24/7 place recognition by view synthesis
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F15%3A00235492" target="_blank" >RIV/68407700:21230/15:00235492 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1109/CVPR.2015.7298790" target="_blank" >http://dx.doi.org/10.1109/CVPR.2015.7298790</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/CVPR.2015.7298790" target="_blank" >10.1109/CVPR.2015.7298790</a>
Alternative languages
Result language
angličtina
Original language name
24/7 place recognition by view synthesis
Original language description
We address the problem of large-scale visual place recognition for situations where t he scene undergoes a major change in appearance, for example, due to illumination (day/night), ch ange of seasons, aging, or structural modifications over time such asbuildings built or destroye d. 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 a cross 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 obs ervation, 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 challe nging dataset of 1,125 camera-phone query images of Tokyo that contain major changes in illuminat ion (day, sunset, night) as well as
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JD - Use of computers, robotics and its application
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/7E13015" target="_blank" >7E13015: Planetary Robotics Data Exploitation</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
CVPR 2015: Proceedings of the 2015 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISBN
978-1-4673-6964-0
ISSN
—
e-ISSN
—
Number of pages
10
Pages from-to
1808-1817
Publisher name
IEEE Computer Society Press
Place of publication
New York
Event location
Boston
Event date
Jun 7, 2015
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—