CV-SLAM using ceiling boundary

Hyukdoo Choi, Dong Yeop Kim, Jae Pil Hwang, Euntai Kim, Young Ouk Kim

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

11 Citations (Scopus)

Abstract

This paper deals with simultaneous localization and mapping(SLAM) problem for a mobile robot that travels around the indoor environments. A single camera looking up the ceiling is used as the only sensor. Line features are extracted from the boundaries between the ceiling and walls and parameterized for SLAM update. Extended Kalman Filter(EKF) is used for simultaneously estimating the current robot pose and building a map with the line features. When the robot is kidnapped, Monte Carlo Localization(MCL) is used for finding the robot pose. To improve the localization performance, the resampling method is modified. The experiment is practiced in our indoor test bed and the proposed algorithms are proved by the experimental results.

Original languageEnglish
Title of host publicationProceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010
Pages228-233
Number of pages6
DOIs
Publication statusPublished - 2010 Sep 1
Event5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010 - Taichung, Taiwan, Province of China
Duration: 2010 Jun 152010 Jun 17

Publication series

NameProceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010

Other

Other5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010
CountryTaiwan, Province of China
CityTaichung
Period10/6/1510/6/17

Fingerprint

Ceilings
Robots
Extended Kalman filters
Mobile robots
Cameras
Sensors
Experiments

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Choi, H., Kim, D. Y., Hwang, J. P., Kim, E., & Kim, Y. O. (2010). CV-SLAM using ceiling boundary. In Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010 (pp. 228-233). [5516788] (Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010). https://doi.org/10.1109/ICIEA.2010.5516788
Choi, Hyukdoo ; Kim, Dong Yeop ; Hwang, Jae Pil ; Kim, Euntai ; Kim, Young Ouk. / CV-SLAM using ceiling boundary. Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010. 2010. pp. 228-233 (Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010).
@inproceedings{af4bee569bfe4d668fc3411a148cc1f1,
title = "CV-SLAM using ceiling boundary",
abstract = "This paper deals with simultaneous localization and mapping(SLAM) problem for a mobile robot that travels around the indoor environments. A single camera looking up the ceiling is used as the only sensor. Line features are extracted from the boundaries between the ceiling and walls and parameterized for SLAM update. Extended Kalman Filter(EKF) is used for simultaneously estimating the current robot pose and building a map with the line features. When the robot is kidnapped, Monte Carlo Localization(MCL) is used for finding the robot pose. To improve the localization performance, the resampling method is modified. The experiment is practiced in our indoor test bed and the proposed algorithms are proved by the experimental results.",
author = "Hyukdoo Choi and Kim, {Dong Yeop} and Hwang, {Jae Pil} and Euntai Kim and Kim, {Young Ouk}",
year = "2010",
month = "9",
day = "1",
doi = "10.1109/ICIEA.2010.5516788",
language = "English",
isbn = "9781424450466",
series = "Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010",
pages = "228--233",
booktitle = "Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010",

}

Choi, H, Kim, DY, Hwang, JP, Kim, E & Kim, YO 2010, CV-SLAM using ceiling boundary. in Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010., 5516788, Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010, pp. 228-233, 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010, Taichung, Taiwan, Province of China, 10/6/15. https://doi.org/10.1109/ICIEA.2010.5516788

CV-SLAM using ceiling boundary. / Choi, Hyukdoo; Kim, Dong Yeop; Hwang, Jae Pil; Kim, Euntai; Kim, Young Ouk.

Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010. 2010. p. 228-233 5516788 (Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010).

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

TY - GEN

T1 - CV-SLAM using ceiling boundary

AU - Choi, Hyukdoo

AU - Kim, Dong Yeop

AU - Hwang, Jae Pil

AU - Kim, Euntai

AU - Kim, Young Ouk

PY - 2010/9/1

Y1 - 2010/9/1

N2 - This paper deals with simultaneous localization and mapping(SLAM) problem for a mobile robot that travels around the indoor environments. A single camera looking up the ceiling is used as the only sensor. Line features are extracted from the boundaries between the ceiling and walls and parameterized for SLAM update. Extended Kalman Filter(EKF) is used for simultaneously estimating the current robot pose and building a map with the line features. When the robot is kidnapped, Monte Carlo Localization(MCL) is used for finding the robot pose. To improve the localization performance, the resampling method is modified. The experiment is practiced in our indoor test bed and the proposed algorithms are proved by the experimental results.

AB - This paper deals with simultaneous localization and mapping(SLAM) problem for a mobile robot that travels around the indoor environments. A single camera looking up the ceiling is used as the only sensor. Line features are extracted from the boundaries between the ceiling and walls and parameterized for SLAM update. Extended Kalman Filter(EKF) is used for simultaneously estimating the current robot pose and building a map with the line features. When the robot is kidnapped, Monte Carlo Localization(MCL) is used for finding the robot pose. To improve the localization performance, the resampling method is modified. The experiment is practiced in our indoor test bed and the proposed algorithms are proved by the experimental results.

UR - http://www.scopus.com/inward/record.url?scp=77956034943&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956034943&partnerID=8YFLogxK

U2 - 10.1109/ICIEA.2010.5516788

DO - 10.1109/ICIEA.2010.5516788

M3 - Conference contribution

AN - SCOPUS:77956034943

SN - 9781424450466

T3 - Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010

SP - 228

EP - 233

BT - Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010

ER -

Choi H, Kim DY, Hwang JP, Kim E, Kim YO. CV-SLAM using ceiling boundary. In Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010. 2010. p. 228-233. 5516788. (Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications, ICIEA 2010). https://doi.org/10.1109/ICIEA.2010.5516788