Loading [MathJax]/extensions/MathMenu.js

Set-Membership Extrinsic Calibration of a 3D LiDAR and a Camera

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autorschaft

Organisationseinheiten

Plum Print visual indicator of research metrics
  • Citations
    • Citation Indexes: 8
  • Captures
    • Readers: 26
see details

Details

OriginalspracheEnglisch
Titel des Sammelwerks2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020
ErscheinungsortLas Vegas, NV, USA
Seiten9012-9019
Seitenumfang8
ISBN (elektronisch)9781728162126
PublikationsstatusVeröffentlicht - 2020

Abstract

To fuse information from a 3D Light Detection and Ranging (LiDAR) sensor and a camera, the extrinsic transformation between the sensor coordinate systems needs to be known. Therefore, an extrinsic calibration must be performed, which is usually based on features extracted from sensor data. Naturally, sensor errors can affect the feature extraction process, and thus distort the calibration result. Unlike previous works, which do not consider the uncertainties of the sensors, we propose a set-membership approach that takes all sensor errors into account. Since the actual error distribution of off-the-shelf sensors is often unknown, we assume to only know bounds (or intervals) enclosing the sensor errors and accordingly introduce novel error models for both sensors. Next, we introduce interval-based approaches to extract corresponding features from images and point clouds. Due to the unknown but bounded sensor errors, we cannot determine the features exactly, but compute intervals guaranteed to enclose them. Subsequently, these feature intervals enable us to formulate a Constraint Satisfaction Problem (CSP). Finally, the CSP is solved to find a set of solutions that is guaranteed to contain the true solution and simultaneously reflects the accuracy of the calibration. Experiments using simulated and real data validate our approach and show its advantages over existing methods.

ASJC Scopus Sachgebiete

Zitieren

Set-Membership Extrinsic Calibration of a 3D LiDAR and a Camera. / Voges, Raphael; Wagner, Bernardo.
2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020. Las Vegas, NV, USA, 2020. S. 9012-9019 9341266.

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Voges, R & Wagner, B 2020, Set-Membership Extrinsic Calibration of a 3D LiDAR and a Camera. in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020., 9341266, Las Vegas, NV, USA, S. 9012-9019. https://doi.org/10.1109/IROS45743.2020.9341266
Voges, R., & Wagner, B. (2020). Set-Membership Extrinsic Calibration of a 3D LiDAR and a Camera. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020 (S. 9012-9019). Artikel 9341266. https://doi.org/10.1109/IROS45743.2020.9341266
Voges R, Wagner B. Set-Membership Extrinsic Calibration of a 3D LiDAR and a Camera. in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020. Las Vegas, NV, USA. 2020. S. 9012-9019. 9341266 doi: 10.1109/IROS45743.2020.9341266
Voges, Raphael ; Wagner, Bernardo. / Set-Membership Extrinsic Calibration of a 3D LiDAR and a Camera. 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020. Las Vegas, NV, USA, 2020. S. 9012-9019
Download
@inproceedings{dccf40a2e10b49d1adc7379f13027ac5,
title = "Set-Membership Extrinsic Calibration of a 3D LiDAR and a Camera",
abstract = "To fuse information from a 3D Light Detection and Ranging (LiDAR) sensor and a camera, the extrinsic transformation between the sensor coordinate systems needs to be known. Therefore, an extrinsic calibration must be performed, which is usually based on features extracted from sensor data. Naturally, sensor errors can affect the feature extraction process, and thus distort the calibration result. Unlike previous works, which do not consider the uncertainties of the sensors, we propose a set-membership approach that takes all sensor errors into account. Since the actual error distribution of off-the-shelf sensors is often unknown, we assume to only know bounds (or intervals) enclosing the sensor errors and accordingly introduce novel error models for both sensors. Next, we introduce interval-based approaches to extract corresponding features from images and point clouds. Due to the unknown but bounded sensor errors, we cannot determine the features exactly, but compute intervals guaranteed to enclose them. Subsequently, these feature intervals enable us to formulate a Constraint Satisfaction Problem (CSP). Finally, the CSP is solved to find a set of solutions that is guaranteed to contain the true solution and simultaneously reflects the accuracy of the calibration. Experiments using simulated and real data validate our approach and show its advantages over existing methods.",
author = "Raphael Voges and Bernardo Wagner",
note = "Funding information: The authors are with the Real Time Systems Group (RTS), Institute of Systems Engineering, Leibniz Universit{\"a}t Hannover, D-30167 Hannover, Germany. {voges,wagner}@rts.uni-hannover.de This work was supported by the German Research Foundation (DFG) as part of the Research Training Group i.c.sens [RTG 2159].",
year = "2020",
doi = "10.1109/IROS45743.2020.9341266",
language = "English",
isbn = "978-1-7281-6213-3",
pages = "9012--9019",
booktitle = "2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020",

}

Download

TY - GEN

T1 - Set-Membership Extrinsic Calibration of a 3D LiDAR and a Camera

AU - Voges, Raphael

AU - Wagner, Bernardo

N1 - Funding information: The authors are with the Real Time Systems Group (RTS), Institute of Systems Engineering, Leibniz Universität Hannover, D-30167 Hannover, Germany. {voges,wagner}@rts.uni-hannover.de This work was supported by the German Research Foundation (DFG) as part of the Research Training Group i.c.sens [RTG 2159].

PY - 2020

Y1 - 2020

N2 - To fuse information from a 3D Light Detection and Ranging (LiDAR) sensor and a camera, the extrinsic transformation between the sensor coordinate systems needs to be known. Therefore, an extrinsic calibration must be performed, which is usually based on features extracted from sensor data. Naturally, sensor errors can affect the feature extraction process, and thus distort the calibration result. Unlike previous works, which do not consider the uncertainties of the sensors, we propose a set-membership approach that takes all sensor errors into account. Since the actual error distribution of off-the-shelf sensors is often unknown, we assume to only know bounds (or intervals) enclosing the sensor errors and accordingly introduce novel error models for both sensors. Next, we introduce interval-based approaches to extract corresponding features from images and point clouds. Due to the unknown but bounded sensor errors, we cannot determine the features exactly, but compute intervals guaranteed to enclose them. Subsequently, these feature intervals enable us to formulate a Constraint Satisfaction Problem (CSP). Finally, the CSP is solved to find a set of solutions that is guaranteed to contain the true solution and simultaneously reflects the accuracy of the calibration. Experiments using simulated and real data validate our approach and show its advantages over existing methods.

AB - To fuse information from a 3D Light Detection and Ranging (LiDAR) sensor and a camera, the extrinsic transformation between the sensor coordinate systems needs to be known. Therefore, an extrinsic calibration must be performed, which is usually based on features extracted from sensor data. Naturally, sensor errors can affect the feature extraction process, and thus distort the calibration result. Unlike previous works, which do not consider the uncertainties of the sensors, we propose a set-membership approach that takes all sensor errors into account. Since the actual error distribution of off-the-shelf sensors is often unknown, we assume to only know bounds (or intervals) enclosing the sensor errors and accordingly introduce novel error models for both sensors. Next, we introduce interval-based approaches to extract corresponding features from images and point clouds. Due to the unknown but bounded sensor errors, we cannot determine the features exactly, but compute intervals guaranteed to enclose them. Subsequently, these feature intervals enable us to formulate a Constraint Satisfaction Problem (CSP). Finally, the CSP is solved to find a set of solutions that is guaranteed to contain the true solution and simultaneously reflects the accuracy of the calibration. Experiments using simulated and real data validate our approach and show its advantages over existing methods.

UR - http://www.scopus.com/inward/record.url?scp=85101771605&partnerID=8YFLogxK

U2 - 10.1109/IROS45743.2020.9341266

DO - 10.1109/IROS45743.2020.9341266

M3 - Conference contribution

SN - 978-1-7281-6213-3

SP - 9012

EP - 9019

BT - 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020

CY - Las Vegas, NV, USA

ER -

Von denselben Autoren