24/7 place recognition by view synthesis

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

24/7 place recognition by view synthesis

Popis výsledku v původním jazyce

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

Název v anglickém jazyce

24/7 place recognition by view synthesis

Popis výsledku anglicky

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

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/7E13015" target="_blank" >7E13015: Planetary Robotics Data Exploitation</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2015

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

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

—

Počet stran výsledku

10

Strana od-do

1808-1817

Název nakladatele

IEEE Computer Society Press

Místo vydání

New York

Místo konání akce

Boston

Datum konání akce

7. 6. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—