A Unified Multiresolution Framework for Automatic Target Recognition (ATR)

Abstract

This report describes the development of multiscale, multiresolution methods for automatic target recognition (ATR). The methods are applied to and developed specifically for synthetic aperture radar data. Applications include high level reasoning over learned target models, information theoretic approaches for pose estimation, and model development from multiple views.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2001
Accession Number
ADA400047

Entities

People

  • Alan Willsky
  • Eric Grimson
  • John Fisher

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Air Platforms
  • Energy and Power Technologies
  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Computational Science
  • Databases
  • Detection
  • Detectors
  • Feature Extraction
  • Information Processing
  • Information Science
  • Information Theory
  • Machine Learning
  • Pattern Recognition
  • Probabilistic Models
  • Random Variables
  • Synthetic Aperture Radar
  • Target Recognition
  • Three Dimensional
  • Two Dimensional

Readers

  • Computer Vision.