Using Local Symmetry for Landmark Selection

Gert Kootstra*, Sjoerd de Jong, Lambert R. B. Schomaker

*Corresponding author for this work

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

Abstract

Most visual Simultaneous Localization And Mapping (SLAM) methods use interest points as landmarks in their maps of the environment. Often the interest points are detected using contrast features, for instance those of the Scale Invariant Feature Transform (SIFT). The SIFT interest points, however, have problems with stability, and noise robustness. Taking our inspiration from human vision, we therefore propose the use of local symmetry to select interest points, Our method, the MUlti-scale Symmetry Transform (MUST), was tested on a robot-generated database including ground-truth information to quantify SLAM performance. We show that interest points selected using symmetry are more robust to noise and contrast manipulations, have a slightly better repeatability, and above all, result in better overall SLAM performance.

Original languageEnglish
Title of host publicationCOMPUTER VISION SYSTEMS, PROCEEDINGS
EditorsM Fritz, B Schiele, JH Piater
Place of PublicationBERLIN
PublisherSpringer
Pages94-103
Number of pages10
ISBN (Print)978-3-642-04666-7
Publication statusPublished - 2009
Event7th International Conference on Computer Vision Systems - , Belgium
Duration: 13-Oct-200915-Oct-2009

Publication series

NameLecture Notes in Computer Science
PublisherSPRINGER-VERLAG BERLIN
Volume5815
ISSN (Print)0302-9743

Other

Other7th International Conference on Computer Vision Systems
Country/TerritoryBelgium
Period13/10/200915/10/2009

Keywords

  • ROBOT LOCALIZATION
  • ACTIVE-VISION
  • FEATURES
  • DETECTORS
  • ATTENTION
  • OBJECTS
  • MODEL
  • SURF

Fingerprint

Dive into the research topics of 'Using Local Symmetry for Landmark Selection'. Together they form a unique fingerprint.

Cite this