Target Classification of Canonical Scatterers Using Classical Estimation and Dictionary Based Techniques

Abstract

This research effort will utilize a hierarchical dictionary-based approach for canonical shape classification within measured synthetic aperture radar (SAR) phase history data. This primary goal of this research is to develop an efficient framework for dictionary based SAR feature extraction using modi ed 3-D radar scattering models. Previous work in this area relies on maximum likelihood (ML) estimation and similar approaches to extract shapes using 2-D signal models. We include characterizations of shape model redundancies caused by similar shape scattering responses. Simulated SAR collection methods, including frequency, elevation aspect, and polarization diversities, are modeled to show reductions in inter-atom correlation. A "molecule" method is used to combine highly correlated atoms to support a basis pursuit (BP) method of feature identifcation. Finally, a Bayesian approach is used to determine a maximum a posteriori (MAP) estimate for each atom, leading to feature classi cation and parameter identifcation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 22, 2012
Accession Number
ADA557230

Entities

People

  • Glenn B. Hammond Ii

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Air Force
  • Compressed Sensing
  • Department Of Defense
  • Detection
  • Electrical Engineering
  • Estimators
  • Feature Extraction
  • Frequency Diversity
  • Governments
  • Linear Programming
  • Radar
  • Signal Processing
  • Synthetic Aperture Radar
  • Target Classification
  • Target Recognition
  • Three Dimensional
  • United States Government

Fields of Study

  • Engineering

Readers

  • Computer Vision.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference