基于SIFT特征的遥感影像自动配准

李晓明; 郑链; 胡占义

doi:10.11834/jrs.200606130

浏览量 : 0 下载量: 4197 CSCD: 80

PDF
导出
分享
收藏
专辑

基于SIFT特征的遥感影像自动配准
SIFT Based Automatic Registration of Remotely-sensed Imagery
2006年第6期页码：885-892
纸质出版：2006
DOI： 10.11834/jrs.200606130
稿件说明：

移动端阅览

[1]李晓明,郑链,胡占义.基于SIFT特征的遥感影像自动配准[J].遥感学报,2006(06):885-892. DOI： 10.11834/jrs.200606130.

LI Xiao-ming~. SIFT Based Automatic Registration of Remotely-sensed Imagery[J]. Journal of Remote Sensing, 2006, (6): 885-892. DOI： 10.11834/jrs.200606130.

摘要

遥感影像的自动配准是长期以来一直未能很好解决的一个重要问题。本文将视频图像匹配中获得巨大成功的SIFT（Scale Invariant Feature Transform）特征应用于遥感影像的自动配准问题中

并且针对遥感影像的成像特点

给出了一种具体的特征匹配方法。对航空和航天遥感影像在不同的变形、不同的光照变化和不同的分辨率下进行的大量实验表明

该方法具有稳定、可靠、快速等特点。

Abstract

Automatic registration of remotely-sensed imagery is a classical problem

and has not been well solved till now.In this paper

SIFT（Scale Invariant Feature Transform） feature

which has shown great success in computer vision

is introduced into image registration in remote sensing.In addition

we also proposed a feature matching approach based on the specific characteristic of the remote sensing imagery.Numerous experiments have been conducted for both aerial and satellite imageries under various conditions such as geometric distortion

illumination variation and different resolution.The results showed that our matching approach performs well

and is stable

reliable and efficient.