Automatic Rapid Updating of ATR Target Knowledge Bases

Abstract

The feasibility of creating a software system to perform automatic rapid updating of AIR target knowledge databases is investigated. Methods of comparing infrared images with CAD model renderings, including object detection, feature extraction, object alignment, match quality evaluation, and CAD model updating are researched and analyzed. A GUI-based software application created to demonstrate object detection, feature extraction, and automatic image alignment is described. An improved method of edge detection based on directional masks and second derivatives of pixel intensities is given. A conceptual software system for rapid updating of AIR knowledge databases is described. A technique for the comparison of images based on line features is discussed. Based on this research it is found that the development of an automatic rapid updating system is feasible.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 17, 1999
Accession Number
ADA364592

Entities

People

  • Barton S. Wells
  • Frederick L. Beckner

Tags

Communities of Interest

  • Materials and Manufacturing Processes
  • Sensors
  • Weapons Technologies

DTIC Thesaurus Topics

  • Application Software
  • Army Aviation
  • Automatic
  • Change Detection
  • Databases
  • Detection
  • Detectors
  • Directional
  • Feature Extraction
  • Image Processing
  • Images
  • Infrared Images
  • Intensity
  • Low Pass Filters
  • Target Recognition
  • Three Dimensional
  • Two Dimensional

Fields of Study

  • Computer science
  • Engineering

Readers

  • Computer Vision.
  • Database Systems and Applications

Technology Areas

  • AI & ML