Long-Term Visual Localization Revisited
Artikel i vetenskaplig tidskrift, 2022
Visual localization enables autonomous vehicles to navigate in their surroundings and augmented reality applications to link virtual to real worlds. Practical visual localization approaches need to be robust to a wide variety of viewing conditions, including day-night changes, as well as weather and seasonal variations, while providing highly accurate six degree-of-freedom (6DOF) camera pose estimates. In this paper, we extend three publicly available datasets containing images captured under a wide variety of viewing conditions, but lacking camera pose information, with ground truth pose information, making evaluation of the impact of various factors on 6DOF camera pose estimation accuracy possible. We also discuss the performance of state-of-the-art localization approaches on these datasets. Additionally, we release around half of the poses for all conditions, and keep the remaining half private as a test set, in the hopes that this will stimulate research on long-term visual localization, learned local image features, and related research areas. Our datasets are available at visuallocalization.net, where we are also hosting a benchmarking server for automatic evaluation of results on the test set. The presented state-of-the-art results are to a large degree based on submissions to our server.
Visualization
Three-dimensional analysis
Solid modelling
relocalization
Visual localization
long-term localization
Cameras
6DOF pose estimation
Robots
benchmark
Trajectory
Benchmark testing
Författare
Carl Toft
Digitala bildsystem och bildanalys
Will Maddern
University of Oxford
Akihiko Torii
Tokyo Institute of Technology
Lars Hammarstrand
Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik
Erik Stenborg
Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik
Daniel Safari
Tokyo Institute of Technology
Danmarks Tekniske Universitet (DTU)
Masatoshi Okutomi
Tokyo Institute of Technology
Marc Pollefeys
Microsoft Corporation
Eidgenössische Technische Hochschule Zürich (ETH)
Josef Sivic
Institut National de Recherche en Informatique et en Automatique (INRIA)
Ceske Vysoke Uceni Technicke v Praze
Tomas Pajdla
Ceske Vysoke Uceni Technicke v Praze
Fredrik Kahl
Digitala bildsystem och bildanalys
Torsten Sattler
Ceske Vysoke Uceni Technicke v Praze
Digitala bildsystem och bildanalys
IEEE Transactions on Pattern Analysis and Machine Intelligence
0162-8828 (ISSN) 19393539 (eISSN)
Vol. 44 4 2074-2088Semantisk kartering & visuell navigering för smarta robotar
Stiftelsen för Strategisk forskning (SSF) (RIT15-0038), 2016-05-01 -- 2021-06-30.
Integrering av geometri och semantik i datorseende
Vetenskapsrådet (VR) (2016-04445), 2017-01-01 -- 2020-12-31.
Infrastruktur
C3SE (Chalmers Centre for Computational Science and Engineering)
Ämneskategorier
Signalbehandling
Datavetenskap (datalogi)
Datorseende och robotik (autonoma system)
DOI
10.1109/TPAMI.2020.3032010
PubMed
33074802