Underwater Acoustic Target Recognition with ResNet18 on ShipsEar Dataset

Abstract

Underwater Acoustic Target Recognition (UATR) remains one of the most challenging tasks in underwater signal processing due to the lack of labeled data acquisition, the impact of the time-space varying intrinsic characteristics, and the interference from other noise sources. To achieve state-of-the-art accuracy, we propose a novel classification method by using the fusion features and a 18-layer Residual Network (ResNet18). The recognition experiments are conducted on the ship-radiated noise dataset named ShipsEar from a real environment, and the accuracy results of 0.943 show that the proposed method is effective for underwater acoustic recognition problems and outperforms other classification methods.