Joint Beamforming and Automated Target Recognition for 3D SAS

Abstract

Unexploded ordnance in cluttered, occluded, and buried environments present a major environmental and security risk for munitions response. Synthetic aperture sonar technology presents an opportunity to mitigate these risks but suffer from reduced fidelity and lowered recognition for potential targets in these challenging environmental conditions. This project develops a suite of algorithms to enhance synthetic aperture sonar beamforming for automated target recognition for buried unexploded ordnance detection. Two innovations are introduced: (1) a new differentiable beamforming method for volumetric synthetic aperture sonar reconstruction, and (2) a machine learning based tone mapper for improving automated target recognition. Both methods were developed using state-of-the-art advances in machine learning and computational imaging and were evaluated on exemplar data from a sub-bottom synthetic aperture sonar of various man-made objects distributed on a lakebed. Benefits to the DoD and the scientific community include new knowledge of how to merge the physics of underwater acoustics and beamforming with machine learning.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 2023
Accession Number
AD1217109

Entities

People

  • Suren Jayasuriya

Organizations

  • Arizona State University

Tags

DTIC Thesaurus Topics

  • Acoustic Detection
  • Acoustics
  • Algorithms
  • Automated Target Recognition
  • Detection
  • Detectors
  • Machine Learning
  • Munitions
  • Neural Networks
  • Recognition
  • Signal Processing
  • Sonar
  • Synthetic Aperture Sonar
  • Target Recognition
  • Three Dimensional
  • Unexploded Ammunition
  • Uxo Detection

Fields of Study

  • Engineering

Readers

  • Acoustical Oceanography.
  • Distributed Systems and Data Platform Development
  • Radar Systems Engineering.

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy