Parametric Study of Diffusion-Enhancement Networks for Spatiotemporal Grouping in Real-Time Artificial Vision

Abstract

This is the first Annual Technical Summary of the MIT Lincoln Laboratory effort into the parametric study of diffusion-enhancement networks for spatiotemporal grouping in real-time artificial vision. Spatiotemporal grouping phenomena are examined in the context of static and time-varying imagery. Dynamics that exhibit static feature grouping on multiple scales as a function of time and long-range apparent motion between time-varying inputs are developed for a biologically plausible diffusion-enhancement bilayer. The architecture consists of a diffusion and a contrast-enhancement layer coupled by feedforward and feedback connections: input is provided by a separate feature extracting layer. The model is cast as an analog circuit that is realizable in VLSI, the parameters of which are selected to satisfy a psychophysical database on apparent motion. Specific Topics include: Neural networks, Astrocyte glial networks, diffusion enhancement, long-range apparent motion, spatiotemporal grouping dynamics, interference suppression.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 04, 1991
Accession Number
ADA239674

Entities

People

  • Allen M. Waxman
  • Robert K. Cunningham

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Air Force
  • Astrocytes
  • Boundaries
  • Cells
  • Contracts
  • Contrast
  • Detectors
  • Differential Equations
  • Diffusion
  • Dynamics
  • Equations
  • Feedback
  • Neuroglia
  • Neurons
  • Simulations
  • Two Dimensional

Readers

  • Control Systems Engineering.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML