3D LiDAR and color camera data fusion

Yuqi Ding, Jiaming Liu, Jinwei Ye, Weidong Xiang, Hsiao Chun Wu, Costas Busch

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

3D LiDAR sensor and 2D color camera provide complementary information of a scene. It is essential to fuse both types of data to obtain a holistic representation of the real-world scene. In this paper, we present a method to fuse the data captured by rigidly mounted LiDAR and camera. We first cocalibrate the LiDAR and camera with a calibration target. We then establish 3D-2D correspondences and fuse the LiDAR and camera data through geometric transformations. Experimental results demonstrate that our method is able to fuse the 3D LiDAR point cloud with the 2D color image efficiently and accurately. Our method is also fast and can be used in autonomous driving applications.

Original languageEnglish (US)
Title of host publication15th IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2020
PublisherIEEE Computer Society
ISBN (Electronic)9781728157849
DOIs
StatePublished - Oct 27 2020
Event15th IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2020 - Paris, France
Duration: Oct 27 2020Oct 29 2020

Publication series

NameIEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB
Volume2020-October
ISSN (Print)2155-5044
ISSN (Electronic)2155-5052

Conference

Conference15th IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2020
CountryFrance
CityParis
Period10/27/2010/29/20

Keywords

  • Calibration
  • Color Camera
  • Data Fusion
  • LiDAR
  • Point Cloud

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications
  • Computer Science Applications
  • Human-Computer Interaction
  • Electrical and Electronic Engineering
  • Media Technology
  • Communication

Fingerprint Dive into the research topics of '3D LiDAR and color camera data fusion'. Together they form a unique fingerprint.

Cite this