Resistive Fuses: Analog Hardware for Detecting Discontinuities in Early Vision

  • John Harris
  • Christof Koch
  • Jin Luo
  • John Wyatt
Part of the The Kluwer International Series in Engineering and Computer Science book series (SECS, volume 80)

Abstract

The detection of discontinuities in motion, intensity, color, and depth is a well studied but difficult problem in computer vision. We discuss our “resistive fuse” circuit—the first hardware circuit that explicitly implements either analog or binary line processes in a controlled fashion. We have successfully designed and tested an analog CMOS VLSI circuit that contains a 1-D resistive network of fuses implementing piece-wise smooth surface interpolation. The segmentation ability of this network is demonstrated for a noisy step-edge input.

We derive the specific current-voltage relationship of the resistive fuse from a number of computational considerations, closely related to the early vision algorithms of Koch, Marroquin and Yuille (1986) and Blake and Zisserman (1987). We discuss the circuit implementation and the performance of the chip. In the last section, we show that a model of our resistive network—in which the resistive fuses have no internal dynamics—has an associated Lyapunov function, the co-content. The network will thus converge, without oscillations, to a stable solution, even in the presence of arbitrary parasitic capacitances throughout the network.

Keywords

Hexagonal Assure Expense 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Birkhoff, G. and Diaz, J. B. (1956). Nonlinear network problems. Quart. Appl. Math. 13:431–443.MathSciNetMATHGoogle Scholar
  2. Blake, A. (1989). Comparison of the efficiency of deterministic and stochastic algorithms for visual reconstruction. IEEE Trans. Pattern Anal. Mach. Intell. 11:2–12.MATHCrossRefGoogle Scholar
  3. Blake, A. and Zisserman, A. (1987). Visual Reconstruction. Cambridge, MA: MIT Press.Google Scholar
  4. Brayton, R. K. and Moser, J. K. (1964). A theory of nonlinear networks—I, II. Quart. Appl. Math. 22(1):1–33 (April)MathSciNetGoogle Scholar
  5. Brayton, R. K. and Moser, J. K. (1964). A theory of nonlinear networks—I, II. Quart. Appl. Math. 22(2):81–104 (July).MathSciNetGoogle Scholar
  6. Chua, L. O., Desoer, C. A., and Kuh, E. S. (1987). Linear and Nonlinear Circuits. New York: McGraw-Hill, pp. 23–34.MATHGoogle Scholar
  7. Duffin, R. J. (1947). Nonlinear networks IIa. Bull. Amer. Math. Soc. 53:963–971.MathSciNetMATHCrossRefGoogle Scholar
  8. Geman, S. and Geman, D. (1984). Stochastic relaxation, Gibbs distribution and the Bayesian restoration of images. IEEE Trans. Pattern Anal. Mach. Intell. 6:721–741.MATHCrossRefGoogle Scholar
  9. Grimson, W. E. L. (1981). From Images to Surfaces. Cambridge, MA: MIT Press.Google Scholar
  10. Harris, J. G. (1989). An analog VLSI chip for thin plate surface interpolation. In Neural Information Processing Systems, ed. D. Touretzky. Palo Alto: Morgan Kaufmann.Google Scholar
  11. Harris, J. G. and Koch, C. (1989). Resistive fuses: circuit implementations of line discontinuities in vision. Snowbird Neural Network Workshop, April 4–7.Google Scholar
  12. Harris, J. G., Koch, C., Staats, E., Luo, J. and Wyatt, J. (1989). Analog hardware for detecting discontinuities in early vision: computational justification and VLSI circuits, in preparation.Google Scholar
  13. Hasler, M. and Neirynck, J., (1986). Nonlinear Circuits. Norwood, MA: Artech House Inc., pp. 172–173.Google Scholar
  14. Hildreth, E. C. (1984). The Measurement of Visual Motion. Cambridge, MA: MIT Press.Google Scholar
  15. Hopfield, J. J. and Tank, D. W. (1985). Neural computation in optimization problems. Biol. Cybern. 52:141–152.MathSciNetMATHGoogle Scholar
  16. Horn, B. K. P. (1989). Parallel networks for machine vision. Artif. Intell. Lab. Memo No. 1071 (MIT, Cambridge).Google Scholar
  17. Horn, B. K. P. and Schunck, B. G. (1981). Determining optical flow. Artif. Intell. 17:185–203.CrossRefGoogle Scholar
  18. Ikeuchi, K. and Horn, B. K. P. (1981). Numerical shape from shading and occluding boundaries. Artif. Intell. 17:141–184.CrossRefGoogle Scholar
  19. Hutchinson, J., Koch, C., Luo, J., and Mead, C. (1988). Computing motion using analog and binary resistive networks. IEEE Computer 21:52–63.Google Scholar
  20. Ikeuchi, K. and Horn, B. K. P. (1981). Numerical shape from shading and occluding boundaries. Artif. Intell. 17:141–184.CrossRefGoogle Scholar
  21. Koch, C., Marroquin, J., and Yuille, A. (1986). Analog “neuronal” networks in early vision. Proc. Natl. Acad. Sci. USA 83:4263–4267.MathSciNetCrossRefGoogle Scholar
  22. Koch, C. (1989). Seeing chips: analog VLSI circuits for computer vision. Neural Computation 1:184–200.CrossRefGoogle Scholar
  23. Liu, S. C. and Harris, J. G. (1989). Generalized smoothing networks in solving early vision problems. Computer Vision and Pattern Recognition Conference.Google Scholar
  24. Luo, J., Koch, C., and Mead, C. (1988). An experimental subthreshold, analog CMOS two-dimensional surface interpolation circuit. Neural Information Processing Systems Conference, Denver, November.Google Scholar
  25. Marr, D. and Poggio, T. (1976). Cooperative computation of stereo disparity. Science 194:283–287.CrossRefGoogle Scholar
  26. Marroquin, J., Mitter, S., and Poggio, T. (1987). Probabilistic solution of ill-posed problems in computational vision. J. Am. Statistic Assoc. 82:76–89.MATHCrossRefGoogle Scholar
  27. Maxwell, J. C. (1891). A Treatise on Electricity and Magnetism, 3rd ed., Vol. I, pp. 407–408. Republished by New York: Dover Publications, 1954.Google Scholar
  28. Mead, C. A. (1985). A sensitive electronic photoreceptor. In 1985 Chapel Hill Conference on Very Large Scale Integration, pp. 463–471.Google Scholar
  29. Mead, C. A. (1989). Analog VLSI and Neural Systems. Reading: Addison-Wesley.MATHGoogle Scholar
  30. Millar, W. (1951). Some general theorems for non-linear systems possessing resistance. Phil. Mag. 42:1150–1160.MathSciNetMATHGoogle Scholar
  31. Nagel, H. H. (1987). On the estimation of optical flow: relations between different approaches and some new results. Artif. Intell. 33:299–324.CrossRefGoogle Scholar
  32. Penfield, P., Jr., Spence, R., and Duinker, S. (1970). Tellegen’s Theorem and Electrical Networks, Cambridge, MA: MIT Press.Google Scholar
  33. Perona, P. and Malik, J. (1988). A network for multiscale image segmentation. Proc. 1988 IEEE Int. Symp. on Circuits and Systems, Espoo, Finland, June, pp. 2565–2568.Google Scholar
  34. Poggio, T., Gamble, E. B., and Little, J. J. (1988). Parallel integration of vision modules. Science 242:436–440.MathSciNetCrossRefGoogle Scholar
  35. Poggio, T. and Koch, C. (1985). Ill-posed problems in early vision: from computational theory to analogue networks. Proc. R. Soc. Lond. B 226:303–323.MATHCrossRefGoogle Scholar
  36. Poggio, T., Torre, V., and Koch, C. (1985). Computational vision and regularization theory. Nature 317:314–319.CrossRefGoogle Scholar
  37. Poggio, T., Voorhees, H., and Yuille, A. (1986). A regularized solution to edge detection. Artif. Intell. Lab Memo No. 833 (MIT, Cambridge).Google Scholar
  38. Sivilotti, M.A., Mahowald, M.A. and Mead, C.A., Real-time visual computation using analog CMOS processing arrays. In: 1987 Stanford Conf. VLSI, pp. 295–312 (MIT Press, Cambridge, 1987).Google Scholar
  39. Standley, D. L., and Wyatt, J. L., Jr. (1989). Stability criterion for lateral inhibition and related networks that is robust in the presence of integrated circuit parasitics. In IEEE Trans. Circuits and Systems 36, May., pp. 675–681Google Scholar
  40. Standley, D. L. (1989). Design criteria extensions for stable lateral inhibition networks in the presence of circuit parasitics. Proc. 1989 IEEE Int. Symp. on Circuits and Systems, Portland, Oregon, May, pp. 837–840.Google Scholar
  41. Tellegen, B. D. H. (1952). A general network theorem, with applications. Phillips Research Reports 7:259–269.MathSciNetMATHGoogle Scholar
  42. Terzopoulos, D. (1983). Multilevel computational processes for visual surface reconstruction. Comp. Vision Graph. Image Proc. 24: 52–96.CrossRefGoogle Scholar
  43. Terzopoulos, D. (1986). Regularization of inverse problems involving discontinuities. IEEE Trans. Pattern Anal. Machine Intell. 8:413–424 (1986).CrossRefGoogle Scholar
  44. Wyatt, J. L., Jr. and Standley, D. L. (1989). Criteria for robust stability in a class of lateral inhibition networks coupled through resistive grids. Neural Computation 1:58–67.CrossRefGoogle Scholar

Copyright information

© Kluwer Academic Publishers 1989

Authors and Affiliations

  • John Harris
    • 1
  • Christof Koch
    • 1
  • Jin Luo
    • 1
  • John Wyatt
    • 2
  1. 1.Computation and Neural Systems ProgramCalifornia Institute of TechnologyPasadenaUSA
  2. 2.Department of Electrical Engineering and Computer Science and Research Laboratory of ElectronicsMassachusetts Institute of TechnologyCambridgeUSA

Personalised recommendations