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.
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