Simulating a Function of Visual Peripheral Processes with an Analog VLSI Network

Authors:
Hua Li;Ching-Ho Chen
Affiliations:
-;-
Venue:
IEEE Micro
Year:
1991

Citing 7
Cited 0

Computing Motion Using Analog and Binary Resistive Networks

Computer
Analog VLSI and neural systems

Analog VLSI and neural systems
The superior colliculus and spatiotemporal translation in the saccadic system

Neural Networks
Standards conversion using motion compensation

Signal Processing - Multidimensional Signal Processing, Part II
Two-stage strategy for motion parameter estimation in dynamic images

Applied Artificial Intelligence
Analysis and Design of Analog Integrated Circuits

Analysis and Design of Analog Integrated Circuits
Analog VLSI Synaptic Matrices as Building Blocks for Neural Networks

IEEE Micro

Quantified Score

Hi-index	0.00

Visualization

Abstract

A two-dimensional analog VLSI network for implementing a function of motion perception during the peripheral process is described. The network contains many nodes, or processing elements (PEs), which operate concurrently in asynchronous fashion. Each PE performs an image-difference operation as well as thresholding to extract motion information on a pixel-by-pixel basis. Analog voltage, which interacts extremely quickly, implements all computations. An energy equilibrium state of the network provides stabilized analog voltage across the network. SPICE simulations and experiments using real images verify the results of the theoretical analysis.