Improving landmark detection accuracy for self-localization through baseboard recognition

Chinthaka Premachandra, Masashi Murakami, Ryo Gohara, Takao Ninomiya, Kiyotaka Kato

Research output: Contribution to journalArticle

Abstract

Acquiring information related to the surrounding environment and environmental mapping are important issues for realizing autonomous robot movement in an unknown environment, and these processes require position estimations for self-localization. We have conducted previous research related to self-localization in indoor environments through baseboard recognition. In that method, a mobile robot performs self-localization using camera-acquired images, from which the intersection of baseboards and the vertical lines of attached doorframes are registered as landmarks. However, this method is limited in that self-localization cannot be performed in cases where baseboards are not partially available or where walls and baseboards are the same color. The present research aims at addressing these issues and implementing the method in an actual mobile robot. The implementing robot is allowed to move autonomously, performing mapping and self-localization in real time. Addressing the problem of same-colored walls requires identification of the border between the wall and the baseboard, so we propose an image processing method for identifying these lines. The problem of lack of baseboards is solved through supplemental use of odometry, which does not rely on visual characteristics. The proposed method is experimentally verified through use of our algorithm to recognize baseboards, perform self-localization, and create maps. The results verify that baseboards can be recognized even when they are the same color as walls. We furthermore verify that landmark-mapping performance when moving in hallways is improved over the previous version.

Original languageEnglish
Pages (from-to)1815-1826
Number of pages12
JournalInternational Journal of Machine Learning and Cybernetics
Volume8
Issue number6
DOIs
Publication statusPublished - 2017 Dec 1

Fingerprint

Mobile robots
Robots
Color
Image processing
Cameras

Keywords

  • Baseboard detection
  • LRF
  • Mapping in unknown environment
  • Self-localization

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Improving landmark detection accuracy for self-localization through baseboard recognition. / Premachandra, Chinthaka; Murakami, Masashi; Gohara, Ryo; Ninomiya, Takao; Kato, Kiyotaka.

In: International Journal of Machine Learning and Cybernetics, Vol. 8, No. 6, 01.12.2017, p. 1815-1826.

Research output: Contribution to journalArticle

Premachandra, Chinthaka ; Murakami, Masashi ; Gohara, Ryo ; Ninomiya, Takao ; Kato, Kiyotaka. / Improving landmark detection accuracy for self-localization through baseboard recognition. In: International Journal of Machine Learning and Cybernetics. 2017 ; Vol. 8, No. 6. pp. 1815-1826.
@article{817671ed099d48fe872a4e73def953cd,
title = "Improving landmark detection accuracy for self-localization through baseboard recognition",
abstract = "Acquiring information related to the surrounding environment and environmental mapping are important issues for realizing autonomous robot movement in an unknown environment, and these processes require position estimations for self-localization. We have conducted previous research related to self-localization in indoor environments through baseboard recognition. In that method, a mobile robot performs self-localization using camera-acquired images, from which the intersection of baseboards and the vertical lines of attached doorframes are registered as landmarks. However, this method is limited in that self-localization cannot be performed in cases where baseboards are not partially available or where walls and baseboards are the same color. The present research aims at addressing these issues and implementing the method in an actual mobile robot. The implementing robot is allowed to move autonomously, performing mapping and self-localization in real time. Addressing the problem of same-colored walls requires identification of the border between the wall and the baseboard, so we propose an image processing method for identifying these lines. The problem of lack of baseboards is solved through supplemental use of odometry, which does not rely on visual characteristics. The proposed method is experimentally verified through use of our algorithm to recognize baseboards, perform self-localization, and create maps. The results verify that baseboards can be recognized even when they are the same color as walls. We furthermore verify that landmark-mapping performance when moving in hallways is improved over the previous version.",
keywords = "Baseboard detection, LRF, Mapping in unknown environment, Self-localization",
author = "Chinthaka Premachandra and Masashi Murakami and Ryo Gohara and Takao Ninomiya and Kiyotaka Kato",
year = "2017",
month = "12",
day = "1",
doi = "10.1007/s13042-016-0560-9",
language = "English",
volume = "8",
pages = "1815--1826",
journal = "International Journal of Machine Learning and Cybernetics",
issn = "1868-8071",
publisher = "Springer Science + Business Media",
number = "6",

}

TY - JOUR

T1 - Improving landmark detection accuracy for self-localization through baseboard recognition

AU - Premachandra, Chinthaka

AU - Murakami, Masashi

AU - Gohara, Ryo

AU - Ninomiya, Takao

AU - Kato, Kiyotaka

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Acquiring information related to the surrounding environment and environmental mapping are important issues for realizing autonomous robot movement in an unknown environment, and these processes require position estimations for self-localization. We have conducted previous research related to self-localization in indoor environments through baseboard recognition. In that method, a mobile robot performs self-localization using camera-acquired images, from which the intersection of baseboards and the vertical lines of attached doorframes are registered as landmarks. However, this method is limited in that self-localization cannot be performed in cases where baseboards are not partially available or where walls and baseboards are the same color. The present research aims at addressing these issues and implementing the method in an actual mobile robot. The implementing robot is allowed to move autonomously, performing mapping and self-localization in real time. Addressing the problem of same-colored walls requires identification of the border between the wall and the baseboard, so we propose an image processing method for identifying these lines. The problem of lack of baseboards is solved through supplemental use of odometry, which does not rely on visual characteristics. The proposed method is experimentally verified through use of our algorithm to recognize baseboards, perform self-localization, and create maps. The results verify that baseboards can be recognized even when they are the same color as walls. We furthermore verify that landmark-mapping performance when moving in hallways is improved over the previous version.

AB - Acquiring information related to the surrounding environment and environmental mapping are important issues for realizing autonomous robot movement in an unknown environment, and these processes require position estimations for self-localization. We have conducted previous research related to self-localization in indoor environments through baseboard recognition. In that method, a mobile robot performs self-localization using camera-acquired images, from which the intersection of baseboards and the vertical lines of attached doorframes are registered as landmarks. However, this method is limited in that self-localization cannot be performed in cases where baseboards are not partially available or where walls and baseboards are the same color. The present research aims at addressing these issues and implementing the method in an actual mobile robot. The implementing robot is allowed to move autonomously, performing mapping and self-localization in real time. Addressing the problem of same-colored walls requires identification of the border between the wall and the baseboard, so we propose an image processing method for identifying these lines. The problem of lack of baseboards is solved through supplemental use of odometry, which does not rely on visual characteristics. The proposed method is experimentally verified through use of our algorithm to recognize baseboards, perform self-localization, and create maps. The results verify that baseboards can be recognized even when they are the same color as walls. We furthermore verify that landmark-mapping performance when moving in hallways is improved over the previous version.

KW - Baseboard detection

KW - LRF

KW - Mapping in unknown environment

KW - Self-localization

UR - http://www.scopus.com/inward/record.url?scp=85032352361&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032352361&partnerID=8YFLogxK

U2 - 10.1007/s13042-016-0560-9

DO - 10.1007/s13042-016-0560-9

M3 - Article

AN - SCOPUS:85032352361

VL - 8

SP - 1815

EP - 1826

JO - International Journal of Machine Learning and Cybernetics

JF - International Journal of Machine Learning and Cybernetics

SN - 1868-8071

IS - 6

ER -