Skip to main content

Analog hardware for detecting discontinuities in early vision


The detection of discontinuities in motion, intensity, color, and depth is a well-studied but difficult problem in computer vision [6]. We discuss the first hardware circuit that explicitly implements either analog or binary line processes in a deterministic fashion. Specifically, we show that the processes of smoothing (using a first-order or membrane type of stabilizer) and of segmentation can be implemented by a single, two-terminal nonlinear voltage-controlled resistor, the “resistive fuse”; and we derive its current-voltage relationship from a number of deterministic approximations to the underlying stochastic Markov random fields algorthms. The concept that the quadratic variation functionals of early vision can be solved via linear resistive networks minimizing power dissipation [37] can be extended to non-convex variational functionals with analog or binary line processes being solved by nonlinear resistive networks minimizing the electrical co-content.

We have successfully designed, tested, and demonstrated an analog CMOS VLSI circuit that contains a 1D resistive network of fuses implementing piecewise smooth surface interpolation. We furthermore demonstrate the segmenting abilities of these analog and deterministic “line processes” by numerically simulating the nonlinear resistive network computing optical flow in the presence of motion discontinuities. Finally, we discuss various circuit implementations of the optical flow computation using these circuits.

This is a preview of subscription content, access via your institution.


  1. 1.

    A.Blake and A.Zisserman. Visual Reconstruction. MIT Press: Cambridge, MA, 1987.

    Google Scholar 

  2. 2.

    A.Blake. “Comparison of the efficiency of deterministic and stochastic algorithms for visual reconstruction,” IEEE Trans. PAMI 11:2–12, 1989.

    Google Scholar 

  3. 3.

    P.B. Chou and C. Brown. “Multimodal reconstruction and segmentation with Markov random fields and HCF optimization,” Proc. Image Understanding Workshop, pp. 214–221. Cambridge, MA, February, 1988.

  4. 4.

    E.Gamble and T.Poggio. “Integration of intensity edges with stereo and motion,“ Artif. Intell. Lab Memo No. 970, MIT, Cambridge, 1987.

    Google Scholar 

  5. 5.

    D.Geiger and F.Girosi. “Parallel and deterministic algorithms for MRFs: surface reconstruction and integration,” AI Memo No. 1114, MIT, Cambridge, 1989.

    Google Scholar 

  6. 6.

    S.Geman and D.Geman. “Stochastic relaxation, Gibbs distribution and Bayesian restoration of images,“ IEEE Trans. PAMI 6:721–741, 1984.

    Google Scholar 

  7. 7.

    W.E.L.Grimson, From Images to Surfaces. MIT Press: Cambridge, MA, 1981.

    Google Scholar 

  8. 8.

    J.G. Harris. “Solving early vision problems with VLSI constraint networks,” AAAI Neural Architectures for Computer Vision Workshop, Minneapolis, August 20, 1988.

  9. 9.

    J.G.Harris. “An analog VLSI chip for thin plate surface interpolation.“ In Neural Information Processing Systems, D.Touretzky (ed.). Morgan Kaufmann: Palo Alto, 1989.

    Google Scholar 

  10. 10.

    J.G. Harris and C. Koch. “Resistive fuses: circuit implementations of line discontinuities in vision,” Snowbird Neural Network Workshop, April 4–7, 1989.

  11. 11.

    J.G.Harris, C.Koch, J.Luo, and J.Wyatt. “Resistive fuses: Analog hardware for detecting discontinuities in early vision,” In Analog VLSI Implementations of Neural Systems, pp. 27–56. C.Mead and M.Ismail (eds.). Kluwer: Norwell, MA, 1989.

    Google Scholar 

  12. 12.

    E.C.Hildreth. The Measurement of Visual Motion. MIT Press: Cambridge, MA, 1984.

    Google Scholar 

  13. 13.

    J.J.Hopfield and D.W.Tank. “Neural computation in optimization problems,” Biological Cybernetics 52:141–152, 1985.

    Google Scholar 

  14. 14.

    B.K.P.Horn. “Determining lightness from an image,” Comput. Graphics Image Process. 3(1): 277–299, 1974.

    Google Scholar 

  15. 15.

    B.K.P.Horn. Robot Vision. MIT Press: Cambridge, 1986.

    Google Scholar 

  16. 16.

    B.K.P.Horn. “Parallel networks for machine vision,” Artif. Intell. Lab. Memo, 1071, MIT, Cambridge, 1988.

    Google Scholar 

  17. 17.

    B.K.P.Horn and B.G.Schunk. “Determining optical flow,” Artificial Intelligence 17:185–203, 1981.

    Google Scholar 

  18. 18.

    K.Huang. Statistical Mechanics. Wiley: New York, 1963.

    Google Scholar 

  19. 19.

    J.Hutchinson, C.Koch, J.Luo, and C.Mead. “Computing motion using analog and binary resistive networks,” IEEE Computer 21:52–63, 1988.

    Google Scholar 

  20. 20.

    K.Ikeuchi and B.K.P.Horn. “Numerical shape from shading and occluding boundaries,” Artificial Intelligence 17:141–184, 1981.

    Google Scholar 

  21. 21.

    C.Koch. “Seeing chips: analog VLSI circuits for computer vision,” Neural Computation 1:184–200, 1989.

    Google Scholar 

  22. 22.

    C. Koch, J. Luo, J. Hutchinson, and C. Mead. “Optical flow and surface interpolation in resistive networks: Algorithms and analog VLSI chips,” In Neural Networks, B. Shriver (ed.). IEEE Computer Science Press Book, in press, 1990.

  23. 23.

    C. Koch, J. Harris, T. Horiuchi, A. Hsu, and J. Luo. “Realtime computer vision and robotics using analog VLSI circuits,” Neural Inform. Process. Systems Conf., Denver, November, 1989.

  24. 24.

    C.Koch, J.Marroquin, and A.Yuille. “Analog neuronal networks in early vision,” Proc. Natl. Acad. Sci. USA 83:4263–4267, 1986.

    Google Scholar 

  25. 25.

    S.C. Liu and J.G. Harris. “Generalized smoothing networks in solving early vision problems,” Comput. Vision Pattern Recog. Conf., 1989

  26. 26.

    J. Luo, C. Koch, and C. Mead. “An experimental subthreshold, analog CMOS two-dimensional surface interpolation circuit,” Neural Inform. Process. Systems Conf., Denver, November, 1988.

  27. 27.

    D.Marr and T.Poggio. “Cooperative computation of stereo disparity,” Science 194:283–287, 1976.

    Google Scholar 

  28. 28.

    J.L.Marroquin. “Probabilistic solution of inverse problems,” AI Lab Memo No. 860, MIT, Cambridge, 1985.

    Google Scholar 

  29. 29.

    J.Marroquin, S.Mitter, and T.Poggio. “Probabilistic solution of ill-posed problems in computational vision,” J. Amer. Statistic. Assoc. 82:76–89, 1987.

    Google Scholar 

  30. 30.

    J.C.Maxwell. A Treatise on Electricity and Magnetism, 3rd ed., vol. I, pp. 407–408, 1891 Republished by Dover Publications: New York 1954.

    Google Scholar 

  31. 31.

    C.A. Mead. “A sensitive electronic photoreceptor.” In 1985 Chapel Hill Conference on Very Large Scale Integration, pp. 463–471, 1985.

  32. 32.

    C.A.Mead. Analog VLSI and Neural Systems. Addison-Wesley: Reading, MA, 1989.

    Google Scholar 

  33. 33.

    W.Millar. “Some general theorems for non-linear systems possessing resistance,” Philosophical Magazine 42:1150–1160, 1951.

    Google Scholar 

  34. 34.

    H.H.Nagel. “On the estimation of optical flow: Relations between different approaches and some new results,” Artificial Intelligence 33:299–324, 1987.

    Google Scholar 

  35. 35.

    J.M.Ortega and W.C.Rheinboldt. Iterative Solution of Nonlinear Equations in Several Variables. Academic Press: New York, 1970.

    Google Scholar 

  36. 36.

    P. Perona and J. Malik. “A network for multiscale image segmentation,” Proc. 1988 IEEE Intern. Symp. on Circuits and Systems, pp. 2565–2568, Espoo, Finland, June, 1988.

  37. 37.

    T.Poggio and C.Koch. “Ill-posed problems in early vision: From computational theory to analogue networks,” Proc. Roy. Soc. Lond. B 226:303–323, 1985.

    Google Scholar 

  38. 38.

    T.Poggio, E.B.Gamble, and J.J.Little. “Parallel integration of vision modules,” Science 242:436–440, 1988.

    Google Scholar 

  39. 39.

    T.Poggio, V.Torre, and C.Koch. “Computational vision and regularization theory,” Nature 317:314–319, 1985.

    Google Scholar 

  40. 40.

    T.Poggio, H.Voorhees, and A.Yuille. “A regularized solution to edge detection,” Artif. Intell. Lab Memo No. 833, MIT, Cambridge, 1986.

    Google Scholar 

  41. 41.

    M.A.Sivilotti, M.A.Mahowald, and C.A.Mead. “Real-time visual computation using analog CMOS processing arrays.” In 1987 Stanford Conf. VLSI, pp. 295–312. MIT Press: Cambridge, 1987.

    Google Scholar 

  42. 42.

    J.E. Tanner. “Integrated optical motion detection.” Ph.D. Thesis, Dept. of Computer Science, Caltech, 1986.

  43. 43.

    D.Terzopoulos. “Multilevel computational processes for visual surface reconstruction,” Comput. Vision Graph. Image Process. 24:52–96, 1983.

    Google Scholar 

  44. 44.

    D.Terzopoulos. “Regularization of inverse problems involving discontinuities,” IEEE Trans. PAMI 8:413–424, 1986.

    Google Scholar 

  45. 45.

    A.Verri and T.Poggio. “Motion field and optical flow: Qualitative properties,” IEEE Trans. PAMI 11:490–498, 1989.

    Google Scholar 

  46. 46.

    A.Verri, F.Girosi, and V.Torre. “Mathematical properties of the two dimensional motion field: From singular points to motion parameters,” J. Opt. Soc. Amer. A 6:469–712, 1989.

    Google Scholar 

  47. 47.

    J.L.WyattJr. and D.L.Standley. “Criteria for robust stability in a class of lateral inhibition networks coupled through resistive grids,” Neural Computation 1:58–67, 1989.

    Google Scholar 

  48. 48.

    A.Yuille and N.M.Grzywacz. “A computational theory for the perception of coherent visual motion,” Nature 333:71–73, 1988.

    Google Scholar 

  49. 49.

    Y.T.Zhou and R.Chellappa. “Computation of optical flow using a neural network.” Proc IEEE Intern. Conf. Neural Networks 2:71–78, San Diego, CA, July, 1988.

    Google Scholar 

Download references

Author information



Rights and permissions

Reprints and Permissions

About this article

Cite this article

Harris, J.G., Koch, C., Staats, E. et al. Analog hardware for detecting discontinuities in early vision. Int J Comput Vision 4, 211–223 (1990).

Download citation


  • Optical Flow
  • Markov Random Field
  • Resistive Network
  • Early Vision
  • VLSI Circuit