Detail publikace

Feature Point Detection under Extreme Lighting Conditions

PŘIBYL, B. CHALMERS, A. ZEMČÍK, P.

Originální název

Feature Point Detection under Extreme Lighting Conditions

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

This paper evaluates the suitability of tone-mapped high dynamic range imagery for feature point detection under extreme lighting conditions. The conditions are extreme in respect to the dynamic range of the lighting within the test scenes used. This dynamic range cannot be captured using standard low dynamic range imagery techniques without loss of detail. Four widely used feature point detectors are used in the experiments: Harris corner detector, Shi-Tomasi, FAST and Fast Hessian. Their repeatability rate is studied under changes of camera viewpoint, camera distance and scene lighting with respect to the image formats used. The results of the experiments show which image formats perform best and what the most appropriate scenarios for their use are. Data used in the experiments is available as supplementary material (http://www.fit.vutbr.cz/~ipribyl/FPinHDR/).

Klíčová slova

feature point detection, interest point detection, corner point detection, Harris corner detector, Shi-Tomasi, FAST, Fast Hessian, SURF, high dynamic range imagery, HDR, Wallis filter

Autoři

PŘIBYL, B.; CHALMERS, A.; ZEMČÍK, P.

Rok RIV

2012

Vydáno

2. 5. 2012

Nakladatel

Comenius University in Bratislava

Místo

Smolenice

ISBN

978-80-223-3211-8

Kniha

Spring Conference on Computer Graphics

Strany od

156

Strany do

163

Strany počet

8

URL

BibTex

@inproceedings{BUT91477,
  author="Bronislav {Přibyl} and Alan {Chalmers} and Pavel {Zemčík}",
  title="Feature Point Detection under Extreme Lighting Conditions",
  booktitle="Spring Conference on Computer Graphics",
  year="2012",
  pages="156--163",
  publisher="Comenius University in Bratislava",
  address="Smolenice",
  doi="10.1145/2448531.2448550",
  isbn="978-80-223-3211-8",
  url="http://doi.acm.org/10.1145/2448531.2448550"
}

Dokumenty