LUMPI: The Leibniz University Multi-Perspective Intersection Dataset

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

  • Steffen Busch
  • Christian Koetsier
  • Jeldrik Axmann
  • Claus Brenner
View graph of relations

Details

Original languageEnglish
Title of host publication2022 IEEE Intelligent Vehicles Symposium
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1127-1134
Number of pages8
ISBN (electronic)9781665488211
ISBN (print)9781665488228
Publication statusPublished - 19 Jul 2022
Event2022 IEEE Intelligent Vehicles Symposium, IV 2022 - Aachen, Germany
Duration: 5 Jun 20229 Jun 2022

Publication series

NameIEEE Intelligent Vehicles Symposium, Proceedings
Volume2022-June

Abstract

Improvements in sensor technologies as well as machine learning methods allow an efficient collection, processing and analysis of the dynamic environment, which can be used for detection and tracking of traffic participants. Current datasets in this domain mostly present a single view, making highly accurate pose estimation impossible due to occlusions. The integration of different, simultaneously acquired data allows to exploit and develop collaboration principles to increase the quality, reliability and integrity of the derived information. This work addresses this problem by providing a multi-view dataset, including 2D image information (videos) obtained by up to three cameras and 3D point clouds from up to five LiDAR sensors together with labels of the traffic participants in the scene. The measurements were conducted during different weather conditions on several days at a large junction in Hanover, Germany, resulting in a total duration of 145 minutes.

ASJC Scopus subject areas

Cite this

LUMPI: The Leibniz University Multi-Perspective Intersection Dataset. / Busch, Steffen; Koetsier, Christian; Axmann, Jeldrik et al.
2022 IEEE Intelligent Vehicles Symposium. Institute of Electrical and Electronics Engineers Inc., 2022. p. 1127-1134 (IEEE Intelligent Vehicles Symposium, Proceedings; Vol. 2022-June).

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Busch, S, Koetsier, C, Axmann, J & Brenner, C 2022, LUMPI: The Leibniz University Multi-Perspective Intersection Dataset. in 2022 IEEE Intelligent Vehicles Symposium. IEEE Intelligent Vehicles Symposium, Proceedings, vol. 2022-June, Institute of Electrical and Electronics Engineers Inc., pp. 1127-1134, 2022 IEEE Intelligent Vehicles Symposium, IV 2022, Aachen, Germany, 5 Jun 2022. https://doi.org/10.1109/IV51971.2022.9827157
Busch, S., Koetsier, C., Axmann, J., & Brenner, C. (2022). LUMPI: The Leibniz University Multi-Perspective Intersection Dataset. In 2022 IEEE Intelligent Vehicles Symposium (pp. 1127-1134). (IEEE Intelligent Vehicles Symposium, Proceedings; Vol. 2022-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IV51971.2022.9827157
Busch S, Koetsier C, Axmann J, Brenner C. LUMPI: The Leibniz University Multi-Perspective Intersection Dataset. In 2022 IEEE Intelligent Vehicles Symposium. Institute of Electrical and Electronics Engineers Inc. 2022. p. 1127-1134. (IEEE Intelligent Vehicles Symposium, Proceedings). doi: 10.1109/IV51971.2022.9827157
Busch, Steffen ; Koetsier, Christian ; Axmann, Jeldrik et al. / LUMPI : The Leibniz University Multi-Perspective Intersection Dataset. 2022 IEEE Intelligent Vehicles Symposium. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 1127-1134 (IEEE Intelligent Vehicles Symposium, Proceedings).
Download
@inproceedings{3061cecea69d46ad917b2bf4ac383bd1,
title = "LUMPI: The Leibniz University Multi-Perspective Intersection Dataset",
abstract = "Improvements in sensor technologies as well as machine learning methods allow an efficient collection, processing and analysis of the dynamic environment, which can be used for detection and tracking of traffic participants. Current datasets in this domain mostly present a single view, making highly accurate pose estimation impossible due to occlusions. The integration of different, simultaneously acquired data allows to exploit and develop collaboration principles to increase the quality, reliability and integrity of the derived information. This work addresses this problem by providing a multi-view dataset, including 2D image information (videos) obtained by up to three cameras and 3D point clouds from up to five LiDAR sensors together with labels of the traffic participants in the scene. The measurements were conducted during different weather conditions on several days at a large junction in Hanover, Germany, resulting in a total duration of 145 minutes.",
author = "Steffen Busch and Christian Koetsier and Jeldrik Axmann and Claus Brenner",
note = "Funding Information: This project is supported by the German Research Foundation (DFG), as part of the Research Training Group i.c.sens, GRK 2159, ”Integrity and Collaboration in Dynamic Sensor Networks” as well as the Lower Saxony Ministry of Science and Culture under grant number ZN3493 within the Lower Saxony “Vorab“ of the Volkswagen Foundation and the Center for Digital Innovations. ; 2022 IEEE Intelligent Vehicles Symposium, IV 2022 ; Conference date: 05-06-2022 Through 09-06-2022",
year = "2022",
month = jul,
day = "19",
doi = "10.1109/IV51971.2022.9827157",
language = "English",
isbn = "9781665488228",
series = "IEEE Intelligent Vehicles Symposium, Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1127--1134",
booktitle = "2022 IEEE Intelligent Vehicles Symposium",
address = "United States",

}

Download

TY - GEN

T1 - LUMPI

T2 - 2022 IEEE Intelligent Vehicles Symposium, IV 2022

AU - Busch, Steffen

AU - Koetsier, Christian

AU - Axmann, Jeldrik

AU - Brenner, Claus

N1 - Funding Information: This project is supported by the German Research Foundation (DFG), as part of the Research Training Group i.c.sens, GRK 2159, ”Integrity and Collaboration in Dynamic Sensor Networks” as well as the Lower Saxony Ministry of Science and Culture under grant number ZN3493 within the Lower Saxony “Vorab“ of the Volkswagen Foundation and the Center for Digital Innovations.

PY - 2022/7/19

Y1 - 2022/7/19

N2 - Improvements in sensor technologies as well as machine learning methods allow an efficient collection, processing and analysis of the dynamic environment, which can be used for detection and tracking of traffic participants. Current datasets in this domain mostly present a single view, making highly accurate pose estimation impossible due to occlusions. The integration of different, simultaneously acquired data allows to exploit and develop collaboration principles to increase the quality, reliability and integrity of the derived information. This work addresses this problem by providing a multi-view dataset, including 2D image information (videos) obtained by up to three cameras and 3D point clouds from up to five LiDAR sensors together with labels of the traffic participants in the scene. The measurements were conducted during different weather conditions on several days at a large junction in Hanover, Germany, resulting in a total duration of 145 minutes.

AB - Improvements in sensor technologies as well as machine learning methods allow an efficient collection, processing and analysis of the dynamic environment, which can be used for detection and tracking of traffic participants. Current datasets in this domain mostly present a single view, making highly accurate pose estimation impossible due to occlusions. The integration of different, simultaneously acquired data allows to exploit and develop collaboration principles to increase the quality, reliability and integrity of the derived information. This work addresses this problem by providing a multi-view dataset, including 2D image information (videos) obtained by up to three cameras and 3D point clouds from up to five LiDAR sensors together with labels of the traffic participants in the scene. The measurements were conducted during different weather conditions on several days at a large junction in Hanover, Germany, resulting in a total duration of 145 minutes.

UR - http://www.scopus.com/inward/record.url?scp=85135370304&partnerID=8YFLogxK

U2 - 10.1109/IV51971.2022.9827157

DO - 10.1109/IV51971.2022.9827157

M3 - Conference contribution

AN - SCOPUS:85135370304

SN - 9781665488228

T3 - IEEE Intelligent Vehicles Symposium, Proceedings

SP - 1127

EP - 1134

BT - 2022 IEEE Intelligent Vehicles Symposium

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 5 June 2022 through 9 June 2022

ER -