Multimodal localization: Stereo over LiDAR map

Zuo, X; Ye, W; Yang, Y; Zheng, R; Vidal‐Calleja, T; Huang, G; Liu, Y

Multimodal localization: Stereo over LiDAR map

Zuo, X Ye, W Yang, Y Zheng, R Vidal‐Calleja, T Huang, G Liu, Y

Permalink

Publisher:: Wiley
Publication Type:: Journal Article
Citation:: Journal of Field Robotics, 2020, 37, (6), pp. 1003-1026
Issue Date:: 2020-01-21

Closed Access

	Filename	Description	Size
	rob.21936.pdf	Published version	10.95 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zuo, X
dc.contributor.author	Ye, W
dc.contributor.author	Yang, Y
dc.contributor.author	Zheng, R
dc.contributor.author	Vidal‐Calleja, T
dc.contributor.author	Huang, G
dc.contributor.author	Liu, Y
dc.date.accessioned	2021-03-08T01:28:11Z
dc.date.available	2021-03-08T01:28:11Z
dc.date.issued	2020-01-21
dc.identifier.citation	Journal of Field Robotics, 2020, 37, (6), pp. 1003-1026
dc.identifier.issn	1556-4959
dc.identifier.issn	1556-4967
dc.identifier.uri	http://hdl.handle.net/10453/146892
dc.description.abstract	In this paper, we present a real‐time high‐precision visual localization system for an autonomous vehicle which employs only low‐cost stereo cameras to localize the vehicle with a priori map built using a more expensive 3D LiDAR sensor. To this end, we construct two different visual maps: a sparse feature visual map for visual odometry (VO) based motion tracking, and a semidense visual map for registration with the prior LiDAR map. To register two point clouds sourced from different modalities (i.e., cameras and LiDAR), we leverage probabilistic weighted normal distributions transformation (ProW‐NDT), by particularly taking into account the uncertainty of source point clouds. The registration results are then fused via pose graph optimization to correct the VO drift. Moreover, surfels extracted from the prior LiDAR map are used to refine the sparse 3D visual features that will further improve VO‐based motion estimation. The proposed system has been tested extensively in both simulated and real‐world experiments, showing that robust, high‐precision, real‐time localization can be achieved.
dc.language	en
dc.publisher	Wiley
dc.relation.ispartof	Journal of Field Robotics
dc.relation.isbasedon	10.1002/rob.21936
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0906 Electrical and Electronic Engineering, 0913 Mechanical Engineering
dc.subject.classification	Industrial Engineering & Automation
dc.title	Multimodal localization: Stereo over LiDAR map
dc.type	Journal Article
utslib.citation.volume	37
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0913 Mechanical Engineering
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	0913 Mechanical Engineering
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAS - Centre for Autonomous Systems
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
utslib.copyright.status	closed_access	*
pubs.consider-herdc	true
dc.date.updated	2021-03-08T01:28:03Z
pubs.issue	6
pubs.publication-status	Published online
pubs.volume	37
utslib.citation.issue	6

Abstract:

In this paper, we present a real‐time high‐precision visual localization system for an autonomous vehicle which employs only low‐cost stereo cameras to localize the vehicle with a priori map built using a more expensive 3D LiDAR sensor. To this end, we construct two different visual maps: a sparse feature visual map for visual odometry (VO) based motion tracking, and a semidense visual map for registration with the prior LiDAR map. To register two point clouds sourced from different modalities (i.e., cameras and LiDAR), we leverage probabilistic weighted normal distributions transformation (ProW‐NDT), by particularly taking into account the uncertainty of source point clouds. The registration results are then fused via pose graph optimization to correct the VO drift. Moreover, surfels extracted from the prior LiDAR map are used to refine the sparse 3D visual features that will further improve VO‐based motion estimation. The proposed system has been tested extensively in both simulated and real‐world experiments, showing that robust, high‐precision, real‐time localization can be achieved.

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

http://hdl.handle.net/10453/146892