Skip to Main content Skip to Navigation
Conference papers

Efficient Dense Matching for Textured Scenes Using Region Growing

Maxime Lhuillier 1
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/inria-00590096
Contributor : Team Perception <>
Submitted on : Thursday, May 5, 2011 - 2:35:41 PM
Last modification on : Friday, June 26, 2020 - 4:04:03 PM
Document(s) archivé(s) le : Saturday, August 6, 2011 - 2:33:40 AM

File

Bmvc98.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00590096, version 1

Collections

IMAG | CNRS | INRIA | UGA

Citation

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⟩

Share

Metrics

Record views

161

Files downloads

295