Sonar-Based Deep Learning for Underwater UXO Remediation

Abstract

The primary objective of this project was to develop novel unexploded ordnance (UXO) detection and classification algorithms specifically for volumetric sonar data from two experimental systems, the Sediment Volume Search Sonar and the Multi-Sensor Towbody. Because no automatic target recognition (ATR) algorithms previously existed for these two new systems, the methods developed here addressed a capability gap. The general-purpose detection algorithm that was created exploited the concept of integral images to flag suspicious regions in a given data volume in a fast, computationally efficient manner. The follow-on classification algorithm was based on deep-learning techniques, specifically deep convolutional neural networks that were extended to function with three-dimensional (i.e., volumetric)input data cubes. The developed algorithms were assessed using large sets of SVSS data, and they were also applied to modest amounts of data from the MuST system. Preliminary results showed the promise of the approaches for detecting and classifying both proud and buried targets in measured volumetric sonar data.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 07, 2021
Accession Number
AD1217121

Entities

People

  • David P. Williams

Organizations

  • Centre for Maritime Research and Experimentation

Tags

DTIC Thesaurus Topics

  • Acoustics
  • Artificial Intelligence
  • Autonomous Underwater Vehicles
  • Computer Vision
  • Convolutional Neural Networks
  • Department Of Defense
  • Detection
  • Detectors
  • Frequency Bands
  • Machine Learning
  • Nato
  • Neural Networks
  • Physics Laboratories
  • Target Recognition
  • Three Dimensional
  • Unexploded Ammunition
  • Warning Systems

Readers

  • Acoustical Oceanography.
  • Neural Network Machine Learning.
  • Sensor Fusion and Tracking Systems.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks