3D Point Clouds Data Super Resolution Aided LiDAR Odometry for Vehicular Positioning in Urban Canyons

Jiang Yue; Weisong Wen; Jin Han; Li Ta Hsu

doi:10.1109/TVT.2021.3069212

3D Point Clouds Data Super Resolution Aided LiDAR Odometry for Vehicular Positioning in Urban Canyons

Jiang Yue, Weisong Wen, Jin Han, Li Ta Hsu

Research output: Journal article publication › Journal article › Academic research › peer-review

9 Citations (Scopus)

Abstract

LiDAR odometry algorithms are extensively studied for vehicular positioning. However, achieving high-precision positioning using low-cost 16-channel LiDAR in urban canyons remains a challenging problem due to the limited point cloud density from low-cost LiDAR and excessive dynamic surrounding objects. To fill this gap, this paper proposes enriching sparse 3D point clouds to denser clouds via a novel deep learning-based superresolution (SR) algorithm before its utilization in 3D LiDAR odometry. We validate the effectiveness of the proposed method using the KITTI dataset and a challenging dataset collected in an urban canyon (with complex environmental structures and dynamic objects) of Hong Kong. We conclude that significantly denser point clouds are achieved with considerable accuracy. In addition, significantly improved performance of 3D LiDAR odometry is obtained in the evaluated dataset collected in an urban canyon of Hong Kong.

Original language	English
Article number	9388922
Pages (from-to)	4098-4112
Number of pages	15
Journal	IEEE Transactions on Vehicular Technology
Volume	70
Issue number	5
DOIs	https://doi.org/10.1109/TVT.2021.3069212
Publication status	Published - May 2021

Keywords

LiDAR
LiDAR odometry
NDT
convolutional neural network
sparse point clouds
superresolution
vehicular positioning

ASJC Scopus subject areas

Automotive Engineering
Aerospace Engineering
Electrical and Electronic Engineering
Applied Mathematics

More information

10.1109/TVT.2021.3069212

Cite this

@article{b06277b5d43a45f19a5afd3ed91deb86,

title = "3D Point Clouds Data Super Resolution Aided LiDAR Odometry for Vehicular Positioning in Urban Canyons",

abstract = "LiDAR odometry algorithms are extensively studied for vehicular positioning. However, achieving high-precision positioning using low-cost 16-channel LiDAR in urban canyons remains a challenging problem due to the limited point cloud density from low-cost LiDAR and excessive dynamic surrounding objects. To fill this gap, this paper proposes enriching sparse 3D point clouds to denser clouds via a novel deep learning-based superresolution (SR) algorithm before its utilization in 3D LiDAR odometry. We validate the effectiveness of the proposed method using the KITTI dataset and a challenging dataset collected in an urban canyon (with complex environmental structures and dynamic objects) of Hong Kong. We conclude that significantly denser point clouds are achieved with considerable accuracy. In addition, significantly improved performance of 3D LiDAR odometry is obtained in the evaluated dataset collected in an urban canyon of Hong Kong.",

keywords = "LiDAR, LiDAR odometry, NDT, convolutional neural network, sparse point clouds, superresolution, vehicular positioning",

author = "Jiang Yue and Weisong Wen and Jin Han and Hsu, {Li Ta}",

note = "Funding Information: Manuscript received May 9, 2020; revised August 27, 2020 and February 1, 2021; accepted March 14, 2021. Date of publication March 29, 2021; date of current version June 9, 2021. This work was supported in part by the Hong Kong PolyU internal Grant on the project ZVKZ, “Navigation for Autonomous Driving Vehicle using Sensor Integration” and in part by the National Natural Science Foundation of China under Grant 61601225. The review of this article was coordinated by Prof. Z. Ma. (Corresponding author: Weisong Wen.) Jiang Yue is with the Nanjing University of Science and Technology, Nanjing, Jiangsu 210014, China, and also with the Intelligent Positioning and Navigation Lab, The Hong Kong Polytechnic University 999077, Hong Kong (e-mail: jiang.yue@polyu.edu.hk). Publisher Copyright: {\textcopyright} 1967-2012 IEEE.",

year = "2021",

month = may,

doi = "10.1109/TVT.2021.3069212",

language = "English",

volume = "70",

pages = "4098--4112",

journal = "IEEE Transactions on Vehicular Technology",

issn = "0018-9545",

publisher = "IEEE",

number = "5",

}

TY - JOUR

T1 - 3D Point Clouds Data Super Resolution Aided LiDAR Odometry for Vehicular Positioning in Urban Canyons

AU - Yue, Jiang

AU - Wen, Weisong

AU - Han, Jin

AU - Hsu, Li Ta

N1 - Funding Information: Manuscript received May 9, 2020; revised August 27, 2020 and February 1, 2021; accepted March 14, 2021. Date of publication March 29, 2021; date of current version June 9, 2021. This work was supported in part by the Hong Kong PolyU internal Grant on the project ZVKZ, “Navigation for Autonomous Driving Vehicle using Sensor Integration” and in part by the National Natural Science Foundation of China under Grant 61601225. The review of this article was coordinated by Prof. Z. Ma. (Corresponding author: Weisong Wen.) Jiang Yue is with the Nanjing University of Science and Technology, Nanjing, Jiangsu 210014, China, and also with the Intelligent Positioning and Navigation Lab, The Hong Kong Polytechnic University 999077, Hong Kong (e-mail: jiang.yue@polyu.edu.hk). Publisher Copyright: © 1967-2012 IEEE.

PY - 2021/5

Y1 - 2021/5

N2 - LiDAR odometry algorithms are extensively studied for vehicular positioning. However, achieving high-precision positioning using low-cost 16-channel LiDAR in urban canyons remains a challenging problem due to the limited point cloud density from low-cost LiDAR and excessive dynamic surrounding objects. To fill this gap, this paper proposes enriching sparse 3D point clouds to denser clouds via a novel deep learning-based superresolution (SR) algorithm before its utilization in 3D LiDAR odometry. We validate the effectiveness of the proposed method using the KITTI dataset and a challenging dataset collected in an urban canyon (with complex environmental structures and dynamic objects) of Hong Kong. We conclude that significantly denser point clouds are achieved with considerable accuracy. In addition, significantly improved performance of 3D LiDAR odometry is obtained in the evaluated dataset collected in an urban canyon of Hong Kong.

AB - LiDAR odometry algorithms are extensively studied for vehicular positioning. However, achieving high-precision positioning using low-cost 16-channel LiDAR in urban canyons remains a challenging problem due to the limited point cloud density from low-cost LiDAR and excessive dynamic surrounding objects. To fill this gap, this paper proposes enriching sparse 3D point clouds to denser clouds via a novel deep learning-based superresolution (SR) algorithm before its utilization in 3D LiDAR odometry. We validate the effectiveness of the proposed method using the KITTI dataset and a challenging dataset collected in an urban canyon (with complex environmental structures and dynamic objects) of Hong Kong. We conclude that significantly denser point clouds are achieved with considerable accuracy. In addition, significantly improved performance of 3D LiDAR odometry is obtained in the evaluated dataset collected in an urban canyon of Hong Kong.

KW - LiDAR

KW - LiDAR odometry

KW - NDT

KW - convolutional neural network

KW - sparse point clouds

KW - superresolution

KW - vehicular positioning

UR - http://www.scopus.com/inward/record.url?scp=85103797780&partnerID=8YFLogxK

U2 - 10.1109/TVT.2021.3069212

DO - 10.1109/TVT.2021.3069212

M3 - Journal article

AN - SCOPUS:85103797780

SN - 0018-9545

VL - 70

SP - 4098

EP - 4112

JO - IEEE Transactions on Vehicular Technology

JF - IEEE Transactions on Vehicular Technology

IS - 5

M1 - 9388922

ER -

3D Point Clouds Data Super Resolution Aided LiDAR Odometry for Vehicular Positioning in Urban Canyons

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this