ParallaxBA: Bundle adjustment using parallax angle feature parametrization

Zhao, L; Huang, S; Sun, Y; Yan, L; Dissanayake, G

ParallaxBA: Bundle adjustment using parallax angle feature parametrization

Zhao, L

Huang, S

Sun, Y Yan, L Dissanayake, G

Permalink

Publication Type:: Journal Article
Citation:: International Journal of Robotics Research, 2015, 34 (4-5), pp. 493 - 516
Issue Date:: 2015-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted Manuscript VersionAdobe PDF (4.64 MB)

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	Sun, Y	en_US
dc.contributor.author	Yan, L	en_US
dc.contributor.author	Dissanayake, G https://orcid.org/0000-0002-7992-0680	en_US
dc.date.issued	2015-01-01	en_US
dc.identifier.citation	International Journal of Robotics Research, 2015, 34 (4-5), pp. 493 - 516	en_US
dc.identifier.issn	0278-3649	en_US
dc.identifier.uri	http://hdl.handle.net/10453/35549
dc.description.abstract	©The Author(s) 2015. The main contribution of this paper is a novel feature parametrization based on parallax angles for bundle adjustment (BA) in structure and motion estimation from monocular images. It is demonstrated that under certain conditions, describing feature locations using their Euclidean XYZ coordinates or using inverse depth in BA leads to ill-conditioned normal equations as well as objective functions that have very small gradients with respect to some of the parameters describing feature locations. The proposed parallax angle feature parametrization in BA (ParallaxBA) avoids both of the above problems leading to better convergence properties and more accurate motion and structure estimates. Simulation and experimental datasets are used to demonstrate the impact of different feature parametrizations on BA, and the improved convergence, efficiency and accuracy of the proposed ParallaxBA algorithm when compared with some existing BA packages such as SBA, sSBA and g2o. The C/C++ source code of ParallaxBA is available on OpenSLAM (https://openslam.org/).	en_US
dc.relation.ispartof	International Journal of Robotics Research	en_US
dc.relation.isbasedon	10.1177/0278364914551583	en_US
dc.subject.classification	Industrial Engineering & Automation	en_US
dc.title	ParallaxBA: Bundle adjustment using parallax angle feature parametrization	en_US
dc.type	Journal Article
utslib.citation.volume	4-5	en_US
utslib.citation.volume	34	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
utslib.for	0913 Mechanical Engineering	en_US
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 Mechanical and Mechatronic Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - CAS - Centre for Autonomous Systems
utslib.copyright.status	open_access
pubs.issue	4-5	en_US
pubs.publication-status	Published	en_US
pubs.volume	34	en_US

Abstract:

©The Author(s) 2015. The main contribution of this paper is a novel feature parametrization based on parallax angles for bundle adjustment (BA) in structure and motion estimation from monocular images. It is demonstrated that under certain conditions, describing feature locations using their Euclidean XYZ coordinates or using inverse depth in BA leads to ill-conditioned normal equations as well as objective functions that have very small gradients with respect to some of the parameters describing feature locations. The proposed parallax angle feature parametrization in BA (ParallaxBA) avoids both of the above problems leading to better convergence properties and more accurate motion and structure estimates. Simulation and experimental datasets are used to demonstrate the impact of different feature parametrizations on BA, and the improved convergence, efficiency and accuracy of the proposed ParallaxBA algorithm when compared with some existing BA packages such as SBA, sSBA and g2o. The C/C++ source code of ParallaxBA is available on OpenSLAM (https://openslam.org/).

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

http://hdl.handle.net/10453/35549