Harris, John G. and Koch, Christof and Staats, Erik and Luo, Jin (1990) Analog hardware for detecting discontinuities in early vision. International Journal of Computer Vision, 4 (3). pp. 211-223. ISSN 0920-5691. http://resolver.caltech.edu/CaltechAUTHORS:20130816-103144812
- Published Version
See Usage Policy.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20130816-103144812
The detection of discontinuities in motion, intensity, color, and depth is a well-studied but difficult problem in computer vision . 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  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.
|Additional Information:||Cover Date: 1990-06-01. We foremost wish to thank Carver Mead for laying the framework upon which we have built our research. Our theoretical ideas would never have been ported into silicon without him. All chips were fabricated through MOSIS with DARPA's support. Research in the laboratory of C.K. is supported by a National Science Foundation grant IST-8700064, Office of Naval Research Young Investigator and National Science Foundation Presidential Young Investigator Awards, the James S. McDonnell Foundation, Rockwell International Science Center and the Hughes Aircraft Artificial Intelligence Center. J.G.H. is funded by a Hughes Aircraft Fellowship.|
|Group:||Koch Laboratory, KLAB|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||KLAB Import|
|Deposited On:||11 Mar 2010 06:07|
|Last Modified:||13 Sep 2013 17:21|
Repository Staff Only: item control page