Uncertainty representation and quantification of 3D Models

Publikation: Beitrag in FachzeitschriftKonferenzaufsatz in FachzeitschriftForschungPeer-Review

Autoren

Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)335-341
Seitenumfang7
FachzeitschriftInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
Jahrgang43
AusgabenummerB2-2022
PublikationsstatusVeröffentlicht - 30 Mai 2022
Veranstaltung2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission II - Nice, Frankreich
Dauer: 6 Juni 202211 Juni 2022

Abstract

The quality of environmental perception is of great interest for localization tasks in autonomous systems. Maps, generated from the sensed information, are often used as additional spatial references in these applications. The quantification of the map uncertainties gives an insight into how reliable and complete the map is, avoiding the potential systematic deviation in pose estimation. Mapping 3D buildings in urban areas using Light detection and ranging (LiDAR) point clouds is a challenging task as it is often subject to uncertain error sources in the real world such as sensor noise and occlusions, which should be well represented in the 3D models for the downstream localization tasks. In this paper, we propose a method to model 3D building façades in complex urban scenes with uncertainty quantification, where the uncertainties of windows and façades are indicated in a probabilistic fashion. The potential locations of the missing objects (here: windows) are inferred by the available data and layout patterns with the Monte Carlo (MC) sampling approach. The proposed 3D building model and uncertainty measures are evaluated using the real-world LiDAR point clouds collected by Riegl Mobile Mapping System. The experimental results show that our uncertainty representation conveys the quality information of the estimated locations and shapes for the modelled map objects.

ASJC Scopus Sachgebiete

Zitieren

Uncertainty representation and quantification of 3D Models. / Zou, Q.; Sester, M.
in: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Jahrgang 43, Nr. B2-2022, 30.05.2022, S. 335-341.

Publikation: Beitrag in FachzeitschriftKonferenzaufsatz in FachzeitschriftForschungPeer-Review

Zou, Q & Sester, M 2022, 'Uncertainty representation and quantification of 3D Models', International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Jg. 43, Nr. B2-2022, S. 335-341. https://doi.org/10.5194/isprs-archives-XLIII-B2-2022-335-2022
Zou, Q., & Sester, M. (2022). Uncertainty representation and quantification of 3D Models. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, 43(B2-2022), 335-341. https://doi.org/10.5194/isprs-archives-XLIII-B2-2022-335-2022
Zou Q, Sester M. Uncertainty representation and quantification of 3D Models. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. 2022 Mai 30;43(B2-2022):335-341. doi: 10.5194/isprs-archives-XLIII-B2-2022-335-2022
Zou, Q. ; Sester, M. / Uncertainty representation and quantification of 3D Models. in: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. 2022 ; Jahrgang 43, Nr. B2-2022. S. 335-341.
Download
@article{bcf2a06c20e1461292bb9a267a132d2f,
title = "Uncertainty representation and quantification of 3D Models",
abstract = "The quality of environmental perception is of great interest for localization tasks in autonomous systems. Maps, generated from the sensed information, are often used as additional spatial references in these applications. The quantification of the map uncertainties gives an insight into how reliable and complete the map is, avoiding the potential systematic deviation in pose estimation. Mapping 3D buildings in urban areas using Light detection and ranging (LiDAR) point clouds is a challenging task as it is often subject to uncertain error sources in the real world such as sensor noise and occlusions, which should be well represented in the 3D models for the downstream localization tasks. In this paper, we propose a method to model 3D building fa{\c c}ades in complex urban scenes with uncertainty quantification, where the uncertainties of windows and fa{\c c}ades are indicated in a probabilistic fashion. The potential locations of the missing objects (here: windows) are inferred by the available data and layout patterns with the Monte Carlo (MC) sampling approach. The proposed 3D building model and uncertainty measures are evaluated using the real-world LiDAR point clouds collected by Riegl Mobile Mapping System. The experimental results show that our uncertainty representation conveys the quality information of the estimated locations and shapes for the modelled map objects. ",
keywords = "3D Map, Integrity, LiDAR, Mobile Mapping, Point Cloud, Uncertainty",
author = "Q. Zou and M. Sester",
note = "Funding Information: This work was funded by the German Research Foundation (DFG) as a part of the Research Training Group GRK2159; 2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission II ; Conference date: 06-06-2022 Through 11-06-2022",
year = "2022",
month = may,
day = "30",
doi = "10.5194/isprs-archives-XLIII-B2-2022-335-2022",
language = "English",
volume = "43",
pages = "335--341",
number = "B2-2022",

}

Download

TY - JOUR

T1 - Uncertainty representation and quantification of 3D Models

AU - Zou, Q.

AU - Sester, M.

N1 - Funding Information: This work was funded by the German Research Foundation (DFG) as a part of the Research Training Group GRK2159

PY - 2022/5/30

Y1 - 2022/5/30

N2 - The quality of environmental perception is of great interest for localization tasks in autonomous systems. Maps, generated from the sensed information, are often used as additional spatial references in these applications. The quantification of the map uncertainties gives an insight into how reliable and complete the map is, avoiding the potential systematic deviation in pose estimation. Mapping 3D buildings in urban areas using Light detection and ranging (LiDAR) point clouds is a challenging task as it is often subject to uncertain error sources in the real world such as sensor noise and occlusions, which should be well represented in the 3D models for the downstream localization tasks. In this paper, we propose a method to model 3D building façades in complex urban scenes with uncertainty quantification, where the uncertainties of windows and façades are indicated in a probabilistic fashion. The potential locations of the missing objects (here: windows) are inferred by the available data and layout patterns with the Monte Carlo (MC) sampling approach. The proposed 3D building model and uncertainty measures are evaluated using the real-world LiDAR point clouds collected by Riegl Mobile Mapping System. The experimental results show that our uncertainty representation conveys the quality information of the estimated locations and shapes for the modelled map objects.

AB - The quality of environmental perception is of great interest for localization tasks in autonomous systems. Maps, generated from the sensed information, are often used as additional spatial references in these applications. The quantification of the map uncertainties gives an insight into how reliable and complete the map is, avoiding the potential systematic deviation in pose estimation. Mapping 3D buildings in urban areas using Light detection and ranging (LiDAR) point clouds is a challenging task as it is often subject to uncertain error sources in the real world such as sensor noise and occlusions, which should be well represented in the 3D models for the downstream localization tasks. In this paper, we propose a method to model 3D building façades in complex urban scenes with uncertainty quantification, where the uncertainties of windows and façades are indicated in a probabilistic fashion. The potential locations of the missing objects (here: windows) are inferred by the available data and layout patterns with the Monte Carlo (MC) sampling approach. The proposed 3D building model and uncertainty measures are evaluated using the real-world LiDAR point clouds collected by Riegl Mobile Mapping System. The experimental results show that our uncertainty representation conveys the quality information of the estimated locations and shapes for the modelled map objects.

KW - 3D Map

KW - Integrity

KW - LiDAR

KW - Mobile Mapping

KW - Point Cloud

KW - Uncertainty

UR - http://www.scopus.com/inward/record.url?scp=85132036681&partnerID=8YFLogxK

U2 - 10.5194/isprs-archives-XLIII-B2-2022-335-2022

DO - 10.5194/isprs-archives-XLIII-B2-2022-335-2022

M3 - Conference article

AN - SCOPUS:85132036681

VL - 43

SP - 335

EP - 341

JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

SN - 1682-1750

IS - B2-2022

T2 - 2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission II

Y2 - 6 June 2022 through 11 June 2022

ER -

Von denselben Autoren