Skip to main navigation Skip to search Skip to main content

Image features-based mobile robot localization

  • Rui Lin*
  • , Zhenhua Wang
  • , Rongchuan Sun
  • , Lining Sun
  • *Corresponding author for this work
  • Soochow University

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

Abstract

Accurate localization plays a pivotal role in mobile robot navigation. In this paper, we present a novel algorithm for mobile robot localization based on image features. First a novel method is proposed to extract distinctive invariant image features, which is coined PLOT (Polynomial Local Orientation Tensor). The stability of these features to image translation, scaling, rotation and illumination changes makes them suitable landmarks for mobile robot localization. The visual landmarks relative to the robot can be established by matching the PLOT features. Mobile robot localization is achieved by matching these distinctive landmarks in the current frame to the database map built simultaneously. RANSAC algorithm is improved, coined extended RANSAC, for mobile robot pose estimate due to its efficiency. Meanwhile, the visual landmarks in the database map are updated correspondingly. Experimental results show that the proposed method based on the PLOT features achieves localization for mobile robot with higher precision.

Original languageEnglish
Title of host publication2012 IEEE International Conference on Information and Automation, ICIA 2012
Pages304-310
Number of pages7
DOIs
StatePublished - 2012
Externally publishedYes
Event2012 IEEE International Conference on Information and Automation, ICIA 2012 - Shenyang, China
Duration: 6 Jun 20128 Jun 2012

Publication series

Name2012 IEEE International Conference on Information and Automation, ICIA 2012

Conference

Conference2012 IEEE International Conference on Information and Automation, ICIA 2012
Country/TerritoryChina
CityShenyang
Period6/06/128/06/12

Keywords

  • PLOT features
  • extended RANSAC
  • localization
  • mobile robot
  • stereo vision

Fingerprint

Dive into the research topics of 'Image features-based mobile robot localization'. Together they form a unique fingerprint.

Cite this