NSSC OpenIR  > 微波遥感部
A novel approach for the registration of weak affine images
Li, Dong; Zhang, Yunhua; Li, D (reprint author), Chinese Acad Sci, Key Lab Microwave Remote Sensing, Ctr Space Sci & Appl Res, 1 Nanertiao, Beijing 100190, Peoples R China.
Department微波遥感部
Source PublicationPATTERN RECOGNITION LETTERS
2012
Volume33Issue:12Pages:1647-1655
ISSN0167-8655
Language英语
KeywordFast Least Trimmed Squares (Fast-lts) Image Registration Parameter Estimation Random Sample Consensus (Ransac) Weak Affine Transformation
AbstractA novel image registration scheme is devised in view of the weak affine transformation, which is a kind of similarity transformation with anisotropic scales or affine transformation without shearing. Two robust algorithms are proposed to retrieve the registration parameters from the error-prone initial correspondences based on the fast least trimmed squares (Fast-LTS) and the random sample consensus (RANSAC). In terms of several criteria, the algorithms are evaluated on three carefully selected datasets from different sensors and the experimental results demonstrate that the proposed scheme and algorithms perform robustly and accurately. Our findings also indicate that the Fast-LTS-based algorithm is more stable and appropriate for image registration than the RANSAC-based algorithm although the speed is slower. (C) 2012 Elsevier B.V. All rights reserved.; A novel image registration scheme is devised in view of the weak affine transformation, which is a kind of similarity transformation with anisotropic scales or affine transformation without shearing. Two robust algorithms are proposed to retrieve the registration parameters from the error-prone initial correspondences based on the fast least trimmed squares (Fast-LTS) and the random sample consensus (RANSAC). In terms of several criteria, the algorithms are evaluated on three carefully selected datasets from different sensors and the experimental results demonstrate that the proposed scheme and algorithms perform robustly and accurately. Our findings also indicate that the Fast-LTS-based algorithm is more stable and appropriate for image registration than the RANSAC-based algorithm although the speed is slower. (C) 2012 Elsevier B.V. All rights reserved.
Indexed BySCI ; EI
Funding Project中国科学院空间科学与应用研究中心
Document Type期刊论文
Identifierhttp://ir.nssc.ac.cn/handle/122/3453
Collection微波遥感部
Corresponding AuthorLi, D (reprint author), Chinese Acad Sci, Key Lab Microwave Remote Sensing, Ctr Space Sci & Appl Res, 1 Nanertiao, Beijing 100190, Peoples R China.
Recommended Citation
GB/T 7714
Li, Dong,Zhang, Yunhua,Li, D . A novel approach for the registration of weak affine images[J]. PATTERN RECOGNITION LETTERS,2012,33(12):1647-1655.
APA Li, Dong,Zhang, Yunhua,&Li, D .(2012).A novel approach for the registration of weak affine images.PATTERN RECOGNITION LETTERS,33(12),1647-1655.
MLA Li, Dong,et al."A novel approach for the registration of weak affine images".PATTERN RECOGNITION LETTERS 33.12(2012):1647-1655.
Files in This Item: Download All
File Name/Size DocType Version Access License
201233121647.pdf(2405KB) 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li, Dong]'s Articles
[Zhang, Yunhua]'s Articles
[Li, D (reprint author), Chinese Acad Sci, Key Lab Microwave Remote Sensing, Ctr Space Sci & Appl Res, 1 Nanertiao, Beijing 100190, Peoples R China.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li, Dong]'s Articles
[Zhang, Yunhua]'s Articles
[Li, D (reprint author), Chinese Acad Sci, Key Lab Microwave Remote Sensing, Ctr Space Sci & Appl Res, 1 Nanertiao, Beijing 100190, Peoples R China.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li, Dong]'s Articles
[Zhang, Yunhua]'s Articles
[Li, D (reprint author), Chinese Acad Sci, Key Lab Microwave Remote Sensing, Ctr Space Sci & Appl Res, 1 Nanertiao, Beijing 100190, Peoples R China.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 201233121647.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.