3D point cloud relocation in the mine scene

Linchong Chen

doi:10.1117/12.2625370

12 December 2021 3D point cloud relocation in the mine scene

Linchong Chen

Proceedings Volume 12127, International Conference on Intelligent Equipment and Special Robots (ICIESR 2021); 121272M (2021) https://doi.org/10.1117/12.2625370
Event: International Conference on Intelligent Equipment and Special Robots (ICIESR 2021), 2021, Qingdao, China

Abstract

Aiming at the problems of difficulty in positioning without GPS signals in the mine scene, the traditional wireless positioning method has a long deployment time and rather low accuracy. The 3D lidar point cloud technology is selected for localization, based on the 3D point cloud SLAM technology. Because the highly similar geometric characteristics of the passageways of mines, the indoor corridor environment was chose for simulation experiments. First, a priori three-dimensional point cloud map was established, then the current frame point cloud matched with the prior map, and finally the pose in the prior map obtained from the matching to be used for tracking. A high-precision dead reckoning odometry was used as a priori pose and redundant localization to increase the system robustness when the lidar odometry fails. For relocation with high real-time and accuracy requirements, NDT(Normal Distributions Transform) matching algorithm was used with two deficiencies of the are improved. First, grids was used to divide the point cloud into different clusters, and then the common size of clusters was used to dynamically determine the NDT resolution; Secondly, the speed of ikdtree and kdtree at rebuilding the tree and searching for nearest neighbors was evaluate, and finally the ikdtree was choosen to replace kdtree to acceleration the process of NDT matching algorithm. And the algorithm has tested at our intelligent car platform.

Citation Download Citation

Linchong Chen "3D point cloud relocation in the mine scene", Proc. SPIE 12127, International Conference on Intelligent Equipment and Special Robots (ICIESR 2021), 121272M (12 December 2021); https://doi.org/10.1117/12.2625370

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Mining

LIDAR

Sensors

Detection and tracking algorithms

Calibration

Distortion

Automatic tracking

Show All Keywords

Keywords/Phrases

Search In:

Publication Years