Underwater Small Target Classification Using Sparse Multi-View Discriminant Analysis and the Invariant Scattering Transform

Andrew Christensen; Ananya Sen Gupta; Ivars Kirsteins

doi:10.3390/jmse12101886

Back

Underwater Small Target Classification Using Sparse Multi-View Discriminant Analysis and the Invariant Scattering Transform

Journal article

Open access

Peer reviewed

Underwater Small Target Classification Using Sparse Multi-View Discriminant Analysis and the Invariant Scattering Transform

Andrew Christensen, Ananya Sen Gupta and Ivars Kirsteins

Journal of marine science and engineering, Vol.12(10), 1886

10/21/2024

DOI: 10.3390/jmse12101886

Files and links (1)

url

https://doi.org/10.3390/jmse12101886View

Published (Version of record) Open Access

Abstract

Sonar automatic target recognition (ATR) systems suffer from complex acoustic scattering, background clutter, and waveguide effects that are ever-present in the ocean. Traditional signal processing techniques often struggle to distinguish targets when noise and complicated target geometries are introduced. Recent advancements in machine learning and wavelet theory offer promising directions for extracting informative features from sonar return data. This work introduces a feature extraction and dimensionality reduction technique using the invariant scattering transform and Sparse Multi-view Discriminant Analysis for identifying highly informative features in the PONDEX09/PONDEX10 datasets. The extracted features are used to train a support vector machine classifier that achieves an average classification accuracy of 97.3% using six unique targets.

wavelets

convolutional networks

multi-view

sparsity

machine learning

small targets

Details

Title: Subtitle: Underwater Small Target Classification Using Sparse Multi-View Discriminant Analysis and the Invariant Scattering Transform
Creators: Andrew Christensen - University of Iowa
Ananya Sen Gupta - University of Iowa
Ivars Kirsteins - Naval Undersea Warfare Center
Resource Type: Journal article
Publication Details: Journal of marine science and engineering, Vol.12(10), 1886
Publisher: MDPI
DOI: 10.3390/jmse12101886
ISSN: 2077-1312
eISSN: 2077-1312
Grant note: Office of Naval Research (ONR)Department of Defense Navy (NEEC): N001742010016
The authors would like to acknowledge the Office of Naval Research (ONR) Grant Nos. N000142112420 and N000142312503 and Department of Defense Navy (NEEC) Grant No. N001742010016 for funding of this research.
Language: English
Date published: 10/21/2024
Academic Unit: Electrical and Computer Engineering
Record Identifier: 9984738390902771

Metrics

1 Record Views