Single Vector Hydrophone DOA Estimation: Leveraging Deep Learning with CNN-CBAM

In recent years, single vector hydrophones have attracted widespread attention in target direction estimation due to their compact design and advantages in complex underwater acoustic environments. However, traditional direction of arrival (DOA) estimation algorithms often struggle to maintain high...

Full description

Saved in:
Bibliographic Details
Main Authors: Fanyu ZENG, Yaning HAN, Hongyuan YANG, Dapeng YANG, Fan ZHENG
Format: Article
Language:English
Published: Institute of Fundamental Technological Research Polish Academy of Sciences 2025-06-01
Series:Archives of Acoustics
Subjects:
Online Access:https://acoustics.ippt.pan.pl/index.php/aa/article/view/4138
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849404152598233088
author Fanyu ZENG
Yaning HAN
Hongyuan YANG
Dapeng YANG
Fan ZHENG
author_facet Fanyu ZENG
Yaning HAN
Hongyuan YANG
Dapeng YANG
Fan ZHENG
author_sort Fanyu ZENG
collection DOAJ
description In recent years, single vector hydrophones have attracted widespread attention in target direction estimation due to their compact design and advantages in complex underwater acoustic environments. However, traditional direction of arrival (DOA) estimation algorithms often struggle to maintain high accuracy in nonstationary noise conditions. This study proposes the novel DOA estimation method based on a convolutional neural network (CNN) and the convolutional block attention module (CBAM). By inputting the covariance matrix of the received signal into the neural network and integrating the CBAM module, this method enhances the model’s sensitivity to critical features. The CBAM module leverages channel and spatial attention mechanisms to adaptively focus on essential information, effectively suppressing noise interference and improving directional accuracy. Specifically, CBAM improves the model’s focus on subtle directional cues in noisy environments, suppressing irrelevant interference while amplifying essential signal components, which is crucial for an accurate DOA estimation. Experimental results under various signal-to-noise ratio (SNR) conditions validate the method’s effectiveness, demonstrating superior noise resistance and estimation precision, providing a robust and efficient solution for underwater acoustic target localization.
format Article
id doaj-art-a3f2bb838aec4d5fa49eccc9b555df96
institution Kabale University
issn 0137-5075
2300-262X
language English
publishDate 2025-06-01
publisher Institute of Fundamental Technological Research Polish Academy of Sciences
record_format Article
series Archives of Acoustics
spelling doaj-art-a3f2bb838aec4d5fa49eccc9b555df962025-08-20T03:37:05ZengInstitute of Fundamental Technological Research Polish Academy of SciencesArchives of Acoustics0137-50752300-262X2025-06-0150218719810.24425/aoa.2025.1536593704Single Vector Hydrophone DOA Estimation: Leveraging Deep Learning with CNN-CBAMFanyu ZENG0Yaning HAN1Hongyuan YANG2Dapeng YANG3Fan ZHENG4Key Laboratory of Geophysical Exploration Equipment, Ministry of Education, College of Instrumentation and Electrical Engineering, Jilin UniversityKey Laboratory of Geophysical Exploration Equipment, Ministry of Education, College of Instrumentation and Electrical Engineering, Jilin UniversityKey Laboratory of Geophysical Exploration Equipment, Ministry of Education, College of Instrumentation and Electrical Engineering, Jilin UniversityKey Laboratory of Geophysical Exploration Equipment, Ministry of Education, College of Instrumentation and Electrical Engineering, Jilin UniversityKey Laboratory of Geophysical Exploration Equipment, Ministry of Education, College of Instrumentation and Electrical Engineering, Jilin UniversityIn recent years, single vector hydrophones have attracted widespread attention in target direction estimation due to their compact design and advantages in complex underwater acoustic environments. However, traditional direction of arrival (DOA) estimation algorithms often struggle to maintain high accuracy in nonstationary noise conditions. This study proposes the novel DOA estimation method based on a convolutional neural network (CNN) and the convolutional block attention module (CBAM). By inputting the covariance matrix of the received signal into the neural network and integrating the CBAM module, this method enhances the model’s sensitivity to critical features. The CBAM module leverages channel and spatial attention mechanisms to adaptively focus on essential information, effectively suppressing noise interference and improving directional accuracy. Specifically, CBAM improves the model’s focus on subtle directional cues in noisy environments, suppressing irrelevant interference while amplifying essential signal components, which is crucial for an accurate DOA estimation. Experimental results under various signal-to-noise ratio (SNR) conditions validate the method’s effectiveness, demonstrating superior noise resistance and estimation precision, providing a robust and efficient solution for underwater acoustic target localization.https://acoustics.ippt.pan.pl/index.php/aa/article/view/4138single vector hydrophonedirection of arrival (doa)convolutional neural network (cnn)convolutional block attention module (cbam)noise resistance
spellingShingle Fanyu ZENG
Yaning HAN
Hongyuan YANG
Dapeng YANG
Fan ZHENG
Single Vector Hydrophone DOA Estimation: Leveraging Deep Learning with CNN-CBAM
Archives of Acoustics
single vector hydrophone
direction of arrival (doa)
convolutional neural network (cnn)
convolutional block attention module (cbam)
noise resistance
title Single Vector Hydrophone DOA Estimation: Leveraging Deep Learning with CNN-CBAM
title_full Single Vector Hydrophone DOA Estimation: Leveraging Deep Learning with CNN-CBAM
title_fullStr Single Vector Hydrophone DOA Estimation: Leveraging Deep Learning with CNN-CBAM
title_full_unstemmed Single Vector Hydrophone DOA Estimation: Leveraging Deep Learning with CNN-CBAM
title_short Single Vector Hydrophone DOA Estimation: Leveraging Deep Learning with CNN-CBAM
title_sort single vector hydrophone doa estimation leveraging deep learning with cnn cbam
topic single vector hydrophone
direction of arrival (doa)
convolutional neural network (cnn)
convolutional block attention module (cbam)
noise resistance
url https://acoustics.ippt.pan.pl/index.php/aa/article/view/4138
work_keys_str_mv AT fanyuzeng singlevectorhydrophonedoaestimationleveragingdeeplearningwithcnncbam
AT yaninghan singlevectorhydrophonedoaestimationleveragingdeeplearningwithcnncbam
AT hongyuanyang singlevectorhydrophonedoaestimationleveragingdeeplearningwithcnncbam
AT dapengyang singlevectorhydrophonedoaestimationleveragingdeeplearningwithcnncbam
AT fanzheng singlevectorhydrophonedoaestimationleveragingdeeplearningwithcnncbam