基于二维极化特征的PolSAR图像决策分类

邵璐熠; 洪文

doi:10.12000/JR16002

基于二维极化特征的PolSAR图像决策分类

DOI: 10.12000/JR16002

邵璐熠^,,
洪文

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 100190)

基金项目:

国家自然科学基金（61431018）

详细信息

作者简介:
邵璐熠(1987-),女,中国科学院电子学研究所在读博士生,研究方向为极化SAR分类及应用。E-mail:shaoluyi28@126.com;洪文(1968-),女,中国科学院电子学研究所研究员,博士生导师,研究方向为雷达信号处理理论、SAR成像算法、微波遥感图像处理及其应用等。E-mail:whong@mail.ie.ac.cn

通讯作者:
邵璐熠shaoluyi28@126.com

计量
- 文章访问数: 2419
- HTML全文浏览量: 495
- PDF下载量: 1176
- 被引次数: 0
出版历程
- 收稿日期: 2016-01-05
- 修回日期: 2016-06-20
- 网络出版日期: 2016-12-28

Decision Tree Classification of PolSAR Image Based on Two-dimensional Polarimetric Features

Shao Luyi^,,
Hong Wen

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

Funds:

The National Natural Science Foundation of China (61431018)

摘要

摘要: 决策树模型在极化SAR数据分类中有着极大的应用价值，既能描述分类结果的极化散射机制，又能获得较好的分类精度。但在对散射机制相似的地物进行分类时，由于经典决策树模型的节点采用的是单个特征，分类精度不理想。因此，该文提出了节点采用2维特征的方法，即在特征集相同的前提下，每次取两个特征组成特征矢量用于节点，提高了经典决策树难以区分的地物的分类精度；并且利用分类结果的混淆矩阵准确定位了导致分类误差的节点，进而对节点进行有针对性的反馈调整，进一步提高了指定地物的分类精度。利用AIRSARFlevoland数据验证了该方法的有效性，并结合极化特征描述了Flevoland地区多种植被的极化散射机制。
- 决策树 /
- 极化特征 /
- 2维特征空间 /
- 混淆矩阵 /
- 结果反馈调整
Abstract: The decision tree model has great significance in the application of polarimetric SAR data classification, whose results in many types of classification applications obtain good accuracy and are interpretable by polarimetric scattering mechanisms.In the traditional decision tree model, because one single feature is employed by the nodes of the decision tree, the accuracy of the classification result tends to be poor, especially, for applications that classify objects with similar scattering characteristics.In this paper, we propose an improved method to create a two-dimensional vector of features instead of one single feature at the decision nodes.As a result, the classification results of the new method adopting the same feature set as the traditional decision tree can achieve better accuracy.In addition, after classification, the new method may employ a confusion matrix to identify the decision node that yields a classification error, which will facilitate the objectoriented feedback adjustment of classification results, thus making it possible to improve the classification accuracy of the specified object.Our experimental results with AIRSAR-Flevoland data prove the validity of the proposed method, and we draw some useful conclusions about the scattering characteristics of several types of vegetation.
- Decision tree /
- Polarimetric features /
- Mapping of two-dimensional feature /
- Confusion matrix /
- Adjustment of the classification results

HTML全文

参考文献(12)

[1]	Van Zyl J J.Unsupervised classification of scattering mechanisms using radar polarimetry data[J].IEEE Transactions on Geoscience and Remote Sensing,1989,27(1):36-45.
[2]	Cloude S R and 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.
[3]	Du L J and Lee J S.Polarimetric SAR image classification based on target decomposition theorem and complex Wishart distribution[C].IEEE International Geoscience and Remote Sensing Symposium,Lincoln,1996,1:439-441.
[4]	Pottier E and Lee J S.Unsupervised classification scheme of PolSAR images based on the complex Wishart distribution and the H/A/a polarimetric decomposition theorem[C].Proceedings of the 3rd European Conference on Synthetic Aperture Radar (EUSAR'00),Munich,2000:265-269.
[5]	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.
[6]	Uhlmann S and Kiranyaz S.Integrating color features in polarimetric SAR image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(4):2197-2216.
[7]	Theodoridis S and Koutroumbas K.Pattern Recognition[M].Fourth Edition,Beijing:China Machine Press,2009:215-222.
[8]	何楚,刘明,许连玉,等.利用特征选择自适应决策树的层次SAR图像分类[J].武汉大学学报(信息科学版),2012,37(1):46-49.He Chu,Liu Ming,Xu Lian-yu,et al..A hierarchical classification method based on feature selection and adaptive decision tree for SAR image[J].Geomatics and Information Science of Wuhan University,2012,37(1):46-49.
[9]	Lee J S and Pottier E.Polarimetric Radar Imaging:From Basics to Applications[M].Boca Raton,FL,USA,CRC Press,2009:55-63,200-205,229-245.
[10]	李航.统计学习方法[M].北京:清华大学出版社,2012:25-26.Li Hang.Statistical Learning Method[M].Beijing:Tsinghua University Press,2012:25-26.
[11]	王明合,张二华,唐振民,等.基于Fisher线性判别分析的语音信号端点检测方法[J].电子与信息学报,2015,37(6):1343-1349.Wang Ming-he,Zhang Er-hua,Tang Zhen-min,et al..Voice activity detection based on Fisher linear discriminant analysis[J].Journal of ElectronicsInformation Technology,2015,37(6):1343-1349.
[12]	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.