Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Universiteit van Ams...arrow_drop_down
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
addClaim

Depth from an image

Authors: Nedović, V.;

Depth from an image

Abstract

Hoe zien mensen diepte in een afbeelding wanneer de scene in feite plat is gemaakt? Ons visueel systeem maakt gebruik van verschillende elementen in een afbeelding om diepte uit te rekenen. Dit is echter een complex proces, dat tot op heden geen volledige duidelijkheid biedt. Hoe kunnen we dit dan op de computer nabootsen, om automatisch diepte te kunnen afleiden? In dit proefschrift, zoeken we de grenzen op tot welke diepte berekend kan worden op basis van één afbeelding, gegeven de mogelijkheden van huidige computers en algoritmes. Eerst formuleren wij geometrische scènecategorieën, opgebouwd uit platte panelen en vergelijkbaar met scènes in theaters. Als we de computer leren een stagetype te herkennen voor elke afbeelding, kunnen we diepte benaderen in de afbeelding. Aanvullend bouwen we de kennis over diepte op uit primitieve afbeeldingselementen. We extraheren lange lijnen in een afbeelding en gebruiken kennis over perspectief om de locatie van maximale afbeeldingsdiepte te achterhalen. Tevens vinden we de randen van afbeeldingsoppervlakte en sorteren deze om te concluderen welke belangrijk zijn voor diepteanalyse. De methodes in het proefschrift en in de geraadpleegde literatuur tonen aan dat de computer goed in staat is diepte te begrijpen, ook op basis van enkele afbeelding.

Country
Netherlands
Related Organizations
  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Related to Research communities
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!