Sonar feature representation with autoencoders and generative adversarial networks

Feature representation in the littoral sonar space is a complicated field due to prevalent channel noise from sound reflections as well as diffraction. The response of a sound wave as it interacts with an object provides insight into the nature of the object itself such as geometry and material comp...

Full description

Saved in:
Bibliographic Details
Published in:The Journal of the Acoustical Society of America 2023-03, Vol.153 (3_supplement), p.A178-A178
Main Authors: Linhardt, Timothy, Sen Gupta, Ananya
Format: Article
Language:English
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Feature representation in the littoral sonar space is a complicated field due to prevalent channel noise from sound reflections as well as diffraction. The response of a sound wave as it interacts with an object provides insight into the nature of the object itself such as geometry and material composition. We approach automated target recognition in this space with feature representation using autoencoders and generative adversarial networks. Through empirical analysis of learned encoding spaces, the dimensionalities of principal features in our sonar data sets are estimated. Real and complex valued training data, processed in various ways, is used to refine which features are represented, and evaluate the importance of phase information while encoding the data. [This research was funded by The Office of Naval Research with Grant No. N00174-20-1-0016.]
ISSN:0001-4966
1520-8524
DOI:10.1121/10.0018583