Enhanced Low-Resolution LiDAR-Camera Calibration via Depth Interpolation and Supervised Contrastive Learning

Zhikang Zhang; Zifan Yu; Suya You; Raghuveer Rao; Sanjeev Agarwal; Fengbo Ren

doi:10.1109/ICASSP49357.2023.10096393

Enhanced Low-Resolution LiDAR-Camera Calibration via Depth Interpolation and Supervised Contrastive Learning

Zhikang Zhang, Zifan Yu, Suya You, Raghuveer Rao, Sanjeev Agarwal, Fengbo Ren

Engineering, Ira A. Fulton Schools of (IAFSE)

Research output: Contribution to journal › Conference article › peer-review

1 Scopus citations

Abstract

Motivated by the increasing application of low-resolution LiDAR, we target the problem of low-resolution LiDAR-camera calibration in this work. The main challenges are two-fold: sparsity and noise in point clouds. To address the problem, we propose to apply depth interpolation to increase the point density and supervised contrastive learning to learn noise-resistant features. The experiments on RELLIS-3D demonstrate that our approach achieves an average mean absolute rotation/translation errors of 0.15cm/0.33° on 32-channel LiDAR point cloud data, which significantly outperforms all reference methods.

Original language	English (US)
Journal	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
DOIs	https://doi.org/10.1109/ICASSP49357.2023.10096393
State	Published - 2023
Event	48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 - Rhodes Island, Greece Duration: Jun 4 2023 → Jun 10 2023

Keywords

image interpolation
LiDAR-camera calibration
low-resolution point cloud
supervised contrastive learning

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP49357.2023.10096393

Cite this

@article{e99760341c1d4f42b94f49580cc33832,

title = "Enhanced Low-Resolution LiDAR-Camera Calibration via Depth Interpolation and Supervised Contrastive Learning",

abstract = "Motivated by the increasing application of low-resolution LiDAR, we target the problem of low-resolution LiDAR-camera calibration in this work. The main challenges are two-fold: sparsity and noise in point clouds. To address the problem, we propose to apply depth interpolation to increase the point density and supervised contrastive learning to learn noise-resistant features. The experiments on RELLIS-3D demonstrate that our approach achieves an average mean absolute rotation/translation errors of 0.15cm/0.33° on 32-channel LiDAR point cloud data, which significantly outperforms all reference methods.",

keywords = "image interpolation, LiDAR-camera calibration, low-resolution point cloud, supervised contrastive learning",

author = "Zhikang Zhang and Zifan Yu and Suya You and Raghuveer Rao and Sanjeev Agarwal and Fengbo Ren",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 ; Conference date: 04-06-2023 Through 10-06-2023",

year = "2023",

doi = "10.1109/ICASSP49357.2023.10096393",

language = "English (US)",

journal = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

issn = "1520-6149",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Enhanced Low-Resolution LiDAR-Camera Calibration via Depth Interpolation and Supervised Contrastive Learning

AU - Zhang, Zhikang

AU - Yu, Zifan

AU - You, Suya

AU - Rao, Raghuveer

AU - Agarwal, Sanjeev

AU - Ren, Fengbo

PY - 2023

Y1 - 2023

N2 - Motivated by the increasing application of low-resolution LiDAR, we target the problem of low-resolution LiDAR-camera calibration in this work. The main challenges are two-fold: sparsity and noise in point clouds. To address the problem, we propose to apply depth interpolation to increase the point density and supervised contrastive learning to learn noise-resistant features. The experiments on RELLIS-3D demonstrate that our approach achieves an average mean absolute rotation/translation errors of 0.15cm/0.33° on 32-channel LiDAR point cloud data, which significantly outperforms all reference methods.

AB - Motivated by the increasing application of low-resolution LiDAR, we target the problem of low-resolution LiDAR-camera calibration in this work. The main challenges are two-fold: sparsity and noise in point clouds. To address the problem, we propose to apply depth interpolation to increase the point density and supervised contrastive learning to learn noise-resistant features. The experiments on RELLIS-3D demonstrate that our approach achieves an average mean absolute rotation/translation errors of 0.15cm/0.33° on 32-channel LiDAR point cloud data, which significantly outperforms all reference methods.

KW - image interpolation

KW - LiDAR-camera calibration

KW - low-resolution point cloud

KW - supervised contrastive learning

UR - http://www.scopus.com/inward/record.url?scp=85180528310&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85180528310&partnerID=8YFLogxK

U2 - 10.1109/ICASSP49357.2023.10096393

DO - 10.1109/ICASSP49357.2023.10096393

M3 - Conference article

AN - SCOPUS:85180528310

SN - 1520-6149

JO - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

JF - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

T2 - 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

Y2 - 4 June 2023 through 10 June 2023

ER -

Enhanced Low-Resolution LiDAR-Camera Calibration via Depth Interpolation and Supervised Contrastive Learning

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this