基于二维极化特征的PolSAR图像决策分类

邵璐熠 洪文

邵璐熠, 洪文. 基于二维极化特征的PolSAR图像决策分类[J]. 雷达学报, 2016, 5(6): 681-691. doi: 10.12000/JR16002
引用本文: 邵璐熠, 洪文. 基于二维极化特征的PolSAR图像决策分类[J]. 雷达学报, 2016, 5(6): 681-691. doi: 10.12000/JR16002
Shao Luyi, Hong Wen. Decision Tree Classification of PolSAR Image Based on Two-dimensional Polarimetric Features[J]. Journal of Radars, 2016, 5(6): 681-691. doi: 10.12000/JR16002
Citation: Shao Luyi, Hong Wen. Decision Tree Classification of PolSAR Image Based on Two-dimensional Polarimetric Features[J]. Journal of Radars, 2016, 5(6): 681-691. doi: 10.12000/JR16002

基于二维极化特征的PolSAR图像决策分类

DOI: 10.12000/JR16002
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

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

Funds: 

The National Natural Science Foundation of China (61431018)

  • 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。

     

  • [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.
  • 加载中
计量
  • 文章访问数:  2421
  • HTML全文浏览量:  496
  • 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

目录

    /

    返回文章
    返回