Long-Term Visual Localization Revisited
Journal article, 2020
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.
benchmark
Visualization
Three-dimensional analysis
long-term localization
Cameras
Benchmark testing
Visual localization
6DOF pose estimation
Solid modelling
Trajectory
Robots
relocalization
Author
Carl Toft
Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering, Imaging and Image Analysis
Will Maddern
University of Oxford
Akihiko Torii
Tokyo Institute of Technology
Lars Hammarstrand
Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering, Signal Processing
Erik Stenborg
Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering, Signal Processing
Daniel Safari
Technical University of Denmark (DTU)
Tokyo Institute of Technology
Masatoshi Okutomi
Tokyo Institute of Technology
Marc Pollefeys
Swiss Federal Institute of Technology in Zürich (ETH)
Microsoft Corporation
Josef Sivic
Institut National de Recherche en Informatique et en Automatique (INRIA)
Czech Technical University in Prague
Tomas Pajdla
Czech Technical University in Prague
Fredrik Kahl
Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering, Imaging and Image Analysis
Torsten Sattler
Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering, Imaging and Image Analysis
Czech Technical University in Prague
IEEE Transactions on Pattern Analysis and Machine Intelligence
0162-8828 (ISSN)
Vol. In pressSemantic Mapping and Visual Navigation for Smart Robots
Swedish Foundation for Strategic Research (SSF), 2016-05-01 -- 2021-06-30.
Integrering av geometri och semantik i datorseende
Swedish Research Council (VR), 2017-01-01 -- 2020-12-31.
Infrastructure
C3SE (Chalmers Centre for Computational Science and Engineering)
Subject Categories
Signal Processing
Computer Science
Computer Vision and Robotics (Autonomous Systems)
DOI
10.1109/TPAMI.2020.3032010