Target recognition in SAR images with support vector machines (SVM)

被引：36

作者：

Tison, Celine ^{[1
]}

Pourthie, Nadine ^{[1
]}

Souyris, Jean-Claude ^{[1
]}

机构：

[1] CNES, DCT SI AR, F-31401 Toulouse 4, France

来源：

IGARSS: 2007 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-12: SENSING AND UNDERSTANDING OUR PLANET | 2007年

关键词：

D O I：

10.1109/IGARSS.2007.4422829

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper addresses object recognition problem in SAR images with SVM classifier; the work has been mainly focused on feature vector definition. Actually, each object is represented by a feature vector and SVM aims to estimate the best hyperplanes that separate classes in the feature space. Very robust definition of feature vector is proposed and tested on real data (MSTAR database). Confusion matrices prove that a very good recognition rate is reached, even for mixed incidence angles configuration.

引用

页码：456 / 459

页数：4

共 9 条

[1]

CORTES C, 1999, MACH LEARN, V20, P1

[2] On the independence of rotation moment invariants [J].