Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Infrared Technology》 2015-01
Add to Favorite Get Latest Update

Remote Sensing Image Registration Based on Strengthened MSER and Harris-Laplace Local Invariant Features

WANG Xiao-Hua;LI Ke;DENG Ka-zhong;YANG Hua-chao;Henan Polytechnic University;China University of Mining and Technology, Jiangsu Key Laboratory of Resources and Environmental Information Engineering;  
A strengthened local invariant feature automatic registration method is proposed for registration of remote sensing images with tilt. The image space transform is corrected by coarse matching with the affine invariant of the MSER features and SIFT descriptor. Then the images are precisely matched by using H-L that can be stable and efficient to extract feature points in 2D and 3D scale space on image rotation and illumination changes condition. Experiment shows that this method can achieve more accurate registration and correct matching rate than SIFT matching method with respect to tilt remote sensing images.
【Fund】: 河南理工大学2014年度博士基金资助项目 编号:B2014-07;; 测绘地理信息公益性行业科研专项项目 编号:201412020;; 校内青年基金 编号:Q2014-02A
【CateGory Index】: TP751
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved