首页 | 本学科首页   官方微博 | 高级检索  
     

利用SIFT和静态小波变换的遥感影像配准方法
引用本文:韩舸,牛瑞卿. 利用SIFT和静态小波变换的遥感影像配准方法[J]. 测绘科学, 2012, 37(5): 61-64
作者姓名:韩舸  牛瑞卿
作者单位:中国地质大学地球物理与空间信息学院,武汉,430074
基金项目:国家高技术研究发展计划(863);国家自然科学基金项目;国土资源部三峡库区三期地质灾害防治重大科学研究项目(SXKY3-3-2)
摘    要:本文首先利用静态小波变换对影像进行多层分解,在其低频子影像上利用SIFT提取特征点集;之后,通过统计不同阀值下的匹配点集精度和数量信息,利用多项式拟合的方法自动建立约束条件,并以此约束条件自动校正控制点集以得到数量可观且高精度的控制点集。试验结果表明,该方法是一种有效的遥感影像配准控制点自动提取方法。

关 键 词:SIFT  静态小波变换  图像配准  遥感

An image registration method based on SIFT and SWT
HAN Ge , NIU Rui-qing. An image registration method based on SIFT and SWT[J]. Science of Surveying and Mapping, 2012, 37(5): 61-64
Authors:HAN Ge    NIU Rui-qing
Affiliation:(Institute of Geophysics and Geomatics,China University of Geosciences,Wuhan 430074,China)
Abstract:In this paper images were decomposed into several sub-images by utilizing SWT firstly.Then feature point-sets were extracted by SIFT using the low frequency images(approximation) as input data.And a fully automatic matching algorithm which is free of arguments was introduced to obtain the matched point-sets by making use of statistical information of matched point-sets obtained with different threshold.It was shown that a considerable number of matched point-sets could be derived with relative high accuracy simultaneously.
Keywords:SIFT  Stationary Wavelet Transform  image registration  remote sensing
本文献已被 CNKI 万方数据 等数据库收录!
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