Unsupervised Classification of Polarimetirc SAR Image Via Improved Manifold Regularized Low-Rank Representation With Multiple Features
Unsupervised Classification of Polarimetirc SAR Image Via Improved Manifold Regularized Low-Rank Representation With Multiple Features
复制标题
基于多特征改进流形正则化低阶表示的极化SAR图像无监督分类
DOI：
10.1109/jstars.2016.2573380
复制
发表时间：
2017-02
影响因子：
5.5
通讯作者：
Jiao Licheng
中科院分区：
文献类型：
--
作者：
Ren Bo;Hou Biao;Zhao Jin;Jiao Licheng
提出了一种新的极化合成孔径雷达（PolSAR）图像非监督分类方法。它结合了极化数据特征（相干矩阵）、极化分解特征（Krogager、Freeman、Yamaguqi、Neuman和H/A/ $\alpha $分解）和灰度共生矩阵特征三种典型特征，全面描述了数据特征。提出了一种基于对称修正Wishart（SRW）距离导出流形正则化低秩表示（SRWM_LRR）的方法，以深入挖掘几何数据结构。该方法采用低秩表示（LRR）来捕捉PolSAR数据的内在全局结构，采用流形正则化来检测数据的局部结构，其中引入SRW距离来度量不同像元之间的相似性，以描述局部流形结构.该算法充分考虑了PolSAR数据的统计特性，同时从数据几何结构的角度综合多个特征来表示像素，以获得更好的分类性能。通过星载和机载SAR系统获取的数据集，包括广泛应用于土地覆盖分类的弗莱沃兰数据集（AIRSAR L波段）和西安数据集（RadarSAT-2 C波段），验证了该方法的有效性和实用性。与传统的Wishart分类器、基于欧氏距离和SRW距离的谱聚类和LRR方法相比，该方法在精度和效率上都有较大的提高，并且具有更好的可视化效果。
In this paper, a novel polarimetric synthetic aperture radar (PolSAR) image unsupervised classification method is proposed. It combines three typical features, including polarimetric data features (coherent matrix), polarimetric decomposition features (Krogager, Freeman, Yamaguqi, Neuman, and H/A/ $\alpha $ decomposition), and gray-level co-occurrence matrix features to comprehensively describe the data characteristics. And it also proposes a symmetric revised Wishart (SRW) distance-derived manifold regularized low-rank representation (SRWM_LRR) method to deeply exploit the geometry data structure. The low-rank representation (LRR) is used to capture the intrinsic global structure of PolSAR data and the manifold regularization is employed to detect the local structure of the data, in which SRW distance is introduced to measure the similarity between different pixels for describing the local manifold structure. This algorithm considers the specific statistics property in PolSAR data and simultaneously integrates multiple features in perspective of data geometry structure to represent pixels for achieving a better classification performance. The effectiveness and practicability of the proposed method are demonstrated by datasets obtained either in spaceborne or airborne SAR system, including the Flevoland dataset (AIRSAR L-Band) extensively used in land classification cover, and Xi'an dataset (RadarSAT-2 C-Band). Compared with the traditional Wishart classifier, Euclidean and SRW distance-based spectral clustering and LRR, the proposed method shows improvement in accuracy and efficiency as well as a better visualization result.
登录
查看更多内容
用于图构建的具有局部约束的低秩表示
影响因子：
6
作者：
Yaoguo Zheng;Xiangrong Zhang;Shuyuan Yang;Licheng Jiao
通讯作者：
Licheng Jiao
DOI：
--
发表时间：
1991-04
期刊：
--
影响因子：
--
作者：
E. Pottier;J. Saillard
通讯作者：
E. Pottier;J. Saillard
影响因子：
1.9
作者：
Tongyuan Zou;Wen Yang;Dengxin Dai;Hong Sun
通讯作者：
Tongyuan Zou;Wen Yang;Dengxin Dai;Hong Sun
影响因子：
8.2
作者：
Yinghua Wang;Hongwei Liu;B. Jiu
通讯作者：
Yinghua Wang;Hongwei Liu;B. Jiu
DOI：
10.1109/tpami.2012.274
发表时间：
2013-07
影响因子：
23.6
作者：
Zhenyue Zhang;Keke Zhao
通讯作者：
Zhenyue Zhang;Keke Zhao