Vision-based global localization based on a hybrid map representation

Ju Hong Park, Soohwan Kim, Nakju Doh, Sung Kee Park

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

In this paper we propose a novel vision-based global localization method based on a hybrid map representation. We employ PCA-SIFT features as visual landmarks and represent the environment with a hybrid map which consists of a global topological map and local metric maps. To localize where a mobile robot is placed, we extract visual features from the currently captured view and match them to the feature database previously constructed according to the hybrid map representation. After filtering noise, we estimate the robot's pose with the qualified matching features by the RANSAC approach. We implemented the proposed method in a real mobile robot and tested in both a home-like room and an office-like corridor. The experimental results show that our vision-based global localization system is acceptable in terms of processing time and accuracy.

Original languageEnglish
Title of host publication2008 International Conference on Control, Automation and Systems, ICCAS 2008
Pages1104-1108
Number of pages5
DOIs
Publication statusPublished - 2008 Dec 1
Event2008 International Conference on Control, Automation and Systems, ICCAS 2008 - Seoul, Korea, Republic of
Duration: 2008 Oct 142008 Oct 17

Other

Other2008 International Conference on Control, Automation and Systems, ICCAS 2008
CountryKorea, Republic of
CitySeoul
Period08/10/1408/10/17

Fingerprint

Mobile robots
Robots
Processing

Keywords

  • Global localization
  • Hybrid map representation
  • Mobile robot
  • PCA-SIFT

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Park, J. H., Kim, S., Doh, N., & Park, S. K. (2008). Vision-based global localization based on a hybrid map representation. In 2008 International Conference on Control, Automation and Systems, ICCAS 2008 (pp. 1104-1108). [4694317] https://doi.org/10.1109/ICCAS.2008.4694317

Vision-based global localization based on a hybrid map representation. / Park, Ju Hong; Kim, Soohwan; Doh, Nakju; Park, Sung Kee.

2008 International Conference on Control, Automation and Systems, ICCAS 2008. 2008. p. 1104-1108 4694317.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Park, JH, Kim, S, Doh, N & Park, SK 2008, Vision-based global localization based on a hybrid map representation. in 2008 International Conference on Control, Automation and Systems, ICCAS 2008., 4694317, pp. 1104-1108, 2008 International Conference on Control, Automation and Systems, ICCAS 2008, Seoul, Korea, Republic of, 08/10/14. https://doi.org/10.1109/ICCAS.2008.4694317
Park JH, Kim S, Doh N, Park SK. Vision-based global localization based on a hybrid map representation. In 2008 International Conference on Control, Automation and Systems, ICCAS 2008. 2008. p. 1104-1108. 4694317 https://doi.org/10.1109/ICCAS.2008.4694317
Park, Ju Hong ; Kim, Soohwan ; Doh, Nakju ; Park, Sung Kee. / Vision-based global localization based on a hybrid map representation. 2008 International Conference on Control, Automation and Systems, ICCAS 2008. 2008. pp. 1104-1108
@inproceedings{02282fb96a774aaa86d7f72d470c7e36,
title = "Vision-based global localization based on a hybrid map representation",
abstract = "In this paper we propose a novel vision-based global localization method based on a hybrid map representation. We employ PCA-SIFT features as visual landmarks and represent the environment with a hybrid map which consists of a global topological map and local metric maps. To localize where a mobile robot is placed, we extract visual features from the currently captured view and match them to the feature database previously constructed according to the hybrid map representation. After filtering noise, we estimate the robot's pose with the qualified matching features by the RANSAC approach. We implemented the proposed method in a real mobile robot and tested in both a home-like room and an office-like corridor. The experimental results show that our vision-based global localization system is acceptable in terms of processing time and accuracy.",
keywords = "Global localization, Hybrid map representation, Mobile robot, PCA-SIFT",
author = "Park, {Ju Hong} and Soohwan Kim and Nakju Doh and Park, {Sung Kee}",
year = "2008",
month = "12",
day = "1",
doi = "10.1109/ICCAS.2008.4694317",
language = "English",
isbn = "9788995003893",
pages = "1104--1108",
booktitle = "2008 International Conference on Control, Automation and Systems, ICCAS 2008",

}

TY - GEN

T1 - Vision-based global localization based on a hybrid map representation

AU - Park, Ju Hong

AU - Kim, Soohwan

AU - Doh, Nakju

AU - Park, Sung Kee

PY - 2008/12/1

Y1 - 2008/12/1

N2 - In this paper we propose a novel vision-based global localization method based on a hybrid map representation. We employ PCA-SIFT features as visual landmarks and represent the environment with a hybrid map which consists of a global topological map and local metric maps. To localize where a mobile robot is placed, we extract visual features from the currently captured view and match them to the feature database previously constructed according to the hybrid map representation. After filtering noise, we estimate the robot's pose with the qualified matching features by the RANSAC approach. We implemented the proposed method in a real mobile robot and tested in both a home-like room and an office-like corridor. The experimental results show that our vision-based global localization system is acceptable in terms of processing time and accuracy.

AB - In this paper we propose a novel vision-based global localization method based on a hybrid map representation. We employ PCA-SIFT features as visual landmarks and represent the environment with a hybrid map which consists of a global topological map and local metric maps. To localize where a mobile robot is placed, we extract visual features from the currently captured view and match them to the feature database previously constructed according to the hybrid map representation. After filtering noise, we estimate the robot's pose with the qualified matching features by the RANSAC approach. We implemented the proposed method in a real mobile robot and tested in both a home-like room and an office-like corridor. The experimental results show that our vision-based global localization system is acceptable in terms of processing time and accuracy.

KW - Global localization

KW - Hybrid map representation

KW - Mobile robot

KW - PCA-SIFT

UR - http://www.scopus.com/inward/record.url?scp=58149091693&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58149091693&partnerID=8YFLogxK

U2 - 10.1109/ICCAS.2008.4694317

DO - 10.1109/ICCAS.2008.4694317

M3 - Conference contribution

SN - 9788995003893

SP - 1104

EP - 1108

BT - 2008 International Conference on Control, Automation and Systems, ICCAS 2008

ER -