Robust Spatiotemporal Stereo for Dynamic Scenes

Jordi Sanchez-Riera 1 Jan Cech 1 Radu Horaud 1
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Stereo matching is a challenging problem, especially in the presence of noise or of weakly textured objects. Using temporal information in a binocular video sequence to increase the discriminability for matching has been introduced in the recent past, but all the proposed methods assume either constant disparity over time, or small object motions, which is not always true. We introduce a novel stereo algorithm that exploits temporal information by robustly aggregating a similarity statistic over time, in order to improve the matching accuracy for weak data, while preserving regions undergoing large motions without introducing artifacts.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/hal-00768766
Contributor : Team Perception <>
Submitted on : Sunday, December 23, 2012 - 7:51:19 PM
Last modification on : Wednesday, April 11, 2018 - 1:59:15 AM
Document(s) archivé(s) le : Sunday, March 24, 2013 - 3:51:08 AM

File

SanchezCechHoraud_ICPR12.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00768766, version 1

Collections

Citation

Jordi Sanchez-Riera, Jan Cech, Radu Horaud. Robust Spatiotemporal Stereo for Dynamic Scenes. ICPR 2012 - 21st International Conference on Pattern Recognition, Nov 2012, Tsukuba Science City, Japan. pp.360-363. ⟨hal-00768766⟩

Share

Metrics

Record views

405

Files downloads

166