QiandaoEar22: A high quality noise dataset for identifying specific ship from multiple underwater acoustic targets using ship-radiated noise

TL;DR

This paper introduces QiandaoEar22, a comprehensive underwater acoustic dataset for ship target recognition, demonstrating high accuracy in identifying specific ships and background noise, and providing benchmarks for future research.

Contribution

The paper releases a new multi-target ship acoustic dataset and evaluates deep learning methods for ship identification, offering insights into feature and network selection.

Findings

Ship-radiated noise can be identified with over 99% accuracy.

Specific ship identification achieves up to 99.56% accuracy.

Provides benchmarks and guidance for future underwater acoustic target recognition research.

Abstract

Target identification of ship-radiated noise is a crucial area in underwater target recognition. However, there is currently a lack of multi-target ship datasets that accurately represent real-world underwater acoustic conditions. To tackle this issue, we conducted experimental data acquisition, resulting in the release of QiandaoEar22 \textemdash a comprehensive underwater acoustic multi-target dataset. This dataset encompasses 9 hours and 28 minutes of real-world ship-radiated noise data and 21 hours and 58 minutes of background noise data. To demonstrate the availability of QiandaoEar22, we executed two experimental tasks. The first task focuses on assessing the presence of ship-radiated noise, while the second task involves identifying specific ships within the recognized targets in the multi-ship mixed data. In the latter task, we extracted eight features from the data and employed six deep learning networks for classification, aiming to evaluate and compare the performance of various features and networks. The experimental results reveal that ship-radiated noise can be successfully identified from background noise in over 99\% of cases. Additionally, for the specific identification of individual ships, the optimal recognition accuracy achieves 99.56\%. Finally, based on our findings, we provide advice on selecting appropriate features and deep learning networks, which may offer valuable insights for related research. Our work not only establishes a benchmark for algorithm evaluation but also inspires the development of innovative methods to enhance UATD and UATR systems.