极化SAR图像特征提取与分类方法研究
|
摘要
极化合成孔径雷达（PolSAR）利用不同极化方式交替发射与接收雷达信号，能够获得极为丰富的目标散射信息，已成为对地探测的重要工具。极化SAR的成功应用依赖于图像解译技术，极化SAR图像解译能够揭示极化SAR图像本质，为极化SAR系统的自动目标识别建立基础。然而由于研究起步较晚，目前极化SAR图像解译技术不够成熟，还不能满足军事与民用领域的需求。为此本文立足于极化SAR图像解译的两个关键问题——特征提取与分类，开展相应的研究工作。
本文研究工作包括极化SAR图像的特征提取与分类两大模块。首先，本文结合极化目标分解与非负特征值理论来开展特征提取的研究工作。其次，本文以极化特征与极化数据统计分布为基础，采用核函数、支持向量机（SVM）以及三重Markov场（TMF）对极化SAR图像分类进行系统研究。论文的主要内容可概括为如下五部分：
第一部分以Van Zyl工作为基础来构建非负特征值理论的知识体系。Van Zyl工作主要包括两点：推导得出表征目标散射机制的协方差矩阵是半正定的；提出非负特征值分解（NNED）模型，并给出在反射对称情况下NNED解法。然而VanZyl工作在理论与方法上需要系统地拓展。本文将Van Zyl工作与拓展工作统称为非负特征值理论，其中拓展工作包括：（1）将“极化矩阵应满足半正定性”命名为极化矩阵的非负特征值约束（NNEC），分析NNEC与NNED之间的关系，论述NNEC在极化目标分解中的作用；（2）解译NNED数学模型的物理意义，提出并证明NNED若干重要性质；（3）提出在非反射对称情况下NNED快速解法。非负特征值理论充实了极化SAR的基本理论，能为极化SAR信息处理的相关技术提供理论支持。本部分工作还将非负特征值理论用于确定子空间分解滤波的阈值，实测极化SAR数据实验验证了所提出的滤波方法能提高斑点噪声的抑制效果且能较好地保持边缘与点目标信息。
第二部分提出非负特征值理论的NNED后向策略，解决Freeman分解的失效问题。本部分主要工作有：（1）论述Freeman分解的有效性等价于余项满足NNEC，并分析已有方法（前向策略及其衍生策略）不能确保余项满足NNEC；（2）以非负特征值理论为基础，提出了NNED后向策略，从原理上分析NNED后向策略能确保余项满足NNEC，进而解决Freeman分解的失效问题；（3）将NNED后向策略应用于Freeman分解及其改进方法，提出了Freeman分解结合非负特征值理论的极化特征提取方法。实测极化SAR数据实验验证了相比于已有Freeman分解方法，所提出的特征提取方法能明显提高城区的二面角散射功率并抑制城区的体散射功率过估计。
第三部分提出非负特征值理论的NNED层次后向策略，并利用NNED后向策略与层次后向策略解决Yamaguchi分解的失效问题。本部分主要工作有：（1）理论分析与实验证实了Yamaguchi分解存在失效问题，指出通过确保余项满足NNEC来解决失效问题；（2）以非负特征值理论为基础，提出了改进的NNED后向策略——层次后向策略，它不仅能解决Yamaguchi分解的失效问题，而且能进一步减少余项功率；（3）将NNED后向策略及其层次后向策略分别应用于Yamaguchi分解及其改进方法，提出了Yamaguchi分解结合非负特征值理论的极化特征提取方法。实测极化SAR数据实验证实相比于已有Yamaguchi分解方法，所提出的特征提取方法能明显提高城区的二面角散射功率并抑制城区的体散射功率过估计，另外层次后向策略的余项功率明显低于后向策略的余项功率。
第四部分首先利用SVM分类方法来评测NNED后向策略与层次后向策略提取的散射功率对极化SAR图像分类的效果，实测极化SAR数据实验表明NNED后向策略与层次后向策略提取的散射功率有助于提高极化SAR图像分类的精度。其次，利用SVM与加权合成核来构建极化SAR图像分类方法，以提高基于SVM的极化SAR图像分类方法性能。构造加权合成核的关键是确定权重系数，本文通过训练样本在特征空间上的距离来确定核函数的权重系数。实测极化SAR数据实验验证了所构造的加权合成核能有效融合多种特征，提高基于SVM的极化SAR图像分类方法性能。
第五部分工作是将TMF及其改进模型应用于极化SAR图像分类，以提高基于MRF的极化SAR图像分类方法性能。本部分主要工作有：（1）分析极化SAR图像的非平稳特性，指出TMF适合处理极化SAR图像分类；（2）提出极化SAR图像分类的TMF模型及算法，利用实测极化SAR数据实验验证了TMF方法优于MRF方法；（3）分析TMF辅助场的局限性，定义了极化SAR图像的平滑特征，并将平滑特征融入到TMF模型提出了TMF-SAF模型，从原理上阐述了TMF-SAF能够克服TMF辅助场的局限性。实测极化SAR数据实验验证了极化SAR图像分类的TMF-SAF方法优于MRF与TMF方法。
Polarimetric synthetic aperture radar (PolSAR) alternately transmits and receivesradar signals in different polarization ways, and can obtain abundant information abouttargets scattering. Up to now, PolSAR has been being one of the most important toolsfor earth observation. Successful applications of PolSAR depend on imageinterpretation technology (IIT). IIT can reveal the nature of PolSAR image, and is thebasis of automatic target recognition (ATR) for PolSAR system. However PolSAR IIThas not met the requirement of military and civil affairs yet, since the start of PolSARIIT is late and its study is not mature. For PolSAR IIT to be well developed, we commitourselves to studying its two key issues: feature extraction and classification.
The body of this dissertation consists of two modules: feature extraction andclassification of PolSAR image. First, we study feature extraction of PolSAR imageusing polarimetric target decomposition (PTD) and non-negative eigenvalue theory(NNET). Second, based on polarization features and statistical distributions of PolSARdata, we study PolSAR image classification using kernel function, support vectormachines (SVM) and triplet Markov field (TMF). The main content of this dissertationconsists of five parts as follows:
In the first part, we construct a knowledge system of NNET which is based on VanZyl’s work. Van Zyl’s work concludes two points:1) he proves that covariance matrices,which can represent targets scattering mechanisms, are positive semi-definite;2) heproposes the model of non-negative eigenvalue decomposition (NNED), and gives thesolution to NNED in reflection symmetry case of PolSAR data. However Van Zyl’swork needs to be matured in theory. Van Zyl’s work and the complementary work in thisdissertation are called by a joint name: NNET. The complementary work consists ofthree aspects.1) The term that polarimetric matrices should satisfy positivesemi-definiteness is called non-negative eigenvalue constraint (NNEC); we analyze therelationship between NNEC and NNED, and introduce the function of NNEC on PTD.2) We interpret the physical meaning of the NNED model; propose and prove severalimportant properties of NNED.3) We propose a fast solution to NNED in non-reflectionsymmetry case of PolSAR data. NNET enriches the essential theory of PolSAR, and cansupport the related techniques of PolSAR information processing. In addition, we applyNNET to determine the threshold of subspace decomposition filter. Real PolSAR data experiments demonstrate that the proposed filter can enhance the speckles suppressionand retain the information of edges and point targets very well.
In the second part, NNED backward strategy (NNED-BS) of NNET is proposed,and the failure of Freeman decomposition (FD) is overcome. This part contributes tofeature extraction of PolSAR image in three aspects:1) we prove that the validity of FDis equivalent to that the remainder of FD satisfies NNEC. And we analyze that theexisting methods, NNED forward strategy (NNED-FS) and its derivation strategies,cannot ensure that the remainder satisfies NNEC.2) NNED-BS based on NNET isproposed. And we analyze that NNED-BS can ensure that the remainder satisfies NNEC,which demonstrates that NNED-BS can deal with the failure of FD.3) We applyNNED-BS to FD and its improved methods, and propose the feature extraction methodcombining FD and NNET. Real PolSAR data experiments show that compared with theexisting FDs, the proposed feature extraction method can greatly enhancedouble-bounce scattering powers and suppress the over-estimation of volume scatteringpowers.
In the third part, we propose NNED hierarchy backward strategy (NNED-HBS) ofNNET, and use NNED-BS and NNED-HBS to overcome the failure of Yamaguchidecomposition (YD), respectively. This part contributes to feature extraction of PolSARimage in three aspects:1) we analyze and prove that YD has the failure, and point outthat the failure can be dealt with if the remainder satisfies NNEC.2) Based on NNET,we propose the improved NNED-BS, viz. NNED-HBS. It can overcome the failureproblem of YD and further reduce the power of the remainder.3) NNED-BS andNNED-HBS are applied to YD and its improved methods, respectively. And then thefeature extraction method combining YD and NNET is proposed. Real PolSAR dataexperiments show that compared with the existing YDs, the proposed feature extractionmethod can greatly enhance double-bounce scattering powers and suppress theover-estimation of volume scattering powers, and in addition the remainder power ofNNED-HBS is much lower than that of NNED-BS.
The fourth part consists of two aspects. First, we use SVM to evaluate the effect ofscattering powers on PolSAR image classification. These scattering powers areextracted by NNED-BS or NNED-HBS. Real PolSAR data experiments demonstratethat these scattering powers are helpful to improve the accuracy of PolSAR imageclassification. Second, we use SVM and weight composite kernel (WCK) to propose aPolSAR image classification method. The proposed method can improve theperformance of PolSAR image classification based on SVM. The key of constructing WCK is to determine the weight coefficients, and these weight coefficients aredetermined by the distances between training samples in feature space. Real PolSARdata experiments show that WCK can efficiently fuse features, and enhance theperformance of PolSAR image classification based on SVM.
In the fifth part, we apply TMF and its improved model to PolSAR imageclassification, and improve the performance of PolSAR image classification based onMRF. This part contributes to PolSAR image classification in three aspects:1) weanalyze the nonstationary statistical property of PolSAR image, and point out that TMFis suitable for dealing with PolSAR image classification.2) We propose the model andalgorithm of TMF for PolSAR image classification. Real PolSAR data experimentsdemonstrate that TMF is superior to MRF for PolSAR image classification.3) Weanalyze the limitations of the auxiliary field of TMF. For the limitations to be overcome,we define a smoothness feature of PolSAR image, and add this feature into the TMFmodel to propose a Wishart TMF with a specific auxiliary field (TMF-SAF). In addition,we analyze that TMF-SAF can overcome the limitations in principle. Real PolSAR dataexperiments demonstrate that TMF-SAF is superior to both MRF and TMF for PolSARimage classification.
本文研究工作包括极化SAR图像的特征提取与分类两大模块。首先，本文结合极化目标分解与非负特征值理论来开展特征提取的研究工作。其次，本文以极化特征与极化数据统计分布为基础，采用核函数、支持向量机（SVM）以及三重Markov场（TMF）对极化SAR图像分类进行系统研究。论文的主要内容可概括为如下五部分：
第一部分以Van Zyl工作为基础来构建非负特征值理论的知识体系。Van Zyl工作主要包括两点：推导得出表征目标散射机制的协方差矩阵是半正定的；提出非负特征值分解（NNED）模型，并给出在反射对称情况下NNED解法。然而VanZyl工作在理论与方法上需要系统地拓展。本文将Van Zyl工作与拓展工作统称为非负特征值理论，其中拓展工作包括：（1）将“极化矩阵应满足半正定性”命名为极化矩阵的非负特征值约束（NNEC），分析NNEC与NNED之间的关系，论述NNEC在极化目标分解中的作用；（2）解译NNED数学模型的物理意义，提出并证明NNED若干重要性质；（3）提出在非反射对称情况下NNED快速解法。非负特征值理论充实了极化SAR的基本理论，能为极化SAR信息处理的相关技术提供理论支持。本部分工作还将非负特征值理论用于确定子空间分解滤波的阈值，实测极化SAR数据实验验证了所提出的滤波方法能提高斑点噪声的抑制效果且能较好地保持边缘与点目标信息。
第二部分提出非负特征值理论的NNED后向策略，解决Freeman分解的失效问题。本部分主要工作有：（1）论述Freeman分解的有效性等价于余项满足NNEC，并分析已有方法（前向策略及其衍生策略）不能确保余项满足NNEC；（2）以非负特征值理论为基础，提出了NNED后向策略，从原理上分析NNED后向策略能确保余项满足NNEC，进而解决Freeman分解的失效问题；（3）将NNED后向策略应用于Freeman分解及其改进方法，提出了Freeman分解结合非负特征值理论的极化特征提取方法。实测极化SAR数据实验验证了相比于已有Freeman分解方法，所提出的特征提取方法能明显提高城区的二面角散射功率并抑制城区的体散射功率过估计。
第三部分提出非负特征值理论的NNED层次后向策略，并利用NNED后向策略与层次后向策略解决Yamaguchi分解的失效问题。本部分主要工作有：（1）理论分析与实验证实了Yamaguchi分解存在失效问题，指出通过确保余项满足NNEC来解决失效问题；（2）以非负特征值理论为基础，提出了改进的NNED后向策略——层次后向策略，它不仅能解决Yamaguchi分解的失效问题，而且能进一步减少余项功率；（3）将NNED后向策略及其层次后向策略分别应用于Yamaguchi分解及其改进方法，提出了Yamaguchi分解结合非负特征值理论的极化特征提取方法。实测极化SAR数据实验证实相比于已有Yamaguchi分解方法，所提出的特征提取方法能明显提高城区的二面角散射功率并抑制城区的体散射功率过估计，另外层次后向策略的余项功率明显低于后向策略的余项功率。
第四部分首先利用SVM分类方法来评测NNED后向策略与层次后向策略提取的散射功率对极化SAR图像分类的效果，实测极化SAR数据实验表明NNED后向策略与层次后向策略提取的散射功率有助于提高极化SAR图像分类的精度。其次，利用SVM与加权合成核来构建极化SAR图像分类方法，以提高基于SVM的极化SAR图像分类方法性能。构造加权合成核的关键是确定权重系数，本文通过训练样本在特征空间上的距离来确定核函数的权重系数。实测极化SAR数据实验验证了所构造的加权合成核能有效融合多种特征，提高基于SVM的极化SAR图像分类方法性能。
第五部分工作是将TMF及其改进模型应用于极化SAR图像分类，以提高基于MRF的极化SAR图像分类方法性能。本部分主要工作有：（1）分析极化SAR图像的非平稳特性，指出TMF适合处理极化SAR图像分类；（2）提出极化SAR图像分类的TMF模型及算法，利用实测极化SAR数据实验验证了TMF方法优于MRF方法；（3）分析TMF辅助场的局限性，定义了极化SAR图像的平滑特征，并将平滑特征融入到TMF模型提出了TMF-SAF模型，从原理上阐述了TMF-SAF能够克服TMF辅助场的局限性。实测极化SAR数据实验验证了极化SAR图像分类的TMF-SAF方法优于MRF与TMF方法。
Polarimetric synthetic aperture radar (PolSAR) alternately transmits and receivesradar signals in different polarization ways, and can obtain abundant information abouttargets scattering. Up to now, PolSAR has been being one of the most important toolsfor earth observation. Successful applications of PolSAR depend on imageinterpretation technology (IIT). IIT can reveal the nature of PolSAR image, and is thebasis of automatic target recognition (ATR) for PolSAR system. However PolSAR IIThas not met the requirement of military and civil affairs yet, since the start of PolSARIIT is late and its study is not mature. For PolSAR IIT to be well developed, we commitourselves to studying its two key issues: feature extraction and classification.
The body of this dissertation consists of two modules: feature extraction andclassification of PolSAR image. First, we study feature extraction of PolSAR imageusing polarimetric target decomposition (PTD) and non-negative eigenvalue theory(NNET). Second, based on polarization features and statistical distributions of PolSARdata, we study PolSAR image classification using kernel function, support vectormachines (SVM) and triplet Markov field (TMF). The main content of this dissertationconsists of five parts as follows:
In the first part, we construct a knowledge system of NNET which is based on VanZyl’s work. Van Zyl’s work concludes two points:1) he proves that covariance matrices,which can represent targets scattering mechanisms, are positive semi-definite;2) heproposes the model of non-negative eigenvalue decomposition (NNED), and gives thesolution to NNED in reflection symmetry case of PolSAR data. However Van Zyl’swork needs to be matured in theory. Van Zyl’s work and the complementary work in thisdissertation are called by a joint name: NNET. The complementary work consists ofthree aspects.1) The term that polarimetric matrices should satisfy positivesemi-definiteness is called non-negative eigenvalue constraint (NNEC); we analyze therelationship between NNEC and NNED, and introduce the function of NNEC on PTD.2) We interpret the physical meaning of the NNED model; propose and prove severalimportant properties of NNED.3) We propose a fast solution to NNED in non-reflectionsymmetry case of PolSAR data. NNET enriches the essential theory of PolSAR, and cansupport the related techniques of PolSAR information processing. In addition, we applyNNET to determine the threshold of subspace decomposition filter. Real PolSAR data experiments demonstrate that the proposed filter can enhance the speckles suppressionand retain the information of edges and point targets very well.
In the second part, NNED backward strategy (NNED-BS) of NNET is proposed,and the failure of Freeman decomposition (FD) is overcome. This part contributes tofeature extraction of PolSAR image in three aspects:1) we prove that the validity of FDis equivalent to that the remainder of FD satisfies NNEC. And we analyze that theexisting methods, NNED forward strategy (NNED-FS) and its derivation strategies,cannot ensure that the remainder satisfies NNEC.2) NNED-BS based on NNET isproposed. And we analyze that NNED-BS can ensure that the remainder satisfies NNEC,which demonstrates that NNED-BS can deal with the failure of FD.3) We applyNNED-BS to FD and its improved methods, and propose the feature extraction methodcombining FD and NNET. Real PolSAR data experiments show that compared with theexisting FDs, the proposed feature extraction method can greatly enhancedouble-bounce scattering powers and suppress the over-estimation of volume scatteringpowers.
In the third part, we propose NNED hierarchy backward strategy (NNED-HBS) ofNNET, and use NNED-BS and NNED-HBS to overcome the failure of Yamaguchidecomposition (YD), respectively. This part contributes to feature extraction of PolSARimage in three aspects:1) we analyze and prove that YD has the failure, and point outthat the failure can be dealt with if the remainder satisfies NNEC.2) Based on NNET,we propose the improved NNED-BS, viz. NNED-HBS. It can overcome the failureproblem of YD and further reduce the power of the remainder.3) NNED-BS andNNED-HBS are applied to YD and its improved methods, respectively. And then thefeature extraction method combining YD and NNET is proposed. Real PolSAR dataexperiments show that compared with the existing YDs, the proposed feature extractionmethod can greatly enhance double-bounce scattering powers and suppress theover-estimation of volume scattering powers, and in addition the remainder power ofNNED-HBS is much lower than that of NNED-BS.
The fourth part consists of two aspects. First, we use SVM to evaluate the effect ofscattering powers on PolSAR image classification. These scattering powers areextracted by NNED-BS or NNED-HBS. Real PolSAR data experiments demonstratethat these scattering powers are helpful to improve the accuracy of PolSAR imageclassification. Second, we use SVM and weight composite kernel (WCK) to propose aPolSAR image classification method. The proposed method can improve theperformance of PolSAR image classification based on SVM. The key of constructing WCK is to determine the weight coefficients, and these weight coefficients aredetermined by the distances between training samples in feature space. Real PolSARdata experiments show that WCK can efficiently fuse features, and enhance theperformance of PolSAR image classification based on SVM.
In the fifth part, we apply TMF and its improved model to PolSAR imageclassification, and improve the performance of PolSAR image classification based onMRF. This part contributes to PolSAR image classification in three aspects:1) weanalyze the nonstationary statistical property of PolSAR image, and point out that TMFis suitable for dealing with PolSAR image classification.2) We propose the model andalgorithm of TMF for PolSAR image classification. Real PolSAR data experimentsdemonstrate that TMF is superior to MRF for PolSAR image classification.3) Weanalyze the limitations of the auxiliary field of TMF. For the limitations to be overcome,we define a smoothness feature of PolSAR image, and add this feature into the TMFmodel to propose a Wishart TMF with a specific auxiliary field (TMF-SAF). In addition,we analyze that TMF-SAF can overcome the limitations in principle. Real PolSAR dataexperiments demonstrate that TMF-SAF is superior to both MRF and TMF for PolSARimage classification.
引文
[1] Massonnet D, Souyris J C. Imaging with synthetic aperture radar [M]. BrokenSound Parkway, NW: EPFL Press,2008.
[2] Cumming I G, Wong F H. Digital processing of synthetic aperture radar data:algorithms and implementation [M]. Norwood, MA: Artech House,2005.
[3] Lee J S, Pottier E. Polarimetric radar imaging from basic to application [M]. NewYork: CRC Press,2011.
[4] Van Zyl J J, Kim Y. Synthetic aperture radar polarimetry [M]. California: JetPropulsion Laboratory,2011:85-155.
[5] Mott H(著),林昌禄(译).天线和雷达中的极化[M].成都:电子科技大学出版社,1989.
[6] Harold Mot(著),杨汝良(译).极化雷达遥感[M].北京：国防工业出版社.2008.
[7]黄培康,殷红成,许小剑.雷达目标特性[M].北京：电子工业出版社.2005.
[8] Tragl K. Polarimetric radar backscattering from reciprocal random targets [J].IEEE Transactions on Geoscience and Remote Sensing,1990,28(6):856–864.
[9]郭睿.极化SAR处理中若干问题的研究[D].西安:西安电子科技大学,2012.
[10]王海江.极化SAR图像分类方法研究[D].成都:电子科技大学,2005.
[11] Jordan R L, Huneycutt B L, Werner M. The SIR-C/X-SAR synthetic apertureradar system [J]. IEEE Transactions on Geoscience and Remote Sensing,1995,33(4):829-839.
[12] Ender H, Joachim G. Experimental results achieved with the airbornemulti-channel SAR system AER-II [J]. EUSAR,1998,2(1):315-318.
[13] http://sar.kangwon.ac.kr/polsar/PolSARpro_demo/
[14] Desnos Y L, Buck C, Guijarro J, et al. ASAR-Envisat’s advanced syntheticaperture radar-building on ERS achievements towards future earth watchmissions[J]. ESA Bull,2000,5(10):91-100.
[15]王文光.极化SAR信息处理技术研究[D].北京:北京航空航天大学,2007.
[16]汪洋.极化合成孔径雷达图像处理及其应用研究[D].合肥:安徽大学,2007.
[17]戴博伟.多极化合成孔径雷达系统与极化信息处理研究[D].北京:中国科学院电子学研究所,2000.
[18]王超.全极化合成孔径雷达图像处理[M].北京:科学出版社,2008.
[19] Pierce L E, Ulaby F T, Sarabandi K, et al. Knowledge-based classification ofpolarimetric SAR images [J]. IEEE Transactions on Geoscience and RemoteSensing,1994,32(5):1081-1086.
[20] Borghys D, Yvinec Y, Perneel C, et al. Supervised feature-based classification ofmulti-channel SAR images [J]. Pattern Recognition Letters,2006,27(4):252-258.
[21] Krogager E. Absolute phase of the radar target scattering matrix [J]. IETElectronic Letter,1990,26(22):1834-1835.
[22] Yang J, Peng Y N, Lin S M. Similarity between two scattering matrices [J]. IETElectronic Letter,2001,37(3):193-194.
[23] Kong J A, Schwartz A A, Yueh H A, et al. Identification of terrain cover using theoptimal polarimetric classifier [J]. J. Electromagn. Waves Applicat.,1998,2(2):171-194.
[24] Lee J S, Grunes M R, Pottier E. Quantitative comparison of classificationcapability: fully polarimetric versus dual and single-polarization SAR [J]. IEEETransactions on Geoscience and Remote Sensing,2001,39(11):2343-2351.
[25] Rignot E, Chellappa R. Segmentation of polarimetric synthetic aperture radar data[J]. IEEE Transaction on Image Processing,1992,1(3):281-300.
[26] Rignot E, Chellappa R, Dubois P. Unsupervised segmentation of polarimetric SARdata using the covariance matrix [J]. IEEE Transactions on Geoscience andRemote Sensing,1992,30(4):697-705.
[27] Dubois P C, Norikane L. Data volume reduction for imaging radar polarimetry [A].IGARSS [C]. CA: IEEE,1989.691–695.
[28] Goodman J W. Some fundamental properties of speckle [J]. J. Opt. Soc.Amer.,1976,66(11):1145–1150.
[29] Lee J S, Grunes M R. Classification of multi-look polarimetric SAR data based oncomplex Wishart distribution [A]. National Telesystems Conference [C].Washington, DC: IEEE,1992.721-724.
[30] Jao J K. Amplitude distribution of composite terrain radar clutter and the Kdistribution [J]. IEEE Transactions on Antennas Propagat.,1984,32(4):1049–1062.
[31] Lee J S, Schuler D L, Lang R H, et al. K distribution for multilook processedpolarimetric SAR imagery [A]. Int. Geosci. And Remote Sens. Symp.[C]. MA:IEEE,1994.2179–2181.
[32] Yu Y, Torre A, Huan S. Partially correlated K-distribution for multi-lookpolarimetric SAR imagery [A]. International Geoscience and Remote SensingSymposium [C]. Lincoln, NE: IEEE,1996.60-62.
[33] Frery A C, Cintra R J, Nascimento A. Entropy-based statistical analysis of PolSARdata [J]. IEEE Transactions on Geoscience and Remote Sensing,2013,51(6):3733-3743.
[34]周晓光.极化SAR图像分类方法研究[D].长沙:国防科学技术大学,2008.
[35]刘涛,黄高明,王雪松.极化SAR图像处理中L分布杂波统计分析[J].自然科学进展,2009,19(1):89-96.
[36] Bombrun L and Beaulieu J M. Fisher distribution for texture modeling ofpolarimetric SAR data [J]. IEEE Geoscience and Remote Sensing Letters,2008,5(3):512-516.
[37] Liu T, Huang G M, Wang X S, et al. Statistical assessment of H_A targetdecomposition theorems in radar polarimetry [J]. Science China,2010,53(2):355–366.
[38] Krogager E. New decomposition of the radar target scattering matrix [J]. IETElectronics Letters,1990,26(18):1525-1526.
[39] Cameron W L, Youssef N N, Leung L K. Simulated polarimetric signature ofprimitive geometrical shapes [J]. IEEE Transactions on Geoscience and RemoteSensing,1996,34(3):793-803.
[40] Touzi R, Charbonneau F. Characterization of symmetric scattering usingpolarimetric SARs [J]. IEEE Transactions on Geoscience and Remote Sensing,2002,40(11):2507-2516.
[41] Cloude S R, Pottier E. A review of target decomposition theorems in radarpolarimetry [J]. IEEE Transactions on Geoscience and Remote Sensing,1996,34(2):498-518.
[42] An W, Cui Y, Yang J, et al. Fast alternatives to H/α for polarimetric SAR [J].IEEE Geoscience and Remote Sensing Letters,2010,7(2):343-347.
[43] Freeman A, Durden S L. A three-component scattering model for polarimetricSAR data [J]. IEEE Transactions on Geoscience and Remote Sensing,1998,36(3):963-973.
[44] An W, Cui Y, Yang J. Three-component model-based decomposition forpolarimetric SAR data [J]. IEEE Transactions on Geoscience and Remote Sensing,2010,48(6):2732-2739.
[45] Van Zyl J J, Arii M, Kim Y. Model-based decomposition of polarimetric SARcovariance matrices constrained for nonnegative eigenvalues [J]. IEEETransactions on Geoscience and Remote Sensing,2011,49(9):3452-3459.
[46] Arii M, Van Zyl J J, Kim Y. A general characterization for polarimetric scatteringfrom vegetation canopies [J]. IEEE Transactions on Geoscience and RemoteSensing,2010,48(9):3349-3357.
[47] Arii M, Van Zyl J J, Kim Y. Adaptive model-based decomposition of polarimetricSAR covariance matrices [J]. IEEE Transactions on Geoscience and RemoteSensing,2011,49(3):1104-1113.
[48] Yamaguchi Y, Moriyama T, Ishido M, et al. Four-component scattering model forpolarimetric SAR image decomposition [J]. IEEE Transactions on Geoscience andRemote Sensing,2005,43(8):1699-1706.
[49] Yamaguchi Y, Yajima Y, Yamada H. A four-component decomposition ofPolSAR images based on the coherency matrix [J]. IEEE Geoscience and RemoteSensing Letters,2006,3(3):292-296.
[50] Yajima Y, Yamaguchi Y, Sato R, et al. PolSAR image analysis of wetlands usingmodified four-component scattering power decomposition [J]. IEEE Transactionson Geoscience and Remote Sensing,2008,46(6):1667-1673.
[51] Sato A, Yamaguchi Y, Singh G, et al. Four-component scattering powerdecomposition with extended volume scattering model [J]. IEEE Geoscience andRemote Sensing Letters,2012,9(2):166-170.
[52] Shan Z, Zhang H, Wang C, et al. Four-component model-based decomposition ofpolarimetric SAR data for special ground objects [J]. IEEE Geoscience andRemote Sensing Letters,2012,9(5):989-994.
[53] Yamaguchi Y, Sato A, Sato R, et al. Four-component scattering powerdecomposition with rotation of coherency matrix [J]. IEEE Transactions onGeoscience and Remote Sensing,2011,49(6):2251-2258.
[54] Bllagente M, Gamba P, Savazzi P. Fuzzy texture characterization of urbanenvironments by SAR data [A]. International Geoscience and Remote SensingSymposium [C]. Hamburg, German: IEEE,1999.1232-1234.
[55] Aiazzi B, Alparone L, Baronti S, et al. Land cover classification of built-up areasthrough enhanced fuzzy nearest-mean reclustering of textural features from X-andC-band polarimetric SAR data [A]. SPIE Conference on SAR Image Analysis,Modeling and Techniques [C]. Barcelona, Spain: IEEE,2003.105-115.
[56] Gonzalez R C, Woods R E. Digital image processing (third edition)[M]. Beijing,China: Publishing House of Electronics Industry,2012.
[57]吴永辉.极化SAR图像分类技术研究[D].长沙:国防科学技术大学,2007.
[58] Bourssou A, Pham K, Au W C, et al. Classification of a polarimetric SAR imageusing fractal concepts [A]. International Geoscience and Remote SensingSymposium [C]. Tokyo, Japan: IEEE,1993.1599-1602.
[59] Yu Y J, Acton S T. Polarimetric SAR image segmentation using texturepartitioning and statistical analysis [A]. International Conference on ImageProcessing [C]. Vancouver, BC: IEEE,2000.677-680.
[60]马秀丽,焦李成.基于分水岭谱聚类的SAR图像分割[J].红外与毫米波学报,2008,27(6):452-456.
[61] Yang W, Wang H, Cao Y F, et al. Classification of polarimetric SAR data basedon multidimensional watershed clustering [J]. Lecture Notes in Computer Science,2006,40(3):157-164.
[62] Alonso-González A, López-Martínez C, Salembier P. Filtering and segmentationof polarimetric SAR data based on binary partition trees [J]. IEEE Transactions onGeoscience and Remote Sensing,2012,50(2):593-605.
[63] Jiang Y, Zhang X L, Shi J. Unsupervised classification of polarimetric SAR Imageby Quad-tree Segment and SVM [A]. Asian and Pacific Conference on SyntheticAperture Radar [C]. Huangshan, China: IEEE,2007.480-483.
[64]吴婉澜.基于子孔径的极化SAR图像目标分类算法研究[D].成都:电子科技大学,2009.
[65]王贞俭.基于Contourlet能量标准差积的极化SAR图像融合[J].中国图象图形学报,2009,14(3):514-519.
[66]张德祥,吴小培,高清维.基于平稳Contourlet变换的极化SAR图像融合[J].电子科技大学学报,2010,39(2):200-203.
[67] Pottier E. Radar target decomposition theorems and unsupervised classification offull polarimetric SAR data [A]. International Geoscience and Remote SensingSymposium [C]. Pasadena, CA: IEEE,1994.1139-1141.
[68] Heermann P D, Khazenie N. Classification of multispectral remote sensing datausing a back-propagation neural network [J]. IEEE Transactions on Geoscienceand Remote Sensing,1992,30(1):81-88.
[69] Sebastiano B S, Fabio Roli. Classification of multisensory remote-sensing imagesby structured neural networks [J]. IEEE Transactions on Geoscience and RemoteSensing,1995,33(3):562-578.
[70] Bischof H, Schneider W, Pinz A J. Multispectral classification of lands-imagesusing neural networks [J]. IEEE Transactions on Geoscience and Remote Sensing,1992,30(3):482-490.
[71] Chen K S, Huang W P, Tsay D H, et al. Classification of multifrequencypolarimetric SAR imagery using learning neural network [J]. IEEE Transactionson Geoscience and Remote Sensing,1996,34(3):814-820.
[72] Hellmannl M, Jagerl G, Kratzschmar E, et al. Classification of full polarimetricSAR-data using artificial neural networks and fuzzy algorithms [A]. InternationalGeoscience and Remote Sensing Symposium [C]. Hamburg, German: IEEE,1995.1995-1997.
[73] Khan K U, Jian Y. Polarimetric synthetic aperture radar image classification by aHybrid method [J]. Tsinghua Science and Technology,2007,12(1):97-104.
[74] Fukuda S, Katagiri R, Hirosawa H. Unsupervised approach for polarimetric SARimage classification using support vector machines [A]. International Geoscienceand Remote Sensing Symposium [C]. Toronto, Canada: IEEE,2002.2599-2601.
[75] Li H T, Gu H Y, Han Y S, et al. Object-oriented classification of polarimetric SARimagery based on statistical region merging and support vector machine [A].International Workshop on Earth Observation and Remote Sensing Applications
[C]. Beijing, China: IEEE,2008.1-6.
[76] Zhang L, Zou B, Jia Q, et al. Polarimetric SAR image classification usingmultiple-component scattering model and support vector machine [A]. in Proc.2ndAsian-Pacific Conference on Synthetic Aperture Radar [C]. Xian, Shanxi: IEEE,2009.805-808.
[77] Chen L, Yang W, Liu Y, et al. Feature evaluation and selection for polarimetricSAR image classification [A]. International Conference on Signal Processing [C].Beijing, China: IEEE,2010.2202-2204.
[78] Lardeux C, Frison P L, Tison C, et al. Support vector machine for multi-frequencySAR polarimetric data classification [J]. IEEE Transactions on Geoscience andRemote Sensing,2009,47(12):4143-4152.
[79] Pottier E, Cloude S R. Unsupervised classification of full polarimetric SAR dataand feature vectors identification using radar target decomposition theorems andentropy analysis [A]. International Geoscience and Remote Sensing Symposium
[C]. Firenze, Italy: IEEE,1995.2247-2249.
[80] Krogager E. An entropy based classification scheme for land applications ofpolarimetric SAR [J]. IEEE Transactions on Geoscience and Remote Sensing,1997,35(1):68-78.
[81] Lee J S, Ainsworth T L, Grunes M R. Monte Carlo evaluation of multi-look effecton entropy alpha anisotropy parameters of polarimetric target decomposition [A].International Conference on Geoscience and Remote Sensing Symposium [C].Denver, CO: IEEE,2006.52-55.
[82] Pellizzeri T M, Lombardo P, Ferriero P, et al. Polarimetric SAR image processingWishart vs H_A_alpha segmentation and classification schemes [A]. InternationalGeoscience and Remote Sensing Symposium [C]. Toulouse, France: IEEE,2003.3976-3978.
[83] Lee J S, Grunes M R, Pottier E, et al. Unsupervised terrain classificationpreserving scattering characteristics [J]. IEEE Transactions on Geoscience andRemote Sensing,2004,42(4):722–731.
[84] Ainsworth T L, Kelly J P, Lee J S. Classification comparisons between dual-polcompact polarimetric and quad-pol SAR imagery [J]. Journal of Photogrammetryand Remote Sensing,2009,64(1):464-471.
[85] Van Zyl J J, Burnette C F. Bayesian classification of polarimetric SAR imagesusing adaptive a priori probabilities [J]. Int. J. Remote Sensing,1992,13(5):835-836.
[86] Lee J S, Grunes M R. Classification of multi-look polarimetric SAR imagery basedon complex Wishart distribution [J]. Int. J. Remote Sensing,1994,15(11):2299-2311.
[87] Lee J S, Grunes M R, Ainsworth T L, et al. Unsupervised classification usingpolarimetric decomposition and the complex Wishart classifier [J]. IEEETransactions on Geoscience and Remote Sensing,1999,37(5):2249-2258.
[88]林伟,王瑞霞,田铮.有限混合Wishart模型分类多视极化SAR图像[J].宇航学报,2009,30(4):1616-1619.
[89] Donald K A, David S, Rüdiger G. Improving PolSAR land cover classificationwith radiometric correction of the coherency matrix [J]. IEEE Journal of SelectedTopics in Applied Earth Observations and Remote Sensing,2012,5(3):848-855.
[90] Silva W B, Freitas C C, Sant’Anna S, et al. Classification of segments in PolSARimagery by minimum stochastic distances between Wishart distributions [J]. IEEEJournal of Selected Topics in Applied Earth Observations and Remote Sensing, tobe published.
[91] Dabboor M, Collins M J, Karathanassi V, et al. An unsupervised classificationapproach for polarimetric SAR data based on the Chernoff distance for complexWishart distribution [J]. IEEE Transactions on Geoscience and Remote Sensing, tobe published.
[92] Chen C H, Du Y. A multi-resolution wavelet analysis for SAR image segmentationusing statistical separability measures [A]. Part of the EUROPTO Conference onImage and Signal Processing for Remote Sensing [C]. Barcelona, Spain: IEEE,1998.104-110.
[93] Kouskoulas Y, Ulaby F T, Pierce L E. The Bayesian hierarchical classifier (BHC)and its application to short vegetation using multifrequency polarimetric SAR [J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(2):469-477.
[94] Ainsworth T L, Lee J S. Polarimetric SAR image classification employingsub-aperture polarimetric analysis [A]. IGARSS [C]. Seoul, Korea: IEEE,2005.48-50.
[95] Dong Y, Milne A K, Forster B C. Segmentation and classification of vegetatedareas using polarimetric SAR image data [J]. IEEE Transactions on Geoscienceand Remote Sensing,2001,39(2):321–329.
[96] Wu Y, Ji K, Yu W, et al. Region-based classification of polarimetric SAR imagesusing Wishart MRF [J]. IEEE Geoscience and Remote Sensing Letters,2008,5(4):668–672.
[1] Van Zyl J J, Arii M, Kim Y. Model-based decomposition of polarimetric SARcovariance matrices constrained for nonnegative eigenvalues [J]. IEEETransactions on Geoscience and Remote Sensing,2011,49(9):3452-3459.
[2] Van Zyl J J, Kim Y. Synthetic aperture radar polarimetry [M]. Hoboken, NJ: Wiley,2011.
[3] Lee J S, Ainsworth T L, and Wang Y. Generalized polarimetric model-baseddecompositions using incoherent scattering models [J]. IEEE Transactions onGeoscience and Remote Sensing, to be published.
[4]王超,张红,陈曦.全极化合成孔径雷达图像处理[M].北京:科学出版社,2008.
[5]周晓光.极化SAR图像分类方法研究[D].长沙:国防科学技术大学,2008.
[6] Harold Mot[著],杨汝良[译].极化雷达遥感[M].北京:国防工业出版社,2008.
[7]金亚秋,徐丰.极化散射与SAR遥感信息理论与方法[M].北京:科学出版社,2008.
[8]庄钊文,肖顺平,王雪松.雷达极化信息处理及其应用[M].北京:国防工业出版社.
[9]王之禹.全极化合成孔径雷达在地物分类领域的应用研究[D].北京:中科院电子所,1999.
[10]徐俊毅.极化雷达遥感图像分类研究[D].北京:清华大学,2002.
[11]汪洋.极化合成孔径雷达图像处理及其应用研究[D].合肥:安徽大学博士论文,2007.
[12] Lee J S, Pottier E. Polarimetric radar imaging from basic to application [M]. NewYork: CRC Press,2011.
[13] Alexander B, Kostinski K, Boerner W M. On foundation of radar polarimetry [J].IEEE Transactions on Antennas and Propagation,34(12):1395-1403.
[14] Guissard A. Mueller and Kennarugh matrices in Radar Polarimetry [J]. IEEETransactions on Geoscience and Remote Sensing,1992,32(3):590-597.
[15] Freeman A, Jakob J, Van Zyl J. Calibration of Stokes and scattering matrix formatpolarimetric SAR data [J]. IEEE Transactions on Geoscience and Remote Sensing,1990,30(3):531-539.
[16] Liu G F, Li M, Wang Y J, et al. Four-component scattering power decompositionof remainder coherency matrices constrained for nonnegative eigenvalues [J].IEEE Geoscience and Remote Sensing Letters, to be published.
[17]方保镕,周继东,李医民.矩阵论[M].北京:清华大学出版社,2005.
[18] Arii M, van Zyl J J, Kim Y. Adaptive model-based decomposition of polarimetricSAR covariance matrices [J]. IEEE Transactions on Geoscience and RemoteSensing,2011,49(3):1104-1113.
[19] Liu G F, Li M, Wang Y J, et al. Fast solution to nonnegative eigenvaluedecomposition for polarimetric SAR [J]. IET Electronics Letters,2013,49(6):419-420.
[20]周晓光,匡纲要,万建伟.多极化SAR图像斑点抑制综述[J].中国图象图形学报,2008,13(3):377-385.
[21] Gu J, Yang J, Zhang H. Speckle filtering in polarimetric SAR data based on thesubspace decomposition [J]. IEEE Transaction on Geoscience and Remote Sensing,2004,42(8):1635-1641.
[22] Yang J, Deng Q, Yue H, et al. Polarimetric whitening filter for POLSAR imagebased on subspace decomposition [J]. Journal of Systems Engineering andElectronics,2008,19(6):1121-1126.
[23] Liu G F, Li M, Wu Y, et al. A novel despeckling algorithm of polarimetric SARimage based on SNR and parameter-vector spectrum amendment [C]//IEEE CIEInternational Conference on Radar. Chengdu: IEEE Press,2011:1459–1462.
[24]刘高峰,李明,王亚军.基于非负特征值分解的极化SAR子空间分解滤波[J].计算机科学,2013,40(5):266-270.
[25]王庆香,李迪,张舞杰.基于多特征的SAR图像的无监督分割[J].计算机科学,2010,37(10):267-270.
[26]邓少平,李平湘,张继贤.基于乘积模型的极化SAR滤波[J].武汉大学学报（信息科学版）,2011,36(10):1168-1171.
[1] Freeman A and Durden S L. A three-component scattering model for polarimetricSAR data [J]. IEEE Transaction on Geoscience and Remote Sensing,1998,36(3):963-973.
[2] Huynen J R. Phenomological theory of radar targets [D]. Delft, Netherlands:Netherlands Tech. Univ,1970.
[3] Cloude S R, Pottier E. A review of target decomposition theorems in radarpolarimetry [J]. IEEE Transaction on Geoscience and Remote Sensing,1996,34(2):498-518.
[4] Durden S L, Klein J D, Zebker H A, et al. Polarimetric radar measurements of aforested area near Mt. Shasta [J]. IEEE Transaction on Geoscience and RemoteSensing,1991,29(6):444-450.
[5]王超,张红,陈曦.全极化合成孔径雷达图像处理[M].北京:科学出版社,2008.
[6] Lee J S, Ainsworth T L. Generalized polarimetric model-based decompositionsusing incoherent scattering models [J]. IEEE Transaction on Geoscience andRemote Sensing, to be published.
[7] Cui Y, Yamaguchi Y, Yang J. On complete model-based decomposition ofpolarimetric SAR coherency matrix data [J]. IEEE Transaction on Geoscience andRemote Sensing, to be published.
[8] Lee J S, Pottier E. Polarimetric radar imaging from basic to application [M]. NewYork: CRC Press,2011.
[9] Cloude S R. Polarisation: Applications in Remote Sensing [M]. New York: OxfordUniversity Press,2010.
[10] An W, Cui Y, Yang J. Three-component model-based decomposition forpolarimetric SAR data [J]. IEEE Transaction on Geoscience and Remote Sensing,2010,48(6):2732-2739.
[11] Cui Y, Yamaguchi Y, Yang J. Three-component power decomposition forpolarimetric SAR data based on adaptive volume scatter modeling [J]. RemoteSensing,2012,4(1):1559-1572.
[12] Singh G, Yamaguchi Y, Park S E. Hybrid Freeman/eigenvalue decompositionmethod with extended volume scattering model [J]. IEEE Geoscience and RemoteSensing Letters, to be published.
[13] Van Zyl J J, Kim Y. Synthetic aperture radar polarimetry [M]. Hoboken, NJ: Wiley,2011.
[14] Van Zyl J J, Arii M, Kim Y. Model-based decomposition of polarimetric SARcovariance matrices constrained for nonnegative eigenvalues [J]. IEEETransactions on Geoscience and Remote Sensing,2011,49(9):3452-3459.
[15] Arii M, van Zyl J J, Kim Y. Adaptive model-based decomposition of polarimetricSAR covariance matrices [J]. IEEE Transactions on Geoscience and RemoteSensing,2011,49(3):1104-1113.
[16] Liu G F, Li M, Wang Y J, et al. Four-component scattering power decompositionof remainder coherency matrices constrained for nonnegative eigenvalues [J].IEEE Geoscience and Remote Sensing Letters, to be published.
[17]刘高峰,李明,王亚军.一种新的基于非反射对称非负特征值分解的Freeman分解[J].电子与信息学报,2013,35(2):369-376.
[18]刘高峰,李明,王亚军.一种改进的极化SAR自适应非负特征值分解[J].电子与信息学报,2013,35(6):1449-1455.
[19] Durden S L, van Zyl J J, Zebker H A. Modeling and observation of the radarpolarization signature of forested areas [J]. IEEE Transactions on Geoscience andRemote Sensing,1989,27(5):290–301.
[20] Kajimoto M, Susaki J. Urban-area extraction from polarimetric SAR images usingpolarization orientation angle [J]. IEEE Geoscience and Remote Sensing Letters,2013,10(2):337-341.
[21] Lee J S, Krogager E. Polarimetric analysis of radar signature of a manmadestructure [J]. IEEE Geoscience and Remote Sensing Letters,2006,4(3):555-559.
[22]方保镕,周继东,李医民.矩阵论[M].北京:清华大学出版社,2005.
[23] Van Zyl J J. Application of Cloude’s target decomposition theorem to polarimetricimaging radar data [A]. Process SPIE Radar Polarimetry [C]. Pasadena, CA:1992.184–212.
[24] http://sar.kangwon.ac.kr/polsar/PolSARpro_demo/
[1] Yamaguchi Y, Moriyama T, Ishido M, et al. Four-component scattering model forpolarimetric SAR image decomposition [J]. IEEE Transactions on Geoscience andRemote Sensing,2005,43(8):1699-1706.
[2] Yang J. On theoretical problems in radar polarimetry [D]. Niigata, Japan: NiigataUniv., Graduate School Sci. Technol.,2000.
[3] Huynen J R. Phenomological theory of radar targets [D]. Delft, Netherlands:Netherlands Tech. Univ,1970.
[4] Cloude S R, Pottier E. A review of target decomposition theorems in radarpolarimetry [J]. IEEE Transaction on Geoscience and Remote Sensing,1996,34(2):498-518.
[5] Durden S L, Klein J D, Zebker H A, et al. Polarimetric radar measurements of aforested area near Mt. Shasta [J]. IEEE Transaction on Geoscience and RemoteSensing,1991,29(6):444-450.
[6]王超,张红,陈曦.全极化合成孔径雷达图像处理[M].北京:科学出版社,2008.
[7] Yamaguchi Y, Yajima Y, Yamada H. A four-component decomposition of PolSARimages based on the coherency matrix [J]. IEEE Geoscience and Remote SensingLetters,2006,3(3):292-296.
[8] Cloude S R. Polarisation: Applications in Remote Sensing [M]. New York: OxfordUniversity Press,2010.
[9] Yajima Y, Yamaguchi Y, Sato R, et al. PolSAR image analysis of wetlands using amodified four-component scattering power decomposition [J]. IEEE Transactionson Geoscience and Remote Sensing,2008,46(6):1667-1673.
[10] Yamaguchi Y, Sato A, Sato R,et al. Four-component scattering power decomposi-tion with rotation of coherency matrix [J]. IEEE Transactions on Geoscience andRemote Sensing,2011,49(6):2251-2258.
[11] Sato A, Yamaguchi Y, Singh G, et al. Four-component scattering power decomposi-tion with extended volume scattering model [J]. IEEE Geoscience and RemoteSensing Letters,2012,9(2):166-171.
[12] Van Zyl J J, Kim Y. Synthetic aperture radar polarimetry [M]. NJ: Wiley,2011.
[13] Liu G F, Li M, Wang Y J, et al. Four-component scattering power decompositionof remainder coherency matrices constrained for nonnegative eigenvalues [J].IEEE Geoscience and Remote Sensing Letters, to be published.
[14]刘高峰,李明,王亚军.基于层次非负特征值约束的Yamaguchi分解[J].电子与信息学报,2013,35(11):2678-2686.
[15] Tragl K. Polarimetric radar backscattering from reciprocal random targets [J].IEEE Transactions on Geoscience and Remote Sensing,1990,28(9):856-864.
[16] Krogager E. Aspects of polarimetric radar imaging [D]. Copenhagen: Danish Def.Res. Est.,1993.
[17] Lee J S, Krogager E, Ainsworth T L, et al. Polarimetric analysis of radar signatureof a manmade structure [J]. IEEE Geoscience and Remote Sensing Letters,2006,3(4):555-559.
[18] Singh G, Yamaguchi Y, Park S E. General four-component scattering powerdecomposition with unitary transformation of coherency matrix [J]. IEEETransactions on Geoscience and Remote Sensing,2013,51(5):2251-2258.
[19]方保镕,周继东,李医民.矩阵论[M].北京:清华大学出版社,2005.
[20] Arii M, van Zyl J J, Kim Y. Adaptive model-based decomposition of polarimetricSAR covariance matrices [J]. IEEE Transactions on Geoscience and RemoteSensing,2011,49(3):1104-1113.
[21] http://sar.kangwon.ac.kr/polsar/PolSARpro_demo/
[22] Lee J S, Pottier E. Polarimetric radar imaging from basic to application [M]. NewYork: CRC Press,2011.
[23] Li Y, Gong H, Wang Q. Adaptive enhancement with speckle reduction for SARimages using mirror-extended curvelet and PSO [A]. in Proc.2010InternationalConference on Pattern Recognition [C]. Istanbul, Turkey: IEEE,2010.4520-4523.
[24]金亚秋,徐丰.极化散射与SAR遥感信息理论与方法[M].北京:科学出版社,2008.
[1] Jiang Y, Zhang X L, Shi J. Unsupervised classification of polarimetric SAR Imageby Quad-tree Segment and SVM [A]. Asian and Pacific Conference on SyntheticAperture Radar [C]. Huangshan, China: IEEE,2007.480-483.
[2] Fukuda S, Katagiri R, Hirosawa H. Unsupervised approach for polarimetric SARimage classification using support vector machines [A]. International Geoscienceand Remote Sensing Symposium [C]. Toronto, Canada: IEEE,2002.2599-2601.
[3] Li H T, Gu H Y, Han Y S, et al. Object-oriented classification of polarimetric SARimagery based on statistical region merging and support vector machine [A].International Workshop on Earth Observation and Remote Sensing Applications[C]. Beijing, China: IEEE,2008.1-6.
[4] Zhang L, Zou B, Jia Q, et al. Polarimetric SAR image classification usingmultiple-component scattering model and support vector machine [A]. in Proc.2ndAsian-Pacific Conference on Synthetic Aperture Radar [C]. Xian, Shanxi: IEEE,2009.805-808.
[5] Zhang L, Zou B, Zhang J. Classification of Polarimetric SAR Image Based onSupport VectorMachine UsingMultiple-Component Scattering Model and TextureFeatures [J]. EURASIP Journal on Advances in Signal Processing,2010,9(5):1-9.
[6] Wu Z C, Ouyang Q D. SVM-and MRF-based method for contextual classificationof polarimetric SAR images [A]. IEEE IGARSS Proceedings [C]. Xian, Shanxi:IEEE,2011.818-821.
[7] Chen L, Yang W, Liu Y, et al. Feature evaluation and selection for polarimetricSAR image classification [A]. International Conference on Signal Processing [C].Beijing, China: IEEE,2010.2202-2204.
[8] Lardeux C, Frison P L, Tison C, et al. Support vector machine for multi-frequencySAR polarimetric data classification [J]. IEEE Transactions on Geoscience andRemote Sensing,2009,47(12):4143-4152.
[9]丁世飞,齐丙娟,谭红艳.支持向量机理论与算法研究综述[J].电子科技大学学报,2011,40(1):2-10.
[10]邓乃扬,田英杰.数据挖掘中的新方法——支持向量机[M].北京:科学出版社,2004.
[11]张莉.支撑矢量机与核方法研究[D].西安:西安电子科技大学,2002.
[12] Vapnik V N(著),张学工(译).统计学习理论的本质[M].北京：清华大学出版社,2000．
[13] Vapnik V N(著),许建华(译).统计学习理论[M].北京：电子工业出版社,2004．
[14]谢塞琴,沈福明,邱雪娜.基于支持向量机的人脸识别方法[J].计算机工程,2009,35(16):186-188.
[15] Gauwenberghs G. Incremental and decremental support vector machine [J].Machine Learning,2001,44(13):409-415.
[16] Tang Y, Jin B, Zhang Yan Q, et a1. Granular support vector machines for medicalbinary classification problems [A]. Proceedings of the IEEE CIBIB [C].Piscataway, HJ: IEEE Computationl Intelligence Society,2004.73-78.
[17]连可,黄建国,王厚军.一种基于遗传算法的SVM决蓑树多分类策略研究[J].电子学报,2008,36(8):1502-l507.
[18]李国正,王猛,曾华军.支持向量机导论[M].北京:电子工业出版社,2004.
[19] Jayadcva R，Khemchandan S C. Twin support vector machines for patternclassification [J]. IEEE Trans on Pattrern Analysis and Machine Intelligence,2007,29(5):905-910.
[20]王宏宇,糜仲春,梁晓艳.一种基于支持向量机回归的推荐算法[J].中国科学院研究生院学报,2007,24(6):742-748.
[21] John Taylor (著),赵玲玲(译).模式分析的核方法[M].北京:机械工业出版社,2006.
[22] Aizerman M, Braverman E, Rozonoer L. Theoretical foundations of the potentialfunction method in pattern recognition learning. Automantion and Remote Control,1964,25(1):821-837.
[23] Guo H，Wang W，Men C. Anovel learning model-kernel granular support vectormachine [A]. Proceeding of the eighth international conference on machinelearning and cybernetic [C]. Baoding: IEEE,2009.930-935.
[24] Richard D (著),李宏东(译).模式分类[M].北京:机械工业出版社,2010.
[25]黄凤岗,宋克欧.模式识别[M].哈尔滨:哈尔滨工程大学出版社,1998.
[26]沈清,汤霖.模式识别导论[M].长沙:国防科技大学出版社,1991.
[27] Damoulas T, Girolami M A. Pattern recognition with a Bayesian kernelcombination machine [J]. Pattern Recognition Letters,2009,30(1):46-54.
[28]郑大念.机器学习中的核方法研究[D].北京:清华大学,2006.
[29] Lanckriet G, Cristianini N, Bartlett P, et al. Learning the kernel matrix withsemide-niteprogramming [J]. The Journal of Machine Learning Research,2004,5(1):27-72.
[30] Vapnik V N. The nature of statistical learning theory [M]. Berlin: Springer,1995.
[31] Bennett K P, Momma M, Embrechts M J. MARK: a boosting algorithm forheterogeneous kernel models [A]. Proceedings of8th ACM-SIGKDD InternationalConference on Knowledge Discovery and Data Mining [C]. Edmonton, Canada:ACM,2002.24-31.
[32] Sonnenburg S, Ratsch G, Schafer C, et al. Large scale multiple kernel learning [J].The Journal of Machine Learning Research,2006,7(7):1531-1565
[33] Tu S T, Chen J Y, Yang W, et al. Laplacian eigenmaps based polarimetricdimensionality reduction for SAR image classification [J]. IEEE Transactions onGeoscience and Remote Sensing,2012,50(1):.170-179.
[34] Ince T, Kiranyaz S, Gabbouj M. Evolutionary RBF classifier for polarimetric SARimages [J]. Expert Systems with Applications:2012,39(9):4710–4717.
[35]刘高峰,李明,王亚军.基于层次非负特征值约束的Yamaguchi分解[J].电子与信息学报,35(11):2678-2686.
[36] Cloude S R, Pottier E. A review of target decomposition theorems in radarpolarimetry [J]. IEEE Transactions on Geoscience and Remote Sensing,1996,34(2):498-518.
[37] Camps-Valls G, Gomez-Chova L. Kernel-based framework for multitemporal andmultisource remote sensing data classification and change detection [J]. IEEETransactions on Geoscience and Remote Sensing,2008,46(6):1822-1835.
[38] Li G Q, Wen C Y, and Li Z L. Model-based online learning with kernels [J]. IEEETransactions on Neural Networks and Learning Systems,2013,24(3):356-369.
[39] http://sar.kangwon.ac.kr/polsar/PolSARpro_demo/
[40] Lee J S, Pottier E. Polarimetric radar imaging from basic to application [M]. NewYork: CRC Press,2011.
[41] Lee J S, Grunes M R, Ainsworth T L, et al. Unsupervised classification usingpolarimetric decomposition and the complex Wishart classifier [J]. IEEETransactions on Geoscience and Remote Sensing,1999,37(5):2249-2258.
[1] Benboudjema D, Pieczynski W. Unsupervised image segmentation using tripletMarkov fields [J]. Computer Vision and Image Understanding,2005,99(3):476-498.
[2] Benboudjema D, Pieczynski W. Unsupervised statistical segmentation ofnonstationary images using triplet Markov fields [J]. IEEE Trans. Pattern Anal.Mach. Intell.,2007,29(8):1367-1378.
[3] Lanchantin P, Lapuyade-Lahorgue J, Pieczynski W. Unsupervised segmentation oftriplet Markov chains hidden with long-memory noise [J]. Signal Processing,2008,88(10):1134-1151.
[4] Pieczynski W. EM and ICE in hidden and triplet Markov field [A]. StochasticModeling Techniques and Data Analysis International Conference [C]. Chania,Greece: ACM,2010.1-9.
[5] Lapuyade-Lahorgue J, Pieczynski W. Unsupervised segmentation of newsemi-Markov chains hidden with long dependence noise [J]. Signal Processing,2010,90(4):2899-2910.
[6] Lanchantin P, Lapuyade-Lahorgue J, Pieczynski W. Unsupervised segmentation ofrandomly switching data hidden with non-Gaussian correlated noise [J]. SignalProcessing,2011,91(5):163-175.
[7] Lapuyade-Lahorgue J, Pieczynski W. Unsupervised segmentation of hiddensemi-Markov non-stationary chains [J]. Signal Processing,2012,92(6):29-42.
[8] Wu Y, Li M, Zhang P, et al. Unsupervised multi-class segmentation of SAR imagesusing triplet Markov fields models based on edge penalty [J]. Pattern RecognitionLetters,2011,32(4):1532-1540.
[9] Zhang P, Li M, Wu Y, et al. Unsupervised multi-class segmentation of SAR imagesusing fuzzy triplet Markov fields model [J]. Pattern Recognition,2013,46(4):1-16.
[10] Zhang P, Li M, Wu Y, et al. SAR image multiclass segmentation using a multiscaleTMF model in wavelet domain [J]. IEEE Geoscience and Remote Sensing Letters,2012,9(6):1099-1104.
[11] Dong Y, Milne A K, Forster B C. Segmentation and classification of vegetatedareas using polarimetric SAR image data [J]. IEEE Transactions on Geoscienceand Remote Sensing,2001,39(2):321–329.
[12] Wu Y H, Ji K, Yu W, et al. Region-based classification of polarimetric SAR imagesusing Wishart MRF [J]. IEEE Geoscience and Remote Sensing Letters,2008,5(4):668-672.
[13] Liu G F, Li M, Wu Y, et al. PolSAR Image Classification Based on Wishart TMFWith Specific Auxiliary Field [J]. IEEE Geoscience and Remote Sensing Letters,to be published.
[14] Li S Z. Markov random field modeling in image analysis [M]. London, British:Springer-Verlag,2009.
[15]黄宇,付琨,吴一戎.基于Markov随机场K-Means图像分割算法[J].电子学报,2009,37(12):2700-2705.
[16]宋晓峰,王爽,刘芳.基于区域MRF和贝叶斯置信传播的SAR图像分割[J].电子学报,2010,38(12):2810-2817.
[17] Boudaren M Y, Monfrini E, Pieczynski W. Unsupervised segmentation of randomdiscrete data hidden with switching noise distributions [J]. IEEE Signal ProcessingLetters,2012,19(10):619-622.
[18]张鹏.基于统计模型的SAR图像降斑和分割方法研究[D].西安:西安电子科技大学,2012.
[19] Derin H, Elliott H. Modeling and segmentation of noisy and textured images usingGibbs random fields [J]. IEEE Trans. Pattern Anal. Machine Intell.,1987,PAMI-9(1):39-55.
[20]李旭超,朱善安.图像分割中的马尔可夫随机场方法综述[J].中国图象图形学报,2007,12(5):789-801.
[21] Lee J S and Pottier E. Polarimetric Radar Imaging from Basic to Application [M].New York: CRC Press,2011:1-30,160-175.
[22] Van Zyl J J and Kim Y. Synthetic Aperture Radar Polarimetry [M]. California: JetPropulsion Laboratory,2011:85-155.
[23]赵力文,周晓光,蒋咏梅.一种基于Freeman分解与散射熵的极化SAR图像迭代分类方法[J].电子与信息学报,2008,30(11):2698-2701.
[24] Zhao Li-wen, Zhou Xiao-guang, and Jiang Yong-mei. Iterative classification ofpolarimetric SAR image based on Freeman decomposition and scattering entropy[J]. Journal of Electronics＆Information Technology,2008,30(11):2698-2701.
[25] Chen Q, Kuang G Y, Li J, et al.. Unsupervised land cover/land use classificationusing PolSAR imagery based on scattering similarity [J]. IEEE Transaction onGeoscience and Remote Sensing,2013,51(3):1817-1825.
[26] Liu B, Hu H, Wang H Y, et al.. Superpixel-based classification with an adaptivenumber of classes for polarimetric SAR images [J]. IEEE Transaction onGeoscience and Remote Sensing,2013,51(2):907-924.
[27] Lee J S, Grunes M R, Kwok R. Classification of multi-look polarimetric SARimagery based on the complex Wishart distribution [J]. Int. J. Remote Sens.,1994,15(11):2299-2311.
[28] Richard D (著),李宏东(译).模式分类[M].北京:机械工业出版社,2010.
[29] http://sar.kangwon.ac.kr/polsar/PolSARpro_demo/
[30] Gonzalez R C, R. E. Woods. Digital image processing third edition [M]. Beijing,China: Publishing House of Electronics Industry,2012.
[2] Cumming I G, Wong F H. Digital processing of synthetic aperture radar data:algorithms and implementation [M]. Norwood, MA: Artech House,2005.
[3] Lee J S, Pottier E. Polarimetric radar imaging from basic to application [M]. NewYork: CRC Press,2011.
[4] Van Zyl J J, Kim Y. Synthetic aperture radar polarimetry [M]. California: JetPropulsion Laboratory,2011:85-155.
[5] Mott H(著),林昌禄(译).天线和雷达中的极化[M].成都:电子科技大学出版社,1989.
[6] Harold Mot(著),杨汝良(译).极化雷达遥感[M].北京：国防工业出版社.2008.
[7]黄培康,殷红成,许小剑.雷达目标特性[M].北京：电子工业出版社.2005.
[8] Tragl K. Polarimetric radar backscattering from reciprocal random targets [J].IEEE Transactions on Geoscience and Remote Sensing,1990,28(6):856–864.
[9]郭睿.极化SAR处理中若干问题的研究[D].西安:西安电子科技大学,2012.
[10]王海江.极化SAR图像分类方法研究[D].成都:电子科技大学,2005.
[11] Jordan R L, Huneycutt B L, Werner M. The SIR-C/X-SAR synthetic apertureradar system [J]. IEEE Transactions on Geoscience and Remote Sensing,1995,33(4):829-839.
[12] Ender H, Joachim G. Experimental results achieved with the airbornemulti-channel SAR system AER-II [J]. EUSAR,1998,2(1):315-318.
[13] http://sar.kangwon.ac.kr/polsar/PolSARpro_demo/
[14] Desnos Y L, Buck C, Guijarro J, et al. ASAR-Envisat’s advanced syntheticaperture radar-building on ERS achievements towards future earth watchmissions[J]. ESA Bull,2000,5(10):91-100.
[15]王文光.极化SAR信息处理技术研究[D].北京:北京航空航天大学,2007.
[16]汪洋.极化合成孔径雷达图像处理及其应用研究[D].合肥:安徽大学,2007.
[17]戴博伟.多极化合成孔径雷达系统与极化信息处理研究[D].北京:中国科学院电子学研究所,2000.
[18]王超.全极化合成孔径雷达图像处理[M].北京:科学出版社,2008.
[19] Pierce L E, Ulaby F T, Sarabandi K, et al. Knowledge-based classification ofpolarimetric SAR images [J]. IEEE Transactions on Geoscience and RemoteSensing,1994,32(5):1081-1086.
[20] Borghys D, Yvinec Y, Perneel C, et al. Supervised feature-based classification ofmulti-channel SAR images [J]. Pattern Recognition Letters,2006,27(4):252-258.
[21] Krogager E. Absolute phase of the radar target scattering matrix [J]. IETElectronic Letter,1990,26(22):1834-1835.
[22] Yang J, Peng Y N, Lin S M. Similarity between two scattering matrices [J]. IETElectronic Letter,2001,37(3):193-194.
[23] Kong J A, Schwartz A A, Yueh H A, et al. Identification of terrain cover using theoptimal polarimetric classifier [J]. J. Electromagn. Waves Applicat.,1998,2(2):171-194.
[24] Lee J S, Grunes M R, Pottier E. Quantitative comparison of classificationcapability: fully polarimetric versus dual and single-polarization SAR [J]. IEEETransactions on Geoscience and Remote Sensing,2001,39(11):2343-2351.
[25] Rignot E, Chellappa R. Segmentation of polarimetric synthetic aperture radar data[J]. IEEE Transaction on Image Processing,1992,1(3):281-300.
[26] Rignot E, Chellappa R, Dubois P. Unsupervised segmentation of polarimetric SARdata using the covariance matrix [J]. IEEE Transactions on Geoscience andRemote Sensing,1992,30(4):697-705.
[27] Dubois P C, Norikane L. Data volume reduction for imaging radar polarimetry [A].IGARSS [C]. CA: IEEE,1989.691–695.
[28] Goodman J W. Some fundamental properties of speckle [J]. J. Opt. Soc.Amer.,1976,66(11):1145–1150.
[29] Lee J S, Grunes M R. Classification of multi-look polarimetric SAR data based oncomplex Wishart distribution [A]. National Telesystems Conference [C].Washington, DC: IEEE,1992.721-724.
[30] Jao J K. Amplitude distribution of composite terrain radar clutter and the Kdistribution [J]. IEEE Transactions on Antennas Propagat.,1984,32(4):1049–1062.
[31] Lee J S, Schuler D L, Lang R H, et al. K distribution for multilook processedpolarimetric SAR imagery [A]. Int. Geosci. And Remote Sens. Symp.[C]. MA:IEEE,1994.2179–2181.
[32] Yu Y, Torre A, Huan S. Partially correlated K-distribution for multi-lookpolarimetric SAR imagery [A]. International Geoscience and Remote SensingSymposium [C]. Lincoln, NE: IEEE,1996.60-62.
[33] Frery A C, Cintra R J, Nascimento A. Entropy-based statistical analysis of PolSARdata [J]. IEEE Transactions on Geoscience and Remote Sensing,2013,51(6):3733-3743.
[34]周晓光.极化SAR图像分类方法研究[D].长沙:国防科学技术大学,2008.
[35]刘涛,黄高明,王雪松.极化SAR图像处理中L分布杂波统计分析[J].自然科学进展,2009,19(1):89-96.
[36] Bombrun L and Beaulieu J M. Fisher distribution for texture modeling ofpolarimetric SAR data [J]. IEEE Geoscience and Remote Sensing Letters,2008,5(3):512-516.
[37] Liu T, Huang G M, Wang X S, et al. Statistical assessment of H_A targetdecomposition theorems in radar polarimetry [J]. Science China,2010,53(2):355–366.
[38] Krogager E. New decomposition of the radar target scattering matrix [J]. IETElectronics Letters,1990,26(18):1525-1526.
[39] Cameron W L, Youssef N N, Leung L K. Simulated polarimetric signature ofprimitive geometrical shapes [J]. IEEE Transactions on Geoscience and RemoteSensing,1996,34(3):793-803.
[40] Touzi R, Charbonneau F. Characterization of symmetric scattering usingpolarimetric SARs [J]. IEEE Transactions on Geoscience and Remote Sensing,2002,40(11):2507-2516.
[41] Cloude S R, Pottier E. A review of target decomposition theorems in radarpolarimetry [J]. IEEE Transactions on Geoscience and Remote Sensing,1996,34(2):498-518.
[42] An W, Cui Y, Yang J, et al. Fast alternatives to H/α for polarimetric SAR [J].IEEE Geoscience and Remote Sensing Letters,2010,7(2):343-347.
[43] Freeman A, Durden S L. A three-component scattering model for polarimetricSAR data [J]. IEEE Transactions on Geoscience and Remote Sensing,1998,36(3):963-973.
[44] An W, Cui Y, Yang J. Three-component model-based decomposition forpolarimetric SAR data [J]. IEEE Transactions on Geoscience and Remote Sensing,2010,48(6):2732-2739.
[45] Van Zyl J J, Arii M, Kim Y. Model-based decomposition of polarimetric SARcovariance matrices constrained for nonnegative eigenvalues [J]. IEEETransactions on Geoscience and Remote Sensing,2011,49(9):3452-3459.
[46] Arii M, Van Zyl J J, Kim Y. A general characterization for polarimetric scatteringfrom vegetation canopies [J]. IEEE Transactions on Geoscience and RemoteSensing,2010,48(9):3349-3357.
[47] Arii M, Van Zyl J J, Kim Y. Adaptive model-based decomposition of polarimetricSAR covariance matrices [J]. IEEE Transactions on Geoscience and RemoteSensing,2011,49(3):1104-1113.
[48] Yamaguchi Y, Moriyama T, Ishido M, et al. Four-component scattering model forpolarimetric SAR image decomposition [J]. IEEE Transactions on Geoscience andRemote Sensing,2005,43(8):1699-1706.
[49] Yamaguchi Y, Yajima Y, Yamada H. A four-component decomposition ofPolSAR images based on the coherency matrix [J]. IEEE Geoscience and RemoteSensing Letters,2006,3(3):292-296.
[50] Yajima Y, Yamaguchi Y, Sato R, et al. PolSAR image analysis of wetlands usingmodified four-component scattering power decomposition [J]. IEEE Transactionson Geoscience and Remote Sensing,2008,46(6):1667-1673.
[51] Sato A, Yamaguchi Y, Singh G, et al. Four-component scattering powerdecomposition with extended volume scattering model [J]. IEEE Geoscience andRemote Sensing Letters,2012,9(2):166-170.
[52] Shan Z, Zhang H, Wang C, et al. Four-component model-based decomposition ofpolarimetric SAR data for special ground objects [J]. IEEE Geoscience andRemote Sensing Letters,2012,9(5):989-994.
[53] Yamaguchi Y, Sato A, Sato R, et al. Four-component scattering powerdecomposition with rotation of coherency matrix [J]. IEEE Transactions onGeoscience and Remote Sensing,2011,49(6):2251-2258.
[54] Bllagente M, Gamba P, Savazzi P. Fuzzy texture characterization of urbanenvironments by SAR data [A]. International Geoscience and Remote SensingSymposium [C]. Hamburg, German: IEEE,1999.1232-1234.
[55] Aiazzi B, Alparone L, Baronti S, et al. Land cover classification of built-up areasthrough enhanced fuzzy nearest-mean reclustering of textural features from X-andC-band polarimetric SAR data [A]. SPIE Conference on SAR Image Analysis,Modeling and Techniques [C]. Barcelona, Spain: IEEE,2003.105-115.
[56] Gonzalez R C, Woods R E. Digital image processing (third edition)[M]. Beijing,China: Publishing House of Electronics Industry,2012.
[57]吴永辉.极化SAR图像分类技术研究[D].长沙:国防科学技术大学,2007.
[58] Bourssou A, Pham K, Au W C, et al. Classification of a polarimetric SAR imageusing fractal concepts [A]. International Geoscience and Remote SensingSymposium [C]. Tokyo, Japan: IEEE,1993.1599-1602.
[59] Yu Y J, Acton S T. Polarimetric SAR image segmentation using texturepartitioning and statistical analysis [A]. International Conference on ImageProcessing [C]. Vancouver, BC: IEEE,2000.677-680.
[60]马秀丽,焦李成.基于分水岭谱聚类的SAR图像分割[J].红外与毫米波学报,2008,27(6):452-456.
[61] Yang W, Wang H, Cao Y F, et al. Classification of polarimetric SAR data basedon multidimensional watershed clustering [J]. Lecture Notes in Computer Science,2006,40(3):157-164.
[62] Alonso-González A, López-Martínez C, Salembier P. Filtering and segmentationof polarimetric SAR data based on binary partition trees [J]. IEEE Transactions onGeoscience and Remote Sensing,2012,50(2):593-605.
[63] Jiang Y, Zhang X L, Shi J. Unsupervised classification of polarimetric SAR Imageby Quad-tree Segment and SVM [A]. Asian and Pacific Conference on SyntheticAperture Radar [C]. Huangshan, China: IEEE,2007.480-483.
[64]吴婉澜.基于子孔径的极化SAR图像目标分类算法研究[D].成都:电子科技大学,2009.
[65]王贞俭.基于Contourlet能量标准差积的极化SAR图像融合[J].中国图象图形学报,2009,14(3):514-519.
[66]张德祥,吴小培,高清维.基于平稳Contourlet变换的极化SAR图像融合[J].电子科技大学学报,2010,39(2):200-203.
[67] Pottier E. Radar target decomposition theorems and unsupervised classification offull polarimetric SAR data [A]. International Geoscience and Remote SensingSymposium [C]. Pasadena, CA: IEEE,1994.1139-1141.
[68] Heermann P D, Khazenie N. Classification of multispectral remote sensing datausing a back-propagation neural network [J]. IEEE Transactions on Geoscienceand Remote Sensing,1992,30(1):81-88.
[69] Sebastiano B S, Fabio Roli. Classification of multisensory remote-sensing imagesby structured neural networks [J]. IEEE Transactions on Geoscience and RemoteSensing,1995,33(3):562-578.
[70] Bischof H, Schneider W, Pinz A J. Multispectral classification of lands-imagesusing neural networks [J]. IEEE Transactions on Geoscience and Remote Sensing,1992,30(3):482-490.
[71] Chen K S, Huang W P, Tsay D H, et al. Classification of multifrequencypolarimetric SAR imagery using learning neural network [J]. IEEE Transactionson Geoscience and Remote Sensing,1996,34(3):814-820.
[72] Hellmannl M, Jagerl G, Kratzschmar E, et al. Classification of full polarimetricSAR-data using artificial neural networks and fuzzy algorithms [A]. InternationalGeoscience and Remote Sensing Symposium [C]. Hamburg, German: IEEE,1995.1995-1997.
[73] Khan K U, Jian Y. Polarimetric synthetic aperture radar image classification by aHybrid method [J]. Tsinghua Science and Technology,2007,12(1):97-104.
[74] Fukuda S, Katagiri R, Hirosawa H. Unsupervised approach for polarimetric SARimage classification using support vector machines [A]. International Geoscienceand Remote Sensing Symposium [C]. Toronto, Canada: IEEE,2002.2599-2601.
[75] Li H T, Gu H Y, Han Y S, et al. Object-oriented classification of polarimetric SARimagery based on statistical region merging and support vector machine [A].International Workshop on Earth Observation and Remote Sensing Applications
[C]. Beijing, China: IEEE,2008.1-6.
[76] Zhang L, Zou B, Jia Q, et al. Polarimetric SAR image classification usingmultiple-component scattering model and support vector machine [A]. in Proc.2ndAsian-Pacific Conference on Synthetic Aperture Radar [C]. Xian, Shanxi: IEEE,2009.805-808.
[77] Chen L, Yang W, Liu Y, et al. Feature evaluation and selection for polarimetricSAR image classification [A]. International Conference on Signal Processing [C].Beijing, China: IEEE,2010.2202-2204.
[78] Lardeux C, Frison P L, Tison C, et al. Support vector machine for multi-frequencySAR polarimetric data classification [J]. IEEE Transactions on Geoscience andRemote Sensing,2009,47(12):4143-4152.
[79] Pottier E, Cloude S R. Unsupervised classification of full polarimetric SAR dataand feature vectors identification using radar target decomposition theorems andentropy analysis [A]. International Geoscience and Remote Sensing Symposium
[C]. Firenze, Italy: IEEE,1995.2247-2249.
[80] Krogager E. An entropy based classification scheme for land applications ofpolarimetric SAR [J]. IEEE Transactions on Geoscience and Remote Sensing,1997,35(1):68-78.
[81] Lee J S, Ainsworth T L, Grunes M R. Monte Carlo evaluation of multi-look effecton entropy alpha anisotropy parameters of polarimetric target decomposition [A].International Conference on Geoscience and Remote Sensing Symposium [C].Denver, CO: IEEE,2006.52-55.
[82] Pellizzeri T M, Lombardo P, Ferriero P, et al. Polarimetric SAR image processingWishart vs H_A_alpha segmentation and classification schemes [A]. InternationalGeoscience and Remote Sensing Symposium [C]. Toulouse, France: IEEE,2003.3976-3978.
[83] Lee J S, Grunes M R, Pottier E, et al. Unsupervised terrain classificationpreserving scattering characteristics [J]. IEEE Transactions on Geoscience andRemote Sensing,2004,42(4):722–731.
[84] Ainsworth T L, Kelly J P, Lee J S. Classification comparisons between dual-polcompact polarimetric and quad-pol SAR imagery [J]. Journal of Photogrammetryand Remote Sensing,2009,64(1):464-471.
[85] Van Zyl J J, Burnette C F. Bayesian classification of polarimetric SAR imagesusing adaptive a priori probabilities [J]. Int. J. Remote Sensing,1992,13(5):835-836.
[86] Lee J S, Grunes M R. Classification of multi-look polarimetric SAR imagery basedon complex Wishart distribution [J]. Int. J. Remote Sensing,1994,15(11):2299-2311.
[87] Lee J S, Grunes M R, Ainsworth T L, et al. Unsupervised classification usingpolarimetric decomposition and the complex Wishart classifier [J]. IEEETransactions on Geoscience and Remote Sensing,1999,37(5):2249-2258.
[88]林伟,王瑞霞,田铮.有限混合Wishart模型分类多视极化SAR图像[J].宇航学报,2009,30(4):1616-1619.
[89] Donald K A, David S, Rüdiger G. Improving PolSAR land cover classificationwith radiometric correction of the coherency matrix [J]. IEEE Journal of SelectedTopics in Applied Earth Observations and Remote Sensing,2012,5(3):848-855.
[90] Silva W B, Freitas C C, Sant’Anna S, et al. Classification of segments in PolSARimagery by minimum stochastic distances between Wishart distributions [J]. IEEEJournal of Selected Topics in Applied Earth Observations and Remote Sensing, tobe published.
[91] Dabboor M, Collins M J, Karathanassi V, et al. An unsupervised classificationapproach for polarimetric SAR data based on the Chernoff distance for complexWishart distribution [J]. IEEE Transactions on Geoscience and Remote Sensing, tobe published.
[92] Chen C H, Du Y. A multi-resolution wavelet analysis for SAR image segmentationusing statistical separability measures [A]. Part of the EUROPTO Conference onImage and Signal Processing for Remote Sensing [C]. Barcelona, Spain: IEEE,1998.104-110.
[93] Kouskoulas Y, Ulaby F T, Pierce L E. The Bayesian hierarchical classifier (BHC)and its application to short vegetation using multifrequency polarimetric SAR [J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(2):469-477.
[94] Ainsworth T L, Lee J S. Polarimetric SAR image classification employingsub-aperture polarimetric analysis [A]. IGARSS [C]. Seoul, Korea: IEEE,2005.48-50.
[95] Dong Y, Milne A K, Forster B C. Segmentation and classification of vegetatedareas using polarimetric SAR image data [J]. IEEE Transactions on Geoscienceand Remote Sensing,2001,39(2):321–329.
[96] Wu Y, Ji K, Yu W, et al. Region-based classification of polarimetric SAR imagesusing Wishart MRF [J]. IEEE Geoscience and Remote Sensing Letters,2008,5(4):668–672.
[1] Van Zyl J J, Arii M, Kim Y. Model-based decomposition of polarimetric SARcovariance matrices constrained for nonnegative eigenvalues [J]. IEEETransactions on Geoscience and Remote Sensing,2011,49(9):3452-3459.
[2] Van Zyl J J, Kim Y. Synthetic aperture radar polarimetry [M]. Hoboken, NJ: Wiley,2011.
[3] Lee J S, Ainsworth T L, and Wang Y. Generalized polarimetric model-baseddecompositions using incoherent scattering models [J]. IEEE Transactions onGeoscience and Remote Sensing, to be published.
[4]王超,张红,陈曦.全极化合成孔径雷达图像处理[M].北京:科学出版社,2008.
[5]周晓光.极化SAR图像分类方法研究[D].长沙:国防科学技术大学,2008.
[6] Harold Mot[著],杨汝良[译].极化雷达遥感[M].北京:国防工业出版社,2008.
[7]金亚秋,徐丰.极化散射与SAR遥感信息理论与方法[M].北京:科学出版社,2008.
[8]庄钊文,肖顺平,王雪松.雷达极化信息处理及其应用[M].北京:国防工业出版社.
[9]王之禹.全极化合成孔径雷达在地物分类领域的应用研究[D].北京:中科院电子所,1999.
[10]徐俊毅.极化雷达遥感图像分类研究[D].北京:清华大学,2002.
[11]汪洋.极化合成孔径雷达图像处理及其应用研究[D].合肥:安徽大学博士论文,2007.
[12] Lee J S, Pottier E. Polarimetric radar imaging from basic to application [M]. NewYork: CRC Press,2011.
[13] Alexander B, Kostinski K, Boerner W M. On foundation of radar polarimetry [J].IEEE Transactions on Antennas and Propagation,34(12):1395-1403.
[14] Guissard A. Mueller and Kennarugh matrices in Radar Polarimetry [J]. IEEETransactions on Geoscience and Remote Sensing,1992,32(3):590-597.
[15] Freeman A, Jakob J, Van Zyl J. Calibration of Stokes and scattering matrix formatpolarimetric SAR data [J]. IEEE Transactions on Geoscience and Remote Sensing,1990,30(3):531-539.
[16] Liu G F, Li M, Wang Y J, et al. Four-component scattering power decompositionof remainder coherency matrices constrained for nonnegative eigenvalues [J].IEEE Geoscience and Remote Sensing Letters, to be published.
[17]方保镕,周继东,李医民.矩阵论[M].北京:清华大学出版社,2005.
[18] Arii M, van Zyl J J, Kim Y. Adaptive model-based decomposition of polarimetricSAR covariance matrices [J]. IEEE Transactions on Geoscience and RemoteSensing,2011,49(3):1104-1113.
[19] Liu G F, Li M, Wang Y J, et al. Fast solution to nonnegative eigenvaluedecomposition for polarimetric SAR [J]. IET Electronics Letters,2013,49(6):419-420.
[20]周晓光,匡纲要,万建伟.多极化SAR图像斑点抑制综述[J].中国图象图形学报,2008,13(3):377-385.
[21] Gu J, Yang J, Zhang H. Speckle filtering in polarimetric SAR data based on thesubspace decomposition [J]. IEEE Transaction on Geoscience and Remote Sensing,2004,42(8):1635-1641.
[22] Yang J, Deng Q, Yue H, et al. Polarimetric whitening filter for POLSAR imagebased on subspace decomposition [J]. Journal of Systems Engineering andElectronics,2008,19(6):1121-1126.
[23] Liu G F, Li M, Wu Y, et al. A novel despeckling algorithm of polarimetric SARimage based on SNR and parameter-vector spectrum amendment [C]//IEEE CIEInternational Conference on Radar. Chengdu: IEEE Press,2011:1459–1462.
[24]刘高峰,李明,王亚军.基于非负特征值分解的极化SAR子空间分解滤波[J].计算机科学,2013,40(5):266-270.
[25]王庆香,李迪,张舞杰.基于多特征的SAR图像的无监督分割[J].计算机科学,2010,37(10):267-270.
[26]邓少平,李平湘,张继贤.基于乘积模型的极化SAR滤波[J].武汉大学学报（信息科学版）,2011,36(10):1168-1171.
[1] Freeman A and Durden S L. A three-component scattering model for polarimetricSAR data [J]. IEEE Transaction on Geoscience and Remote Sensing,1998,36(3):963-973.
[2] Huynen J R. Phenomological theory of radar targets [D]. Delft, Netherlands:Netherlands Tech. Univ,1970.
[3] Cloude S R, Pottier E. A review of target decomposition theorems in radarpolarimetry [J]. IEEE Transaction on Geoscience and Remote Sensing,1996,34(2):498-518.
[4] Durden S L, Klein J D, Zebker H A, et al. Polarimetric radar measurements of aforested area near Mt. Shasta [J]. IEEE Transaction on Geoscience and RemoteSensing,1991,29(6):444-450.
[5]王超,张红,陈曦.全极化合成孔径雷达图像处理[M].北京:科学出版社,2008.
[6] Lee J S, Ainsworth T L. Generalized polarimetric model-based decompositionsusing incoherent scattering models [J]. IEEE Transaction on Geoscience andRemote Sensing, to be published.
[7] Cui Y, Yamaguchi Y, Yang J. On complete model-based decomposition ofpolarimetric SAR coherency matrix data [J]. IEEE Transaction on Geoscience andRemote Sensing, to be published.
[8] Lee J S, Pottier E. Polarimetric radar imaging from basic to application [M]. NewYork: CRC Press,2011.
[9] Cloude S R. Polarisation: Applications in Remote Sensing [M]. New York: OxfordUniversity Press,2010.
[10] An W, Cui Y, Yang J. Three-component model-based decomposition forpolarimetric SAR data [J]. IEEE Transaction on Geoscience and Remote Sensing,2010,48(6):2732-2739.
[11] Cui Y, Yamaguchi Y, Yang J. Three-component power decomposition forpolarimetric SAR data based on adaptive volume scatter modeling [J]. RemoteSensing,2012,4(1):1559-1572.
[12] Singh G, Yamaguchi Y, Park S E. Hybrid Freeman/eigenvalue decompositionmethod with extended volume scattering model [J]. IEEE Geoscience and RemoteSensing Letters, to be published.
[13] Van Zyl J J, Kim Y. Synthetic aperture radar polarimetry [M]. Hoboken, NJ: Wiley,2011.
[14] Van Zyl J J, Arii M, Kim Y. Model-based decomposition of polarimetric SARcovariance matrices constrained for nonnegative eigenvalues [J]. IEEETransactions on Geoscience and Remote Sensing,2011,49(9):3452-3459.
[15] Arii M, van Zyl J J, Kim Y. Adaptive model-based decomposition of polarimetricSAR covariance matrices [J]. IEEE Transactions on Geoscience and RemoteSensing,2011,49(3):1104-1113.
[16] Liu G F, Li M, Wang Y J, et al. Four-component scattering power decompositionof remainder coherency matrices constrained for nonnegative eigenvalues [J].IEEE Geoscience and Remote Sensing Letters, to be published.
[17]刘高峰,李明,王亚军.一种新的基于非反射对称非负特征值分解的Freeman分解[J].电子与信息学报,2013,35(2):369-376.
[18]刘高峰,李明,王亚军.一种改进的极化SAR自适应非负特征值分解[J].电子与信息学报,2013,35(6):1449-1455.
[19] Durden S L, van Zyl J J, Zebker H A. Modeling and observation of the radarpolarization signature of forested areas [J]. IEEE Transactions on Geoscience andRemote Sensing,1989,27(5):290–301.
[20] Kajimoto M, Susaki J. Urban-area extraction from polarimetric SAR images usingpolarization orientation angle [J]. IEEE Geoscience and Remote Sensing Letters,2013,10(2):337-341.
[21] Lee J S, Krogager E. Polarimetric analysis of radar signature of a manmadestructure [J]. IEEE Geoscience and Remote Sensing Letters,2006,4(3):555-559.
[22]方保镕,周继东,李医民.矩阵论[M].北京:清华大学出版社,2005.
[23] Van Zyl J J. Application of Cloude’s target decomposition theorem to polarimetricimaging radar data [A]. Process SPIE Radar Polarimetry [C]. Pasadena, CA:1992.184–212.
[24] http://sar.kangwon.ac.kr/polsar/PolSARpro_demo/
[1] Yamaguchi Y, Moriyama T, Ishido M, et al. Four-component scattering model forpolarimetric SAR image decomposition [J]. IEEE Transactions on Geoscience andRemote Sensing,2005,43(8):1699-1706.
[2] Yang J. On theoretical problems in radar polarimetry [D]. Niigata, Japan: NiigataUniv., Graduate School Sci. Technol.,2000.
[3] Huynen J R. Phenomological theory of radar targets [D]. Delft, Netherlands:Netherlands Tech. Univ,1970.
[4] Cloude S R, Pottier E. A review of target decomposition theorems in radarpolarimetry [J]. IEEE Transaction on Geoscience and Remote Sensing,1996,34(2):498-518.
[5] Durden S L, Klein J D, Zebker H A, et al. Polarimetric radar measurements of aforested area near Mt. Shasta [J]. IEEE Transaction on Geoscience and RemoteSensing,1991,29(6):444-450.
[6]王超,张红,陈曦.全极化合成孔径雷达图像处理[M].北京:科学出版社,2008.
[7] Yamaguchi Y, Yajima Y, Yamada H. A four-component decomposition of PolSARimages based on the coherency matrix [J]. IEEE Geoscience and Remote SensingLetters,2006,3(3):292-296.
[8] Cloude S R. Polarisation: Applications in Remote Sensing [M]. New York: OxfordUniversity Press,2010.
[9] Yajima Y, Yamaguchi Y, Sato R, et al. PolSAR image analysis of wetlands using amodified four-component scattering power decomposition [J]. IEEE Transactionson Geoscience and Remote Sensing,2008,46(6):1667-1673.
[10] Yamaguchi Y, Sato A, Sato R,et al. Four-component scattering power decomposi-tion with rotation of coherency matrix [J]. IEEE Transactions on Geoscience andRemote Sensing,2011,49(6):2251-2258.
[11] Sato A, Yamaguchi Y, Singh G, et al. Four-component scattering power decomposi-tion with extended volume scattering model [J]. IEEE Geoscience and RemoteSensing Letters,2012,9(2):166-171.
[12] Van Zyl J J, Kim Y. Synthetic aperture radar polarimetry [M]. NJ: Wiley,2011.
[13] Liu G F, Li M, Wang Y J, et al. Four-component scattering power decompositionof remainder coherency matrices constrained for nonnegative eigenvalues [J].IEEE Geoscience and Remote Sensing Letters, to be published.
[14]刘高峰,李明,王亚军.基于层次非负特征值约束的Yamaguchi分解[J].电子与信息学报,2013,35(11):2678-2686.
[15] Tragl K. Polarimetric radar backscattering from reciprocal random targets [J].IEEE Transactions on Geoscience and Remote Sensing,1990,28(9):856-864.
[16] Krogager E. Aspects of polarimetric radar imaging [D]. Copenhagen: Danish Def.Res. Est.,1993.
[17] Lee J S, Krogager E, Ainsworth T L, et al. Polarimetric analysis of radar signatureof a manmade structure [J]. IEEE Geoscience and Remote Sensing Letters,2006,3(4):555-559.
[18] Singh G, Yamaguchi Y, Park S E. General four-component scattering powerdecomposition with unitary transformation of coherency matrix [J]. IEEETransactions on Geoscience and Remote Sensing,2013,51(5):2251-2258.
[19]方保镕,周继东,李医民.矩阵论[M].北京:清华大学出版社,2005.
[20] Arii M, van Zyl J J, Kim Y. Adaptive model-based decomposition of polarimetricSAR covariance matrices [J]. IEEE Transactions on Geoscience and RemoteSensing,2011,49(3):1104-1113.
[21] http://sar.kangwon.ac.kr/polsar/PolSARpro_demo/
[22] Lee J S, Pottier E. Polarimetric radar imaging from basic to application [M]. NewYork: CRC Press,2011.
[23] Li Y, Gong H, Wang Q. Adaptive enhancement with speckle reduction for SARimages using mirror-extended curvelet and PSO [A]. in Proc.2010InternationalConference on Pattern Recognition [C]. Istanbul, Turkey: IEEE,2010.4520-4523.
[24]金亚秋,徐丰.极化散射与SAR遥感信息理论与方法[M].北京:科学出版社,2008.
[1] Jiang Y, Zhang X L, Shi J. Unsupervised classification of polarimetric SAR Imageby Quad-tree Segment and SVM [A]. Asian and Pacific Conference on SyntheticAperture Radar [C]. Huangshan, China: IEEE,2007.480-483.
[2] Fukuda S, Katagiri R, Hirosawa H. Unsupervised approach for polarimetric SARimage classification using support vector machines [A]. International Geoscienceand Remote Sensing Symposium [C]. Toronto, Canada: IEEE,2002.2599-2601.
[3] Li H T, Gu H Y, Han Y S, et al. Object-oriented classification of polarimetric SARimagery based on statistical region merging and support vector machine [A].International Workshop on Earth Observation and Remote Sensing Applications[C]. Beijing, China: IEEE,2008.1-6.
[4] Zhang L, Zou B, Jia Q, et al. Polarimetric SAR image classification usingmultiple-component scattering model and support vector machine [A]. in Proc.2ndAsian-Pacific Conference on Synthetic Aperture Radar [C]. Xian, Shanxi: IEEE,2009.805-808.
[5] Zhang L, Zou B, Zhang J. Classification of Polarimetric SAR Image Based onSupport VectorMachine UsingMultiple-Component Scattering Model and TextureFeatures [J]. EURASIP Journal on Advances in Signal Processing,2010,9(5):1-9.
[6] Wu Z C, Ouyang Q D. SVM-and MRF-based method for contextual classificationof polarimetric SAR images [A]. IEEE IGARSS Proceedings [C]. Xian, Shanxi:IEEE,2011.818-821.
[7] Chen L, Yang W, Liu Y, et al. Feature evaluation and selection for polarimetricSAR image classification [A]. International Conference on Signal Processing [C].Beijing, China: IEEE,2010.2202-2204.
[8] Lardeux C, Frison P L, Tison C, et al. Support vector machine for multi-frequencySAR polarimetric data classification [J]. IEEE Transactions on Geoscience andRemote Sensing,2009,47(12):4143-4152.
[9]丁世飞,齐丙娟,谭红艳.支持向量机理论与算法研究综述[J].电子科技大学学报,2011,40(1):2-10.
[10]邓乃扬,田英杰.数据挖掘中的新方法——支持向量机[M].北京:科学出版社,2004.
[11]张莉.支撑矢量机与核方法研究[D].西安:西安电子科技大学,2002.
[12] Vapnik V N(著),张学工(译).统计学习理论的本质[M].北京：清华大学出版社,2000．
[13] Vapnik V N(著),许建华(译).统计学习理论[M].北京：电子工业出版社,2004．
[14]谢塞琴,沈福明,邱雪娜.基于支持向量机的人脸识别方法[J].计算机工程,2009,35(16):186-188.
[15] Gauwenberghs G. Incremental and decremental support vector machine [J].Machine Learning,2001,44(13):409-415.
[16] Tang Y, Jin B, Zhang Yan Q, et a1. Granular support vector machines for medicalbinary classification problems [A]. Proceedings of the IEEE CIBIB [C].Piscataway, HJ: IEEE Computationl Intelligence Society,2004.73-78.
[17]连可,黄建国,王厚军.一种基于遗传算法的SVM决蓑树多分类策略研究[J].电子学报,2008,36(8):1502-l507.
[18]李国正,王猛,曾华军.支持向量机导论[M].北京:电子工业出版社,2004.
[19] Jayadcva R，Khemchandan S C. Twin support vector machines for patternclassification [J]. IEEE Trans on Pattrern Analysis and Machine Intelligence,2007,29(5):905-910.
[20]王宏宇,糜仲春,梁晓艳.一种基于支持向量机回归的推荐算法[J].中国科学院研究生院学报,2007,24(6):742-748.
[21] John Taylor (著),赵玲玲(译).模式分析的核方法[M].北京:机械工业出版社,2006.
[22] Aizerman M, Braverman E, Rozonoer L. Theoretical foundations of the potentialfunction method in pattern recognition learning. Automantion and Remote Control,1964,25(1):821-837.
[23] Guo H，Wang W，Men C. Anovel learning model-kernel granular support vectormachine [A]. Proceeding of the eighth international conference on machinelearning and cybernetic [C]. Baoding: IEEE,2009.930-935.
[24] Richard D (著),李宏东(译).模式分类[M].北京:机械工业出版社,2010.
[25]黄凤岗,宋克欧.模式识别[M].哈尔滨:哈尔滨工程大学出版社,1998.
[26]沈清,汤霖.模式识别导论[M].长沙:国防科技大学出版社,1991.
[27] Damoulas T, Girolami M A. Pattern recognition with a Bayesian kernelcombination machine [J]. Pattern Recognition Letters,2009,30(1):46-54.
[28]郑大念.机器学习中的核方法研究[D].北京:清华大学,2006.
[29] Lanckriet G, Cristianini N, Bartlett P, et al. Learning the kernel matrix withsemide-niteprogramming [J]. The Journal of Machine Learning Research,2004,5(1):27-72.
[30] Vapnik V N. The nature of statistical learning theory [M]. Berlin: Springer,1995.
[31] Bennett K P, Momma M, Embrechts M J. MARK: a boosting algorithm forheterogeneous kernel models [A]. Proceedings of8th ACM-SIGKDD InternationalConference on Knowledge Discovery and Data Mining [C]. Edmonton, Canada:ACM,2002.24-31.
[32] Sonnenburg S, Ratsch G, Schafer C, et al. Large scale multiple kernel learning [J].The Journal of Machine Learning Research,2006,7(7):1531-1565
[33] Tu S T, Chen J Y, Yang W, et al. Laplacian eigenmaps based polarimetricdimensionality reduction for SAR image classification [J]. IEEE Transactions onGeoscience and Remote Sensing,2012,50(1):.170-179.
[34] Ince T, Kiranyaz S, Gabbouj M. Evolutionary RBF classifier for polarimetric SARimages [J]. Expert Systems with Applications:2012,39(9):4710–4717.
[35]刘高峰,李明,王亚军.基于层次非负特征值约束的Yamaguchi分解[J].电子与信息学报,35(11):2678-2686.
[36] Cloude S R, Pottier E. A review of target decomposition theorems in radarpolarimetry [J]. IEEE Transactions on Geoscience and Remote Sensing,1996,34(2):498-518.
[37] Camps-Valls G, Gomez-Chova L. Kernel-based framework for multitemporal andmultisource remote sensing data classification and change detection [J]. IEEETransactions on Geoscience and Remote Sensing,2008,46(6):1822-1835.
[38] Li G Q, Wen C Y, and Li Z L. Model-based online learning with kernels [J]. IEEETransactions on Neural Networks and Learning Systems,2013,24(3):356-369.
[39] http://sar.kangwon.ac.kr/polsar/PolSARpro_demo/
[40] Lee J S, Pottier E. Polarimetric radar imaging from basic to application [M]. NewYork: CRC Press,2011.
[41] Lee J S, Grunes M R, Ainsworth T L, et al. Unsupervised classification usingpolarimetric decomposition and the complex Wishart classifier [J]. IEEETransactions on Geoscience and Remote Sensing,1999,37(5):2249-2258.
[1] Benboudjema D, Pieczynski W. Unsupervised image segmentation using tripletMarkov fields [J]. Computer Vision and Image Understanding,2005,99(3):476-498.
[2] Benboudjema D, Pieczynski W. Unsupervised statistical segmentation ofnonstationary images using triplet Markov fields [J]. IEEE Trans. Pattern Anal.Mach. Intell.,2007,29(8):1367-1378.
[3] Lanchantin P, Lapuyade-Lahorgue J, Pieczynski W. Unsupervised segmentation oftriplet Markov chains hidden with long-memory noise [J]. Signal Processing,2008,88(10):1134-1151.
[4] Pieczynski W. EM and ICE in hidden and triplet Markov field [A]. StochasticModeling Techniques and Data Analysis International Conference [C]. Chania,Greece: ACM,2010.1-9.
[5] Lapuyade-Lahorgue J, Pieczynski W. Unsupervised segmentation of newsemi-Markov chains hidden with long dependence noise [J]. Signal Processing,2010,90(4):2899-2910.
[6] Lanchantin P, Lapuyade-Lahorgue J, Pieczynski W. Unsupervised segmentation ofrandomly switching data hidden with non-Gaussian correlated noise [J]. SignalProcessing,2011,91(5):163-175.
[7] Lapuyade-Lahorgue J, Pieczynski W. Unsupervised segmentation of hiddensemi-Markov non-stationary chains [J]. Signal Processing,2012,92(6):29-42.
[8] Wu Y, Li M, Zhang P, et al. Unsupervised multi-class segmentation of SAR imagesusing triplet Markov fields models based on edge penalty [J]. Pattern RecognitionLetters,2011,32(4):1532-1540.
[9] Zhang P, Li M, Wu Y, et al. Unsupervised multi-class segmentation of SAR imagesusing fuzzy triplet Markov fields model [J]. Pattern Recognition,2013,46(4):1-16.
[10] Zhang P, Li M, Wu Y, et al. SAR image multiclass segmentation using a multiscaleTMF model in wavelet domain [J]. IEEE Geoscience and Remote Sensing Letters,2012,9(6):1099-1104.
[11] Dong Y, Milne A K, Forster B C. Segmentation and classification of vegetatedareas using polarimetric SAR image data [J]. IEEE Transactions on Geoscienceand Remote Sensing,2001,39(2):321–329.
[12] Wu Y H, Ji K, Yu W, et al. Region-based classification of polarimetric SAR imagesusing Wishart MRF [J]. IEEE Geoscience and Remote Sensing Letters,2008,5(4):668-672.
[13] Liu G F, Li M, Wu Y, et al. PolSAR Image Classification Based on Wishart TMFWith Specific Auxiliary Field [J]. IEEE Geoscience and Remote Sensing Letters,to be published.
[14] Li S Z. Markov random field modeling in image analysis [M]. London, British:Springer-Verlag,2009.
[15]黄宇,付琨,吴一戎.基于Markov随机场K-Means图像分割算法[J].电子学报,2009,37(12):2700-2705.
[16]宋晓峰,王爽,刘芳.基于区域MRF和贝叶斯置信传播的SAR图像分割[J].电子学报,2010,38(12):2810-2817.
[17] Boudaren M Y, Monfrini E, Pieczynski W. Unsupervised segmentation of randomdiscrete data hidden with switching noise distributions [J]. IEEE Signal ProcessingLetters,2012,19(10):619-622.
[18]张鹏.基于统计模型的SAR图像降斑和分割方法研究[D].西安:西安电子科技大学,2012.
[19] Derin H, Elliott H. Modeling and segmentation of noisy and textured images usingGibbs random fields [J]. IEEE Trans. Pattern Anal. Machine Intell.,1987,PAMI-9(1):39-55.
[20]李旭超,朱善安.图像分割中的马尔可夫随机场方法综述[J].中国图象图形学报,2007,12(5):789-801.
[21] Lee J S and Pottier E. Polarimetric Radar Imaging from Basic to Application [M].New York: CRC Press,2011:1-30,160-175.
[22] Van Zyl J J and Kim Y. Synthetic Aperture Radar Polarimetry [M]. California: JetPropulsion Laboratory,2011:85-155.
[23]赵力文,周晓光,蒋咏梅.一种基于Freeman分解与散射熵的极化SAR图像迭代分类方法[J].电子与信息学报,2008,30(11):2698-2701.
[24] Zhao Li-wen, Zhou Xiao-guang, and Jiang Yong-mei. Iterative classification ofpolarimetric SAR image based on Freeman decomposition and scattering entropy[J]. Journal of Electronics＆Information Technology,2008,30(11):2698-2701.
[25] Chen Q, Kuang G Y, Li J, et al.. Unsupervised land cover/land use classificationusing PolSAR imagery based on scattering similarity [J]. IEEE Transaction onGeoscience and Remote Sensing,2013,51(3):1817-1825.
[26] Liu B, Hu H, Wang H Y, et al.. Superpixel-based classification with an adaptivenumber of classes for polarimetric SAR images [J]. IEEE Transaction onGeoscience and Remote Sensing,2013,51(2):907-924.
[27] Lee J S, Grunes M R, Kwok R. Classification of multi-look polarimetric SARimagery based on the complex Wishart distribution [J]. Int. J. Remote Sens.,1994,15(11):2299-2311.
[28] Richard D (著),李宏东(译).模式分类[M].北京:机械工业出版社,2010.
[29] http://sar.kangwon.ac.kr/polsar/PolSARpro_demo/
[30] Gonzalez R C, R. E. Woods. Digital image processing third edition [M]. Beijing,China: Publishing House of Electronics Industry,2012.