Learning and Recognition in Natural Environments

Abstract

We present a system for learning descriptions of objects, and for subsequently recognizing learned objects, that functions in outdoor, natural environments. We describe in detail two modes of functioning within this system: (1) unguided, bottom-up learning of object descriptions directly from image data; (2) top-down recognition of objects whose approximate position and structure are known by use of image-level matching. We then argue that the systems's performance in these two modes indicates that robust outdoor performance can be achieved within the structure of our vision system.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 05, 1987
Accession Number
ADA459990

Entities

People

  • Alex P. Pentland
  • R. Bolles

Organizations

  • SRI International

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Availability
  • Classification
  • Contracts
  • Environment
  • Information Operations
  • Instructions
  • Learning
  • Monitoring
  • Recognition
  • Security
  • Standards

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Theoretical Analysis.