An Underwater Acoustic Target Recognition Method Based on Spectrograms with Different Resolutions

This paper focuses on the automatic target recognition (ATR) method based ship-radiated noise and proposes an underwater acoustic (UATR) ResNet. In proposed method, a multi-window spectral analysis (MWSA) is used to solve difficulty that traditional time–frequency (T–F) has in extracting multiple signal characteristics simultaneously. MWSA generates spectrograms with different T–F resolutions through window processing provide input for classifier. Because of insufficient number samples, conditional deep convolutional generative adversarial network (cDCGAN) model was designed high-quality data augmentation. Experimental results real show UATR good classification performance.