Abstract
In this paper we describe the way for an efficient design of velocity-tuned spatiotemporal filters using analogue neural networks. The filter presented here has a simple velocity-matched structure discrete in space but continuous in time yielding to efficient VLSI realisations and it overcomes some drawbacks of previous similar approaches found in the literature. We show how this filter can be used to compute a distributed representation of velocity similar to that obtained with classical spatiotemporal frequency-tuned Gabor filters.
Similar content being viewed by others
References
H.B. Barlow and W.R. Levick, “The mechanism of directionally selective units in rabbit's retina”, Journal of Physiology, pp. 178–549, 1965.
J.L. Barron, D.J. Fleet and S.S. Beauchemin, “Performances of optical flow techniques”, International Journal of Computer Vision, 12(1), 43–77, 1994.
T. Delbrück, “Silicon retina with correlation-based, velocity-tuned pixels”, IEEE Trans. Neural Networks, 4, 529–541, May 1993.
R. Douglas, M. Mahowald, and C. Mead, “Neuromorphic analogue VLSI”, Annu. Rev. Neurosci., 18, 255–281, 1995.
D.J. Heeger, “Model for the extraction of image flow”, Journal of Optical Society of America A, 4(8), 1455–1471, August 1987.
M. Hirahara and T. Nagano, “A neural network model for visual motion detection that can explain psychophysical and neurophysiological phenomena”, Biological Cybernetics, (68), 247–252, 1993.
B.K.P. Horn and B.G. Schunck, “Determining optical flow”, Artificial intelligence, 17, 185–203, 1981.
C.A. Mead and M.A. Mahowald, “A silicon model of early visual processing”, Neural Networks, 1, 91–97, 1988.
A. Mitiche and P. Bouthemy. “Computation and analysis of image motion: a synopsis of current problems and methods”, International Journal of Computer Vision, 19(1), 29–55, 1996.
W. Reichardt, “Evaluation of optical motion information by movement detectors”, J. Comp. Physiol., 161, 533–547, 1987.
Bertram E. Shi, “An analog neural network for gabor-type image filtering”, in: International conference on neural information processing, Vol. 1, pp. 417–422, Hong Kong, September 1996.
Bertram E. Shi and Leon O. Chua, “Resistive grid image filtering: Input/output analysis via de CNN framework”, IEEE Trans. on circuits and systems-I, 39(7), 531–548, July 1992.
Bertram E. Shi, Tamás Roska, and Leon O. Chua, “Design of linear cellular neural networks for motion sensitive filtering”, IEEE Trans. on circuits and systems-II, 40(5), 320–331, May 1993.
E.P. Simoncelli and D.J. Heeger, “A model of neural responses in visual area MT”, Vision Research 38(5): 743–761, 1998.
A. Torralba and J. Hérault, “From retinal circuits to motion processing: a neuromorphic approach to velocity estimation”, in: Michel Verleysen (ed.) ESANN'97, pp. 47–54, D facto, Brussels, Belgium, April 1997.
A.B. Watson and A.J. Ahumada, “A look at motion in the frequency domain”, in: J.K. Tsotsos (ed.), Motion: perception and representation, pp. 1–10, Association for computing machinery, New York, 1983.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Torralba, A., Hérault, J. Minimal complexity velocity-tuned filters with analogue neuromorphic networks: A theoretical approach for efficient design. Neural Processing Letters 8, 229–239 (1998). https://doi.org/10.1023/A:1009677701643
Issue Date:
DOI: https://doi.org/10.1023/A:1009677701643