Autonomous selection, registration, and recognition of objects for visual SLAM in indoor environments

Yong Ju Lee, Jae-Bok Song

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

11 Citations (Scopus)

Abstract

SLAM is very important in autonomous navigation of a mobile robot. Mapping is the task of modeling the robot's environment and localization is the process of determining its position and orientation with respect to the global map. For successful SLAM performance, landmarks for pose estimation should be continuously observed. In this paper, autonomous recognition and registration of objects as visual landmarks is proposed for autonomous visual SLAM. SIFT and the contour detection algorithms are adopted to distinguish the objects from the background. Autonomous object recognition can enable the robot to recognize some objects without giving any object information to the robot and it can help the vision system to cope with unknown environments. Furthermore, by using object information, a small number of landmarks can be used in the same area compared to other visual SLAM schemes using corners and lines or scene recognition. Various experiments show that the proposed visual SLAM can improve autonomous navigation of a mobile robot.

Original languageEnglish
Title of host publicationICCAS 2007 - International Conference on Control, Automation and Systems
Pages668-673
Number of pages6
DOIs
Publication statusPublished - 2007 Dec 1
EventInternational Conference on Control, Automation and Systems, ICCAS 2007 - Seoul, Korea, Republic of
Duration: 2007 Oct 172007 Oct 20

Other

OtherInternational Conference on Control, Automation and Systems, ICCAS 2007
CountryKorea, Republic of
CitySeoul
Period07/10/1707/10/20

Fingerprint

Robots
Mobile robots
Navigation
Object recognition
Experiments

Keywords

  • Appearance based recognition
  • Object recognition
  • SIFT
  • SLAM

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Lee, Y. J., & Song, J-B. (2007). Autonomous selection, registration, and recognition of objects for visual SLAM in indoor environments. In ICCAS 2007 - International Conference on Control, Automation and Systems (pp. 668-673). [4406983] https://doi.org/10.1109/ICCAS.2007.4406983

Autonomous selection, registration, and recognition of objects for visual SLAM in indoor environments. / Lee, Yong Ju; Song, Jae-Bok.

ICCAS 2007 - International Conference on Control, Automation and Systems. 2007. p. 668-673 4406983.

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

Lee, YJ & Song, J-B 2007, Autonomous selection, registration, and recognition of objects for visual SLAM in indoor environments. in ICCAS 2007 - International Conference on Control, Automation and Systems., 4406983, pp. 668-673, International Conference on Control, Automation and Systems, ICCAS 2007, Seoul, Korea, Republic of, 07/10/17. https://doi.org/10.1109/ICCAS.2007.4406983
Lee YJ, Song J-B. Autonomous selection, registration, and recognition of objects for visual SLAM in indoor environments. In ICCAS 2007 - International Conference on Control, Automation and Systems. 2007. p. 668-673. 4406983 https://doi.org/10.1109/ICCAS.2007.4406983
Lee, Yong Ju ; Song, Jae-Bok. / Autonomous selection, registration, and recognition of objects for visual SLAM in indoor environments. ICCAS 2007 - International Conference on Control, Automation and Systems. 2007. pp. 668-673
@inproceedings{1b80156401a8451180ec3e8176059dc9,
title = "Autonomous selection, registration, and recognition of objects for visual SLAM in indoor environments",
abstract = "SLAM is very important in autonomous navigation of a mobile robot. Mapping is the task of modeling the robot's environment and localization is the process of determining its position and orientation with respect to the global map. For successful SLAM performance, landmarks for pose estimation should be continuously observed. In this paper, autonomous recognition and registration of objects as visual landmarks is proposed for autonomous visual SLAM. SIFT and the contour detection algorithms are adopted to distinguish the objects from the background. Autonomous object recognition can enable the robot to recognize some objects without giving any object information to the robot and it can help the vision system to cope with unknown environments. Furthermore, by using object information, a small number of landmarks can be used in the same area compared to other visual SLAM schemes using corners and lines or scene recognition. Various experiments show that the proposed visual SLAM can improve autonomous navigation of a mobile robot.",
keywords = "Appearance based recognition, Object recognition, SIFT, SLAM",
author = "Lee, {Yong Ju} and Jae-Bok Song",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/ICCAS.2007.4406983",
language = "English",
isbn = "8995003871",
pages = "668--673",
booktitle = "ICCAS 2007 - International Conference on Control, Automation and Systems",

}

TY - GEN

T1 - Autonomous selection, registration, and recognition of objects for visual SLAM in indoor environments

AU - Lee, Yong Ju

AU - Song, Jae-Bok

PY - 2007/12/1

Y1 - 2007/12/1

N2 - SLAM is very important in autonomous navigation of a mobile robot. Mapping is the task of modeling the robot's environment and localization is the process of determining its position and orientation with respect to the global map. For successful SLAM performance, landmarks for pose estimation should be continuously observed. In this paper, autonomous recognition and registration of objects as visual landmarks is proposed for autonomous visual SLAM. SIFT and the contour detection algorithms are adopted to distinguish the objects from the background. Autonomous object recognition can enable the robot to recognize some objects without giving any object information to the robot and it can help the vision system to cope with unknown environments. Furthermore, by using object information, a small number of landmarks can be used in the same area compared to other visual SLAM schemes using corners and lines or scene recognition. Various experiments show that the proposed visual SLAM can improve autonomous navigation of a mobile robot.

AB - SLAM is very important in autonomous navigation of a mobile robot. Mapping is the task of modeling the robot's environment and localization is the process of determining its position and orientation with respect to the global map. For successful SLAM performance, landmarks for pose estimation should be continuously observed. In this paper, autonomous recognition and registration of objects as visual landmarks is proposed for autonomous visual SLAM. SIFT and the contour detection algorithms are adopted to distinguish the objects from the background. Autonomous object recognition can enable the robot to recognize some objects without giving any object information to the robot and it can help the vision system to cope with unknown environments. Furthermore, by using object information, a small number of landmarks can be used in the same area compared to other visual SLAM schemes using corners and lines or scene recognition. Various experiments show that the proposed visual SLAM can improve autonomous navigation of a mobile robot.

KW - Appearance based recognition

KW - Object recognition

KW - SIFT

KW - SLAM

UR - http://www.scopus.com/inward/record.url?scp=48349143627&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48349143627&partnerID=8YFLogxK

U2 - 10.1109/ICCAS.2007.4406983

DO - 10.1109/ICCAS.2007.4406983

M3 - Conference contribution

AN - SCOPUS:48349143627

SN - 8995003871

SN - 9788995003879

SP - 668

EP - 673

BT - ICCAS 2007 - International Conference on Control, Automation and Systems

ER -