基于去取向理论的全极化SAR图像模糊非监督聚类  

Unsupervised Classification of Polarimetric SAR Image Using Deorientation Theory and Complex Wishart Distribution

作　　者：康欣[1] 韩崇昭[1] 徐丰[2] 王英华[1] 

机构地区：[1]西安交通大学综合自动化研究所,西安710049 [2]复旦大学波散射与遥感信息教育部重点实验室,上海200433

出　　处：《电子与信息学报》2007年第4期822-826,共5页Journal of Electronics & Information Technology

基　　金：国家973项目(2001CB309403)资助课题

摘　　要：由于复杂散射体的随机取向导致其回波具有一定的波动性,利用目标分解理论对全极化SAR图像进行分类时,分类结果会出现一定程度的错分现象。该文提出了一种新的非监督分类算法,该算法首先根据去取向理论,将目标向量旋转到最小交叉极化方向;然后,采用u/v/H参数描述散射机制,以模糊隶属函数代替参数平面的“硬”阈值划分;最后,以多元复Wishart分布描述相干矩阵,基于Bayes极大似然分类准则进行分类。以中国广东淡水附近的L波段NASA/JPLSIR-C全极化SAR图像作为实验数据进行了仿真试验,并进一步对聚类中心的迁移进行了讨论。试验和讨论结果表明:同基于H/α和类k-mean的算法比较,该文的聚类算法对聚类效果有明显改善,类别对应的散射机制也更为准确,分类结果有利于地表类型的自动识别。Scatter targets of complex terrain surfaces with random orientation product random fluctuating echoes. This leads to a confused classification by directly using target decomposition on full polarimetric SAR （PolSAR） image. To solve this problem, a new unsupervised classification method is proposed in this paper. Firstly, the target vector is transformed to the state with minimization of cross-polarization （min-x-pol）; then the parameters u/v/H are used to characterized scattering mechanism, and the fuzzy membership is adopted instead of ＂hard＂ division of parameter plan; finally, characterizing the coherency matrix as multivariable complex Wishart distribution, the polarimetric SAR image is classified based on Bayes maximum likelihood criteria. Experiment is performed on a L-band NASA/JPL SIR-C polarimetric SAR image over Danshui town, Guangdong, P.R. China. Furthermore, the movements of the clustering centers are discussed. Compared with the k-mean like method based on H/α^-, the results show that the proposed method provides a significant performance improvement in classification result and the associated scattering mechanism of class is more accurate. The classification result is beneficial for automatic recognition of terrain type.

关 键 词：合成孔径雷达 去取向 无监督分类 模糊聚类 雷达极化 

分 类 号：TN957.52[电子电信—信号与信息处理]