Skip to Main content Skip to Navigation
Conference papers

Fast segmentation-based dense stereo from quasi-dense matching

Abstract : We propose a segmentation-based dense stereo algorithm within an energy minimization framework. The cost function includes a new consistency term to take into account an initial quasi-dense disparity map and handles occlusions explicitly. Based on quasi-dense matching and color segmentation, optimization is performed efficiently by assuming a constant disparity for each region. The assumption is made robust by over-segmentation and a dynamic region splitting method done by graph cut. The efficiency and accuracy of the algorithm are demonstrated on standard stereo data. Experiment results show that the algorithm compares favorably with other state-of-the-art stereo algorithms.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00118599
Contributor : Maxime Lhuillier <>
Submitted on : Tuesday, December 5, 2006 - 5:05:29 PM
Last modification on : Tuesday, October 9, 2018 - 9:44:15 AM
Document(s) archivé(s) le : Friday, May 13, 2011 - 9:14:01 PM

Files

Accv04.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00118599, version 1

Citation

Yichen Wei, Maxime Lhuillier, Long Quan. Fast segmentation-based dense stereo from quasi-dense matching. Jan 2004, pp.CDROM. ⟨hal-00118599⟩

Share

Metrics

Record views

137

Files downloads

83