Using a Kernel Adatron for Object Classification with RCS Data

Abstract

Rapid identification of object from radar cross section (RCS) signals is important for many space and military applications. This identification is a problem in pattern recognition which either neural networks or support vector machines should prove to be high-speed. Bayesian networks would also provide value but require significant preprocessing of the signals. In this paper, we describe the use of a support vector machine for object identification from synthesized RCS data. Our best results are from data fusion of X-band and S-band signals, where we obtained 99.4%, 95.3%, 100% and 95.6% correct identification for cylinders frusta, spheres, and polygons, respectively. We also compare our results with a Bayesian approach and show that the SVM is three orders of magnitude faster, as measured by the number of floating point operations.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 28, 2010
Accession Number
ADA523977

Entities

People

  • Edward A. Rietman
  • James T. Demers
  • Marten F. Byl

Organizations

  • Physical Sciences (United States)

Tags

Communities of Interest

  • Autonomy
  • Sensors
  • Weapons Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence Software
  • Bayesian Networks
  • Computational Science
  • Computer Vision
  • Feature Extraction
  • Frequency
  • Identification
  • Image Recognition
  • Machine Learning
  • Models
  • Neural Networks
  • Pattern Recognition
  • Radar Cross Sections
  • Recognition
  • Supervised Machine Learning
  • X Band

Readers

  • Graph Algorithms and Convex Optimization.
  • Neural Network Machine Learning.
  • Radar Systems Engineering.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • Space
  • Space - Space Objects