Skip to main navigation Skip to search Skip to main content

An automatic and efficient calibration method for LiDAR-camera in targetless environments

  • Fengli Yang
  • , Juzhi Zhu
  • , Long Zhao*
  • *Corresponding author for this work
  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Accurate calibration of LiDAR and camera in targetless environments is a crucial task in various applications. This paper proposes an automatic and efficient calibrationmethod forLiDARand camera in such environments. Firstly, the collected LiDAR point cloud and image data are preprocessed. Considering the richness of edges in natural environments, we incorporated edge features to establish the 2D- 3D correspondence between LiDAR and camera data. Additionally, we employed RANSAC to obtain a rough estimation of the LiDAR-camera transformation. Given the initial guess, we further optimize the transform estimation based on normalized information distance (a cross-modal distance measure based on mutual information). Experimental evaluations confirm the accuracy and efficiency of the proposed method in targetless environments.

Original languageEnglish
Title of host publicationProceedings of 2023 Chinese Intelligent Systems Conference - Volume II
EditorsYingmin Jia, Weicun Zhang, Yongling Fu, Jiqiang Wang
PublisherSpringer Science and Business Media Deutschland GmbH
Pages867-876
Number of pages10
ISBN (Print)9789819968817
DOIs
StatePublished - 2023
Event19th Chinese Intelligent Systems Conference, CISC 2023 - Ningbo, China
Duration: 14 Oct 202315 Oct 2023

Publication series

NameLecture Notes in Electrical Engineering
Volume1090 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference19th Chinese Intelligent Systems Conference, CISC 2023
Country/TerritoryChina
CityNingbo
Period14/10/2315/10/23

Keywords

  • Edge features
  • Extrinsic parameters
  • LiDAR-camera calibration

Fingerprint

Dive into the research topics of 'An automatic and efficient calibration method for LiDAR-camera in targetless environments'. Together they form a unique fingerprint.

Cite this