Experiments to Correct a Digital Data Base Using Scene Analysis.

Abstract

A research strategy for automated screening of mapping and reconnaissance imagery based on map-guided scene analysis has been formulated based on the artificial intelligence concept of generate-and-test. Given explicit terrain data encoded in a digital map, procedures operating on a set of knowledge representations seek to predict what terrain components might be contained within each specified map category, the potential state(s) of each terrain component and plausible feature space values corresponding to such terrestial patterns based on spatial and radiometric characteristics of the sensor. A frame system serves to store the diverse map, terrain and sensor knowledge in a consistant and coherent manner. For experimental purposes, both metric photography and synthetic aperture radar (SAR) imagery from airborne and spaceborne platforms will be utilized. To support this map-guided scene analysis research, software modules have been developed.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1983
Accession Number
ADA157749

Entities

People

  • H. Ranzinger

Tags

Communities of Interest

  • Autonomy
  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Aerial Photography
  • Artificial Intelligence
  • Cameras
  • Computer Graphics
  • Data Sets
  • Databases
  • Detectors
  • Digital Data
  • Digital Image Processing
  • Digital Images
  • Digital Maps
  • Image Processing
  • Images
  • Lisp Programming Language
  • Photography
  • Synthetic Aperture Radar
  • Three Dimensional

Readers

  • Computer Vision.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • Space