Minimal complexity velocity-tuned filters with analogue neuromorphic networks: A theoretical approach for efficient design

Authors:
A. Torralba;J. Hérault
Affiliations:
Laboratoire des Images et des Signaux (LIS), Institut National Polytechnique de Grenoble, 46 avenue Félix Viallet, 38031 Grenoble Cedex, France, E-mail: Email: torralba@tirf.inpg.fr;Laboratoire des Images et des Signaux (LIS), Institut National Polytechnique de Grenoble, 46 avenue Félix Viallet, 38031 Grenoble Cedex, France, E-mail: Email: torralba@tirf.inpg.fr
Venue:
Neural Processing Letters
Year:
1998

Citing 2
Cited 1

Performance of optical flow techniques

International Journal of Computer Vision
Computation and analysis of image motion: a synopsis of current problems and methods

International Journal of Computer Vision

Asymmetrical Filters for Vision Chips: a Basis for the Design of Large Sets of Spatial and Spatiotemporal Filters

MICRONEURO '99 Proceedings of the 7th International Conference on Microelectronics for Neural, Fuzzy and Bio-Inspired Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we describe the way for an efficient design ofvelocity-tuned spatiotemporal filters using analogue neural networks. Thefilter presented here has a simple velocity-matched structure discrete inspace but continuous in time yielding to efficient VLSI realisations and itovercomes some drawbacks of previous similar approaches found in theliterature. We show how this filter can be used to compute a distributedrepresentation of velocity similar to that obtained with classicalspatiotemporal frequency-tuned Gabor filters.