A target localization method based on multi-task densely connected neural networks

Aiming to address the localization problem of surface or underwater targets in a shallow sea environment, this paper investigates the localization of underwater acoustic targets using their radiated noise. A method for localizing underwater acoustic targets based on densely connected neural networks with multi-task learning and a convolutional block attention mechanism is proposed in this paper. The proposed method can simultaneously estimate the range and depth of the target. The input feature for network training is obtained by calculating the normalized sample covariance matrix of broadband data received by the vertical line array using the normal mode propagation model. Additionally, vectorization compression is applied to process the input features, effectively reducing the required number of parameters. Furthermore, through parameter sensitivity analysis, we discuss how the mismatch of marine environmental parameters and sound speed profiles affects target localization performance. Simulation results demonstrate that compared to traditional matched field processing methods, the proposed method exhibits higher localization accuracy and generalization ability in mismatched marine environments.