Abstract

Data sets of well­ labelled and diverse acoustic imagery of the seabed are scarce. However, a recent breakthrough in synthetic aperture sonar (SAS) image simulation has facilitated the rapid generation of realistic echo data. The synthetic data include important aspects of the acoustic wave physics, such as aspect­ dependence, layover, diffraction, speckle, focusing errors, and artefacts. Moreover, it provides high­ fidelity label information. This combination of speed, realism, and detail has enabled the use of synthetic data to improve the volume and diversity of training data for deep learning algorithms in automatic target recognition (ATR). We present an overview of the rapid simulation model, alongside an existing SAS simulation model, and demonstrate its application to ATR training for the detection and classification of underwater munitions and unexploded ordnance.
Original languageEnglish
Title of host publicationProceedings of the 7th Underwater Acoustics Conference and Exhibition, UACE 2023
EditorsM. Taroudakis
PublisherI.A.C.M, Foundation for Research and Technology - Hellas
Pages321-328
Number of pages8
Publication statusPublished - 30 Jun 2023
Event6th Underwater Acoustics Conference & Exhibition - Online, Kalamata, Greece
Duration: 20 Jun 202125 Jun 2021
Conference number: 6th
https://www.uaconferences.org/

Publication series

NameUnderwater Acoustic Conference and Exhibition Series

Conference

Conference6th Underwater Acoustics Conference & Exhibition
Abbreviated titleUACE2021
Country/TerritoryGreece
CityKalamata
Period20/06/2125/06/21
Internet address

Keywords

  • ATR
  • UXO
  • Machine learning
  • SAS
  • Simulation

Fingerprint

Dive into the research topics of 'Improvement of Automatic Target Recognition Through Synthetic Data Augmentation'. Together they form a unique fingerprint.

Cite this