Long-term visual localization in large scale urban environments exploiting street level imagery
Autor:in (Körperschaft)
Publikationsdatum
2020
Typ der Arbeit
Studiengang
Sammlung
Typ
01A - Beitrag in wissenschaftlicher Zeitschrift
Herausgeber:innen
Herausgeber:in (Körperschaft)
Betreuer:in
Übergeordnetes Werk
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Themenheft
DOI der Originalpublikation
Link
Reihe / Serie
Reihennummer
Jahrgang / Band
V-2-2020
Ausgabe / Nummer
Seiten / Dauer
Patentnummer
Verlag / Herausgebende Institution
Copernicus
Verlagsort / Veranstaltungsort
Auflage
Version
Programmiersprache
Abtretungsempfänger:in
Praxispartner:in/Auftraggeber:in
Zusammenfassung
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°.
Schlagwörter
Ubiquitous positioning, Visual localization, Image-based localization, Long-term matching, Image orientation, Pose estimation, Benchmark, Georeferencing
Fachgebiet (DDC)
600 - Technik, Medizin, angewandte Wissenschaften
Veranstaltung
Startdatum der Ausstellung
Enddatum der Ausstellung
Startdatum der Konferenz
Enddatum der Konferenz
Datum der letzten Prüfung
ISBN
ISSN
2194-9050
2194-9042
2194-9042
Sprache
Englisch
Während FHNW Zugehörigkeit erstellt
Ja
Zukunftsfelder FHNW
Publikationsstatus
Veröffentlicht
Begutachtung
Peer-Review der ganzen Publikation
Open Access-Status
Gold
Lizenz
Zitation
MEYER, Jonas, Daniel RETTENMUND und Stephan NEBIKER, 2020. Long-term visual localization in large scale urban environments exploiting street level imagery. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2020. Bd. V-2-2020. DOI 10.5194/isprs-annals-v-2-2020-57-2020. Verfügbar unter: https://doi.org/10.26041/fhnw-9510