Object Discrimination Based on Depth-From-Occlusion

Abstract

We present a model of how objects can be visually discriminated based on the extraction of depth from occlusion. Object discrimination requires consideration of both the binding problem and the problem of segmentation. We propose that the visual system binds contours and surfaces by identifying 'proto-objects' compact regions bounded by close contours. Proto-objects can then be linked into larger structures. The model is simulated by a system of interconnected neural networks. The networks have biologically-motivated architectures and utilize a distributed representation of depth. We present simulations that demonstrate three robust psychophysical properties of the system. In order to discriminate objects in the visual world, the nervous system must solve two fundamental problems: binding and segmentation. The binding problem (Barlow, 1981) addresses how the attributes of an object shape, color, motion, depth are linked to create an individual object. Segmentation deal with the converse problem of how separate objects are distinguished.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1991
Accession Number
ADA248104

Entities

People

  • Leif H. Finkel
  • Paul Sajda

Organizations

  • University of Pennsylvania

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Artificial Intelligence Software
  • Boundaries
  • Cognition
  • Computational Neuroscience
  • Computational Science
  • Computer Vision
  • Construction
  • Continuity
  • Discrimination
  • Firing Rate
  • Image Recognition
  • Neural Networks
  • Object Recognition
  • Psychology
  • Recognition
  • Simulations
  • Simulators

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Theoretical Analysis.
  • Vision Science/Vision Psychology/Cognitive Neuroscience.

Technology Areas

  • AI & ML