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

Abstract

This is the second Annual Technical Summary of the MIT Lincoln Laboratory 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 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 data base on apparent motion.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 24, 1992
Accession Number
ADA256059

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
  • Brain
  • Cells
  • Computing System Architectures
  • Contracts
  • Contrast
  • Databases
  • Diffusion
  • Equations
  • Feedback
  • Network Architecture
  • Neuroglia
  • Neurons
  • Simulations
  • Two Dimensional
  • Visual Cortex

Readers

  • Computer Vision.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy