Citation: Wang, G.; Wei, X.; Chen, Y.;
Zhang, T.; Hou, M.; Liu, Z. A
Multi-Channel Descriptor for
LiDAR-Based Loop Closure
Detection and Its Application. Remote
Sens. 2022, 14, 5877. https://doi.org/
10.3390/rs14225877
Academic Editors: M. Jamal Deen,
Subhas Mukhopadhyay,
Yangquan Chen, Simone Morais,
Nunzio Cennamo and Junseop Lee
Received: 1 August 2022
Accepted: 16 November 2022
Published: 19 November 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
A Multi-Channel Descriptor for LiDAR-Based Loop Closure
Detection and Its Application
Gang Wang
1,2,3,4,
*, Xiaomeng Wei
2
, Yu Chen
2
, Tongzhou Zhang
1
, Minghui Hou
1
and Zhaohan Liu
5
1
College of Computer Science and Technology, Jilin University, Changchun 130012, China
2
College of Software, Jilin University, Changchun 130012, China
3
Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education,
Jilin University, Changchun 130012, China
4
State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun 130012, China
5
College of Electronic Science and Engineering, Jilin University, Changchun 130012, China
* Correspondence: gangwang@jlu.edu.cn
Abstract:
Simultaneous localization and mapping (SLAM) algorithm is a prerequisite for unmanned
ground vehicle (UGV) localization, path planning, and navigation, which includes two essential
components: frontend odometry and backend optimization. Frontend odometry tends to amplify the
cumulative error continuously, leading to ghosting and drifting on the mapping results. However,
loop closure detection (LCD) can be used to address this technical issue by significantly eliminating
the cumulative error. The existing LCD methods decide whether a loop exists by constructing local or
global descriptors and calculating the similarity between descriptors, which attaches great importance
to the design of discriminative descriptors and effective similarity measurement mechanisms. In
this paper, we first propose novel multi-channel descriptors (CMCD) to alleviate the lack of point
cloud single information in the discriminative power of scene description. The distance, height,
and intensity information of the point cloud is encoded into three independent channels of the
shadow-casting region (bin) and then compressed it into a two-dimensional global descriptor. Next,
an ORB-based dynamic threshold feature extraction algorithm (DTORB) is designed using objective
2D descriptors to describe the distributions of global and local point clouds. Then, a DTORB-
based similarity measurement method is designed using the rotation-invariance and visualization
characteristic of descriptor features to overcome the subjective tendency of the constant threshold
ORB algorithm in descriptor feature extraction. Finally, verification is performed over KITTI odometry
sequences and the campus datasets of Jilin University collected by us. The experimental results
demonstrate the superior performance of our method to the state-of-the-art approaches.
Keywords:
autonomous driving; unmanned ground vehicle; LiDAR; simultaneous localization and
mapping; loop closure detection
1. Introduction
SLAM [
1
] is a key technology in the field of UGV, which can provide a prior map for
UGV to perform the positioning function. The SLAM system [
2
–
4
] estimates the poses
of vehicles within a certain period of time through the continuous data collected by the
sensors and builds incremental maps via these estimated poses to achieve the goals of
self-orientation and mapping. Undoubtedly, accurate estimation of poses is a key link in
the whole process. The higher the accuracy of pose estimation, the higher the mapping
quality. However, the traditional pose estimation methods that rely only on the interframe
matching of the odometer are prone to the problem of error accumulation. The estimated
trajectory of a system in long-time operation is bound to deviate significantly from the
actual moving trajectory. These drift errors can be corrected by additional information
provided by the LCD algorithm [
5
,
6
], which can recognize the revisited region by building
a new constraint relationship between the current and historical frames to supplement
Remote Sens. 2022, 14, 5877. https://doi.org/10.3390/rs14225877 https://www.mdpi.com/journal/remotesensing
