3D LiDAR-based point cloud map registration

Using spatial location of visual features

Minhwan Shin, Jaeseung Kim, Jongmin Jeong, Jin Bae Park

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, a novel approach for the registration method of 3D point cloud maps is presented. During the operation of unmanned system, the construction of 3D maps for the environment is an important prerequisite for many navigation tasks. Generally 3D maps are widely utilized to recognize the location of the unmanned agent. Traditional map aligning techniques that use ICP (Iterative Closest Point) method relate points having the closest distance in different cloud maps in order to combine and extend the 3D maps. The method can be easily adopted in registration among sparse point cloud maps or consecutive scanning problems. However, this approach takes long computation time when aligning large scale maps including a lot of points. Therefore, an improved 3D point cloud map registration method is proposed to register precisely and effectively two maps using low-cost cameras. By combining odometry information derived from the SLAM (Simultaneous Localization and Mapping) procedure and the 3D position of the selected image feature points, location of the coexisting places in both maps are extracted. Then, the estimation of rigid body transform between the origins of each map is achieved. The effectiveness of the presented method is quantitatively validated by experiment on challenging instances of the merging problem and comparison with an existing registration method.

Original languageEnglish
Title of host publication2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages373-378
Number of pages6
ISBN (Electronic)9781538613054
DOIs
Publication statusPublished - 2018 Feb 13
Event2nd International Conference on Robotics and Automation Engineering, ICRAE 2017 - Shanghai, China
Duration: 2017 Dec 292017 Dec 31

Publication series

Name2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017
Volume2017-December

Other

Other2nd International Conference on Robotics and Automation Engineering, ICRAE 2017
CountryChina
CityShanghai
Period17/12/2917/12/31

Fingerprint

Point Cloud
Lidar
Registration
Vision
Point Location
Simultaneous Localization and Mapping
Feature Point
Merging
Rigid Body
Navigation
Consecutive
Scanning
Camera
Cameras
Transform

All Science Journal Classification (ASJC) codes

  • Control and Optimization
  • Mechanical Engineering
  • Control and Systems Engineering

Cite this

Shin, M., Kim, J., Jeong, J., & Park, J. B. (2018). 3D LiDAR-based point cloud map registration: Using spatial location of visual features. In 2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017 (pp. 373-378). (2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017; Vol. 2017-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRAE.2017.8291413
Shin, Minhwan ; Kim, Jaeseung ; Jeong, Jongmin ; Park, Jin Bae. / 3D LiDAR-based point cloud map registration : Using spatial location of visual features. 2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 373-378 (2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017).
@inproceedings{3813ed731e8c4d4aad836d6b1aa33b35,
title = "3D LiDAR-based point cloud map registration: Using spatial location of visual features",
abstract = "In this paper, a novel approach for the registration method of 3D point cloud maps is presented. During the operation of unmanned system, the construction of 3D maps for the environment is an important prerequisite for many navigation tasks. Generally 3D maps are widely utilized to recognize the location of the unmanned agent. Traditional map aligning techniques that use ICP (Iterative Closest Point) method relate points having the closest distance in different cloud maps in order to combine and extend the 3D maps. The method can be easily adopted in registration among sparse point cloud maps or consecutive scanning problems. However, this approach takes long computation time when aligning large scale maps including a lot of points. Therefore, an improved 3D point cloud map registration method is proposed to register precisely and effectively two maps using low-cost cameras. By combining odometry information derived from the SLAM (Simultaneous Localization and Mapping) procedure and the 3D position of the selected image feature points, location of the coexisting places in both maps are extracted. Then, the estimation of rigid body transform between the origins of each map is achieved. The effectiveness of the presented method is quantitatively validated by experiment on challenging instances of the merging problem and comparison with an existing registration method.",
author = "Minhwan Shin and Jaeseung Kim and Jongmin Jeong and Park, {Jin Bae}",
year = "2018",
month = "2",
day = "13",
doi = "10.1109/ICRAE.2017.8291413",
language = "English",
series = "2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "373--378",
booktitle = "2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017",
address = "United States",

}

Shin, M, Kim, J, Jeong, J & Park, JB 2018, 3D LiDAR-based point cloud map registration: Using spatial location of visual features. in 2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017. 2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017, vol. 2017-December, Institute of Electrical and Electronics Engineers Inc., pp. 373-378, 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017, Shanghai, China, 17/12/29. https://doi.org/10.1109/ICRAE.2017.8291413

3D LiDAR-based point cloud map registration : Using spatial location of visual features. / Shin, Minhwan; Kim, Jaeseung; Jeong, Jongmin; Park, Jin Bae.

2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017. Institute of Electrical and Electronics Engineers Inc., 2018. p. 373-378 (2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017; Vol. 2017-December).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - 3D LiDAR-based point cloud map registration

T2 - Using spatial location of visual features

AU - Shin, Minhwan

AU - Kim, Jaeseung

AU - Jeong, Jongmin

AU - Park, Jin Bae

PY - 2018/2/13

Y1 - 2018/2/13

N2 - In this paper, a novel approach for the registration method of 3D point cloud maps is presented. During the operation of unmanned system, the construction of 3D maps for the environment is an important prerequisite for many navigation tasks. Generally 3D maps are widely utilized to recognize the location of the unmanned agent. Traditional map aligning techniques that use ICP (Iterative Closest Point) method relate points having the closest distance in different cloud maps in order to combine and extend the 3D maps. The method can be easily adopted in registration among sparse point cloud maps or consecutive scanning problems. However, this approach takes long computation time when aligning large scale maps including a lot of points. Therefore, an improved 3D point cloud map registration method is proposed to register precisely and effectively two maps using low-cost cameras. By combining odometry information derived from the SLAM (Simultaneous Localization and Mapping) procedure and the 3D position of the selected image feature points, location of the coexisting places in both maps are extracted. Then, the estimation of rigid body transform between the origins of each map is achieved. The effectiveness of the presented method is quantitatively validated by experiment on challenging instances of the merging problem and comparison with an existing registration method.

AB - In this paper, a novel approach for the registration method of 3D point cloud maps is presented. During the operation of unmanned system, the construction of 3D maps for the environment is an important prerequisite for many navigation tasks. Generally 3D maps are widely utilized to recognize the location of the unmanned agent. Traditional map aligning techniques that use ICP (Iterative Closest Point) method relate points having the closest distance in different cloud maps in order to combine and extend the 3D maps. The method can be easily adopted in registration among sparse point cloud maps or consecutive scanning problems. However, this approach takes long computation time when aligning large scale maps including a lot of points. Therefore, an improved 3D point cloud map registration method is proposed to register precisely and effectively two maps using low-cost cameras. By combining odometry information derived from the SLAM (Simultaneous Localization and Mapping) procedure and the 3D position of the selected image feature points, location of the coexisting places in both maps are extracted. Then, the estimation of rigid body transform between the origins of each map is achieved. The effectiveness of the presented method is quantitatively validated by experiment on challenging instances of the merging problem and comparison with an existing registration method.

UR - http://www.scopus.com/inward/record.url?scp=85050961088&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050961088&partnerID=8YFLogxK

U2 - 10.1109/ICRAE.2017.8291413

DO - 10.1109/ICRAE.2017.8291413

M3 - Conference contribution

T3 - 2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017

SP - 373

EP - 378

BT - 2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Shin M, Kim J, Jeong J, Park JB. 3D LiDAR-based point cloud map registration: Using spatial location of visual features. In 2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017. Institute of Electrical and Electronics Engineers Inc. 2018. p. 373-378. (2017 2nd International Conference on Robotics and Automation Engineering, ICRAE 2017). https://doi.org/10.1109/ICRAE.2017.8291413