Underwater acoustic target recognition based on sub-band concatenated Mel spectrogram and multidomain attention mechanism

Underwater acoustic target recognition is extremely challenging because of the pronounced background noise and intricate sound propagation patterns inherent to maritime environments. Herein, we propose a sub-band concatenated Mel spectrogram to amplify low-frequency ship-radiated noise. This method enhances features through multispectrogram concatenation. Furthermore, we introduce a multidomain attention mechanism to enhance the performance of a simple residual network to develop a lightweight CFTANet model. The recognition accuracies of the recognition system are 90.60% and 96.40% on two open datasets. On the DeepShip dataset, the recognition accuracy is 7.06% higher than those of previous state-of-the-art methods.