ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume V-2-2020
https://doi.org/10.5194/isprs-annals-V-2-2020-57-2020
https://doi.org/10.5194/isprs-annals-V-2-2020-57-2020
03 Aug 2020
 | 03 Aug 2020

LONG-TERM VISUAL LOCALIZATION IN LARGE SCALE URBAN ENVIRONMENTS EXPLOITING STREET LEVEL IMAGERY

J. Meyer, D. Rettenmund, and S. Nebiker

Keywords: Visual Localization, Image-Based Localization, Long-Term Matching, Image Orientation, Pose Estimation, Benchmark, Georeferencing, Ubiquitous Positioning

Abstract. In this paper, we present our approach for robust long-term visual localization in large scale urban environments exploiting street level imagery. Our approach consists of a 2D-image based localization using image retrieval (NetVLAD) to select reference images. This is followed by a 3D-structure based localization with a robust image matcher (DenseSfM) for accurate pose estimation. This visual localization approach is evaluated by means of the ‘Sun’ subset of the RobotCar seasons dataset, which is part of the Visual Localization benchmark. As the results on the RobotCar benchmark dataset are nearly on par with the top ranked approaches, we focused our investigations on reproducibility and performance with own data. For this purpose, we created a dataset with street-level imagery. In order to have independent reference and query images, we used a road-based and a tram-based mapping campaign with a time difference of four years. The approximately 90% successfully oriented images of both datasets are a good indicator for the robustness of our approach. With about 50% success rate, every second image could be localized with a position accuracy better than 0.25 m and a rotation accuracy better than 2°.