Robust Visual Loop Closure Detection with Repetitive Features

Seongwon Lee; Hyung Gi Jo; Hae Min Cho; Euntai Kim

doi:10.1109/URAI.2018.8441872

Robust Visual Loop Closure Detection with Repetitive Features

Seongwon Lee, Hyung Gi Jo, Hae Min Cho, Euntai Kim

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

Loop closure detection problem is an essential issue in simultaneous localization and mapping (SLAM) problem. In particular, visual loop closure detection, which using a visual sensor, should be robust to environmental conditions like confusion caused by repeated structures. In this paper, we propose a robust visual loop closure detection algorithm through restrained repetitive features observed in repeating structures. The proposed algorithm aims to extract bag of visual words (BoVW) for each image frame with RootSIFT extraction, improve it by restrain dominantly repetitive features, calculates histogram similarity score with histogram comparing method and finally decides loop closure pair(s). Experimental results show that the proposed algorithm robustly performs loop closure detection.

Original language	English
Title of host publication	2018 15th International Conference on Ubiquitous Robots, UR 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	891-895
Number of pages	5
ISBN (Print)	9781538663349
DOIs	https://doi.org/10.1109/URAI.2018.8441872
Publication status	Published - 2018 Aug 20
Event	15th International Conference on Ubiquitous Robots, UR 2018 - Honolulu, United States Duration: 2018 Jun 27 → 2018 Jun 30

Publication series

Name	2018 15th International Conference on Ubiquitous Robots, UR 2018

Other

Other	15th International Conference on Ubiquitous Robots, UR 2018
Country/Territory	United States
City	Honolulu
Period	18/6/27 → 18/6/30

Bibliographical note

Funding Information:
This work was supported by the Industrial Convergence Core Technology Development Program (No. 10063172, Development of robot intelligence technology for mobility with learning capability toward robust and seamless indoor and outdoor autonomous navigation) funded by the Ministry of Trade, industry & Energy (MOTIE), Korea.

Publisher Copyright:
© 2018 IEEE.

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Control and Optimization
Mechanical Engineering

Access to Document

10.1109/URAI.2018.8441872

Cite this

Lee, S., Jo, H. G., Cho, H. M., & Kim, E. (2018). Robust Visual Loop Closure Detection with Repetitive Features. In 2018 15th International Conference on Ubiquitous Robots, UR 2018 (pp. 891-895). [8441872] (2018 15th International Conference on Ubiquitous Robots, UR 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/URAI.2018.8441872

@inproceedings{187f56bd96454a048b23bd8160f05be4,

title = "Robust Visual Loop Closure Detection with Repetitive Features",

abstract = "Loop closure detection problem is an essential issue in simultaneous localization and mapping (SLAM) problem. In particular, visual loop closure detection, which using a visual sensor, should be robust to environmental conditions like confusion caused by repeated structures. In this paper, we propose a robust visual loop closure detection algorithm through restrained repetitive features observed in repeating structures. The proposed algorithm aims to extract bag of visual words (BoVW) for each image frame with RootSIFT extraction, improve it by restrain dominantly repetitive features, calculates histogram similarity score with histogram comparing method and finally decides loop closure pair(s). Experimental results show that the proposed algorithm robustly performs loop closure detection.",

author = "Seongwon Lee and Jo, {Hyung Gi} and Cho, {Hae Min} and Euntai Kim",

note = "Funding Information: This work was supported by the Industrial Convergence Core Technology Development Program (No. 10063172, Development of robot intelligence technology for mobility with learning capability toward robust and seamless indoor and outdoor autonomous navigation) funded by the Ministry of Trade, industry & Energy (MOTIE), Korea. Publisher Copyright: {\textcopyright} 2018 IEEE.; 15th International Conference on Ubiquitous Robots, UR 2018 ; Conference date: 27-06-2018 Through 30-06-2018",

year = "2018",

month = aug,

day = "20",

doi = "10.1109/URAI.2018.8441872",

language = "English",

isbn = "9781538663349",

series = "2018 15th International Conference on Ubiquitous Robots, UR 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "891--895",

booktitle = "2018 15th International Conference on Ubiquitous Robots, UR 2018",

address = "United States",

}

Lee, S, Jo, HG, Cho, HM & Kim, E 2018, Robust Visual Loop Closure Detection with Repetitive Features. in 2018 15th International Conference on Ubiquitous Robots, UR 2018., 8441872, 2018 15th International Conference on Ubiquitous Robots, UR 2018, Institute of Electrical and Electronics Engineers Inc., pp. 891-895, 15th International Conference on Ubiquitous Robots, UR 2018, Honolulu, United States, 18/6/27. https://doi.org/10.1109/URAI.2018.8441872

Robust Visual Loop Closure Detection with Repetitive Features. / Lee, Seongwon; Jo, Hyung Gi; Cho, Hae Min et al.
2018 15th International Conference on Ubiquitous Robots, UR 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 891-895 8441872 (2018 15th International Conference on Ubiquitous Robots, UR 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Robust Visual Loop Closure Detection with Repetitive Features

AU - Lee, Seongwon

AU - Jo, Hyung Gi

AU - Cho, Hae Min

AU - Kim, Euntai

N1 - Funding Information: This work was supported by the Industrial Convergence Core Technology Development Program (No. 10063172, Development of robot intelligence technology for mobility with learning capability toward robust and seamless indoor and outdoor autonomous navigation) funded by the Ministry of Trade, industry & Energy (MOTIE), Korea. Publisher Copyright: © 2018 IEEE.

PY - 2018/8/20

Y1 - 2018/8/20

N2 - Loop closure detection problem is an essential issue in simultaneous localization and mapping (SLAM) problem. In particular, visual loop closure detection, which using a visual sensor, should be robust to environmental conditions like confusion caused by repeated structures. In this paper, we propose a robust visual loop closure detection algorithm through restrained repetitive features observed in repeating structures. The proposed algorithm aims to extract bag of visual words (BoVW) for each image frame with RootSIFT extraction, improve it by restrain dominantly repetitive features, calculates histogram similarity score with histogram comparing method and finally decides loop closure pair(s). Experimental results show that the proposed algorithm robustly performs loop closure detection.

AB - Loop closure detection problem is an essential issue in simultaneous localization and mapping (SLAM) problem. In particular, visual loop closure detection, which using a visual sensor, should be robust to environmental conditions like confusion caused by repeated structures. In this paper, we propose a robust visual loop closure detection algorithm through restrained repetitive features observed in repeating structures. The proposed algorithm aims to extract bag of visual words (BoVW) for each image frame with RootSIFT extraction, improve it by restrain dominantly repetitive features, calculates histogram similarity score with histogram comparing method and finally decides loop closure pair(s). Experimental results show that the proposed algorithm robustly performs loop closure detection.

UR - http://www.scopus.com/inward/record.url?scp=85053493957&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053493957&partnerID=8YFLogxK

U2 - 10.1109/URAI.2018.8441872

DO - 10.1109/URAI.2018.8441872

M3 - Conference contribution

AN - SCOPUS:85053493957

SN - 9781538663349

T3 - 2018 15th International Conference on Ubiquitous Robots, UR 2018

SP - 891

EP - 895

BT - 2018 15th International Conference on Ubiquitous Robots, UR 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 15th International Conference on Ubiquitous Robots, UR 2018

Y2 - 27 June 2018 through 30 June 2018

ER -

Robust Visual Loop Closure Detection with Repetitive Features

Abstract

Publication series

Other

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this