Issues in Automatic Object Recognition: Linking Geometry and Material Data to Predictive Signature Codes

Abstract

The principal focus of Automatic Object Recognition (AOR) involves the generation of appropriate algorithms to process the output of multi spectral sensor arrays. Given the high dimensionality that characterizes the signatures of targets of interest, it is normally impossible to satisfy the need for raw signature data by means of measurement records alone. Individual sensor characteristics in conjunction with aspect angle dependence, target and background configuration (singly and in synergism), and multi spectral tradeoffs inexorably lead to a requirement for predictive signature modeling methods. By means of this stratagem, a measured signature database can be leveraged significantly, improving the fidelity of the simulation. Irrespective of the specific representation used for three dimensional geometry and material database, rarely does a predictive signature application code read that database directly. Rather, a specific interrogation method is used to pass particular geometric and material attributes to the application code. Clearly the nature of the physics employed in the application is both enabled and constrained by the form of the interrogation process used.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 1991
Accession Number
ADA233607

Entities

People

  • Edwin O. Davisson
  • Michael J. Muus
  • Paul H. Deitz

Organizations

  • Ballistic Research Laboratory

Tags

Communities of Interest

  • Electronic Warfare
  • Energy and Power Technologies
  • Ground and Sea Platforms
  • Sensors
  • Space
  • Weapons Technologies

DTIC Thesaurus Topics

  • Air Force Facilities
  • Application Software
  • Computational Science
  • Computer Science
  • Computer Vision
  • Databases
  • Diffraction
  • Electromagnetic Scattering
  • Engineers
  • Geography
  • Geometry
  • Image Processing
  • Object Recognition
  • Reliability
  • Test And Evaluation
  • Three Dimensional
  • Two Dimensional

Readers

  • Computational Fluid Dynamics (CFD)
  • Neural Network Machine Learning.
  • Systems Analysis and Design