MODS: Fast and robust method for two-view matching

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F15%3A00235507" target="_blank" >RIV/68407700:21230/15:00235507 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1016/j.cviu.2015.08.005" target="_blank" >http://dx.doi.org/10.1016/j.cviu.2015.08.005</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.cviu.2015.08.005" target="_blank" >10.1016/j.cviu.2015.08.005</a>

Jazyk výsledku

angličtina

Název v původním jazyce

MODS: Fast and robust method for two-view matching

Popis výsledku v původním jazyce

Abstract A novel algorithm for wide-baseline matching called MODS - matching on demand with view synthesis - is presented. The MODS algorithm is experimentally shown to solve a broader range of wide-baseline problems than the state of the art while beingnearly as fast as standard matchers on simple problems. The apparent robustness vs. speed trade-off is finessed by the use of progressively more time-consuming feature detectors and by on-demand generation of synthesized images that is performed until areliable estimate of geometry is obtained. We introduce an improved method for tentative correspondence selection, applicable both with and without view synthesis. A modification of the standard first to second nearest distance rule increases the numberof correct matches by 5-20% at no additional computational cost. Performance of the MODS algorithm is evaluated on several standard publicly available datasets, and on a new set of geometrically challenging wide baseline problems that is

Název v anglickém jazyce

MODS: Fast and robust method for two-view matching

Popis výsledku anglicky

Abstract A novel algorithm for wide-baseline matching called MODS - matching on demand with view synthesis - is presented. The MODS algorithm is experimentally shown to solve a broader range of wide-baseline problems than the state of the art while beingnearly as fast as standard matchers on simple problems. The apparent robustness vs. speed trade-off is finessed by the use of progressively more time-consuming feature detectors and by on-demand generation of synthesized images that is performed until areliable estimate of geometry is obtained. We introduce an improved method for tentative correspondence selection, applicable both with and without view synthesis. A modification of the standard first to second nearest distance rule increases the numberof correct matches by 5-20% at no additional computational cost. Performance of the MODS algorithm is evaluated on several standard publicly available datasets, and on a new set of geometrically challenging wide baseline problems that is

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/GBP103%2F12%2FG084" target="_blank" >GBP103/12/G084: Centrum pro multi-modální interpretaci dat velkého rozsahu</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 periodika

Computer Vision and Image Understanding

ISSN

1077-3142

e-ISSN

—

Svazek periodika

141

Číslo periodika v rámci svazku

december

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

13

Strana od-do

81-93

Kód UT WoS článku

000364981500007

EID výsledku v databázi Scopus

2-s2.0-84948571032