CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
Tracks selection for robust, efficient and scalable large-scale structure from motion
Cui, Hainan1; Shen, Shuhan1,2; Hu, Zhanyi1,2,3; Cui Hainan(崔海楠)
Source PublicationPATTERN RECOGNITION
2017-12-01
Volume72Issue:72Pages:341-354
SubtypeArticle
AbstractCurrently global structure-from-motion (SfM) pipeline consists of four steps: estimating camera rotations first, then computing camera positions, triangulating tracks, and finally doing bundle adjustment. However, for large-scale SfM problems, the tracks are usually too noisy and redundant for the bundle adjustment. Thus in this work, we propose a novel fast tracks selection method to improve both efficiency and robustness of the bundle adjustment. Firstly, three selection criteria: Compactness, Accurateness, and Connectedness, are introduced, where the first two are to calculate a selection priority for each track and the third is to guarantee the completeness of scene structure. Then, to satisfy these criteria, a more informative subset of tracks is selected by covering multiple spanning trees of epipolar geometry graph. Since tracks selection acts only an intermediate step in the whole SfM pipeline, it can be in principle embedded into any global SfM pipelines. To validate the effectiveness of our tracks selection module, we insert it into a state-of-the-art global SfM system and compare it with three other selection methods. Extensive experiments show that by embedding our tracks selection module, the new SfM system performs similarly or better than the original one in terms of reconstruction completeness and accuracy, but is much more efficient and scalable for large-scale scene reconstructions. Finally, our tracks selection module is further embedded into two other global SfM systems to demonstrated its versatility. (C) 2017 Elsevier Ltd. All rights reserved.
KeywordTracks Selection Bundle Adjustment Structure From Motion
WOS HeadingsScience & Technology ; Technology
DOI10.1016/j.patcog.2017.08.002
Indexed BySCI
Language英语
Funding OrganizationNSFC (Natural Science Foundation of China)(61333015) ; National Key R&D Program of China(2016YFB0502002) ; NSFC(61421004 ; 61632003)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000411545400025
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/19643
Collection模式识别国家重点实验室_机器人视觉
Corresponding AuthorCui Hainan(崔海楠)
Affiliation1.Chinese Acad Sci, Inst Automat, NLPR, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Beijing, Peoples R China
3.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Cui, Hainan,Shen, Shuhan,Hu, Zhanyi,et al. Tracks selection for robust, efficient and scalable large-scale structure from motion[J]. PATTERN RECOGNITION,2017,72(72):341-354.
APA Cui, Hainan,Shen, Shuhan,Hu, Zhanyi,&Cui Hainan.(2017).Tracks selection for robust, efficient and scalable large-scale structure from motion.PATTERN RECOGNITION,72(72),341-354.
MLA Cui, Hainan,et al."Tracks selection for robust, efficient and scalable large-scale structure from motion".PATTERN RECOGNITION 72.72(2017):341-354.
Files in This Item: Download All
File Name/Size DocType Version Access License
HainanCui_PR.pdf(5402KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Cui, Hainan]'s Articles
[Shen, Shuhan]'s Articles
[Hu, Zhanyi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Cui, Hainan]'s Articles
[Shen, Shuhan]'s Articles
[Hu, Zhanyi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Cui, Hainan]'s Articles
[Shen, Shuhan]'s Articles
[Hu, Zhanyi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: HainanCui_PR.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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