Modeling errors in small baseline stereo for SLAM

Damith C. Herath, K. R.S. Kodagoda, Gamini Dissanayake

Research output: A Conference proceeding or a Chapter in BookConference contribution

7 Citations (Scopus)

Abstract

In the past few years, there has been significant advancement in localization and mapping using stereo cameras. Despite the recent successes, reliably generating an accurate geometric map of a large indoor area using stereo vision still poses significant challenges due to the accuracy and reliability of depth information especially with small baselines. Most stereo vision based applications presented to date have used medium to large baseline stereo cameras with Gaussian error models. Here we make an attempt to analyze the significance of errors in small baseline (usually <0.1m) stereo cameras and the validity of the Gaussian assumption used in the implementation of Kalman Filter based SLAM algorithms. Sensor errors are analyzed through experimentations carried out in the form of a robotic mapping. Then we show that SLAM solutions based on the Extended Kalman Filter (EKF) could become inconsistent due to the nature of the observation models used.

Original languageEnglish
Title of host publication9th International Conference on Control, Automation, Robotics and Vision, 2006, ICARCV '06
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event9th International Conference on Control, Automation, Robotics and Vision, 2006, ICARCV '06 - Singapore, Singapore
Duration: 5 Dec 20068 Dec 2006

Conference

Conference9th International Conference on Control, Automation, Robotics and Vision, 2006, ICARCV '06
CountrySingapore
CitySingapore
Period5/12/068/12/06

Fingerprint

Stereo vision
Cameras
Extended Kalman filters
Kalman filters
Robotics
Sensors

Cite this

Herath, D. C., Kodagoda, K. R. S., & Dissanayake, G. (2006). Modeling errors in small baseline stereo for SLAM. In 9th International Conference on Control, Automation, Robotics and Vision, 2006, ICARCV '06 [4150352] https://doi.org/10.1109/ICARCV.2006.345368
Herath, Damith C. ; Kodagoda, K. R.S. ; Dissanayake, Gamini. / Modeling errors in small baseline stereo for SLAM. 9th International Conference on Control, Automation, Robotics and Vision, 2006, ICARCV '06. 2006.
@inproceedings{9dacf4729ffe4222b85827e5922777da,
title = "Modeling errors in small baseline stereo for SLAM",
abstract = "In the past few years, there has been significant advancement in localization and mapping using stereo cameras. Despite the recent successes, reliably generating an accurate geometric map of a large indoor area using stereo vision still poses significant challenges due to the accuracy and reliability of depth information especially with small baselines. Most stereo vision based applications presented to date have used medium to large baseline stereo cameras with Gaussian error models. Here we make an attempt to analyze the significance of errors in small baseline (usually <0.1m) stereo cameras and the validity of the Gaussian assumption used in the implementation of Kalman Filter based SLAM algorithms. Sensor errors are analyzed through experimentations carried out in the form of a robotic mapping. Then we show that SLAM solutions based on the Extended Kalman Filter (EKF) could become inconsistent due to the nature of the observation models used.",
keywords = "Sensor modeling, SLAM, Stereo vision",
author = "Herath, {Damith C.} and Kodagoda, {K. R.S.} and Gamini Dissanayake",
year = "2006",
doi = "10.1109/ICARCV.2006.345368",
language = "English",
isbn = "1424403421",
booktitle = "9th International Conference on Control, Automation, Robotics and Vision, 2006, ICARCV '06",

}

Herath, DC, Kodagoda, KRS & Dissanayake, G 2006, Modeling errors in small baseline stereo for SLAM. in 9th International Conference on Control, Automation, Robotics and Vision, 2006, ICARCV '06., 4150352, 9th International Conference on Control, Automation, Robotics and Vision, 2006, ICARCV '06, Singapore, Singapore, 5/12/06. https://doi.org/10.1109/ICARCV.2006.345368

Modeling errors in small baseline stereo for SLAM. / Herath, Damith C.; Kodagoda, K. R.S.; Dissanayake, Gamini.

9th International Conference on Control, Automation, Robotics and Vision, 2006, ICARCV '06. 2006. 4150352.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Modeling errors in small baseline stereo for SLAM

AU - Herath, Damith C.

AU - Kodagoda, K. R.S.

AU - Dissanayake, Gamini

PY - 2006

Y1 - 2006

N2 - In the past few years, there has been significant advancement in localization and mapping using stereo cameras. Despite the recent successes, reliably generating an accurate geometric map of a large indoor area using stereo vision still poses significant challenges due to the accuracy and reliability of depth information especially with small baselines. Most stereo vision based applications presented to date have used medium to large baseline stereo cameras with Gaussian error models. Here we make an attempt to analyze the significance of errors in small baseline (usually <0.1m) stereo cameras and the validity of the Gaussian assumption used in the implementation of Kalman Filter based SLAM algorithms. Sensor errors are analyzed through experimentations carried out in the form of a robotic mapping. Then we show that SLAM solutions based on the Extended Kalman Filter (EKF) could become inconsistent due to the nature of the observation models used.

AB - In the past few years, there has been significant advancement in localization and mapping using stereo cameras. Despite the recent successes, reliably generating an accurate geometric map of a large indoor area using stereo vision still poses significant challenges due to the accuracy and reliability of depth information especially with small baselines. Most stereo vision based applications presented to date have used medium to large baseline stereo cameras with Gaussian error models. Here we make an attempt to analyze the significance of errors in small baseline (usually <0.1m) stereo cameras and the validity of the Gaussian assumption used in the implementation of Kalman Filter based SLAM algorithms. Sensor errors are analyzed through experimentations carried out in the form of a robotic mapping. Then we show that SLAM solutions based on the Extended Kalman Filter (EKF) could become inconsistent due to the nature of the observation models used.

KW - Sensor modeling

KW - SLAM

KW - Stereo vision

UR - http://www.scopus.com/inward/record.url?scp=34547162466&partnerID=8YFLogxK

U2 - 10.1109/ICARCV.2006.345368

DO - 10.1109/ICARCV.2006.345368

M3 - Conference contribution

SN - 1424403421

SN - 9781424403424

BT - 9th International Conference on Control, Automation, Robotics and Vision, 2006, ICARCV '06

ER -

Herath DC, Kodagoda KRS, Dissanayake G. Modeling errors in small baseline stereo for SLAM. In 9th International Conference on Control, Automation, Robotics and Vision, 2006, ICARCV '06. 2006. 4150352 https://doi.org/10.1109/ICARCV.2006.345368