Robust ground plane detection from 3D point clouds

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

31 Scopus citations

Abstract

Ground provides useful and basic information such as traversal regions and location of 3D objects. The given point cloud may contain a point not only from ground, but also from other objects such as walls and people. Those points from other objects can disturb to find and identify a ground plane. In this paper, we propose robust and fast ground plane detection with an asymmetric kernel and RANSAC. We derive a probabilistic model of a 3D point based on an observation that a point from other objects is always above the ground. The asymmetric kernel is its approximation for fast computation, which is incorporated with RANSAC as a score function. We demonstrate effectiveness of our proposed method as quantitative experiments with our on-road 3D LiDAR dataset. The experimental result presents that our method was sufficiently accurate with slightly more computation. Finally, we also show our ground detection's application to augmented perception and visualization for drivers and remote operators.

Original languageEnglish
Title of host publicationInternational Conference on Control, Automation and Systems
PublisherIEEE Computer Society
Pages1076-1081
Number of pages6
ISBN (Electronic)9788993215069
DOIs
StatePublished - 16 Dec 2014
Event2014 14th International Conference on Control, Automation and Systems, ICCAS 2014 - Gyeonggi-do, Korea, Republic of
Duration: 22 Oct 201425 Oct 2014

Publication series

NameInternational Conference on Control, Automation and Systems
ISSN (Print)1598-7833

Conference

Conference2014 14th International Conference on Control, Automation and Systems, ICCAS 2014
Country/TerritoryKorea, Republic of
CityGyeonggi-do
Period22/10/1425/10/14

Keywords

  • 3D point cloud
  • asymmetric kernel
  • ground plane detection
  • obstacle detection
  • RANSAC
  • traversable region

Fingerprint

Dive into the research topics of 'Robust ground plane detection from 3D point clouds'. Together they form a unique fingerprint.

Cite this