Clustering and probabilistic matching of arbitrarily shaped ceiling features for monocular vision-based SLAM

Seo Yeon Hwang, Jae-Bok Song

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

This paper presents improved extraction and matching methods for arbitrarily shaped (AS) ceiling features for monocular vision-based simultaneous localization and mapping. The feature descriptor, which is robust to illumination changes, comprises the vertex distribution, size, and orientation strength of the region of interest. However, to cope with the problem of vertices being detected at different positions in successive images, Bayes rule is applied to preserve robust vertices and remove rarely observed vertices. Moreover, unstable features surrounded by similar features are clustered to create a robust feature by calculating their similarities to adjacent clusters. AS features from the proposed scheme are used as landmarks in the extended Kalman filter, and the effectiveness of the proposed scheme is verified through various experiments in real environments.

Original languageEnglish
Pages (from-to)739-747
Number of pages9
JournalAdvanced Robotics
Volume27
Issue number10
DOIs
Publication statusPublished - 2013 Jul 1

Fingerprint

Ceilings
Extended Kalman filters
Lighting
Experiments

Keywords

  • arbitrarily shaped feature
  • ceiling
  • mobile robot
  • SLAM

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Human-Computer Interaction
  • Computer Science Applications
  • Hardware and Architecture
  • Software

Cite this

Clustering and probabilistic matching of arbitrarily shaped ceiling features for monocular vision-based SLAM. / Hwang, Seo Yeon; Song, Jae-Bok.

In: Advanced Robotics, Vol. 27, No. 10, 01.07.2013, p. 739-747.

Research output: Contribution to journalArticle

@article{99eebeee2a134f14a8925fc139a6fec5,
title = "Clustering and probabilistic matching of arbitrarily shaped ceiling features for monocular vision-based SLAM",
abstract = "This paper presents improved extraction and matching methods for arbitrarily shaped (AS) ceiling features for monocular vision-based simultaneous localization and mapping. The feature descriptor, which is robust to illumination changes, comprises the vertex distribution, size, and orientation strength of the region of interest. However, to cope with the problem of vertices being detected at different positions in successive images, Bayes rule is applied to preserve robust vertices and remove rarely observed vertices. Moreover, unstable features surrounded by similar features are clustered to create a robust feature by calculating their similarities to adjacent clusters. AS features from the proposed scheme are used as landmarks in the extended Kalman filter, and the effectiveness of the proposed scheme is verified through various experiments in real environments.",
keywords = "arbitrarily shaped feature, ceiling, mobile robot, SLAM",
author = "Hwang, {Seo Yeon} and Jae-Bok Song",
year = "2013",
month = "7",
day = "1",
doi = "10.1080/01691864.2013.785377",
language = "English",
volume = "27",
pages = "739--747",
journal = "Advanced Robotics",
issn = "0169-1864",
publisher = "Taylor and Francis Ltd.",
number = "10",

}

TY - JOUR

T1 - Clustering and probabilistic matching of arbitrarily shaped ceiling features for monocular vision-based SLAM

AU - Hwang, Seo Yeon

AU - Song, Jae-Bok

PY - 2013/7/1

Y1 - 2013/7/1

N2 - This paper presents improved extraction and matching methods for arbitrarily shaped (AS) ceiling features for monocular vision-based simultaneous localization and mapping. The feature descriptor, which is robust to illumination changes, comprises the vertex distribution, size, and orientation strength of the region of interest. However, to cope with the problem of vertices being detected at different positions in successive images, Bayes rule is applied to preserve robust vertices and remove rarely observed vertices. Moreover, unstable features surrounded by similar features are clustered to create a robust feature by calculating their similarities to adjacent clusters. AS features from the proposed scheme are used as landmarks in the extended Kalman filter, and the effectiveness of the proposed scheme is verified through various experiments in real environments.

AB - This paper presents improved extraction and matching methods for arbitrarily shaped (AS) ceiling features for monocular vision-based simultaneous localization and mapping. The feature descriptor, which is robust to illumination changes, comprises the vertex distribution, size, and orientation strength of the region of interest. However, to cope with the problem of vertices being detected at different positions in successive images, Bayes rule is applied to preserve robust vertices and remove rarely observed vertices. Moreover, unstable features surrounded by similar features are clustered to create a robust feature by calculating their similarities to adjacent clusters. AS features from the proposed scheme are used as landmarks in the extended Kalman filter, and the effectiveness of the proposed scheme is verified through various experiments in real environments.

KW - arbitrarily shaped feature

KW - ceiling

KW - mobile robot

KW - SLAM

UR - http://www.scopus.com/inward/record.url?scp=84878676565&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878676565&partnerID=8YFLogxK

U2 - 10.1080/01691864.2013.785377

DO - 10.1080/01691864.2013.785377

M3 - Article

VL - 27

SP - 739

EP - 747

JO - Advanced Robotics

JF - Advanced Robotics

SN - 0169-1864

IS - 10

ER -