Stereovision disparity analysis by two-dimensional motion charge map inspired in neurobiology

Authors:
José M. López-Valles;Miguel A. Fernández;Antonio Fernández-Caballero;Francisco J. Gómez
Affiliations:
Universidad de Castilla-La Mancha, Escuela Universitaria Politécnica de Cuenca, Cuenca, Spain;Escuela Politécnica Superior de Albacete, Universidad de Castilla-La Mancha, Albacete, Spain;Escuela Politécnica Superior de Albacete, Universidad de Castilla-La Mancha, Albacete, Spain;Escuela Politécnica Superior de Albacete, Universidad de Castilla-La Mancha, Albacete, Spain
Venue:
BVAI'05 Proceedings of the First international conference on Brain, Vision, and Artificial Intelligence
Year:
2005

Citing 8
Cited 1

Three-dimensional computer vision: a geometric viewpoint

Three-dimensional computer vision: a geometric viewpoint
Hierarchical stereo and motion correspondence using feature groupings

International Journal of Computer Vision
Non-parametric Local Transforms for Computing Visual Correspondence

ECCV '94 Proceedings of the Third European Conference-Volume II on Computer Vision - Volume II
Unifying Stereo, Motion and Object Recognition via Epipolar Geometry

ACCV '95 Invited Session Papers from the Second Asian Conference on Computer Vision: Recent Developments in Computer Vision
On motion detection through a multi-layer neural network architecture

Neural Networks
Advances in Computational Stereo

IEEE Transactions on Pattern Analysis and Machine Intelligence
Length-speed ratio (LSR) as a characteristic for moving elements real-time classification

Real-Time Imaging
Computational Experiments with a Feature Based Stereo Algorithm

IEEE Transactions on Pattern Analysis and Machine Intelligence

Modelling the Stereovision-Correspondence-Analysis task by Lateral Inhibition in Accumulative Computation problem-solving method

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Up to date several strategies of how to retrieve depth information from a sequence of images have been described. In this paper a method that is inspired in Neurobiology and that turns around the symbiosis existing between stereovision and motion is introduced. A motion representation in form of a two-dimensional motion charge map, based in the so-called permanency memories mechanism is presented. For each pair of frame of a video stereovision sequence, the method displaces the left permanency stereo-memory on the epipolar restriction basis over the right one, in order to analyze the disparities of the motion trails calculated.