首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于梯度径向夹角直方图的异源图像匹配
引用本文:李壮,雷志辉,于起峰.基于梯度径向夹角直方图的异源图像匹配[J].测绘学报,2011,40(3):318-325.
作者姓名:李壮  雷志辉  于起峰
作者单位:1. 国防科技大学;2. 国防科学技术大学;
基金项目:国家863计划(2007AA12Z121)
摘    要:提出一种图像全局特征描述方法——梯度径向夹角金字塔直方图.该特征不受图像灰度级非线性变换和图像旋转的影响,具有较强的抗噪声能力.基于该特征的匹配算法能够对存在旋转变换的异源图像进行匹配.用SAR图像和可见光图像对匹配算法进行测试,结果表明基于梯度径向夹角金字塔直方图匹配方法的匹配成功率优于传统方法.由于对基准图进行离线...

关 键 词:异源图像  图像匹配  旋转不变  梯度矢量  径向矢量  金字塔直方图
收稿时间:2010-02-24
修稿时间:2010-06-21

Matching Multi-sensor Images Based on Gradient Radius Angle Pyramid Histogram
LI Zhuang,LEI Zhihui,YU Qifeng.Matching Multi-sensor Images Based on Gradient Radius Angle Pyramid Histogram[J].Acta Geodaetica et Cartographica Sinica,2011,40(3):318-325.
Authors:LI Zhuang  LEI Zhihui  YU Qifeng
Institution:LI Zhuang,LEI Zhihui,YU Qifeng College of Aerospace and Material Engineering,National University of Defense Technology,Changsha 410073,China
Abstract:A novel image feature named gradient radius angle pyramid histogram(GRAPH) is proposed.The GRAPH feature is invariable to nonlinear transform of grey level and image rotation,and is robust to noise.Based on GRAPH feature,we get a robust and fast image matching algorithm that can match rotated and shifted multi-sensor images.SAR images and optical images are used to test this matching method.The results show that the new matching algorithm has higher success rate than traditional method.As the reference imag...
Keywords:multi-sensor image  image matching  rotate-invariant  gradient vector  radial direction vector  pyramid histogram  
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《测绘学报》浏览原始摘要信息
点击此处可从《测绘学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号