Efficient Dense Matching for Textured Scenes Using Region Growing - Archive ouverte HAL Access content directly
Conference Papers Year : 1998

Efficient Dense Matching for Textured Scenes Using Region Growing

(1)
1

Abstract

We present a simple and efficient dense matching method based on region growing techniques, which can be applied to a wide range of globally textured images like many outdoor scenes. Our method can deal with non-rigid scenes and large camera motions. First a few highly distinctive features like points or areas are extracted and matched. These initial matches are then used in a correlation-based region growing step which propagates the matches in textured and more ambiguous regions of the images. The implementation of the algorithm is also given and is demonstrated on real image pairs.
Fichier principal
Vignette du fichier
Bmvc98.pdf (1.09 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00590096 , version 1 (05-05-2011)

Identifiers

  • HAL Id : inria-00590096 , version 1

Cite

Maxime Lhuillier. Efficient Dense Matching for Textured Scenes Using Region Growing. 9th British Machine Vision Conference (BMVC '98), 1998, Southampton, United Kingdom. pp.700--709. ⟨inria-00590096⟩
71 View
109 Download

Share

Gmail Facebook Twitter LinkedIn More