Recognizing Objects in a Natural Environment: A Contextual Vision System (CVS)

Abstract

Existing machine vision techniques are not competent to reliably recognize objects in unconstrained views of natural scenes. In this paper we identify a number of weaknesses in current recognition systems, including an inability to solve the partitioning problem or to effectively use context and other types of knowledge beyond that of immediate object appearance. We propose specific mechanisms for dealing with some of these problems and describe the design of a vision system that incorporates these new mechanisms. The system has been partially implemented and we include some experimental results indicative of its operation and performance.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 1989
Accession Number
ADA460946

Entities

People

  • Martin A. Fischler
  • Thomas M. Strat

Organizations

  • SRI International

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Availability
  • Classification
  • Computer Vision
  • Contracts
  • Environment
  • Identification
  • Information Operations
  • Instructions
  • Monitoring
  • Recognition
  • Security
  • Standards
  • Workshops

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Organizational Process Management (OPM).
  • Sensor Fusion and Tracking Systems.