Abstract
The computational capabilities of linear lattice network has been investigated through the analysis, synthesys and realization of CMOS circuits able to implement the 1-D convolution with Gabor-like operators. The area of the single processing cell is 83μm × 70 μm. The feasibility of the approach has been verified experimentally over a network of various sizes, up to 36 cells. Applications to stereopsys and motion analysis are described.
Preview
Unable to display preview. Download preview PDF.
References
E.H. Adelson and J.R. Bergen. Spatiotemporal energy models for the perception of motion. J. Opt. Soc. Amer., 2:284–321, 1985.
W.T. Freeman and E.H. Adelson. The design and use of steerable filters. IEEE Trams. Pattern Anal. Mach. Intell., 13(9):891–906, 1991.
C. Koch, J. Marroquin, and A. Yuille. Analog “neuronal” networks in early vision. Proc. Natl. Acad. Sci., 83:4263–4267, 1986.
C.A. Mead. Analog VLSI and Neural Systems. Addison-Wesley, Reading, 1989.
T. Poggio, V. Torre, and C. Koch. Computational vision and regularization theory. Nature, 317:638–643, 1985.
L. Raffo. Analysis and synthesis of resistive networks for distributed visual elaborations. Electronics Letters, 32(8):743, April 1996.
T.D. Sanger. Stereo disparity computation using Gabor filters. Biol. Cybern., 59:405–418, 1988.
E.A. Vittoz. Analog VLSI signal processing: Why, where, and how? J. of VLSI Signal Processing, 8:27–44, 1994.
J.L. Wyatt, C. Keast, M. Seidel, D. Standley, B. Horn, Knight T., C. Sodini, H.-S. Lee, and T. Poggio. Analog VLSI systems for image acquisition and fast early vision processing. Int. J. of Computer Vision, 8:217–230, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bisio, G.M., Bo, G.M., Confalone, M., Raffo, L., Sabatini, S.P., Zizola, M.P. (1997). An analog VLSI computational engine for early vision tasks. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020310
Download citation
DOI: https://doi.org/10.1007/BFb0020310
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive