计算机应用 ›› 2018, Vol. 38 ›› Issue (1): 132-136.DOI: 10.11772/j.issn.1001-9081.2017071719

• 人工智能 • 上一篇    下一篇

利用可分性指数的极化SAR图像特征选择与多层SVM分类

李平, 徐新, 董浩, 邓旭   

  1. 武汉大学 电子信息学院, 武汉 430072
  • 收稿日期:2017-07-13 修回日期:2017-09-06 出版日期:2018-01-10 发布日期:2018-01-22
  • 通讯作者: 徐新
  • 作者简介:李平(1992-),女,湖北襄阳人,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;董浩(1990-),男,河南周口人,博士研究生,主要研究方向:合成孔径雷达图像解译;邓旭(1993-),女,云南昭通人,硕士研究生,主要研究方向:合成孔径雷达图像解译。
  • 基金资助:
    高分辨率观测系统重大专项技术研究与开发项目(03-Y20A10-9001-15/16);综合减灾空间信息服务应用示范项目。

Polarimetric SAR image feature selection and multi-layer SVM classification using divisibility index

LI Ping, XU Xin, DONG Hao, DENG Xu   

  1. School of Electronic Information, Wuhan University, Wuhan Hubei 430072, China
  • Received:2017-07-13 Revised:2017-09-06 Online:2018-01-10 Published:2018-01-22
  • Supported by:
    This work is partially supported by the Technology Research and Development Major Project of High-Resolution Earth Observation System (03-Y20A10-9001-15/16), the Comprehensive Disaster Demonstration Project of Spatial Information Services.

摘要: 可分性指数(SI)可用来选择各类地物的有效分类特征,但在多维特征以及地物可分性较好的情况下,只利用可分性指数进行特征选择不能有效去除特征之间的冗余性。基于此,提出了利用可分性指数并辅以顺序后退(SBS)算法进行特征选择与多层支持向量机(SVM)分类的方法。首先,由各类地物在所有特征下的可分性指数选择分类地物和特征;然后,以该地物的分类精度为评估依据,利用顺序后退法筛选特征;其次,由剩余地物之间的可分性指数和顺序后退法依次选择各类地物的分类特征;最后利用多层SVM进行分类。实验结果表明,与只利用可分性指数选择特征进行多层SVM分类的方法相比,所提方法的分类精度提高了2%,各类地物的分类精度均高于86%,且运行时间为原来方法的一半。

关键词: 合成孔径雷达, 特征选择, 可分性指数, 顺序后退法, 多层支持向量机分类

Abstract: Separability Index (SI) can be used to select effective classification features, but in the case of multi-dimensional features and good separability of geology, the use of separability index for feature selection can not effectively remove redundancy. Based on this, a method of feature selection and multi-layer Support Vector Machine (SVM) classification was proposed by using separability index and Sequential Backward Selection (SBS) algorithm. Firstly, the classification object and features were determined according to the SIs of all the ground objects under all the features, and then based on the classification accuracies of the objects, the SBS algorithm was used to select the features again. Secondly, the features of next ground objects were determined by the separability index of remaining objects and the SBS algorithm in turn. Finally, the multi-layer SVM was used for classification. The experimental results show that the classification accuracy of the proposed method is improved by 2% compared with the method of multi-layer SVM classification where features are selected only based on the SI, and the classification accuracy of all kinds of objects is higher than 86%, and the running time is half of the original method.

Key words: Synthetic Aperture Radar (SAR), feature selection, Separability Index (SI), Sequential Backward Selection (SBS) method, multi-layer Support Vector Machine (SVM) classification

中图分类号: