计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (15): 156-158.DOI: 10.3778/j.issn.1002-8331.2010.15.046

• 图形、图像、模式识别 • 上一篇    下一篇

一种有效的SAR图像目标识别方法

付 燕,詹新光   

  1. 西安科技大学 计算机学院,西安 710054
  • 收稿日期:2008-11-17 修回日期:2009-03-12 出版日期:2010-05-21 发布日期:2010-05-21
  • 通讯作者: 付 燕

Efficient method of SAR image target recognition

FU Yan,ZHAN Xin-guang   

  1. College of Computer,Xi’an University of Science and Technology,Xi’an 710054,China
  • Received:2008-11-17 Revised:2009-03-12 Online:2010-05-21 Published:2010-05-21
  • Contact: FU Yan

摘要: SAR图像目标识别是SAR图像应用中非常重要的环节,但由于SAR图像中相干斑噪声的存在,使得传统方法不能很好地对SAR图像进行分类识别。结合不变矩特征提取和支持向量机分类方法的优势,提出了一种有效的SAR图像目标识别方法,采用该方法对含有飞机和坦克目标的SAR图像进行了目标识别实验,取得了较好的识别效果。

关键词: 合成孔径雷达图像, 目标识别, 不变矩, 支持向量机

Abstract: SAR image target recognition is a key step in the application of SAR image.For the existing of speckle in SAR image,It can’t be recognized well with traditional methods.According to the advantages of invariant moments extraction and support vector machine(SVM) classification,an efficient method of SAR image target recognition is proposed.In the experiments of recognizing planes and tanks,better results have been obtained with this new method.

Key words: Synthetic Aperture Radar(SAR) image, target recognition, invariant moments, Support Vector Machine

中图分类号: