The Community for Technology Leaders
Green Image
Issue No. 02 - Feb. (2018 vol. 40)
ISSN: 0162-8828
pp: 257-271
Akihiko Torii , Department of Systems and Control Engineering, the School of Engineering, Tokyo Institute of Technology, Tokyo, Japan
Relja Arandjelovic , Departement d'Informatique de l?École Normale Supérieure, Inria, WILLOW, ENS/INRIA/CNRS UMR, Paris
Josef Sivic , Departement d'Informatique de l?École Normale Supérieure, Inria, WILLOW, ENS/INRIA/CNRS UMR, Paris
Masatoshi Okutomi , Department of Systems and Control Engineering, the School of Engineering, Tokyo Institute of Technology, Tokyo, Japan
Tomas Pajdla , Department of Cybernetics, Faculty of Electrical Engineering, Center for Machine Perception, Czech Technical University in Prague, Praha, Czechia
ABSTRACT
We address the problem of large-scale visual place recognition for situations where the scene undergoes a major change in appearance, for example, due to illumination (day/night), change of seasons, aging, or structural modifications over time such as buildings being built or destroyed. Such situations represent a major challenge for current large-scale place recognition methods. This work has the following three principal contributions. First, we demonstrate that matching across large changes in the scene appearance becomes much easier when both the query image and the database image depict the scene from approximately the same viewpoint. Second, based on this observation, we develop a new place recognition approach that combines (i) an efficient synthesis of novel views with (ii) a compact indexable image representation. Third, we introduce a new challenging dataset of 1,125 camera-phone query images of Tokyo that contain major changes in illumination (day, sunset, night) as well as structural changes in the scene. We demonstrate that the proposed approach significantly outperforms other large-scale place recognition techniques on this challenging data.
INDEX TERMS
Lighting, Three-dimensional displays, Databases, Image recognition, Feature extraction, Visualization, Aging
CITATION

A. Torii, R. Arandjelovic, J. Sivic, M. Okutomi and T. Pajdla, "24/7 Place Recognition by View Synthesis," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 40, no. 2, pp. 257-271, 2018.
doi:10.1109/TPAMI.2017.2667665
286 ms
(Ver 3.3 (11022016))