A modular hybrid SLAM for the 3D mapping of large scale environments

Underground mining environments pose many unique challenges to the task of creating extensive, survey quality 3D maps. The extreme characteristics of such environments require a modular mapping solution which has no dependency on Global Positioning Systems (GPS), physical odometry, a priori informat...

Full description

Bibliographic Details
Main Authors: Le Cras, Jared, Paxman, Jonathan
Other Authors: Danwei Wang
Format: Conference Paper
Published: IEEE 2012
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/22812
_version_ 1848750976017629184
author Le Cras, Jared
Paxman, Jonathan
author2 Danwei Wang
author_facet Danwei Wang
Le Cras, Jared
Paxman, Jonathan
author_sort Le Cras, Jared
building Curtin Institutional Repository
collection Online Access
description Underground mining environments pose many unique challenges to the task of creating extensive, survey quality 3D maps. The extreme characteristics of such environments require a modular mapping solution which has no dependency on Global Positioning Systems (GPS), physical odometry, a priori information or motion model simplification. These restrictions rule out many existing 3D mapping approaches. This work examines a hybrid approach to mapping, fusing omnidirectional vision and 3D range data to produce an automatically registered, accurate and dense 3D map. A series of discrete 3D laser scans are registered through a combination of vision based bearing-only localization and scan matching with the Iterative Closest Point (ICP) algorithm. Depth information provided by the laser scans is used to correctly scale the bearing-only feature map, which in turn supplies an initial pose estimate for a registration algorithm to build the 3D map and correct localization drift. The resulting extensive maps require no external instrumentation or a priori information. Preliminary testing demonstrated the ability of the hybrid system to produce a highly accurate 3D map of an extensive indoor space.
first_indexed 2025-11-14T07:45:23Z
format Conference Paper
id curtin-20.500.11937-22812
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:45:23Z
publishDate 2012
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-228122017-09-13T15:59:26Z A modular hybrid SLAM for the 3D mapping of large scale environments Le Cras, Jared Paxman, Jonathan Danwei Wang mining localization omnivision sensor fusion 3D mapping SLAM Underground mining environments pose many unique challenges to the task of creating extensive, survey quality 3D maps. The extreme characteristics of such environments require a modular mapping solution which has no dependency on Global Positioning Systems (GPS), physical odometry, a priori information or motion model simplification. These restrictions rule out many existing 3D mapping approaches. This work examines a hybrid approach to mapping, fusing omnidirectional vision and 3D range data to produce an automatically registered, accurate and dense 3D map. A series of discrete 3D laser scans are registered through a combination of vision based bearing-only localization and scan matching with the Iterative Closest Point (ICP) algorithm. Depth information provided by the laser scans is used to correctly scale the bearing-only feature map, which in turn supplies an initial pose estimate for a registration algorithm to build the 3D map and correct localization drift. The resulting extensive maps require no external instrumentation or a priori information. Preliminary testing demonstrated the ability of the hybrid system to produce a highly accurate 3D map of an extensive indoor space. 2012 Conference Paper http://hdl.handle.net/20.500.11937/22812 10.1109/ICARCV.2012.6485300 IEEE fulltext
spellingShingle mining
localization
omnivision
sensor fusion
3D mapping
SLAM
Le Cras, Jared
Paxman, Jonathan
A modular hybrid SLAM for the 3D mapping of large scale environments
title A modular hybrid SLAM for the 3D mapping of large scale environments
title_full A modular hybrid SLAM for the 3D mapping of large scale environments
title_fullStr A modular hybrid SLAM for the 3D mapping of large scale environments
title_full_unstemmed A modular hybrid SLAM for the 3D mapping of large scale environments
title_short A modular hybrid SLAM for the 3D mapping of large scale environments
title_sort modular hybrid slam for the 3d mapping of large scale environments
topic mining
localization
omnivision
sensor fusion
3D mapping
SLAM
url http://hdl.handle.net/20.500.11937/22812