Exploiting Auxiliary Information for Improved Underwater Target Classification with Convolutional Neural Networks

Thibaud Berthomier, David P. Williams, Benoit D'Ales, Samantha Dugelay

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations

Abstract

This work deals with the classification of objects as targets or clutter in synthetic aperture sonar (SAS) imagery using convolutional neural networks (CNNs). First, a new image-annotation tool is developed that allows extra auxiliary information (beyond the basic binary label) to be easily recorded about a given input image. The additional information consists of an estimate of the image quality; the local background environment; and for targets, the specific object shape, orientation, and length. The architecture of the CNNs - specifically the final dense layer and output layer - is then modified so that these extra quantities are additional outputs to be predicted simultaneously. As such, the task of the augmented CNNs becomes to provide a richer representation of an image beyond the binary label. This more complete operational picture can then better inform subsequent mine countermeasures (MCM) decisions. Experiments on a set of real, measured SAS data collected at sea demonstrate that tiny CNNs can accurately predict the additional auxiliary qualities without suffering a significant drop in binary classification performance.

Original languageEnglish (US)
Title of host publication2020 Global Oceans 2020
Subtitle of host publicationSingapore - U.S. Gulf Coast
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728154466
DOIs
StatePublished - Oct 5 2020
Event2020 Global Oceans: Singapore - U.S. Gulf Coast, OCEANS 2020 - Biloxi, United States
Duration: Oct 5 2020Oct 30 2020

Publication series

Name2020 Global Oceans 2020: Singapore - U.S. Gulf Coast

Conference

Conference2020 Global Oceans: Singapore - U.S. Gulf Coast, OCEANS 2020
Country/TerritoryUnited States
CityBiloxi
Period10/5/2010/30/20

All Science Journal Classification (ASJC) codes

  • Oceanography
  • Automotive Engineering
  • Instrumentation
  • Signal Processing

Fingerprint

Dive into the research topics of 'Exploiting Auxiliary Information for Improved Underwater Target Classification with Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this