Resistive Fuses: 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. 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.
KeywordsOptical Flow Resistive Network Line Discontinuity Circuit Implementation Surface Interpolation
Unable to display preview. Download preview PDF.
- Blake, A. and Zisserman, A. (1987). Visual Reconstruction. Cambridge, MA: MIT Press.Google Scholar
- Grimson, W. E. L. (1981). From Images to Surfaces. Cambridge, MA: MIT Press.Google Scholar
- 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
- 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
- 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
- Hasler, M. and Neirynck, J., (1986). Nonlinear Circuits. Norwood, MA: Artech House Inc., pp. 172–173.Google Scholar
- Hildreth, E. C. (1984). The Measurement of Visual Motion. Cambridge, MA: MIT Press.Google Scholar
- Horn, B. K. P. (1989). Parallel networks for machine vision. Artif. Intell. Lab. Memo No. 1071 (MIT, Cambridge).Google Scholar
- 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
- Liu, S. C. and Harris, J. G. (1989). Generalized smoothing networks in solving early vision problems. Computer Vision and Pattern Recognition Conference.Google Scholar
- 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
- 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
- Mead, C. A. (1985). A sensitive electronic photoreceptor. In 1985 Chapel Hill Conference on Very Large Scale Integration, pp. 463–471.Google Scholar
- Penfield, P., Jr., Spence, R., and Duinker, S. (1970). Tellegen’s Theorem and Electrical Networks, Cambridge, MA: MIT Press.Google Scholar
- 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
- Poggio, T., Voorhees, H., and Yuille, A. (1986). A regularized solution to edge detection. Artif. Intell. Lab Memo No. 833 (MIT, Cambridge).Google Scholar
- 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
- 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
- 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