elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Datenschutz | Kontakt | English
Schriftgröße: [-] Text [+]

Learning to Localize in New Environments from Synthetic Training Data

Winkelbauer, Dominik und Denninger, Maximilian und Triebel, Rudolph (2021) Learning to Localize in New Environments from Synthetic Training Data. In: 2021 IEEE International Conference on Robotics and Automation, ICRA 2021, Seiten 5840-5846. ICRA 2021, 30. May - 5. June 2021, Xi'an, China. doi: 10.1109/ICRA48506.2021.9560872. ISBN 978-172819077-8. ISSN 1050-4729.

[img] PDF
3MB

Offizielle URL: https://ieeexplore.ieee.org/document/9560872

Kurzfassung

Most existing approaches for visual localization either need a detailed 3D model of the environment or, in the case of learning-based methods, must be retrained for each new scene. This can either be very expensive or simply impossible for large, unknown environments, for example in search-and-rescue scenarios. Although there are learning-based approaches that operate scene-agnostically, the generalization capability of these methods is still outperformed by classical approaches. In this paper, we present an approach that can generalize to new scenes by applying specific changes to the model architecture, including an extended regression part, the use of hierarchical correlation layers, and the exploitation of scale and uncertainty information. Our approach outperforms the 5-point algorithm using SIFT features on equally big images and additionally surpasses all previous learning-based approaches that were trained on different data. It is also superior to most of the approaches that were specifically trained on the respective scenes. We also evaluate our approach in a scenario where only very few reference images are available, showing that under such more realistic conditions our learning-based approach considerably exceeds both existing learning-based and classical methods.

elib-URL des Eintrags:https://elib.dlr.de/143564/
Dokumentart:Konferenzbeitrag (Vortrag)
Titel:Learning to Localize in New Environments from Synthetic Training Data
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Winkelbauer, DominikDominik.Winkelbauer (at) dlr.dehttps://orcid.org/0000-0001-7443-1071NICHT SPEZIFIZIERT
Denninger, MaximilianMaximilian.Denninger (at) dlr.dehttps://orcid.org/0000-0002-1557-2234NICHT SPEZIFIZIERT
Triebel, RudolphRudolph.Triebel (at) dlr.dehttps://orcid.org/0000-0002-7975-036XNICHT SPEZIFIZIERT
Datum:2021
Erschienen in:2021 IEEE International Conference on Robotics and Automation, ICRA 2021
Referierte Publikation:Ja
Open Access:Ja
Gold Open Access:Nein
In SCOPUS:Ja
In ISI Web of Science:Ja
DOI:10.1109/ICRA48506.2021.9560872
Seitenbereich:Seiten 5840-5846
ISSN:1050-4729
ISBN:978-172819077-8
Status:veröffentlicht
Stichwörter:Localization, Robotics, Computer Vision, Machine Learning, Deep Learning
Veranstaltungstitel:ICRA 2021
Veranstaltungsort:Xi'an, China
Veranstaltungsart:internationale Konferenz
Veranstaltungsdatum:30. May - 5. June 2021
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Raumfahrt
HGF - Programmthema:Robotik
DLR - Schwerpunkt:Raumfahrt
DLR - Forschungsgebiet:R RO - Robotik
DLR - Teilgebiet (Projekt, Vorhaben):R - Multisensorielle Weltmodellierung (RM) [RO]
Standort: Oberpfaffenhofen
Institute & Einrichtungen:Institut für Robotik und Mechatronik (ab 2013) > Perzeption und Kognition
Hinterlegt von: Winkelbauer, Dominik
Hinterlegt am:28 Okt 2021 11:02
Letzte Änderung:27 Mär 2024 15:07

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
electronic library verwendet EPrints 3.3.12
Gestaltung Webseite und Datenbank: Copyright © Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.