Appearance-based loop detection from 3D laser data using the normal distributions transform

Martin Magnusson, Henrik Andreasson, Andreas Nüchter, Achim J. Lilienthal

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

96 Scopus citations

Abstract

We propose a new approach to appearance based loop detection from metric 3D maps, exploiting the NDT surface representation. Locations are described with feature histograms based on surface orientation and smoothness, and loop closure can be detected by matching feature histograms. We also present a quantitative performance evaluation using two realworld data sets, showing that the proposed method works well in different environments.

Original languageEnglish
Title of host publication2009 IEEE International Conference on Robotics and Automation, ICRA '09
Pages23-28
Number of pages6
DOIs
StatePublished - 2009
Externally publishedYes
Event2009 IEEE International Conference on Robotics and Automation, ICRA '09 - Kobe, Japan
Duration: 12 May 200917 May 2009

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)1050-4729

Conference

Conference2009 IEEE International Conference on Robotics and Automation, ICRA '09
Country/TerritoryJapan
CityKobe
Period12/05/0917/05/09

Fingerprint

Dive into the research topics of 'Appearance-based loop detection from 3D laser data using the normal distributions transform'. Together they form a unique fingerprint.

Cite this