Journal of Computer Applications ›› 2017, Vol. 37 ›› Issue (1): 244-250.DOI: 10.11772/j.issn.1001-9081.2017.01.0244

Previous Articles     Next Articles

Polarimetric synthetic aperture radar feature analysis and classification based on multi-layer support vector machine classifier

SONG Chao, XU Xin, GUI Rong, XIE Xinfang, XU Feng   

  1. School of Electronic Information, Wuhan University, Wuhan Hubei 430072, China
  • Received:2016-06-02 Revised:2016-07-25 Online:2017-01-10 Published:2017-01-09
  • Supported by:
    This work is partially supported by the Technology Research and Development of the Major Project of High-Resolution Earth Observation System under Grant (03-Y20A10-9001-15/16), the Comprehensive Disaster Demonstration Project of Spatial Information Services.

基于多层支持向量机的极化合成孔径雷达特征分析与分类

宋超, 徐新, 桂容, 谢欣芳, 徐丰   

  1. 武汉大学 电子信息学院, 武汉 430072
  • 通讯作者: 徐新
  • 作者简介:宋超(1992-),男,福建福州人,硕士研究生,主要研究方向:合成孔径雷达图像解译;徐新(1967-),男,湖北武汉人,教授,博士生导师,博士,主要研究方向:信号与信息处理;桂容(1990-),女,湖北武汉人,硕士研究生,主要研究方向:合成孔径雷达图像解译;谢欣芳(1994-),女,河南周口人,硕士研究生,主要研究方向:合成孔径雷达图像解译;徐丰(1980-),男,北京人,副研究员,硕士,主要研究方向:合成孔径雷达图像在防灾减灾方面的应用。
  • 基金资助:
    高分辨率对地观测系统重大专项技术与开发项目(03-Y20A10-9001-15/16);综合减灾空间信息服务应用示范项目。

Abstract: In order to make full use of the ability of of Synthetic Aperture Radar (SAR) images with different polarization features for characterizing different types of ground objects, an analysis and classification approach of polarimetric SAR feature based on multi-layer Support Vector Machine (SVM) classifier was proposed. Firstly, the optimal feature subsets suitable for different terrain types were determined through the feature analysis. Then, the method of hierarchical classification tree was used for SVM classification step by step according to the feature subset of each object type.Finally, the overall final result was obtained. The experimental results of RadarSAT-2 polarimetric SAR image classification show that, the classification accuracy of the proposed approach is approximately 85% for four kinds of ground objects such as water area, cultivated land, forest land and urban area and the overall classification accuracy is up to 86%. The proposed approach can make full use of the characteristics of the different ground object target types, improve the classification accuracy and reduce the time complexity.

Key words: polarimetric Synthetic Aperture Radar (SAR) image, feature analysis of ground object, multi-layer Support Vector Machine (SVM), supervised classification

摘要: 为了充分利用极化合成孔径雷达(SAR)图像不同极化特征对不同地物目标类型的刻画能力,提出一种基于多层支持向量机(SVM)的极化SAR特征分析与分类方法。该方法首先通过特征分析确定适合不同地物类型的最佳特征子集;然后采用分层分类树的方式,根据每一种地物类型的特征子集逐层进行SVM分类;最终得到整体分类结果。RadarSAT-2极化SAR图像分类实验结果表明所提方法水域、耕地、林地、城区4类地物分类精度为85%左右,总体分类精度达到86%。该算法充分利用了不同地物目标类型的特性,提高了分类精度,也降低了算法时间复杂度。

关键词: 极化合成孔径雷达图像, 地物目标特征分析, 多层支持向量机, 监督分类

CLC Number: