1 March 1992 Neurovision processor for designing intelligent sensors
Author Affiliations +
Abstract
A programmable multi-task neuro-vision processor, called the Positive-Negative (PN) neural processor, is proposed as a plausible hardware mechanism for constructing robust multi-task vision sensors. The computational operations performed by the PN neural processor are loosely based on the neural activity fields exhibited by certain nervous tissue layers situated in the brain. The neuro-vision processor can be programmed to generate diverse dynamic behavior that may be used for spatio-temporal stabilization (STS), short-term visual memory (STVM), spatio-temporal filtering (STF) and pulse frequency modulation (PFM). A multi- functional vision sensor that performs a variety of information processing operations on time- varying two-dimensional sensory images can be constructed from a parallel and hierarchical structure of numerous individually programmed PN neural processors.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Madan M. Gupta, Madan M. Gupta, George K. Knopf, George K. Knopf, } "Neurovision processor for designing intelligent sensors", Proc. SPIE 1608, Intelligent Robots and Computer Vision X: Neural, Biological, and 3-D Methods, (1 March 1992); doi: 10.1117/12.135124; https://doi.org/10.1117/12.135124
PROCEEDINGS
15 PAGES


SHARE
RELATED CONTENT

Pyramidal neurovision architecture for vision machines
Proceedings of SPIE (August 19 1993)
Neural Network For Optical Flow Estimation
Proceedings of SPIE (February 28 1990)
High-Level Planning And Low-Level Control
Proceedings of SPIE (February 18 1988)
Multitask neural network for vision machine systems
Proceedings of SPIE (January 31 1991)
Interweaving reason, action, and perception
Proceedings of SPIE (October 31 1992)

Back to Top