Increasing efficiency in disparity calculation

Authors:
Jarno Ralli;Francisco Pelayo;Javier Diaz
Affiliations:
University of Granada, Escuela Técnica Superior de Ingenierías Informática y de, Telecomunicación, Departamento de Arquitectura y Tecnología de Computadores, Granada, Spai ...;University of Granada, Escuela Técnica Superior de Ingenierías Informática y de, Telecomunicación, Departamento de Arquitectura y Tecnología de Computadores, Granada, Spai ...;University of Granada, Escuela Técnica Superior de Ingenierías Informática y de, Telecomunicación, Departamento de Arquitectura y Tecnología de Computadores, Granada, Spai ...
Venue:
BVAI'07 Proceedings of the 2nd international conference on Advances in brain, vision and artificial intelligence
Year:
2007

Citing 5
Cited 1

Three-dimensional computer vision: a geometric viewpoint

Three-dimensional computer vision: a geometric viewpoint
Introductory Techniques for 3-D Computer Vision

Introductory Techniques for 3-D Computer Vision
Multiple View Geometry in Computer Vision

Multiple View Geometry in Computer Vision
Advances in Computational Stereo

IEEE Transactions on Pattern Analysis and Machine Intelligence
An explicit and compact coding of geometric and structural image information applied to stereo processing

Pattern Recognition Letters

Short Communication: A method for sparse disparity densification using voting mask propagation

Journal of Visual Communication and Image Representation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper a trade-off between the computation effort and the accuracy of the resulting disparity map, obtained using interpolation over spatial domain, is presented. The accuracy of the obtained disparity map is presented as the mean squared error calculated over the known disparity ground truth of test images, while efficiency increase is presented in terms of algorithm run-times. Even when reducing the search space for correspondences using epipolar geometry, disparity calculation methods are considered computationally more expensive than interpolation. We show that substantial efficiency increase can be gained using interpolation, in comparison to calculating the dense disparity map directly. As will be shown interpolation also permits us to approximate a disparity value for the occluded pixels. The main contribution of our work is the disparity calculation efficiency increase using interpolation, that fits the sparse disparity map as a 2D surface.