Real-time visual loop-closure detection

Adrien Angeli; Stéphane Doncieux; Jean Arcady Meyer; David Filliat

doi:10.1109/ROBOT.2008.4543475

Real-time visual loop-closure detection

Adrien Angeli
, Stéphane Doncieux
, Jean Arcady Meyer
, David Filliat

Sorbonne Université

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

Abstract

In robotic applications of visual simultaneous localization and mapping, loop-closure detection and global localization are two issues that require the capacity to recognize a previously visited place from current camera measurements. We present an online method that makes it possible to detect when an image comes from an already perceived scene using local shape information. Our approach extends the bag of visual words method used in image recognition to incremental conditions and relies on Bayesian filtering to estimate loop-closure probability. We demonstrate the efficiency of our solution by real-time loop-closure detection under strong perceptual aliasing conditions in an indoor image sequence taken with a handheld camera.

Original language	English
Title of host publication	2008 IEEE International Conference on Robotics and Automation, ICRA 2008
Pages	1842-1847
Number of pages	6
DOIs	https://doi.org/10.1109/ROBOT.2008.4543475
Publication status	Published - 18 Sept 2008
Event	2008 IEEE International Conference on Robotics and Automation, ICRA 2008 - Pasadena, CA, United States Duration: 19 May 2008 → 23 May 2008

Publication series

Name	Proceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)	1050-4729

Conference

Conference	2008 IEEE International Conference on Robotics and Automation, ICRA 2008
Country/Territory	United States
City	Pasadena, CA
Period	19/05/08 → 23/05/08

Access to Document

10.1109/ROBOT.2008.4543475

Cite this

@inproceedings{0600845e1e3346a6b924d155f04a644a,

title = "Real-time visual loop-closure detection",

abstract = "In robotic applications of visual simultaneous localization and mapping, loop-closure detection and global localization are two issues that require the capacity to recognize a previously visited place from current camera measurements. We present an online method that makes it possible to detect when an image comes from an already perceived scene using local shape information. Our approach extends the bag of visual words method used in image recognition to incremental conditions and relies on Bayesian filtering to estimate loop-closure probability. We demonstrate the efficiency of our solution by real-time loop-closure detection under strong perceptual aliasing conditions in an indoor image sequence taken with a handheld camera.",

author = "Adrien Angeli and St{\'e}phane Doncieux and Meyer, \{Jean Arcady\} and David Filliat",

year = "2008",

month = sep,

day = "18",

doi = "10.1109/ROBOT.2008.4543475",

language = "English",

isbn = "9781424416479",

series = "Proceedings - IEEE International Conference on Robotics and Automation",

pages = "1842--1847",

booktitle = "2008 IEEE International Conference on Robotics and Automation, ICRA 2008",

note = "2008 IEEE International Conference on Robotics and Automation, ICRA 2008 ; Conference date: 19-05-2008 Through 23-05-2008",

}

Angeli, A, Doncieux, S, Meyer, JA & Filliat, D 2008, Real-time visual loop-closure detection. in 2008 IEEE International Conference on Robotics and Automation, ICRA 2008., 4543475, Proceedings - IEEE International Conference on Robotics and Automation, pp. 1842-1847, 2008 IEEE International Conference on Robotics and Automation, ICRA 2008, Pasadena, CA, United States, 19/05/08. https://doi.org/10.1109/ROBOT.2008.4543475

Real-time visual loop-closure detection. / Angeli, Adrien; Doncieux, Stéphane; Meyer, Jean Arcady et al.
2008 IEEE International Conference on Robotics and Automation, ICRA 2008. 2008. p. 1842-1847 4543475 (Proceedings - IEEE International Conference on Robotics and Automation).

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

TY - GEN

T1 - Real-time visual loop-closure detection

AU - Angeli, Adrien

AU - Doncieux, Stéphane

AU - Meyer, Jean Arcady

AU - Filliat, David

PY - 2008/9/18

Y1 - 2008/9/18

N2 - In robotic applications of visual simultaneous localization and mapping, loop-closure detection and global localization are two issues that require the capacity to recognize a previously visited place from current camera measurements. We present an online method that makes it possible to detect when an image comes from an already perceived scene using local shape information. Our approach extends the bag of visual words method used in image recognition to incremental conditions and relies on Bayesian filtering to estimate loop-closure probability. We demonstrate the efficiency of our solution by real-time loop-closure detection under strong perceptual aliasing conditions in an indoor image sequence taken with a handheld camera.

AB - In robotic applications of visual simultaneous localization and mapping, loop-closure detection and global localization are two issues that require the capacity to recognize a previously visited place from current camera measurements. We present an online method that makes it possible to detect when an image comes from an already perceived scene using local shape information. Our approach extends the bag of visual words method used in image recognition to incremental conditions and relies on Bayesian filtering to estimate loop-closure probability. We demonstrate the efficiency of our solution by real-time loop-closure detection under strong perceptual aliasing conditions in an indoor image sequence taken with a handheld camera.

UR - https://www.scopus.com/pages/publications/51649121164

U2 - 10.1109/ROBOT.2008.4543475

DO - 10.1109/ROBOT.2008.4543475

M3 - Conference contribution

AN - SCOPUS:51649121164

SN - 9781424416479

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 1842

EP - 1847

BT - 2008 IEEE International Conference on Robotics and Automation, ICRA 2008

T2 - 2008 IEEE International Conference on Robotics and Automation, ICRA 2008

Y2 - 19 May 2008 through 23 May 2008

ER -

Real-time visual loop-closure detection

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this