| 基于相关向量机的SAR图像飞机目标分类方法研究 |
| |
| 引用本文： | 张维坤,叶伟,李国靖.基于相关向量机的SAR图像飞机目标分类方法研究[J].电子测量技术,2017,40(1):151-154. |
| |
| 作者姓名： | 张维坤 叶伟 李国靖 |
| |
| 作者单位： | 1. 装备学院研究生院 北京 101416;2. 装备学院信息装备系 北京 101416 |
| |
| 摘 要： | 随着合成孔径雷达(SAR)成像技术的发展,SAR图像的数据处理和图像分类工作近年来成为研究热点.在本文中,将相关向量机(RVM)应用于SAR图像目标分类识别,对3类飞机仿真目标进行分类,从分类正确率、分类时间、泛化能力和鲁棒性方面全面考察其性能.与支持向量机(SVM)相比,相关向量机没有多余的参数调整,核函数不需要满足Mercer条件,可以获得更多的稀疏模型.仿真结果表明,在对3种类型的飞机仿真目标进行分类的情况下,使用RVM方法总体分类性能略高于SVM.
|
| 关 键 词： | 相关向量机 支持向量机 SAR图像 飞机目标 |
Research on aircraft target classification method based on RVM for SAR Image |
| |
| Zhang Weikun,Ye Wei and Li Guojing.Research on aircraft target classification method based on RVM for SAR Image[J].Electronic Measurement Technology,2017,40(1):151-154. |
| |
| Authors: | Zhang Weikun Ye Wei and Li Guojing |
| |
| Abstract: | With the development of Synthetic Aperture Radar technology,SAR image data processing and image classification and recognition has become a hot research topic in recent years.This article will apply to the relevant vector machine classification SAR image of the target,to classify three kinds of aircraft simulation target,from the classification accuracy and classification time,generalization ability and robustness of comprehensive study of its performance.Compared with support vector machine,relevant vector machine without adjusting the extra parameter,kernel function does not need to satisfy the Mercer condition,can get more sparse model.The simulation results show that the classification of three types of aircraft simulation target,this paper classified the RVM method in performance is slightly higher than that of SVM. |
| |
| Keywords: | relevant vector machine support vector machine SAR image aircraft target |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《电子测量技术》浏览原始摘要信息 |
|
点击此处可从《电子测量技术》下载全文 |
|
