Visual localization in urban environments employing 3D city models

Reliable pose information is essential for many applications, such as for navigation or surveying tasks. Though GNSS is a well-established technique to retrieve that information, it often fails in urban environments due to signal occlusion or multi-path effects. In addition, GNSS might be subject to...

Full description

Saved in:
Bibliographic Details
Main Authors: Y. Loeper, M. Gerke, A. Alamouri, A. Kern, M. S. Bajauri, P. Fanta-Jende
Format: Article
Language:English
Published: Copernicus Publications 2024-12-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-2-W8-2024/311/2024/isprs-archives-XLVIII-2-W8-2024-311-2024.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846122224065445888
author Y. Loeper
M. Gerke
A. Alamouri
A. Kern
M. S. Bajauri
P. Fanta-Jende
author_facet Y. Loeper
M. Gerke
A. Alamouri
A. Kern
M. S. Bajauri
P. Fanta-Jende
author_sort Y. Loeper
collection DOAJ
description Reliable pose information is essential for many applications, such as for navigation or surveying tasks. Though GNSS is a well-established technique to retrieve that information, it often fails in urban environments due to signal occlusion or multi-path effects. In addition, GNSS might be subject to jamming or spoofing, which requires an alternative, complementary positioning method. We introduce a visual localization method which employs building models according to the CityGML standard. In contrast to the most commonly used sources for scene representation in visual localization, such as structure-from-motion (SfM) points clouds, CityGML models are already freely available for many cites worldwide, do not require a large amount of memory and the scene representation database does not have to be generated from images. Yet, 3D models are rarely used because they usually lack properties such as texture or only contain general geometric structures. Our approach utilizes the boundary representation (BREP) of the CityGML models in Level of Detail (LOD) 2 and the geometry of the query image scene from extracted straight line segments. We investigate how we can use an energy function to determine the quality of the correspondence between the line segments of the query image and the projected line segments of the CityGML model based on a specific camera pose. This is then optimized to estimate the camera pose of the query image. We show that a rough estimation of the camera pose is possible purely via the distribution of the line segments and without prior calculation of features and their descriptors. Furthermore, many possibilities and approaches for improvements remain open. However, if these approaches are taken into account, we expect CityGML models to be a promising option for scene representation in visual localization.
format Article
id doaj-art-03b6adb57f4a48c1b9cf37037c9aadbe
institution Kabale University
issn 1682-1750
2194-9034
language English
publishDate 2024-12-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-03b6adb57f4a48c1b9cf37037c9aadbe2024-12-14T22:32:07ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342024-12-01XLVIII-2-W8-202431131810.5194/isprs-archives-XLVIII-2-W8-2024-311-2024Visual localization in urban environments employing 3D city modelsY. Loeper0M. Gerke1A. Alamouri2A. Kern3M. S. Bajauri4P. Fanta-Jende5Institute of Geodesy and Photogrammetry, Technische Universität Braunschweig, Brunswick, GermanyInstitute of Geodesy and Photogrammetry, Technische Universität Braunschweig, Brunswick, GermanyInstitute of Geodesy and Photogrammetry, Technische Universität Braunschweig, Brunswick, GermanyInstitute of Flight Guidance, Technische Universität Braunschweig, Brunswick, GermanyInstitute of Geodesy and Photogrammetry, Technische Universität Braunschweig, Brunswick, GermanyUnit Assistive and Autonomous Systems, Center for Vision, Automation and Control, AIT Austrian Institute of Technology, Vienna, AustriaReliable pose information is essential for many applications, such as for navigation or surveying tasks. Though GNSS is a well-established technique to retrieve that information, it often fails in urban environments due to signal occlusion or multi-path effects. In addition, GNSS might be subject to jamming or spoofing, which requires an alternative, complementary positioning method. We introduce a visual localization method which employs building models according to the CityGML standard. In contrast to the most commonly used sources for scene representation in visual localization, such as structure-from-motion (SfM) points clouds, CityGML models are already freely available for many cites worldwide, do not require a large amount of memory and the scene representation database does not have to be generated from images. Yet, 3D models are rarely used because they usually lack properties such as texture or only contain general geometric structures. Our approach utilizes the boundary representation (BREP) of the CityGML models in Level of Detail (LOD) 2 and the geometry of the query image scene from extracted straight line segments. We investigate how we can use an energy function to determine the quality of the correspondence between the line segments of the query image and the projected line segments of the CityGML model based on a specific camera pose. This is then optimized to estimate the camera pose of the query image. We show that a rough estimation of the camera pose is possible purely via the distribution of the line segments and without prior calculation of features and their descriptors. Furthermore, many possibilities and approaches for improvements remain open. However, if these approaches are taken into account, we expect CityGML models to be a promising option for scene representation in visual localization.https://isprs-archives.copernicus.org/articles/XLVIII-2-W8-2024/311/2024/isprs-archives-XLVIII-2-W8-2024-311-2024.pdf
spellingShingle Y. Loeper
M. Gerke
A. Alamouri
A. Kern
M. S. Bajauri
P. Fanta-Jende
Visual localization in urban environments employing 3D city models
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title Visual localization in urban environments employing 3D city models
title_full Visual localization in urban environments employing 3D city models
title_fullStr Visual localization in urban environments employing 3D city models
title_full_unstemmed Visual localization in urban environments employing 3D city models
title_short Visual localization in urban environments employing 3D city models
title_sort visual localization in urban environments employing 3d city models
url https://isprs-archives.copernicus.org/articles/XLVIII-2-W8-2024/311/2024/isprs-archives-XLVIII-2-W8-2024-311-2024.pdf
work_keys_str_mv AT yloeper visuallocalizationinurbanenvironmentsemploying3dcitymodels
AT mgerke visuallocalizationinurbanenvironmentsemploying3dcitymodels
AT aalamouri visuallocalizationinurbanenvironmentsemploying3dcitymodels
AT akern visuallocalizationinurbanenvironmentsemploying3dcitymodels
AT msbajauri visuallocalizationinurbanenvironmentsemploying3dcitymodels
AT pfantajende visuallocalizationinurbanenvironmentsemploying3dcitymodels