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

In recent years, single vector hydrophones have attracted widespread attention in target direction esti-mation 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 non-stationary noise conditions. This study proposes the novel DOA estimation method based on a convolutionalneural network (CNN) and the convolutional block attention module (CBAM). By inputting the covariancematrix of the received signal into the neural network and integrating the CBAM module, this method enhancesthe model’s sensitivity to critical features. The CBAM module leverages channel and spatial attention mech-anisms to adaptively focus on essential information, effectively suppressing noise interference and improvingdirectional accuracy. Specifically, CBAM improves the model’s focus on subtle directional cues in noisy envi-ronments, suppressing irrelevant interference while amplifying essential signal components, which is crucial foran accurate DOA estimation. Experimental results under various signal-to-noise ratio (SNR) conditions val-idate the method’s effectiveness, demonstrating superior noise resistance and estimation precision, providinga robust and efficient solution for underwater acoustic target localization.