Radar Clutter Effects in a Target Classifier.

Abstract

A previously proposed algorithm for the classification of periodically amplitude modulated targets is studied for its possible use in an air-to-ground radar situation. The assumptions necessary for the use of the algorithm are discussed and the limitations and scope of the problem are presented. Classification probabilities of error are presented based on worst case analysis of clutter conditions in the received radar signal. Analysis is provided for a two class problem and a three class problem using both nearest neighbor rules and stepwise discriminant analysis for classification. The clutter in these problems is studied under conditions of spectral spreading and increased clutter signal power. The effect on probability of error is found to be small enough that there are definite possibilities for the use of this algorithm in some air-to-ground applications. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1978
Accession Number
ADA064180

Entities

People

  • Joseph M. Renaud

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies
  • Sensors
  • Weapons Technologies

DTIC Thesaurus Topics

  • Air Force
  • Algorithms
  • Clutter
  • Databases
  • Detection
  • Discriminant Analysis
  • Doppler Effect
  • Frequency Bands
  • Frequency Domain
  • Machine Learning
  • Radar
  • Radar Clutter
  • Radar Signals
  • Recognition
  • Statistics
  • Target Classification
  • Target Recognition

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Neural Network Machine Learning.
  • Regression Analysis.