Exploiting phase information in synthetic aperture sonar images for target classification

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

10 Scopus citations

Abstract

It is demonstrated that the phase information present in complex high-frequency synthetic aperture sonar (SAS) imagery can be exploited for successful object classification. That is, without using the amplitude content of the imagery, man-made targets can be discriminated from naturally occurring clutter. To exploit the information ostensibly hidden in the phase imagery, relatively simple convolutional neural networks (CNNs) are trained, “from scratch,” on a large database of SAS phase images collected at sea. Inference is then performed on real SAS data collected at sea during five other surveys that span multiple geographical locations and a variety of seafloor types and conditions. These experimental results on the test data illustrate that the phase information alone can produce favorable object classification performance. To our knowledge, this work is the first to demonstrate this finding.

Original languageEnglish (US)
Title of host publication2018 OCEANS - MTS/IEEE Kobe Techno-Oceans, OCEANS - Kobe 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538616543
DOIs
StatePublished - Dec 4 2018
Event2018 OCEANS - MTS/IEEE Kobe Techno-Oceans, OCEANS - Kobe 2018 - Kobe, Japan
Duration: May 28 2018May 31 2018

Publication series

Name2018 OCEANS - MTS/IEEE Kobe Techno-Oceans, OCEANS - Kobe 2018

Other

Other2018 OCEANS - MTS/IEEE Kobe Techno-Oceans, OCEANS - Kobe 2018
Country/TerritoryJapan
CityKobe
Period5/28/185/31/18

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Oceanography
  • Space and Planetary Science
  • Energy Engineering and Power Technology
  • Ocean Engineering
  • Acoustics and Ultrasonics
  • Instrumentation

Fingerprint

Dive into the research topics of 'Exploiting phase information in synthetic aperture sonar images for target classification'. Together they form a unique fingerprint.

Cite this