kersten P R,Lee J S,Ainsworth T L,et al.Classification of polarimetric synthetic aperture radar images using fuzzy clustering.Proc.International Geoscience and Remote Sensing Symposium,Toulouse,France,October 2003:150-156.
[83]Wong Y F and Posner E C.A new clustering algorithm applicable to multispectral and polarimetric SAR images.IEEE Trans.on Geoscience and Remote Sensing,1993,31(3):634-644.
[84]Dong Y,Milne A K,and Forster B C.Segmentation and classification of vegetated areas using polarimetric SAR image data.IEEE Trans.on Geoscience and Remote Sensing,2001,39(2):321-329.
[85] Rignot E and Chellappa R. Segmentation of polarimetric synthetic aperture radar data. IEEE Trans. on Image Processing, 1992, 1 (3): 281-300.
[86] Chandrasekhar S. Radiative transfer. New York: Dover, 1960.
[87] van Zyl J J. Application of Cloude's target decomposition theorem to polarimetric imaging radar data. Proc. SPIE Conference on Radar Polarimetry, vol. 1748, San Diego, California, USA, July 1992: 184-191.
[88] Cloude S R and Pottier E. A review of target decomposition theorems in radar polarimetry. IEEE Trans. on Geoscience and Remote Sensing, 1996, 34 (2): 498-518.
[89] 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. Proc. SPIE Conference on Radar Polarimetry, vol. 1748, San Diego, California, USA, July 1992: 72-85.
[90] van Zyl J J. Unsupervised classification of scattering behavior using radar polarimetry data. IEEE Trans. on Geoscience and Remote Sensing, 1989, 27 (1): 36-45.
[91] Qong M, Tadono T, Wakabayashi H, et al. Mueller matrix based classification of polarimetric SAR data. Proc. International Geoscience and Remote Sensing Symposium, Honolulu, Hawaii, USA, July 2000: 375-377.
[92] Dong Y, Forster B, and Ticehurst C. Polarimetric image classification using optimal decomposition of radar polarization signatures. Proc. International Geoscience and Remote Sensing Symposium, Lincoln, Nebraska, USA, May 1996: 1556-1558.
[93] Dong Y, Forster B, and Ticehurst C. A new decomposition of radar polarization signatures. IEEE Trans. on Geoscience and Remote Sensing, 1998, 36 (3): 933-939.
[94] Krogager E, Dall J, and Madsen S N. The sphere, diplane, helix decomposition recent results with polarimetric SAR data. Proc. Third International Workshop on Radar Polarimetry, March 1995: 621-625.
[95] Krogager E, Boerner W M, and Madsen S N. Feature-motivated Sinclair matrix (sphere/diplane/helix) decomposition and its application to target sorting for land feature classification. Proc. SPIE Conference on Wideband Interferometric Sensing and Imaging Polarimetry, vol. 3120, December 1997: 144-154.
[96] Moriyama T, Nakamura M, and Yamaguchi Y. Radar polarimetry applied to the classification of underground targets. Proc. SPIE Conference on Wideband Interferometric Sensing and Imaging Polarimetry, vol. 3120, December 1997: 182-189.
[97] Cameron W L and Leung L K. Feature motivated polarization scattering matrix decomposition. Proc. IEEE International Radar Conference, May 1990: 549-557.
[98] Cameron W L, Youssef N N, and Leung L K. Simulated polarimetric signatures of primitive geometrical shapes. IEEE Trans. on Geoscience and Remote Sensing, 1996, 34 (3): 793-803.
[99] Touzi R and Charbonneau F. Characterization of symmetric scattering using polarimetric SARs. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 414-416.
[100] Touzi R and Charbonneau F. Characterization of target symmetric scattering using polarimetric SARs. IEEE Trans. on Geoscience and Remote Sensing, 2002, 40 (11): 2507-2516.
[101] Freeman A and Durden S. A three-component scattering model to describe polarimetric SAR data. Proc. SPIE Conference on Radar Polarimetry, vol. 1748, San Diego, California, USA, July 1992: 213-224.
[102] Freeman A and Durden S L. A three-component scattering model for polarimetric SAR data. IEEE Trans. on Geoscience and Remote Sensing, 1998, 36 (3): 963-973.
[103] Freeman A. Fitting a two-component scattering model to polarimetric SAR data. Proc. International Geoscience and Remote Sensing Symposium, Houston, Texas, USA, June 1999: 2649-2651.
[104] Yamaguchi Y, Moriyama T, Ishido M, et al. Four-component scattering model for polarimetric SAR image decomposition. IEEE Trans. on Geoscience and Remote Sensing, 2005, 43 (8): 1699-1706.
[105] Holm W A and Barnes R M. On radar polarization mixed target state decomposition techniques. Proc. IEEE National Radar Conference, April 1988: 249-254.
[106] Yamaguchi Y, Yajima Y, and Yamada H. A four-component decomposition of POLSAR images based on the coherency matrix. IEEE Geoscience and Remote Sensing Letters, 2006, 3 (3): 292-296.
[107] Cloude S R. Radar target decomposition theorems. IEE Electronics Letters, 1985, 21 (1): 22-24.
[108] Cloude S R. An entropy based classification scheme for polarimetric SAR data. Proc. International Geoscience and Remote Sensing Symposium, Florence, Italy, July 1995: 2000-2002.
[109] Hellmann M. A new approach for interpretation of SAR-data using polarimetric techniques. Proc. International Geoscience and Remote Sensing Symposium, Seattle, Washington, USA, July 1998: 2195-2197.
[110] Belhadj Z, Benazza A, and Hidoussi N. Classification of radar images in polarimetric remote sensing. Proc. International Conference on Image Processing, Seattle, Washington, USA, July 1998: 574-577.
[111] Verdi J S, Lee R, Kersten PR,et al. Comparative analysis of polarimetric SAR image exploitation algorithms for environmental stress-change monitoring. Proc. International Geoscience and Remote Sensing Symposium, Hamburg, Germany, June 1999:2449-2451.
[112] Lopez-Sanchez J M, Fortuny-Guasch J, and Sieber A J. Experimental validation of an entropy-based classification scheme using a wide-band polarimetric radar. Proc. International Geoscience and Remote Sensing Symposium, Seattle, Washington, USA, July 1998: 2381-2383.
[113] Ferro-Famil L, Pottier E, Saillard J, et al. The potential of full polarimetric SAR data to classify dry snowcover. Proc. International Geoscience and Remote Sensing Symposium, Hamburg, Germany, June 1999: 1792-1794.
[114] Park S E and Moon W M. Classification of the polarimetric SAR using fuzzy boundaries in entropy and alpha plane. Proc. International Geoscience and Remote Sensing Symposium, Seoul, Korea, July 2005: 5517-5519.
[115] Du L J and Lee J S. Polarimetric SAR image classification based on target decomposition theorem and complex Wishart distribution. Proc. International Geoscience and Remote Sensing Symposium, Lincoln, Nebraska, USA, May 1996:439-441.
[116] Lombardo P, Pellizzeri T M, and Tomasuolo A. A joint classification technique based on multivariate annealing segmentation and "H/A/α" decomposition for fully polarimetric SAR images of suburban areas.Proc.International Geoscience and Remote Sensing Symposium,Sydney,Australia,July 2001:2922-2924.
[117]陈体刚,李彦佐.全极化SAR图像中相干矩阵特征值及其应用.信息与电子工程,2005,3(3):161-166.
[118]Pottier E and Cloude S R.Application of the H/A/alpha polarimetric decomposition theorem for land classification.Proc.SPIE Conference on Wideband Interferometric Sensing and Imaging Polarimetry,vol.3120,December 1997:132-143.
[119]Hellmann M,Jager G,Kratzschmar E,et al.Classification of full polarimetric SAR-data using artificial neural networks and fuzzy algorithms.Proc.International Geoscience and Remote Sensing Symposium,Hamburg,Germany,June 1999:1995-1997.
[120]Hellmann M,Jager G,and Pottier E.Fuzzy clustering and interpretation of fully polarimetric SAR data.Proc.International Geoscience and Remote Sensing Symposium,Sydney,Australia,July 2001:2790-2792.
[121]Praks J,Arslan A N,Alasalmi H,et al.SAR target decomposition for stochastic natural targets for L- and C-band.Proc.International Geoscience and Remote Sensing Symposium,Hamburg,Germany,June 1999:1558-1560.
[122]Praks J and Hallikainen M.A novel approach in polarimetric covariance matrix eigendecomposition.Proc.International Geoscience and Remote Sensing Symposium,Honolulu,Hawaii,USA,July 2000:1119-1121.
[123]Hoekman D H and Vissers M A M.A new polarimetric classification approach evaluated for agricultural crops.IEEE Trans.on Geoscience and Remote Sensing,2003,41(12):2881-2889.
[124]Fukuda S and Hirosawa H.A wavelet-based texture feature set applied to classification of multifrequency polarimetric SAR images.IEEE Trans.on Geoscience and Remote Sensing,1999,37(5):2282-2286.
[125]Bourissou A,Pham K,Au W C,et al.Classification of a polarimetric SAR image using fractal concepts.Proc.International Geoscience and Remote Sensing Symposium,Tokyo,Japan,August 1993:1599-1601.
[126]陈劲松,邵芸,林晖.全极化SAR数据在地表覆盖/利用监测中的应用.国土资源遥感,2004,(60):39-42.
[127]王晓兰,戴博伟,杨汝良.全极化合成孔径雷达多视图像的极化特征分析.电子与信息学报,2002,24(4):507-513.
[128]余海坤,张永红,王云甲.利用极化SAR数据进行土地覆盖分类研究.海洋测绘,2006,26(3):34-38.
[129]Kouskoulas Y,Ulaby F T,and Pierce L E.The Bayesian hierarchical classifier (BHC) and its application to short vegetation using multifrequency polarimetric SAR.IEEE Trans.on Geoscience and Remote Sensing,2004,42(2):469-477.
[130]Loiselet M and Grandin J F.Polarization study for better classification.Proc.SPIE Conference on Radar Processing,Technology,and Applications Ⅳ,vol.3810,September 1999:180-190.
[131]Moriyama T,Uratsuka S,Umehara T,et al.A study on extraction of urban areas from polarimetric synthetic aperture radar image.Proc.International Geoscience and Remote Sensing Symposium,Anchorage,Alaska,USA,September 2004:703-706.
[132]Touzi R,Goze S,Toan T L,et al.Polarimetric discriminators for SAR images.IEEE Trans.on Geoscience and Remote Sensing,1992,30(5):973-980.
[133]Skriver H and Dierking W.Knowledge-based sea ice classification by polarimetric SAR.Proc.International Geoscience and Remote Sensing Symposium,September 2004:204-207.
[134]Pierce L E,Ulaby F T,Sarabandi K,et al.Knowledge-based classification of polarimetric SAR images.IEEE Trans.on Geoscience and Remote Sensing,1994,32(5):1081-1086.
[135]Rodriguez K M,Weissel J K,and Kim Y.Classification of landslide surfaces using fully polarimetric SAR:examples from Taiwan.Proc.International Geoscience and Remote Sensing Symposium,Toronto,Canada,June 2002:2918-2920.
[136]Yang J,Xiong T,and Peng Y N.Polarimetric SAR image classification by using generalized optimization of polarimetric contrast enhancement.International Journal of Remote Sensing,2006,27(16):3413-3424.
[137]Jin Y Q and Xu F.A new set of the parameters for the terrain surface classification in polarimetric SAR image based on deorientation of polarimetric scattering vector.Proc.International Geoscience and Remote Sensing Symposium,Denver,Colorado,USA,July 2006:1403-1406.
[138]陈劲松,邵芸,董庆等.全极化SAR数据信息提取研究.遥感技术与应用,2003,18(3):153-158.
[139]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.中国图象图形学报,2004,9(5):552-556.
[140]Kahny D and Wiesbeck W.Optimum input parameters for classification of multifrequency polarimetric SAR-data using neural networks.Proc.International Geoscience and Remote Sensing Symposium,Helsinki,Finland,June 1991:2157-2160.
[141]Pottier E.Classification of earth terrain in polarimetric SAR images using neural nets modelization.Proc.SPIE Conference on Radar Polarimetry,vol.1748,San Diego,California,USA,July 1992:321-332.
[142]Ricard M R and Crawford M M.Multiscale hierarchical classification of wetland environments using SAR data.Proc.International Geoscience and Remote Sensing Symposium,Seattle,Washington,USA,July 1998:354-356.
[143]Ito Y and Omatu S.A polarimetric SAR data classification method using neural networks.Proc.International Geoscience and Remote Sensing Symposium,Seattle,Washington,USA,July 1998:1790-1792.
[144]Hosokawa M and Hoshi T.Polarimetric SAR data classification method using the self-organizing map.Proc.International Geoscience and Remote Sensing Symposium,Toronto,Canada,June 2002:3468-3470.
[145]Ersahin K,Scheuchl B,and Cumming Ⅰ.Incorporating texture information into polarimetric radar classification using neural networks.Proc.International Geoscience and Remote Sensing Symposium,Anchorage,Alaska,USA,September 2004:560-563.
[146]Putignano C,Schiavon G,and Solimini D.Self-organizing neural networks for unsupervised classification of polarimetric SAR data on complex landscapes.Proc.International Geoscience and Remote Sensing Symposium,Denver,Colorado,USA,July 2006:504-506.
[147]Lee J S,Grunes M R,Ainsworth T L,et al.Unsupervised classification using polarimetric decomposition and the complex Wishart classifier.IEEE Trans.on Geoscience and Remote Sensing,1999,37(5):2249-2258.
[148]Khan K U and Yang J.Novel features for polarimetric SAR image classification by neural network.Proc.International Conference on Neural Networks and Brain,October 2005:165-170.
[149]王翠珍,郭华东.极化雷达目标分解方法用于岩性分类.遥感学报,2000,4(3):219-223.
[150]Bellagente M,Gamba P,and Savazzi P.Fuzzy texture characterization of urban environments by SAR data.Proc.International Geoscience and Remote Sensing Symposium,Hamburg,Germany,June 1999:1232-1234.
[151]Aiazzi B,Alparone L,Baronti S,et al.Land cover classification of built-up areas through enhanced fuzzy nearest-mean reclustering of textural features from X- and C-band polarimetric SAR data.Proc.SPIE Conference on SAR Image Analysis,Modeling,and Techniques Ⅵ,vol.5236,Barcelona,Spain,September 2003:105-115.
[152]Fukuda S and Hirosawa H.Land cover classification from multifrequency polarimetric synthetic aperture radar data using wavelet-based textural information.Proc.International Geoscience and Remote Sensing Symposium,Seattle,Washington,USA,July 1998:357-359.
[153]刘国庆,熊红,黄顺吉.基于小波变换和马尔可夫随机场的极化SAR图像自动分类.电子科学学刊,2000,22(3):359-365.
[154]Ersahin K,Cumming I G,and Yedlin M J.Classification of polarimetric SAR data using spectral graph partitioning.Proc.International Geoscience and Remote Sensing Symposium,Denver,Colorado,USA,July 2006:1756-1759.
[155]Pellizzeri T M,Lombardo P,and Ferriero P.Polarimetric SAR image processing:Wishart vs "H/A/alpha" segmentation and classification schemes.Proc.International Geoscience and Remote Sensing Symposium,Toulouse,France,July 2003:3976-3978.
[156]Dabboor M and Karathanassi V.A knowledge-based classification method for polarimetric SAR data.Proc.SPIE Conference on SAR Image Analysis,Modeling,and Techniques Ⅶ,vol.5980,October 2005:59800C-59801-59812.
[157]Lee J S,Grunes M R,Ainsworth T L,et al.Unsupervised classification using polarimetric decomposition and complex Wishart classifier.Proc.International Geoscience and Remote Sensing Symposium,Seattle,Washington,USA,July 1998:2178-2180.
[158]Cao F and Hong W.A new classification method based on Cloude-Pottier eigenvalue eigenvector decomposition.Proc.International Geoscience and Remote Sensing Symposium,Seoul,Korea,July 2005:296-299.
[159]Cao F,Hong W,and Wu Y R.An unsupervised classification for fully polarimetric SAR data using IHSL transform and the FCM algorithm.Proc.International Geoscience and Remote Sensing Symposium,Denver,Colorado,USA,July 2006:1273-1276.
[160]Benz U and Pottier E.Object based analysis of polarimetric SAR data in alpha-entropy-anisotropy decomposition using fuzzy classification by eCognition.Proc.International Geoscience and Remote Sensing Symposium,Sydney,Australia,July 2001:1427-1429.
[161]Pottier E.Radar target decomposition theorems and unsupervised classification of full polarimetric SAR data.Proc.International Geoscience and Remote Sensing Symposium,Pasadena,California,USA,August 1994:1139-1141.
[162]Pottier E and Cloude S R.Unsupervised classification of full polarimetric SAR data and feature vectors identification using radar target decomposition theorems and entropy analysis.Proc.International Geoscience and Remote Sensing Symposium,Florence,Italy,July 1995:2247-2249.
[163]Lee K Y,Liew S C,and Kwoh L K.Land cover classification of polarimetric synthetic aperture radar(POLSAR) data based on scattering mechanisms and complex Wishart distribution.Proc.International Geoscience and Remote Sensing Symposium,Toronto,Canada,June 2002:2602-2604.
[164]Lee J S,Grunes M R,Pottier E,et al.Unsupervised terrain classification preserving polarimetric scattering characteristics.IEEE Trans.on Geoscience and Remote Sensing,2004,42(4):722-731.
[165]Schuler D L,Lee J S,and De Grandi G.Spiral eddy detection using surfactant slick patterns and polarimetric SAR image decomposition techniques.Proc.International Geoscience and Remote Sensing Symposium,Anchorage,Alaska,USA,September 2004:212-215.
[166]Putignano C,Schiavon G,Solimini D,et al.Unsupervised classification of a central Italy landscape by polarimetric L-band SAR data.Proc.International Geoscience and Remote Sensing Symposium,Seoul,Korea,July 2005:1291-1294.
[167]Scheuchl B,Caves R,Cumming Ⅰ,et al.Automated sea ice classification using spaceborne polarimetric SAR data.Proc.International Geoscience and Remote Sensing Symposium,Sydney,Australia,July 2001:3117-3119.
[168]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.
[169]Xu J Y,Yang J,Peng Y N,et al.Using cross-entropy for polarimetric SAR image classification.Proc.International Geoscience and Remote Sensing Symposium,Toronto,Canada,June 2002:1917-1919.
[170]Xu J Y,Yang J,and Peng Y N.New method of feature extraction in polarimetric SAR image classification.Proc.SPIE Conference on Battlespace Digitization and Network-Centric Warfare Ⅱ.vol.4741,August 2002:337-344.
[171]Arini N S.Post-segmentation feature-based classification of synthetic aperture radar data.Proc.International Geoscience and Remote Sensing Symposium,Seoul,Korea,June 2002:1615-1617.
[172]徐俊毅,杨健,彭应宁.双波段极化雷达遥感图像分类的新方法.中国科学E辑,2005,35(10):1083-1095.
[173]王之禹,朱敏慧,白有天.基于最优状态的多波段全极化SAR数据ML分类方法.电子与信息学报,2001,23(5):507-511.
[174]Lardeux C,Frison P L,Rudant J P,et al.Use of the SVM classification with polarimetric SAR data for land use cartography.Proc.International Geoscience and Remote Sensing Symposium,Denver,Colorado,USA,July 2006:493-496.
[175]Alberga V,Satalino G,and Staykova D K.Polarimetric SAR observables for land cover classification:analyses and comparisons.Proc.SPIE Conference on SAR Image Analysis,Modeling,and Techniques Ⅷ,vol.6363,September 2006:636305-636301-636312.
[176]Mott H著,林昌禄等译,向敬成等校.天线和雷达中的极化.成都:电子科技大学出版社,1989.
[177]Guissard A.Mueller and Kennaugh matrices in radar polarimetry.IEEE Trans.on Geoscience and Remote Sensing,1994,32(3):590-597.
[178]Cloude S R.Special unitary groups in polarimetry theory.Proc.SPIE Conference on Polarization Analysis and Measurement Ⅱ,vol.2265,September 1994:292-303.
[179]Kostinski A B and Boerner W M.On foundations of radar polarimetry.IEEE Trans.on Antennas and Propagation,1986,AP-34(12):1395-1404.
[180]Lee J S,Hoppel K W,Mango S A,et al.Intensity and phase statistics of multilook polarimetric and interferometric SAR imagery.IEEE Trans.on Geoscience and Remote Sensing,1994,32(5):1017-1028.
[181]Lee J S,Schuler D L,Lang R H,et al.K-distribution for multi-look processed polarimetric SAR imagery.Proc.International Geoscience and Remote Sensing Symposium,Pasadena,California,USA,August 1994:2179-2181.
[182]Joughin Ⅰ R,Winebrenner D P,and Percival D B.Probability density functions for multilook polarimetric signatures.IEEE Trans.on Geoscience and Remote Sensing,1994,32(3):562-574.
[183]Vapnik V N著,许建华,张学工译.统计学习理论.北京:电子工业出版社,2004.
[184]Vapnik V N著,张学工译.统计学习理论的本质.北京:清华大学出版社,2000.
[185]Cristianini N,Shawe-Taylor J著,李国正等译.支持向量机导论.北京:电子工业出版社,2005.
[186]Cortes C and Vapnik V N.Support vector networks.Machine Learning,1995,20(3):273-297.
[187]Zhao Q and Principe J.Support vector machines for SAR automatic target recognition.IEEE Trans.on Aerospace and Electronic Systems,2001,37(2):643-654.
[188]边肇祺,张学工等编著.模式识别.北京:清华大学出版社,2000.
[189]Hsu C W and Lin C J.A comparison of methods for multi-class support vector machines.IEEE Trans.on Neural Networks,2002,13(2):415-425.
[190]Jain A and Zongker D.Feature selection:evaluation,application,and small sample performance.IEEE Trans.on Pattern Analysis and Machine Intelligence,1997,19(2):153-158.
[191]Liu H and Yu L.Toward integrating feature selection algorithms for classification and clustering.IEEE Trans.on Knowledge and Data Engineering,2005,17(4):491-502.
[192]Hall M A.Correlation-based feature selection for discrete and numeric class machine learning.Proc.International Conference on Machine Learning,San Francisco,USA,June 2000:359-366.
[193]Mitra P,Murthy C A,and Pal S K.Unsupervised feature selection using feature similarity.IEEE Trans.on Pattern Analysis and Machine Intelligence,2002,24(3):301-312.
[194]Caruana R and Freitag D.Greedy attribute selection.Proc.International Conference on Machine Learning,San Francisco,USA,July 1994:28-36.
[195]Dy J G and Brodley C E.Feature subset selection and order identification for unsupervised learning.Proc.International Conference on Machine Learning,San Francisco,USA,June 2000:247-254.
[196] Sindhwani V, Rakshit S, Deodhare D, et al. Feature selection in MLPs and SVMs based on maximum output information. IEEE Trans. on Geoscience and Remote Sensing, 2004, 15 (4): 937-948.
[197] Ng A Y. On feature selection: learning with exponentially many irrelevant features as training examples. Proc. International Conference on Machine Learning, Wisconsin, USA, July 1998: 404-412.
[198] Xing E, Jordan M, and Karp R. Feature selection for high-dimensional genomic microarray data. Proc. International Conference on Machine Learning, Massachusetts, USA, June 2001: 601-608.
[199] Das S. Filters, wrappers and a boosting-based hybrid for feature selection. Proc. International Conference on Machine Learning, Massachusetts, USA, June 2001: 74-81.
[200] Somol P and Pudil P. Oscillating search algorithms for feature selection. Proc. International Conference on Pattern Recognition, September 2000: 406-409.
[201] Narendra P M and Fukunaga K. A branch and bound algorithm for feature subset selection. IEEE Trans. on Computers, 1977, 26: 917-922.
[202] Pudil P, Novovicova J, and Kittler J. Floating search methods in feature selection. Pattern Recognition Letters, 1994, 15: 1119-1125.
[203] Kononenko I. Estimating attributes: analysis and extensions of RELIEF. Proc. European Conference on Machine Learning, Sicily, Italy, April 1994: 171-182.
[204] Lee J S, Grunes M R, Pottier E, et al. Segmentation of polarimetric SAR images. Proc. International Geoscience and Remote Sensing Symposium, Sydney, Australia, July 2001: 414-416.
[205] Geman S and Geman D. Stochastic relaxation, Gibbs distribution and the Bayesian restoration of images. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1984, PAMI-6 (6): 721-741.
[206] Kottke D P, Fiore P D, Brown K L, et al. A design for HMM-based SAR ATR. Proc. SPIE Conference on Algorithms for Synthetic Aperture Radar Imagery V, Orlando, Florida, USA, April 1998: 541-551.
[207] Besag J. On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society, 1986, B48 (3): 259-302.
[208] Fwu J K and Djuric P M. Unsupervised vector image segmentation by a tree structure-ICM algorithm. IEEE Trans. on Medical Imaging, 1996, 15 (6): 871-880.
[209] Rignot E, Chellappa R, and Dubois P. Unsupervised segmentation of polarimetric SAR data using the covariance matrix. IEEE Trans. on Geoscience and Remote Sensing, 1992, 30 (4): 697-705.
[210] Andreadis A, Benelli B, and Garzelli A. Detail-preserving segmentation of polarimetric SAR imagery. Proc. International Geoscience and Remote Sensing Symposium, Lincoln, Nebraska, USA, May 1996: 377-379.
[211] 章毓晋. 图像分割. 北京:科学出版社,2001.
[212] Yu Y J and Acton S T. Polarimetric SAR image segmentation using texture partitioning and statistical analysis. Proc. International Conference on Image Processing, September 2000: 677-680.
[213] Moreels P and Smrekar S E. Watershed identification of polygonal patterns in noisy SAR images. IEEE Trans. on Image Processing, 2003, 12 (7): 740-750.
[2]张直中.微波成像术.北京:科学出版社,1990.
[3]杨士中.合成孔径雷达.北京:国防工业出版社,1981.
[4]庄钊文,削顺平,王雪松.雷达极化信息处理及其应用.北京:国防工业出版社,1999.
[5]Hubbert J C.A comparison of radar,optic,and specular null polarization theories.IEEE Trans.on Geoscience and Remote Sensing,1994,32(3):658-671.
[6]Zebker H A and van Zyl J J.Imaging radar polarimetry:a review.Proc.IEEE,1991,79(11):1583-1606.
[7]Sinclair G.The transmission and reception of elliptically polarized waves.Proc.IRE,1950,38(2):148-151.
[8]Kennaugh E M.Polarization properties of radar reflections.Master's thesis.Columbus,Ohio,USA:The Ohio State University,March 1952.
[9]Huynen J R.Measurement of the target scattering matrix.Proc.IEEE,1965,53(8):936-946.
[10]Huynen J R.Phenomenological theory of radar targets.Ph.D.dissertation.Delft,The Netherlands:Tech.Univ.Delft,1970.
[11]Touzi R,Boerner W M,Lee J S.et al.A review of polarimetry in the context of synthetic aperture radar:concepts and information extraction.Canadian Journal of Remote Sensing,2004,30(3):380-407.
[12]Poelman A J and Guy J R F.Polarization information utilization in primary radar:an introduction and up-date to activities at SHAPE technical centre.Mathematical and Physical Sciences,1985,143:521-572.
[13]van Zyl J J and Zebker H A.Imaging radar polarization signatures:theory and observation.Radio Science,1987,22:529-543.
[14]Zebker H A,van Zyl J J,and Held D N.Imaging radar polarimetry from wave synthesis.Journal of Geophysical Research,1987,92:683-701.
[15]Chu A,Kim Y J,van Zyl J J,et al.The NASA/JPL AIRSAR integrated processor.Proc.International Geoscience and Remote Sensing Symposium,Washington,USA,July 1998:1908-1910.
[16]van Zyl J J,Carande R,Lou Y L,et al.The NASA/JPL three-frequency polarimetric AIRSAR system.Proc.International Geoscience and Remote Sensing Symposium,Texas,USA,May 1992:649-651.
[17]Kozma A,Nichols A D,Rawson R F.et al.Multifrequency polarimetric SAR for remote sensing.Proc.International Geoscience and Remote Sensing Symposium,Zurich,Switzerland,September 1986:715-720.
[18]Sullivan R,Nichols A,Rawson R,et al.Polarimetric X/L/C-band SAR.Proc.IEEE International Radar Conference,Michigan,USA,April 1988:9-14.
[19]Horn R.The DLR airborne SAR project E-SAR.Proc.International Geoscience and Remote Sensing Symposium,Nebraska,USA,May 1996:1624-1628.
[20]Horn R,Werner M,and Mayr B.Extension of the DLR airborne synthetic aperture radar,E-SAR,to X-band.Proc.International Geoscience and Remote Sensing Symposium,Maryland,USA,May 1990:2047-2049.
[21] Scheiber R, Reigber A, Ulbricht A, et al. Overview of interferometric data acquisition and processing modes of the experimental airborne SAR system of DLR. Proc. International Geoscience and Remote Sensing Symposium, Hamburg, Germany, June 1999: 35-37.
[22] Livingstone C E, Gray A L, Hawkins R K, et al. The CCRS airborne SAR systems: radar for remote sensing research. Canadian Journal of Remote Sensing, 1995, 21 (4): 468-491.
[23] Livingstone C E, Lukowski T I, Rey M T, et al. CCRS/DREO synthetic aperture radar polarimetry - status report. Proc. International Geoscience and Remote Sensing Symposium, Maryland, USA, May 1990: 1671-1674.
[24] Hoffmann K and Fischer P. DOSAR: a multifrequency polarimetric and interferometric airborne SAR-system. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 1708-1710.
[25] Skou N, Granholm J, Woelders K, et al. A high resolution polarimetric L-band SAR - design and first results. Proc. International Geoscience and Remote Sensing Symposium, Florence, Italy, July 1995: 1779-1782.
[26] Christensen E L, Skou N, Dall J, et al. EMISAR: an absolutely calibrated polarimetric L- and C-band SAR. IEEE Trans, on Geoscience and Remote Sensing, 1998, 36 (6): 1852-1865.
[27] Christensen E L and Dall J. EMISAR: a dual-frequency, polarimetric airborne SAR. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 1711-1713.
[28] Sheen D R, Strawitch C M, and Lewis T B. UHF wideband SAR design and preliminary results. Proc. International Geoscience and Remote Sensing Symposium, California, USA, August 1994: 289-291.
[29] Sheen D R, Shackman S J, VandenBerg N L, et al. The P-3 ultra-wideband SAR: description and examples. Proc. IEEE International Radar Conference, Michigan, USA, May 1996: 50-53.
[30] Sheen D R, VandenBerg N L, Shackman S J, et al. P-3 ultra-wideband SAR: description and examples. IEEE Aerospace and Electronic Systems Magazine, 1996: 25-30.
[31] Greidanus H, Hoogeboom P, and Koomen P. First results and status of the PHARUS phased array airborne SAR. Proc. International Geoscience and Remote Sensing Symposium, Nebraska, USA, May 1996: 1633-1635.
[32] Hoogeboom P, Snoeij P, Koomen P J, et al. The PHARUS project, results of the definition study including the SAR testbed PHARS. IEEE Trans. on Geoscience and Remote Sensing, 1992, 30 (4): 723-735.
[33] Uratsuka S, Satake M, Kobayashi T, et al. High-resolution dual-bands interferometric and polarimetric airborne SAR (Pi-SAR) and its applications. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 1720-1722.
[34] Uratsuka S, Moriyama T, Umehara T, et al. Disastrous environment after earthquake observed by airborne SAR (Pi-SAR). Proc. International Geoscience and Remote Sensing Symposium, Seoul, Korea, July 2005: 4081-4083.
[35] Wang H P, Ouchi K, Watanabe M, et al. In search of the statistical properties of high-resolution polarimetric SAR data for the measurements of forest biomass beyond the RCS saturation limits. IEEE Geoscience and Remote Sensing Letters, 2006, 3 (4): 495-499.
[36] Dubois-Fernandez P, Cantalloube H, and Dupuis X. Clutter statistical analysis for high resolution SAR data. Proc. International Geoscience and Remote Sensing Symposium, Alaska, USA, September 2004: 1781-1783.
[37] Dubois-Fernandez P, du Plessis O R, le Coz D, et al. The ONERA RAMSES SAR system. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 1723-1725.
[38] Dreuillet P, Paillou P, Cantalloube H, et al. P band data collection and investigations utilizing the RAMSES SAR facility. Proc. International Geoscience and Remote Sensing Symposium, Toulouse, France, July 2003: 4262-4264.
[39] Schimpf H, Essen H, Boehmsdorff S, et al. MEMPHIS - a fully polarimetric experimental radar. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 1714-1716.
[40] Essen H, Fuchs H H, and Pagels A. Remote sensing of the sea surface by millimeterwave SAR. Proc. SPIE Conference on Remote Sensing of the Ocean, Sea Ice, and Large Water Regions, vol. 6360, September 2006: 63600N-63601-63608.
[41] Jordan R L, Huneycutt B L, and Werner M. The SIR-C/X-SAR synthetic aperture radar system. Proc. IEEE, 1991, 79 (6): 827-838.
[42] Jordan R L, Huneycutt B L, and Werner M. The SIR-C/X-SAR synthetic aperture radar system. IEEE Trans. on Geoscience and Remote Sensing, 1995, 33 (4): 829-839.
[43] Hawkins R K, Touzi R, Wolfe J, et al. ASAR AP mode performance and applications potential. Proc. International Geoscience and Remote Sensing Symposium, Toulouse, France, July 2003: 1115-1117.
[44] Kimura H and Ito N. ALOS PALSAR: The Japanese second-generation spaceborne SAR and its applications. Proc. SPIE Conference on Microwave Remote Sensing of the Atmosphere and Environment II, vol. 4152, December 2000: 110-119.
[45] http://alos.jaxa.jp/index-e.html.
[46] http://www.jaxa.jp/about/index e.html.
[47] http://www. jaxa.jp/projects/rockets/h2a/index_e.html.
[48] Schulz-Stellenfleth J, Lehner S, and Horstmann J. Use of TerraSAR-X for oceanography. Proc. International Geoscience and Remote Sensing Symposium, Seoul, Korea, July 2005: 4886-4889.
[49] Stangl M, Werninghaus R, Schweizer B, et al. TerraSAR-X technologies and first results. IEE Proc. Radar Sonar Navigation, 2006, 153 (2): 86-95.
[50] http://www.RADARSAT2.info.
[51] 刘永坦. 雷达成像技术. 哈尔滨: 哈尔滨工业大学出版社, 1999.
[52] Cloude S R and Pottier E. An entropy based classification scheme for land applications of polarimetric SAR. IEEE Trans. on Geoscience and Remote Sensing, 1997, 35 (1): 68-78.
[53] Baronti S, Macelloni G, Paloscia S, et al. Analysis of an automatic method for surface classification using multifrequency multipolarization SAR data. Proc. International Geoscience and Remote Sensing Symposium, Florence, Italy, July 1995: 973-975.
[54] Ferrazzoli P, Paloscia S, Pampaloni P, et al. The potential of multifrequency polarimetric SAR in assessing agricultural and arboreous biomass. IEEE Trans. on Geoscience and Remote Sensing, 1997, 35 (1): 5-17.
[55] Ferrazzoli P, Guerriero L, and Schiavon G. Experimental and model investigation on radar classification capability. IEEE Trans. on Geoscience and Remote Sensing, 1999, 37 (2): 960-968.
[56] Fujita M and Tamura D. Land use classification of SIR-C imagery based on a published database of multi-polarization backscattering. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 1956-1958.
[57] Du L J and Grunes M R. Unsupervised segmentation of multi-polarization SAR images based on amplitude and texture characteristics. Proc. International Geoscience and Remote Sensing Symposium, Honolulu, Hawaii, USA, July 2000: 1122-1124.
[58] Chen K S, Huang W P, Tsay D H, et al. Classification of multifrequency polarimetric SAR imagery using a dynamic learning neural network. IEEE Trans. on Geoscience and Remote Sensing, 1996, 34 (3): 814-820.
[59] Tzeng Y C and Chen K S. A fuzzy neural network to SAR image classification. IEEE Trans. on Geoscience and Remote Sensing, 1998, 36 (1): 301-307.
[60] Frate F D, Schiavon G, Solimini D, et al. Crop classification using multiconfiguration C-band SAR data. IEEE Trans. on Geoscience and Remote Sensing, 2003, 41 (7): 1611-1619.
[61] Benz U C. Supervised fuzzy analysis of single- and multichannel SAR data. IEEE Trans. on Geoscience and Remote Sensing, 1999, 37 (2): 1023-1037.
[62] Fukuda S and Hirosawa H. Support vector machine classification of land cover: application to polarimetric SAR data. Proc. International Geoscience and Remote Sensing Symposium, Sydney, Australia, July 2001: 187-189.
[63] Fukuda S, Katagiri R, and Hirosawa H. Unsupervised approach for polarimetric SAR image classification using support vector machines. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 2599-2601.
[64] Pellizzeri T M and Lombardo P. Model-based processing of multifrequency polarimetric SAR images of urban areas. Proc. GRSS/ISPRS Joint Workshop on Data Fusion and Remote Sensing over Urban Areas, May 2003: 47-51.
[65] Lombardo P. Optimal classification of polarimetric SAR images using segmentation. Proc. IEEE International Radar Conference, Long Beach, California, April 2002: 8-13.
[66] Treitz P M, Filho O R, Howarth P J, et al. Textural processing of multi-polarization SAR for agricultural crop classification. Proc. International Geoscience and Remote Sensing Symposium, Lincoln, Nebraska, USA, May 1996: 1986-1988.
[67] Lee J S. Feature classification using multi-look polarimetric SAR imagery. Proc. International Geoscience and Remote Sensing Symposium, Houston, Texas, USA, May 1992: 77-79.
[68] Skriver H, Svendsen M T, Nielsen F, et al. Crop classification by polarimetric SAR. Proc. International Geoscience and Remote Sensing Symposium, Hamburg, Germany, June 1999: 2333-2335.
[69] Scheuchl B and Cumming I G. Potential of RADARSAT-2 for sea ice classification. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 2185-2187.
[70]Lee J S,Grunes M R,Ainsworth T L,et al.Quantitative comparison of classification capability:fully-polarimetric versus partially polarimetric SAR.Proc.International Geoscience and Remote Sensing Symposium,Honolulu,Hawaii,USA,July 2000:1101-1103.
[71]Lee J S,Grunes M R,and Pottier E.Quantitative comparison of classification capability:fully polarimetric versus dual and single-polarization SAR.IEEE Trans.on Geoscience and Remote Sensing,2001,39(11):2343-2351.
[72]Liu G Q,Huang S J,Torre A,et al.Bayesian classification of multi-look polarimetric SAR images with a generalized multiplicative speckle model.Proc.SPIE Conference on Algorithms for Synthetic Aperture Radar Imagery Ⅳ,vol.3070,July 1997:398-405.
[73]刘国庆,熊红,黄顺吉等.多视极化合成孔径雷达图象的分类和极化通道优化.电子科学学刊,1998,20(1):56-61.
[74]Tran T N,Wehrens R,and Hoekman D H.Initialization of Markov Random Field clustering of large polarimetric SAR images.Proc.International Geoscience and Remote Sensing Symposium,Anchorage,Alaska,USA,September 2004:714-717.
[75]Tran T N,Wehrens R,Hoekman D H,et al.Initialization of Markov random field clustering of large remote sensing images.IEEE Trans.on Geoscience and Remote Sensing,2005,43(8):1912-1919.
[76]Frery A C,Correia A H,and Freitas C C.Multifrequency full polarimetric SAR classification with multiple sources of statistical evidence.Proc.International Geoscience and Remote Sensing Symposium,Denver,Colorado,USA,July 2006:4195-4197.
[77]Freitas C C,Frery A C,and Correia A H.The polarimetric G distribution for SAR data analysis.Environmetrics,2005,16(1):13-31.
[78]Hara Y,Atkins R G,Yueh S H,et al.Application of neural networks to radar image classification.IEEE Trans.on Geoscience and Remote Sensing,1994,32(1):100-109.
[79]Hara Y,Atkins R G,Shin R T,et al.Application of neural networks for sea ice classification in polarimetric SAR images.IEEE Trans.on Geoscience and Remote Sensing,1995,33(3):740-748.
[80]Chen C T,Chen K S,and Lee J S.The use of fully polarimetric information for the fuzzy neural classification of SAR images.IEEE Trans.on Geoscience and Remote Sensing,2003,41(9):2089-2100.
[81]Du L,Lee J S,and Mango S A.Fuzzy classification of Earth terrain covers using multi-look polarimetric SAR image data.Proc.International Geoscience and Remote Sensing Symposium,Tokyo,Japan,August 1993:1602-1604.
[82]Kersten P R,Lee J S,Ainsworth T L,et al.Classification of polarimetric synthetic aperture radar images using fuzzy clustering.Proc.International Geoscience and Remote Sensing Symposium,Toulouse,France,October 2003:150-156.
[83]Wong Y F and Posner E C.A new clustering algorithm applicable to multispectral and polarimetric SAR images.IEEE Trans.on Geoscience and Remote Sensing,1993,31(3):634-644.
[84]Dong Y,Milne A K,and Forster B C.Segmentation and classification of vegetated areas using polarimetric SAR image data.IEEE Trans.on Geoscience and Remote Sensing,2001,39(2):321-329.
[85] Rignot E and Chellappa R. Segmentation of polarimetric synthetic aperture radar data. IEEE Trans. on Image Processing, 1992, 1 (3): 281-300.
[86] Chandrasekhar S. Radiative transfer. New York: Dover, 1960.
[87] van Zyl J J. Application of Cloude's target decomposition theorem to polarimetric imaging radar data. Proc. SPIE Conference on Radar Polarimetry, vol. 1748, San Diego, California, USA, July 1992: 184-191.
[88] Cloude S R and Pottier E. A review of target decomposition theorems in radar polarimetry. IEEE Trans. on Geoscience and Remote Sensing, 1996, 34 (2): 498-518.
[89] 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. Proc. SPIE Conference on Radar Polarimetry, vol. 1748, San Diego, California, USA, July 1992: 72-85.
[90] van Zyl J J. Unsupervised classification of scattering behavior using radar polarimetry data. IEEE Trans. on Geoscience and Remote Sensing, 1989, 27 (1): 36-45.
[91] Qong M, Tadono T, Wakabayashi H, et al. Mueller matrix based classification of polarimetric SAR data. Proc. International Geoscience and Remote Sensing Symposium, Honolulu, Hawaii, USA, July 2000: 375-377.
[92] Dong Y, Forster B, and Ticehurst C. Polarimetric image classification using optimal decomposition of radar polarization signatures. Proc. International Geoscience and Remote Sensing Symposium, Lincoln, Nebraska, USA, May 1996: 1556-1558.
[93] Dong Y, Forster B, and Ticehurst C. A new decomposition of radar polarization signatures. IEEE Trans. on Geoscience and Remote Sensing, 1998, 36 (3): 933-939.
[94] Krogager E, Dall J, and Madsen S N. The sphere, diplane, helix decomposition recent results with polarimetric SAR data. Proc. Third International Workshop on Radar Polarimetry, March 1995: 621-625.
[95] Krogager E, Boerner W M, and Madsen S N. Feature-motivated Sinclair matrix (sphere/diplane/helix) decomposition and its application to target sorting for land feature classification. Proc. SPIE Conference on Wideband Interferometric Sensing and Imaging Polarimetry, vol. 3120, December 1997: 144-154.
[96] Moriyama T, Nakamura M, and Yamaguchi Y. Radar polarimetry applied to the classification of underground targets. Proc. SPIE Conference on Wideband Interferometric Sensing and Imaging Polarimetry, vol. 3120, December 1997: 182-189.
[97] Cameron W L and Leung L K. Feature motivated polarization scattering matrix decomposition. Proc. IEEE International Radar Conference, May 1990: 549-557.
[98] Cameron W L, Youssef N N, and Leung L K. Simulated polarimetric signatures of primitive geometrical shapes. IEEE Trans. on Geoscience and Remote Sensing, 1996, 34 (3): 793-803.
[99] Touzi R and Charbonneau F. Characterization of symmetric scattering using polarimetric SARs. Proc. International Geoscience and Remote Sensing Symposium, Toronto, Canada, June 2002: 414-416.
[100] Touzi R and Charbonneau F. Characterization of target symmetric scattering using polarimetric SARs. IEEE Trans. on Geoscience and Remote Sensing, 2002, 40 (11): 2507-2516.
[101] Freeman A and Durden S. A three-component scattering model to describe polarimetric SAR data. Proc. SPIE Conference on Radar Polarimetry, vol. 1748, San Diego, California, USA, July 1992: 213-224.
[102] Freeman A and Durden S L. A three-component scattering model for polarimetric SAR data. IEEE Trans. on Geoscience and Remote Sensing, 1998, 36 (3): 963-973.
[103] Freeman A. Fitting a two-component scattering model to polarimetric SAR data. Proc. International Geoscience and Remote Sensing Symposium, Houston, Texas, USA, June 1999: 2649-2651.
[104] Yamaguchi Y, Moriyama T, Ishido M, et al. Four-component scattering model for polarimetric SAR image decomposition. IEEE Trans. on Geoscience and Remote Sensing, 2005, 43 (8): 1699-1706.
[105] Holm W A and Barnes R M. On radar polarization mixed target state decomposition techniques. Proc. IEEE National Radar Conference, April 1988: 249-254.
[106] Yamaguchi Y, Yajima Y, and Yamada H. A four-component decomposition of POLSAR images based on the coherency matrix. IEEE Geoscience and Remote Sensing Letters, 2006, 3 (3): 292-296.
[107] Cloude S R. Radar target decomposition theorems. IEE Electronics Letters, 1985, 21 (1): 22-24.
[108] Cloude S R. An entropy based classification scheme for polarimetric SAR data. Proc. International Geoscience and Remote Sensing Symposium, Florence, Italy, July 1995: 2000-2002.
[109] Hellmann M. A new approach for interpretation of SAR-data using polarimetric techniques. Proc. International Geoscience and Remote Sensing Symposium, Seattle, Washington, USA, July 1998: 2195-2197.
[110] Belhadj Z, Benazza A, and Hidoussi N. Classification of radar images in polarimetric remote sensing. Proc. International Conference on Image Processing, Seattle, Washington, USA, July 1998: 574-577.
[111] Verdi J S, Lee R, Kersten PR,et al. Comparative analysis of polarimetric SAR image exploitation algorithms for environmental stress-change monitoring. Proc. International Geoscience and Remote Sensing Symposium, Hamburg, Germany, June 1999:2449-2451.
[112] Lopez-Sanchez J M, Fortuny-Guasch J, and Sieber A J. Experimental validation of an entropy-based classification scheme using a wide-band polarimetric radar. Proc. International Geoscience and Remote Sensing Symposium, Seattle, Washington, USA, July 1998: 2381-2383.
[113] Ferro-Famil L, Pottier E, Saillard J, et al. The potential of full polarimetric SAR data to classify dry snowcover. Proc. International Geoscience and Remote Sensing Symposium, Hamburg, Germany, June 1999: 1792-1794.
[114] Park S E and Moon W M. Classification of the polarimetric SAR using fuzzy boundaries in entropy and alpha plane. Proc. International Geoscience and Remote Sensing Symposium, Seoul, Korea, July 2005: 5517-5519.
[115] Du L J and Lee J S. Polarimetric SAR image classification based on target decomposition theorem and complex Wishart distribution. Proc. International Geoscience and Remote Sensing Symposium, Lincoln, Nebraska, USA, May 1996:439-441.
[116] Lombardo P, Pellizzeri T M, and Tomasuolo A. A joint classification technique based on multivariate annealing segmentation and "H/A/α" decomposition for fully polarimetric SAR images of suburban areas.Proc.International Geoscience and Remote Sensing Symposium,Sydney,Australia,July 2001:2922-2924.
[117]陈体刚,李彦佐.全极化SAR图像中相干矩阵特征值及其应用.信息与电子工程,2005,3(3):161-166.
[118]Pottier E and Cloude S R.Application of the H/A/alpha polarimetric decomposition theorem for land classification.Proc.SPIE Conference on Wideband Interferometric Sensing and Imaging Polarimetry,vol.3120,December 1997:132-143.
[119]Hellmann M,Jager G,Kratzschmar E,et al.Classification of full polarimetric SAR-data using artificial neural networks and fuzzy algorithms.Proc.International Geoscience and Remote Sensing Symposium,Hamburg,Germany,June 1999:1995-1997.
[120]Hellmann M,Jager G,and Pottier E.Fuzzy clustering and interpretation of fully polarimetric SAR data.Proc.International Geoscience and Remote Sensing Symposium,Sydney,Australia,July 2001:2790-2792.
[121]Praks J,Arslan A N,Alasalmi H,et al.SAR target decomposition for stochastic natural targets for L- and C-band.Proc.International Geoscience and Remote Sensing Symposium,Hamburg,Germany,June 1999:1558-1560.
[122]Praks J and Hallikainen M.A novel approach in polarimetric covariance matrix eigendecomposition.Proc.International Geoscience and Remote Sensing Symposium,Honolulu,Hawaii,USA,July 2000:1119-1121.
[123]Hoekman D H and Vissers M A M.A new polarimetric classification approach evaluated for agricultural crops.IEEE Trans.on Geoscience and Remote Sensing,2003,41(12):2881-2889.
[124]Fukuda S and Hirosawa H.A wavelet-based texture feature set applied to classification of multifrequency polarimetric SAR images.IEEE Trans.on Geoscience and Remote Sensing,1999,37(5):2282-2286.
[125]Bourissou A,Pham K,Au W C,et al.Classification of a polarimetric SAR image using fractal concepts.Proc.International Geoscience and Remote Sensing Symposium,Tokyo,Japan,August 1993:1599-1601.
[126]陈劲松,邵芸,林晖.全极化SAR数据在地表覆盖/利用监测中的应用.国土资源遥感,2004,(60):39-42.
[127]王晓兰,戴博伟,杨汝良.全极化合成孔径雷达多视图像的极化特征分析.电子与信息学报,2002,24(4):507-513.
[128]余海坤,张永红,王云甲.利用极化SAR数据进行土地覆盖分类研究.海洋测绘,2006,26(3):34-38.
[129]Kouskoulas Y,Ulaby F T,and Pierce L E.The Bayesian hierarchical classifier (BHC) and its application to short vegetation using multifrequency polarimetric SAR.IEEE Trans.on Geoscience and Remote Sensing,2004,42(2):469-477.
[130]Loiselet M and Grandin J F.Polarization study for better classification.Proc.SPIE Conference on Radar Processing,Technology,and Applications Ⅳ,vol.3810,September 1999:180-190.
[131]Moriyama T,Uratsuka S,Umehara T,et al.A study on extraction of urban areas from polarimetric synthetic aperture radar image.Proc.International Geoscience and Remote Sensing Symposium,Anchorage,Alaska,USA,September 2004:703-706.
[132]Touzi R,Goze S,Toan T L,et al.Polarimetric discriminators for SAR images.IEEE Trans.on Geoscience and Remote Sensing,1992,30(5):973-980.
[133]Skriver H and Dierking W.Knowledge-based sea ice classification by polarimetric SAR.Proc.International Geoscience and Remote Sensing Symposium,September 2004:204-207.
[134]Pierce L E,Ulaby F T,Sarabandi K,et al.Knowledge-based classification of polarimetric SAR images.IEEE Trans.on Geoscience and Remote Sensing,1994,32(5):1081-1086.
[135]Rodriguez K M,Weissel J K,and Kim Y.Classification of landslide surfaces using fully polarimetric SAR:examples from Taiwan.Proc.International Geoscience and Remote Sensing Symposium,Toronto,Canada,June 2002:2918-2920.
[136]Yang J,Xiong T,and Peng Y N.Polarimetric SAR image classification by using generalized optimization of polarimetric contrast enhancement.International Journal of Remote Sensing,2006,27(16):3413-3424.
[137]Jin Y Q and Xu F.A new set of the parameters for the terrain surface classification in polarimetric SAR image based on deorientation of polarimetric scattering vector.Proc.International Geoscience and Remote Sensing Symposium,Denver,Colorado,USA,July 2006:1403-1406.
[138]陈劲松,邵芸,董庆等.全极化SAR数据信息提取研究.遥感技术与应用,2003,18(3):153-158.
[139]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.中国图象图形学报,2004,9(5):552-556.
[140]Kahny D and Wiesbeck W.Optimum input parameters for classification of multifrequency polarimetric SAR-data using neural networks.Proc.International Geoscience and Remote Sensing Symposium,Helsinki,Finland,June 1991:2157-2160.
[141]Pottier E.Classification of earth terrain in polarimetric SAR images using neural nets modelization.Proc.SPIE Conference on Radar Polarimetry,vol.1748,San Diego,California,USA,July 1992:321-332.
[142]Ricard M R and Crawford M M.Multiscale hierarchical classification of wetland environments using SAR data.Proc.International Geoscience and Remote Sensing Symposium,Seattle,Washington,USA,July 1998:354-356.
[143]Ito Y and Omatu S.A polarimetric SAR data classification method using neural networks.Proc.International Geoscience and Remote Sensing Symposium,Seattle,Washington,USA,July 1998:1790-1792.
[144]Hosokawa M and Hoshi T.Polarimetric SAR data classification method using the self-organizing map.Proc.International Geoscience and Remote Sensing Symposium,Toronto,Canada,June 2002:3468-3470.
[145]Ersahin K,Scheuchl B,and Cumming Ⅰ.Incorporating texture information into polarimetric radar classification using neural networks.Proc.International Geoscience and Remote Sensing Symposium,Anchorage,Alaska,USA,September 2004:560-563.
[146]Putignano C,Schiavon G,and Solimini D.Self-organizing neural networks for unsupervised classification of polarimetric SAR data on complex landscapes.Proc.International Geoscience and Remote Sensing Symposium,Denver,Colorado,USA,July 2006:504-506.
[147]Lee J S,Grunes M R,Ainsworth T L,et al.Unsupervised classification using polarimetric decomposition and the complex Wishart classifier.IEEE Trans.on Geoscience and Remote Sensing,1999,37(5):2249-2258.
[148]Khan K U and Yang J.Novel features for polarimetric SAR image classification by neural network.Proc.International Conference on Neural Networks and Brain,October 2005:165-170.
[149]王翠珍,郭华东.极化雷达目标分解方法用于岩性分类.遥感学报,2000,4(3):219-223.
[150]Bellagente M,Gamba P,and Savazzi P.Fuzzy texture characterization of urban environments by SAR data.Proc.International Geoscience and Remote Sensing Symposium,Hamburg,Germany,June 1999:1232-1234.
[151]Aiazzi B,Alparone L,Baronti S,et al.Land cover classification of built-up areas through enhanced fuzzy nearest-mean reclustering of textural features from X- and C-band polarimetric SAR data.Proc.SPIE Conference on SAR Image Analysis,Modeling,and Techniques Ⅵ,vol.5236,Barcelona,Spain,September 2003:105-115.
[152]Fukuda S and Hirosawa H.Land cover classification from multifrequency polarimetric synthetic aperture radar data using wavelet-based textural information.Proc.International Geoscience and Remote Sensing Symposium,Seattle,Washington,USA,July 1998:357-359.
[153]刘国庆,熊红,黄顺吉.基于小波变换和马尔可夫随机场的极化SAR图像自动分类.电子科学学刊,2000,22(3):359-365.
[154]Ersahin K,Cumming I G,and Yedlin M J.Classification of polarimetric SAR data using spectral graph partitioning.Proc.International Geoscience and Remote Sensing Symposium,Denver,Colorado,USA,July 2006:1756-1759.
[155]Pellizzeri T M,Lombardo P,and Ferriero P.Polarimetric SAR image processing:Wishart vs "H/A/alpha" segmentation and classification schemes.Proc.International Geoscience and Remote Sensing Symposium,Toulouse,France,July 2003:3976-3978.
[156]Dabboor M and Karathanassi V.A knowledge-based classification method for polarimetric SAR data.Proc.SPIE Conference on SAR Image Analysis,Modeling,and Techniques Ⅶ,vol.5980,October 2005:59800C-59801-59812.
[157]Lee J S,Grunes M R,Ainsworth T L,et al.Unsupervised classification using polarimetric decomposition and complex Wishart classifier.Proc.International Geoscience and Remote Sensing Symposium,Seattle,Washington,USA,July 1998:2178-2180.
[158]Cao F and Hong W.A new classification method based on Cloude-Pottier eigenvalue eigenvector decomposition.Proc.International Geoscience and Remote Sensing Symposium,Seoul,Korea,July 2005:296-299.
[159]Cao F,Hong W,and Wu Y R.An unsupervised classification for fully polarimetric SAR data using IHSL transform and the FCM algorithm.Proc.International Geoscience and Remote Sensing Symposium,Denver,Colorado,USA,July 2006:1273-1276.
[160]Benz U and Pottier E.Object based analysis of polarimetric SAR data in alpha-entropy-anisotropy decomposition using fuzzy classification by eCognition.Proc.International Geoscience and Remote Sensing Symposium,Sydney,Australia,July 2001:1427-1429.
[161]Pottier E.Radar target decomposition theorems and unsupervised classification of full polarimetric SAR data.Proc.International Geoscience and Remote Sensing Symposium,Pasadena,California,USA,August 1994:1139-1141.
[162]Pottier E and Cloude S R.Unsupervised classification of full polarimetric SAR data and feature vectors identification using radar target decomposition theorems and entropy analysis.Proc.International Geoscience and Remote Sensing Symposium,Florence,Italy,July 1995:2247-2249.
[163]Lee K Y,Liew S C,and Kwoh L K.Land cover classification of polarimetric synthetic aperture radar(POLSAR) data based on scattering mechanisms and complex Wishart distribution.Proc.International Geoscience and Remote Sensing Symposium,Toronto,Canada,June 2002:2602-2604.
[164]Lee J S,Grunes M R,Pottier E,et al.Unsupervised terrain classification preserving polarimetric scattering characteristics.IEEE Trans.on Geoscience and Remote Sensing,2004,42(4):722-731.
[165]Schuler D L,Lee J S,and De Grandi G.Spiral eddy detection using surfactant slick patterns and polarimetric SAR image decomposition techniques.Proc.International Geoscience and Remote Sensing Symposium,Anchorage,Alaska,USA,September 2004:212-215.
[166]Putignano C,Schiavon G,Solimini D,et al.Unsupervised classification of a central Italy landscape by polarimetric L-band SAR data.Proc.International Geoscience and Remote Sensing Symposium,Seoul,Korea,July 2005:1291-1294.
[167]Scheuchl B,Caves R,Cumming Ⅰ,et al.Automated sea ice classification using spaceborne polarimetric SAR data.Proc.International Geoscience and Remote Sensing Symposium,Sydney,Australia,July 2001:3117-3119.
[168]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.
[169]Xu J Y,Yang J,Peng Y N,et al.Using cross-entropy for polarimetric SAR image classification.Proc.International Geoscience and Remote Sensing Symposium,Toronto,Canada,June 2002:1917-1919.
[170]Xu J Y,Yang J,and Peng Y N.New method of feature extraction in polarimetric SAR image classification.Proc.SPIE Conference on Battlespace Digitization and Network-Centric Warfare Ⅱ.vol.4741,August 2002:337-344.
[171]Arini N S.Post-segmentation feature-based classification of synthetic aperture radar data.Proc.International Geoscience and Remote Sensing Symposium,Seoul,Korea,June 2002:1615-1617.
[172]徐俊毅,杨健,彭应宁.双波段极化雷达遥感图像分类的新方法.中国科学E辑,2005,35(10):1083-1095.
[173]王之禹,朱敏慧,白有天.基于最优状态的多波段全极化SAR数据ML分类方法.电子与信息学报,2001,23(5):507-511.
[174]Lardeux C,Frison P L,Rudant J P,et al.Use of the SVM classification with polarimetric SAR data for land use cartography.Proc.International Geoscience and Remote Sensing Symposium,Denver,Colorado,USA,July 2006:493-496.
[175]Alberga V,Satalino G,and Staykova D K.Polarimetric SAR observables for land cover classification:analyses and comparisons.Proc.SPIE Conference on SAR Image Analysis,Modeling,and Techniques Ⅷ,vol.6363,September 2006:636305-636301-636312.
[176]Mott H著,林昌禄等译,向敬成等校.天线和雷达中的极化.成都:电子科技大学出版社,1989.
[177]Guissard A.Mueller and Kennaugh matrices in radar polarimetry.IEEE Trans.on Geoscience and Remote Sensing,1994,32(3):590-597.
[178]Cloude S R.Special unitary groups in polarimetry theory.Proc.SPIE Conference on Polarization Analysis and Measurement Ⅱ,vol.2265,September 1994:292-303.
[179]Kostinski A B and Boerner W M.On foundations of radar polarimetry.IEEE Trans.on Antennas and Propagation,1986,AP-34(12):1395-1404.
[180]Lee J S,Hoppel K W,Mango S A,et al.Intensity and phase statistics of multilook polarimetric and interferometric SAR imagery.IEEE Trans.on Geoscience and Remote Sensing,1994,32(5):1017-1028.
[181]Lee J S,Schuler D L,Lang R H,et al.K-distribution for multi-look processed polarimetric SAR imagery.Proc.International Geoscience and Remote Sensing Symposium,Pasadena,California,USA,August 1994:2179-2181.
[182]Joughin Ⅰ R,Winebrenner D P,and Percival D B.Probability density functions for multilook polarimetric signatures.IEEE Trans.on Geoscience and Remote Sensing,1994,32(3):562-574.
[183]Vapnik V N著,许建华,张学工译.统计学习理论.北京:电子工业出版社,2004.
[184]Vapnik V N著,张学工译.统计学习理论的本质.北京:清华大学出版社,2000.
[185]Cristianini N,Shawe-Taylor J著,李国正等译.支持向量机导论.北京:电子工业出版社,2005.
[186]Cortes C and Vapnik V N.Support vector networks.Machine Learning,1995,20(3):273-297.
[187]Zhao Q and Principe J.Support vector machines for SAR automatic target recognition.IEEE Trans.on Aerospace and Electronic Systems,2001,37(2):643-654.
[188]边肇祺,张学工等编著.模式识别.北京:清华大学出版社,2000.
[189]Hsu C W and Lin C J.A comparison of methods for multi-class support vector machines.IEEE Trans.on Neural Networks,2002,13(2):415-425.
[190]Jain A and Zongker D.Feature selection:evaluation,application,and small sample performance.IEEE Trans.on Pattern Analysis and Machine Intelligence,1997,19(2):153-158.
[191]Liu H and Yu L.Toward integrating feature selection algorithms for classification and clustering.IEEE Trans.on Knowledge and Data Engineering,2005,17(4):491-502.
[192]Hall M A.Correlation-based feature selection for discrete and numeric class machine learning.Proc.International Conference on Machine Learning,San Francisco,USA,June 2000:359-366.
[193]Mitra P,Murthy C A,and Pal S K.Unsupervised feature selection using feature similarity.IEEE Trans.on Pattern Analysis and Machine Intelligence,2002,24(3):301-312.
[194]Caruana R and Freitag D.Greedy attribute selection.Proc.International Conference on Machine Learning,San Francisco,USA,July 1994:28-36.
[195]Dy J G and Brodley C E.Feature subset selection and order identification for unsupervised learning.Proc.International Conference on Machine Learning,San Francisco,USA,June 2000:247-254.
[196] Sindhwani V, Rakshit S, Deodhare D, et al. Feature selection in MLPs and SVMs based on maximum output information. IEEE Trans. on Geoscience and Remote Sensing, 2004, 15 (4): 937-948.
[197] Ng A Y. On feature selection: learning with exponentially many irrelevant features as training examples. Proc. International Conference on Machine Learning, Wisconsin, USA, July 1998: 404-412.
[198] Xing E, Jordan M, and Karp R. Feature selection for high-dimensional genomic microarray data. Proc. International Conference on Machine Learning, Massachusetts, USA, June 2001: 601-608.
[199] Das S. Filters, wrappers and a boosting-based hybrid for feature selection. Proc. International Conference on Machine Learning, Massachusetts, USA, June 2001: 74-81.
[200] Somol P and Pudil P. Oscillating search algorithms for feature selection. Proc. International Conference on Pattern Recognition, September 2000: 406-409.
[201] Narendra P M and Fukunaga K. A branch and bound algorithm for feature subset selection. IEEE Trans. on Computers, 1977, 26: 917-922.
[202] Pudil P, Novovicova J, and Kittler J. Floating search methods in feature selection. Pattern Recognition Letters, 1994, 15: 1119-1125.
[203] Kononenko I. Estimating attributes: analysis and extensions of RELIEF. Proc. European Conference on Machine Learning, Sicily, Italy, April 1994: 171-182.
[204] Lee J S, Grunes M R, Pottier E, et al. Segmentation of polarimetric SAR images. Proc. International Geoscience and Remote Sensing Symposium, Sydney, Australia, July 2001: 414-416.
[205] Geman S and Geman D. Stochastic relaxation, Gibbs distribution and the Bayesian restoration of images. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1984, PAMI-6 (6): 721-741.
[206] Kottke D P, Fiore P D, Brown K L, et al. A design for HMM-based SAR ATR. Proc. SPIE Conference on Algorithms for Synthetic Aperture Radar Imagery V, Orlando, Florida, USA, April 1998: 541-551.
[207] Besag J. On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society, 1986, B48 (3): 259-302.
[208] Fwu J K and Djuric P M. Unsupervised vector image segmentation by a tree structure-ICM algorithm. IEEE Trans. on Medical Imaging, 1996, 15 (6): 871-880.
[209] Rignot E, Chellappa R, and Dubois P. Unsupervised segmentation of polarimetric SAR data using the covariance matrix. IEEE Trans. on Geoscience and Remote Sensing, 1992, 30 (4): 697-705.
[210] Andreadis A, Benelli B, and Garzelli A. Detail-preserving segmentation of polarimetric SAR imagery. Proc. International Geoscience and Remote Sensing Symposium, Lincoln, Nebraska, USA, May 1996: 377-379.
[211] 章毓晋. 图像分割. 北京:科学出版社,2001.
[212] Yu Y J and Acton S T. Polarimetric SAR image segmentation using texture partitioning and statistical analysis. Proc. International Conference on Image Processing, September 2000: 677-680.
[213] Moreels P and Smrekar S E. Watershed identification of polygonal patterns in noisy SAR images. IEEE Trans. on Image Processing, 2003, 12 (7): 740-750.