Large-scale monocular SLAM by local bundle adjustment and map joining

Zhao, L; Huang, S; Yan, L; Wang, JJ; Hu, G; Dissanayake, G

Large-scale monocular SLAM by local bundle adjustment and map joining

Zhao, L

Huang, S

Yan, L Wang, JJ

Hu, G Dissanayake, G

Permalink

Publication Type:: Conference Proceeding
Citation:: 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010, 2010, pp. 431 - 436
Issue Date:: 2010-12-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download full textAdobe PDF (203.31 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Zhao, L https://orcid.org/0000-0003-4063-8183	en_US
dc.contributor.author	Huang, S https://orcid.org/0000-0002-6124-4178	en_US
dc.contributor.author	Yan, L	en_US
dc.contributor.author	Wang, JJ https://orcid.org/0000-0002-6282-0456	en_US
dc.contributor.author	Hu, G	en_US
dc.contributor.author	Dissanayake, G https://orcid.org/0000-0002-7992-0680	en_US
dc.date.issued	2010-12-01	en_US
dc.identifier.citation	11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010, 2010, pp. 431 - 436	en_US
dc.identifier.isbn	9781424478132	en_US
dc.identifier.uri	http://hdl.handle.net/10453/16326
dc.description.abstract	This paper first demonstrates an interesting property of bundle adjustment (BA), "scale drift correction". Here "scale drift correction" means that BA can converge to the correct solution (up to a scale) even if the initial values of the camera pose translations and point feature positions are calculated using very different scale factors. This property together with other properties of BA makes it the best approach for monocular Simultaneous Localization and Mapping (SLAM), without considering the computational complexity. This naturally leads to the idea of using local BA and map joining to solve large-scale monocular SLAM problem, which is proposed in this paper. The local maps are built through Scale-Invariant Feature Transform (SIFT) for feature detection and matching, random sample consensus (RANSAC) paradigm at different levels for robust outlier removal, and BA for optimization. To reduce the computational cost of the large-scale map building, the features in each local map are judiciously selected and then the local maps are combined using a recently developed 3D map joining algorithm. The proposed large-scale monocular SLAM algorithm is evaluated using a publicly available dataset with centimeter-level ground truth. ©2010 IEEE.	en_US
dc.relation	http://purl.org/au-research/grants/arc/LP0884112R2
dc.relation.ispartof	11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010	en_US
dc.relation.isbasedon	10.1109/ICARCV.2010.5707820	en_US
dc.title	Large-scale monocular SLAM by local bundle adjustment and map joining	en_US
dc.type	Conference Proceeding
utslib.for	090602 Control Systems, Robotics and Automation	en_US
dc.location.activity	Singapore	en_US
dc.location.activity	Singapore, SINGAPORE
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Civil and Environmental Engineering
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - CAS - Centre for Autonomous Systems
pubs.organisational-group	/University of Technology Sydney/Strength - CBI - Centre for Built Infrastructure
utslib.copyright.status	open_access
pubs.publication-status	Published	en_US

Abstract:

This paper first demonstrates an interesting property of bundle adjustment (BA), "scale drift correction". Here "scale drift correction" means that BA can converge to the correct solution (up to a scale) even if the initial values of the camera pose translations and point feature positions are calculated using very different scale factors. This property together with other properties of BA makes it the best approach for monocular Simultaneous Localization and Mapping (SLAM), without considering the computational complexity. This naturally leads to the idea of using local BA and map joining to solve large-scale monocular SLAM problem, which is proposed in this paper. The local maps are built through Scale-Invariant Feature Transform (SIFT) for feature detection and matching, random sample consensus (RANSAC) paradigm at different levels for robust outlier removal, and BA for optimization. To reduce the computational cost of the large-scale map building, the features in each local map are judiciously selected and then the local maps are combined using a recently developed 3D map joining algorithm. The proposed large-scale monocular SLAM algorithm is evaluated using a publicly available dataset with centimeter-level ground truth. ©2010 IEEE.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/16326