An Enhanced Correlation-Based Method for Stereo Correspondence with Sub-Pixel Accuracy

Emmanouil Psarakis 1 Georgios Evangelidis 2, *
* Corresponding author
2 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 : The invariance of the similarity measure in photomet- ric distortions as well as its capability in producing sub- pixel accuracy are two desired and often required features in most stereo vision applications. In this paper we pro- pose a new correlation-based measure which incorporates both mentioned requirements. Specifically, by using an ap- propriate interpolation scheme in the candidate windows of the matching image, and using the classical zero mean normalized cross correlation function, we introduce a suit- able measure. Although the proposed measure is a non- linear function of the sub-pixel displacement parameter, its maximization results in a closed form solution, resulting in reduced complexity for its use in matching techniques. Ap- plication of the proposed measure in a number of bench- mark stereo pair images reveals its superiority over existing correlation-based techniques used for sub-pixel accuracy.
Document type :
Conference papers
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download


https://hal.inria.fr/hal-00864387
Contributor : Team Perception <>
Submitted on : Monday, September 23, 2013 - 3:18:03 PM
Last modification on : Wednesday, April 11, 2018 - 1:53:24 AM
Long-term archiving on: Friday, April 7, 2017 - 12:56:15 AM

Files

ICCV_2005.pdf
Files produced by the author(s)

Identifiers

Collections

CNRS | INRIA | IMAG | UGA

Citation

Emmanouil Psarakis, Georgios Evangelidis. An Enhanced Correlation-Based Method for Stereo Correspondence with Sub-Pixel Accuracy. 10th IEEE International Conference on Computer Vision (ICCV), Oct 2005, Beijing, China. pp.907-912, ⟨10.1109/ICCV.2005.33⟩. ⟨hal-00864387⟩

Share

Metrics

Record views

569

Files downloads

730