|
|||||
|
|
| 基于SIFT特征的遥感影像自动配准 | |
| 引用本文： | 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,2006,10(6):885-892. |
| 作者姓名： | 李晓明 郑链 胡占义 |
| 作者单位： | 1. 北京理工大学,机电工程学院,北京,100081;山西大学,数学系,山西,太原,030006 2. 北京理工大学,机电工程学院,北京,100081 3. 中国科学院,自动化研究所模式识别国家重点实验室,北京,100080 |
| 基金项目： | 国家自然科学基金;山西省自然科学基金 |
| 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。 |
| 关 键 词： | 遥感影像 自动配准 图像配准 |
| 文章编号： | 1007-4619(2006)06-0885-08 |
| 收稿时间： | 2005-09-05 |
| 修稿时间： | 2005-11-23 |
SIFT Based Automatic Registration of Remotely-sensed Imagery |
|
| LI Xiao-ming,ZHENG Lian and HU Zhan-yi.SIFT Based Automatic Registration of Remotely-sensed Imagery[J].Journal of Remote Sensing,2006,10(6):885-892. | |
| Authors: | LI Xiao-ming ZHENG Lian and HU Zhan-yi |
| Institution: | 1. Department of Mechatronic Engineering, Beijing Institute of Technology, Beijing 100081, China; 2. Department of Mathematics, Shanxi University, Shanxi Taiyuan 030006, China; 3. National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100080, China |
| 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. |
| Keywords: | SIFT |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |
| 点击此处可从《遥感学报》浏览原始摘要信息 | |
| 点击此处可从《遥感学报》下载免费的PDF全文 | |