Vision-based SLAM using natural features in indoor environments

Miró, JV; Dissanayake, G; Zhou, W

Vision-based SLAM using natural features in indoor environments

Miró, JV

Dissanayake, G

Zhou, W

Permalink

Publication Type:: Conference Proceeding
Citation:: Proceedings of the 2005 Intelligent Sensors, Sensor Networks and Information Processing Conference, 2005, 2005 pp. 151 - 156
Issue Date:: 2005-12-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download full textAdobe PDF (213.73 kB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Miró, JV https://orcid.org/0000-0002-0083-7797	en_US
dc.contributor.author	Dissanayake, G https://orcid.org/0000-0002-7992-0680	en_US
dc.contributor.author	Zhou, W https://orcid.org/0000-0002-1680-2521	en_US
dc.date.issued	2005-12-01	en_US
dc.identifier.citation	Proceedings of the 2005 Intelligent Sensors, Sensor Networks and Information Processing Conference, 2005, 2005 pp. 151 - 156	en_US
dc.identifier.isbn	0780393996	en_US
dc.identifier.isbn	9780780393998	en_US
dc.identifier.uri	http://hdl.handle.net/10453/2619
dc.description.abstract	This paper presents a practical approach to solve the simultaneous localization and mapping (SLAM) problem for autonomous mobile platforms by using natural visual landmarks obtained from an stereoscopic camera. It is an attempt to depart from traditional sensors such as laser rangefinders in order to gain the many benefits of nature-inspired information-rich 3D vision sensors. Whilst this makes the system fully observable in that the sensor provide enough information (range and bearing) to compute the full 2D estate of the observed landmarks from a single position, it is also true that depth information is difficult to rely on, particularly on measurements beyond a few meters (in fact the full 3D estate is observable, but here robot motion is constrained to 2D and only the 2D problem is considered). The work presented here is an attempt to overcome such a drawback by tackling the problem from a partially measurable SLAM perspective in that only landmark bearing from one of the cameras is employed in the fusion estimation. Range information estimates from the stereo pair is only used during map building in the landmark initialization phase in order to provide a reasonably accurate initial estimate. An additional benefit of the approach presented here lies in the data association aspect of SLAM. The availability of powerful feature extraction algorithms from the vision community, such as SIFT, permits a more flexible SLAM implementation separated from feature representation, extraction and matching, essentially carrying out matching with minimal recourse to geometry. Simulation results on real data illustrate the validity of the approach. © 2005 IEEE.	en_US
dc.relation.ispartof	Proceedings of the 2005 Intelligent Sensors, Sensor Networks and Information Processing Conference	en_US
dc.title	Vision-based SLAM using natural features in indoor environments	en_US
dc.type	Conference Proceeding
utslib.citation.volume	2005	en_US
utslib.for	0902 Automotive Engineering	en_US
dc.location.activity	Melbourne, Australia	en_US
dc.location.activity	ISI:000242473000006
dc.location.activity	Melbourne, AUSTRALIA
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 Computer Science
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.publication-status	Published	en_US
pubs.volume	2005	en_US

Abstract:

This paper presents a practical approach to solve the simultaneous localization and mapping (SLAM) problem for autonomous mobile platforms by using natural visual landmarks obtained from an stereoscopic camera. It is an attempt to depart from traditional sensors such as laser rangefinders in order to gain the many benefits of nature-inspired information-rich 3D vision sensors. Whilst this makes the system fully observable in that the sensor provide enough information (range and bearing) to compute the full 2D estate of the observed landmarks from a single position, it is also true that depth information is difficult to rely on, particularly on measurements beyond a few meters (in fact the full 3D estate is observable, but here robot motion is constrained to 2D and only the 2D problem is considered). The work presented here is an attempt to overcome such a drawback by tackling the problem from a partially measurable SLAM perspective in that only landmark bearing from one of the cameras is employed in the fusion estimation. Range information estimates from the stereo pair is only used during map building in the landmark initialization phase in order to provide a reasonably accurate initial estimate. An additional benefit of the approach presented here lies in the data association aspect of SLAM. The availability of powerful feature extraction algorithms from the vision community, such as SIFT, permits a more flexible SLAM implementation separated from feature representation, extraction and matching, essentially carrying out matching with minimal recourse to geometry. Simulation results on real data illustrate the validity of the approach. © 2005 IEEE.

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

http://hdl.handle.net/10453/2619