Accommodation in Computer Vision.

Abstract

The author describes an evolving computer vision system in which the parameters of the camera are controlled by the computer. It is distinguished from conventional picture processing systems by the fact that sensor accommodation is automatic and treated as an integral part of the recognition process. Accommodation improves the reliability and efficiency of machine perception by matching the information provided by the sensor with that required by specific perceptual functions. The advantages of accommodation are demonstrated in the context of five key functions in computer vision: acquisition, contour following, verifying the presence of an expected edge, range-finding, and color recognition. (Author)

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 1970
Accession Number
AD0748565

Entities

People

  • Jay Martin Tenenbaum

Organizations

  • Stanford University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Computer Programs
  • Computer Vision
  • Computers
  • Image Processing
  • Machine Perception
  • Range Finding
  • Recognition

Fields of Study

  • Computer science

Readers

  • Applied Combinatorial Optimization and Logic Circuit Design.
  • Computer Science.
  • Vision Science/Vision Psychology/Cognitive Neuroscience.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - DoD AI Strategy
  • AI & ML - Machine Translation