一种联合特征值信息的全极化SAR图像监督分类方法

邢艳肖; 张毅; 李宁; 王宇; 胡桂香

doi:10.12000/JR16019

一种联合特征值信息的全极化SAR图像监督分类方法

DOI: 10.12000/JR16019

1.
(中国科学院电子学研究所北京 100190
2.
(中国科学院大学北京 100039)

基金项目:

国家自然科学基金优秀青年基金(61422113)

详细信息

作者简介:
邢艳肖(1990–),女,河北邯郸人,中国科学院电子学研究所通信与信息系统专业硕士研究生,研究方向为极化合成孔径雷达图像分类方法。E-mail:1090433237@qq.com张毅(1971–),男,上海人,现为中国科学院电子学研究所研究员,硕士生导师,研究方向为高速数字信号处理、合成孔径雷达信号处理新技术研究、合成孔径雷达系统设计等。E-mail:zhangyi@mail.ie.ac.cn李宁(1987–),男,安徽天长人,毕业于中国科学院电子学研究所,获得博士学位,现为中国科学院电子学研究所助理研究员,研究方向为多模式合成孔径雷达成像及其应用技术。E-mail:lining_nuaa@163.com王宇(1980–),男,河南人,现为中国科学院电子学研究所研究员,博士生导师,研究方向为SAR系统设计与信号处理技术。E-mail:yuwang@mail.ie.ac.cn胡桂香(1990–),女,黑龙江佳木斯人,在中国科学院电子学研究所攻读硕士学位,研究方向为合成孔径雷达海面风场反演与油膜检测。

通讯作者:
邢艳肖1090433237@qq.com

计量
- 文章访问数: 2559
- HTML全文浏览量: 599
- PDF下载量: 1122
- 被引次数: 0
出版历程
- 收稿日期: 2016-01-25
- 修回日期: 2016-03-11
- 网络出版日期: 2016-04-28

Polarimetric SAR Image Supervised Classification Method Integrating Eigenvalues

1.
(Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China)
2.
(University of Chinese Academy of Sciences, Beijing 100039, China)

Funds:

The National Natural Science Foundation of China (61422113)

摘要

摘要: 基于H/平面的分类器对于具有相似散射类型的地物的分类能力很差,为此该文直接使用特征值特征来进行分类。首先提取特征值特征,并使用一种自适应调整高斯分量个数的高斯混合模型对特征值分布进行较为准确地拟合,然后采用朴素贝叶斯分类器进行初步分类。针对可能存在特征值分布较为相近导致错分的问题,计算每两类地物的特征值分布的相似度,将相似度大于给定阈值的类别对组成相似性表,对于这些相似对再用基于Wishart距离的K近邻分类器进行细分。综合分析机载和星载SAR数据上的实验结果,表明这种方法能够克服基于H/的非监督分类方法对于特征值利用的一些不足,且与基于SVM的分类方法效果相当。
- 极化SAR /
- 地物分类 /
- 特征值
Abstract: Since classification methods based on H/ space have the drawback of yielding poor classification results for terrains with similar scattering features, in this study, we propose a polarimetric Synthetic Aperture Radar (SAR) image classification method based on eigenvalues. First, we extract eigenvalues and fit their distribution with an adaptive Gaussian mixture model. Then, using the naive Bayesian classifier, we obtain preliminary classification results. The distribution of eigenvalues in two kinds of terrains may be similar, leading to incorrect classification in the preliminary step. So, we calculate the similarity of every terrain pair, and add them to the similarity table if their similarity is greater than a given threshold. We then apply the Wishart distance-based KNN classifier to these similar pairs to obtain further classification results. We used the proposed method on both airborne and spaceborne SAR datasets, and the results show that our method can overcome the shortcoming of the H/-based unsupervised classification method for eigenvalues usage, and produces comparable results with the Support Vector Machine (SVM)-based classification method.
- Polarimetric Synthetic Aperture Radar (SAR) /
- Terrain classification /
- Eigenvalues

HTML全文

参考文献(17)

[1]	Lee J S and Pottier E. 极化合成孔径雷达成像基础与应用[M]. 北京: 电子工业出版社, 2013: 199-223. Lee J S and Pottier E. Polarimetric Radar Imaging: From Basics to Applications[M]. Beijing: Publishing House of Electronic Industry, 2013: 199-223.
[2]	滑文强, 王爽, 侯彪. 基于半监督学习的SVM-Wishart极化SAR图像分类方法[J]. 雷达学报, 2015, 4(1): 93-98. Hua Wen-qiang, Wang Shuang, and Hou Biao. Semi-supervised learning for classification of polarimetric SAR images based on SVM-Wishart[J]. Journal of Radars, 2015, 4(1): 93-98.
[3]	Lee J S, Grunes M R, and Kwok R. Classification of multilook polarimetric SAR imagery based on complex Wishart distribution[J]. International Journal of Remote Sensing, 1994, 15(11): 2299-2311.
[4]	Cloude S R and Pottier E. An entropy based classication scheme for land applications of polarimetric SAR[J]. IEEE Transactions on Geoscience and Remote Sensing, 1997, 35(1): 68-78.
[5]	Tzeng Y C and Chen K S. A fuzzy neural network to SAR image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 1998, 36(1): 301-307.
[6]	Lee J S, Grunes M R, Ainsworth T L, et al.. Unsupervised classification using polarimetricdecomposition and the complex Wishart classifier[J]. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(5): 2249-2258.
[7]	Famil L F, Pottier E, and Lee J S. Unsupervised classification of multifrequency and fully polarimetric SAR images based on the H/A/-Wishart classifier[J]. IEEE Transactions on Geoscience and Remote Sensing, 2001, 39(11): 2332-2342.
[8]	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.
[9]	Cao F, Hong W, and Wu Y R. An unsupervised segmentation with an adaptive number of clusters using theSPAN/H//Aspace and the complex Wishart clusteringfor fully polarimetric SAR data analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(11): 3454-3467.
[10]	Lardeux C, Frison P L, Tison C, et al.. Support vector machine for multifrequency SAR polarimetric data classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(12): 4143-4151.
[11]	Cloude S R and Pottier E. A review of target decomposition theorems in radar polarimetry[J]. IEEE Transactions on Geoscience and Remote Sensing, 1996, 34(2): 498-518.
[12]	周伟, 孙艳丽, 许成斌, 等. 一种多极化SAR 舰船目标与方位向模糊鉴别方法[J]. 雷达学报, 2015, 4(1): 84-92. Zhou Wei, Sun Yan-li, Xu Cheng-bin, et al.. A method for discrimination of ship target and azimuth ambiguity in multi-polarimetric SAR imagery[J]. Journal of Radars, 2015, 4(1): 84-92.
[13]	Gou S P, Qiao X, Zhang X R, et al.. Eigenvalue analysis-based approach for POL-SAR image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(2): 805-818.
[14]	李航. 统计学习方法[M]. 北京: 清华大学出版社, 2012: 37-53. Li Hang. Statistical Learning Methods[M]. Beijing: Tsinghua University Press, 2000: 37-53.
[15]	王鑫. 基于高斯混合模型的k均值初始化EM 算法的研究[J]. 商丘师范学院学报, 2012, 28(12): 11-14. Wang Xin. Gaussian mixture model based k-means to initialize the EM algorithm[J]. Journal of Shangqiu Normal University, 2012, 28(12): 11-14.
[16]	Dempster A P, Laird N M, and Rubin D B. Maximum-likelihood from incomplete data via the EM algorithm[J]. Journal of the Royal Statistical Society, 1977, 39(1): 1-38.
[17]	Liu B, Hu H, Wang H Y, et al.. Superpixel-based classification with an adaptive number of classes for polarimetric SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(2): 907-924.