Abstract：In this paper, an unsupervised algorithm is proposed to classify the data of fully polarimetric synthetic aperture Radar(PolSAR). The proposed method combines the Freeman-Durden with the scattering model based development of the decomposition algorithm and the K-Wishart distribution based on non Gauss. This is mainly composed of three steps. The first is the application of Freeman-Durden decomposition of the pixel to divide the scattering into three types: surface scattering, volume scattering and dihedral scattering, and then by using the shape parameter the scattering type can be divided into three types. After that, the eight neighborhood priori probabilities for each pixel are calculated to improve the classification distance and calculate the cluster centers. Finally, the iterative K-Wishart classifier is applied to PolSAR image for accurate classification and the color padding scheme. Different from Wishart distribution, the K-wishart distribution is not only suitable for uniform regional data description, but also very strong for the general uneven regional data description. The experiment results show that the proposed method has better classification performance than Freeman-Durden decomposition and complex Wishart distribution.
许斌. 基于非高斯分布的全极化SAR数据无监督分类[J]. 国土资源遥感, 2017, 29(2): 90-96.
XU Bin. Unsupervised classification of fully polarimetric SAR data based on non-Gauss distribution. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(2): 90-96.
[1] Shi L,Zhang L F,Yang J,et al.Supervised graph embedding for Polarimetric SAR image classification[J].IEEE Geoscience and Remote Sensing Letters,2013,10(2):216-220. [2] Shang F,Hirose A.Use of Poincare sphere parameters for fast supervised PolSAR land classification[C]//Proceedings of 2013 IEEE International Geoscience and Remote Sensing Symposium.Melbourne,VIC:IEEE,2013:3175-3178. [3] Wang S,Liu K,Pei J J,et al.Unsupervised classification of fully polarimetric SAR images based on scattering power entropy and copolarized ratio[J].IEEE Geoscience and Remote Sensing Letters,2013,10(3):622-626. [4] Zhang S,Wang S,Chen B,et al.Classification method for fully PolSAR data based on three novel parameters[J].IEEE Geoscience and Remote Sensing Letters,2014,11(8):39-44. [5] Cloude S R,Pottier E.An entropy based classification scheme for land applications of Polarimetric SAR[J].IEEE Transactions on Geoscience and Remote Sensing,1997,35(1):68-78. [6] Lee J S,Grunes M R,Ainsworth T L,et al.Unsupervised classification using polarimetric decomposition and the complex wishart classifier[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(5):2249-2258. [7] Lee J S,Grunes M R,Pottier E,et al.Unsupervised terrain classification preserving polarimetric scattering characteristics[J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(4):722-731. [8] Doulgeris A P,Anfinsen S N,Eltoft T.Classification with a non-Gaussian model for PolSAR data[J].IEEE Transactions on Geoscience and Remote Sensing,2008,46(10):2999-3009. [9] Doulgeris A P,Anfinsen S N,Eltoft T.Automated non-Gaussian clustering of polarimetric synthetic aperture radar images[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(10):3665-3676. [10] 任俊英,苏彩霞,曹永锋.基于中间层特征的全极化SAR监督地物分类[J].遥感技术与应用,2014,29(2):330-337. Ren J Y,Su C X,Cao Y F.Supervised land-use classification of full polarization SAR image based on middle level feature[J].Remote Sensing Technology and Application,2014,29(2):330-337. [11] Lee J S,Grunes M R,Kwok R.Classification of multi-look polarimetric SAR imagery based on complex Wishart distribution[J].International Journal of Remote Sensing,1994,15(11):2299-2311. [12] Lee J S,Grunes M R,de Grandi G.Polarimetric SAR speckle filtering and its implication for classification[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(5):2363-2373. [13] 陈 博,王 爽,焦李成,等.贝叶斯集成框架下的极化SAR图像分类[J].西安电子科技大学学报(自然科学版),2015,42(2):45-51. Chen B,Wang S,Jiao L C,et al.Polarimetric SAR image classification via naive Bayes combination[J].Journal of Xidian University,2015,42(2):45-51. [14] 赵力文,周晓光,蒋咏梅,等.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(1):2698-2701. Zhao L W,Zhou X G,Jiang Y M,et al.Iterative classification of polarimetric SAR image based on Freeman decomposition and scattering entropy[J].Journal of Electronics & Information Technology,2008,30(1):2698-2701. [15] 郁文贤,柳 彬,丁拥科,等.高分辨率、多时相SAR图像数据集的构建[J].测绘通报,2014(s1):119-122. Yu W X,Liu B,Ding Y K,et al.Construction of high resolution multi-temporal SAR image dataset[J].Bulletin of Surveying and Mapping,2014(s1):119-122. [16] 陈 博,王 爽,焦李成,等.利用0-1矩阵分解集成的极化SAR图像分类[J].电子与信息学报,2015,37(6):1495-1501. Chen B,Wang S,Jiao L C,et al.Polarimetric SAR image classification via weighted ensemble based on 0-1 matrix decomposition[J].Journal of Electronics & Information Technology,2015,37(6):1495-1501. [17] 钟微宇,沈 汀.结合多特征和SVM的SAR图像分割[J].计算机应用研究,2013,30(9):2846-2851. Zhong W Y,Shen T.Multiple features and SVM combined SAR image segmentation[J].Application Research of Computers,2013,30(9):2846-2851. [18] 杨学志,叶 铭,吴克伟,等.结构保持的双边滤波极化SAR图像降噪[J].电子与信息学报,2015,37(2):268-275. Yang X Z,Ye M,Wu K W,et al.Speckle reduction for PolSAR image based on structure preserving bilateral filtering[J].Journal of Electronics & Information Technology,2015,37(2):268-275. [19] 陈 军,杜培军,谭 琨,等.一种基于Pauli分解和支持向量机的全极化合成孔径雷达监督分类算法[J].科学技术与工程,2014,14(17):104-108,142. Chen J,Du P J,Tan K,et al.A supervised classification algorithm based on Pauli decomposition and SVM on polarimetric SAR image[J].Science Technology and Engineering,2014,14(17):104-108,142. [20] 马文婷,杨 健,高 伟,等.面向极化SAR图像配准的极化特征[J].清华大学学报(自然科学版),2014,54(2):270-274. Ma W T,Yang J,Gao W,et al.Polarimetric feature for registration of polarimetric SAR images[J].Journal of Tsinghua University:Science and Technology,2014,54(2):270-274. [21] 李崇谦.基于K-Wishart分布的极化SAR图像分类研究[D].西安:西安电子科技大学,2013. Li C Q.Polarimetric SAR Image Classification Based on K-Wishart Distribution[D].Xi’an:Xidian University,2013.
2017, Vol. 29 
