CASIA OpenIR  > 09年以前成果
A new normalized method on line-based homography estimation
Zeng, Hui; Deng, Xiaoming; Hu, Zhanyi
2008-07-01
发表期刊PATTERN RECOGNITION LETTERS
卷号29期号:9页码:1236-1244
文章类型Article
摘要It is a conventional belief that line-based approaches perform better than point-based ones for homography estimation, as the line-fitting is generally more noise resistant than point detection. In this note, we show that blithely using line-based estimation is a risky business. More specifically, we show that when the image line(s) is (are) passing through or close to the origin, the line-based homography estimation could become wildly unstable whereas the point-based estimation performs normally. To tackle this problem, a new normalized method specially designed for line-based homography estimation is proposed and validated by extensive experiments. (c) 2008 Elsevier B.V. All rights reserved.
关键词Point-based Homography Estimation Line-based Homography Estimation Visual Metrology Data Normalization
WOS标题词Science & Technology ; Technology
关键词[WOS]CAMERA CALIBRATION
收录类别SCI
语种英语
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000256961500008
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/9689
专题09年以前成果
作者单位Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100080, Peoples R China
推荐引用方式
GB/T 7714
Zeng, Hui,Deng, Xiaoming,Hu, Zhanyi. A new normalized method on line-based homography estimation[J]. PATTERN RECOGNITION LETTERS,2008,29(9):1236-1244.
APA Zeng, Hui,Deng, Xiaoming,&Hu, Zhanyi.(2008).A new normalized method on line-based homography estimation.PATTERN RECOGNITION LETTERS,29(9),1236-1244.
MLA Zeng, Hui,et al."A new normalized method on line-based homography estimation".PATTERN RECOGNITION LETTERS 29.9(2008):1236-1244.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zeng, Hui]的文章
[Deng, Xiaoming]的文章
[Hu, Zhanyi]的文章
百度学术
百度学术中相似的文章
[Zeng, Hui]的文章
[Deng, Xiaoming]的文章
[Hu, Zhanyi]的文章
必应学术
必应学术中相似的文章
[Zeng, Hui]的文章
[Deng, Xiaoming]的文章
[Hu, Zhanyi]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。