Advanced Physics and Statistics-Based Algorithms for Standoff IED Detection

Abstract

Standoff radar systems have the potential to detect buried hazards at safe distances. However, low target-to-clutter ratios and limited spatial resolution resulting from forward-looking measurement geometries limit the performance of automated detection and classification algorithms. The project researched and developed algorithms and measurement approaches to mitigate these limitations. Specifically, the project investigated buried object radar imaging, neural network ATR feature extraction, transfer learning to estimate algorithm extensibility, improvement of buried object imaging using quadratic lifting inversion, and buried object detection and imaging using a ground penetrating radar on a small UAS platform.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 30, 2019
Accession Number
AD1087526

Entities

People

  • Benjamin Hart
  • Brian Thelen
  • Christopher Rickerd
  • Christopher Roussi
  • Erick Vega
  • Ismael Xique
  • Joseph Burns
  • Joseph Lindgren
  • Matthew Masarik

Organizations

  • Michigan Technological University

Tags

Communities of Interest

  • Air Platforms
  • Autonomy
  • Energy and Power Technologies
  • Sensors

DTIC Thesaurus Topics

  • Accuracy
  • Aircrafts
  • Artificial Intelligence Software
  • Computer Vision
  • Computers
  • Data Mining
  • Data Processing
  • Detection
  • Detectors
  • Dielectric Permittivity
  • Feature Extraction
  • Information Science
  • Machine Learning
  • Neural Networks
  • Radar
  • Signal Processing
  • Target Recognition

Readers

  • Neural Network Machine Learning.
  • Sensor Fusion and Tracking Systems.
  • Unmanned Aerial System (UAS) Autonomous Capabilities and Mission Reconnaissance.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks