Optical Flow and Surface Interpolation in Resistive Networks: Algorithms and Analog VLSI Chips
Abstract
To us, and to other biological organisms, vision seems effortless. We open our eyes and we "see" the world in all its color, brightness, and movement. Flies, frogs, cats, and humans can all equally well perceive a rapidly changing environment and act on it. Yet, we have great difficulties when trying to endow our machines with similar abilities. In this article, we describe recent developments in the theory of early vision that led from the formulation of the motion problem as an ill-posed one to its solution by minimizing certain "cost" functions. These cost or energy functions can be mapped onto simple analog and digital resistive networks. For instance, as detailed in this chapter, we can compute the optical flow by injecting currents into resistive networks and recording the resulting stationary voltage distribution at each node. These networks, which are implemented in subthreshold, analog, complementary metal oxide semiconductor (CMOS) very large scale integrated (VLSI) circuits, are very attractive for their technological potential.
Additional Information
An early version of this model was developed and implemented in collaboration with A.L. Yuille (1987). Matthew Avalos and Andrew Hsu wrote the code for the Imaging Technology system, and Eric Staats for the Ncube. C.K. is supported by an Office of Naval Research Young Investigator Award and grants from the NSF Advanced Engineering Program (EET-8714710 and IST-8700064), the James Lee Powell Foundation and Rockwell International Science Center. C.M. is supported by the Office of Naval Research and the System Development Foundation.Attached Files
Submitted - Optical_Flow_and_Surface_Interpolation_in_Resistive_Networks_1989.pdf
Files
Name | Size | Download all |
---|---|---|
md5:b7e281a6c25af936e08af6066d5ee8b3
|
7.2 MB | Preview Download |
Additional details
- Eprint ID
- 61710
- Resolver ID
- CaltechAUTHORS:20151029-101037556
- Office of Naval Research (ONR)
- NSF
- EET-8714710
- NSF
- IST-8700064
- James Lee Powell Foundation
- Rockwell International Science Center
- System Development Foundation
- Created
-
2015-10-29Created from EPrint's datestamp field
- Updated
-
2020-03-03Created from EPrint's last_modified field
- Caltech groups
- Koch Laboratory (KLAB)