QiandaoEar22

Citation Author(s):
Feng
HONG
Shanghai Acoustics Laboratory, Chinese Academy of Sciences
Xiaoyang
DU
Shanghai Acoustics Laboratory, Chinese Academy of Sciences
Submitted by:
FENG HONG
Last updated:
Mon, 06/17/2024 - 04:22
DOI:
10.2206/QDE22
Data Format:
WAV
License:
Creative Commons Attribution
400 Views
Categories:
Artificial Intelligence
Signal Processing
Remote Sensing
Keywords:
Ship-radiated noise dataset, Underwater acoustic target recognition, Underwater acoustic target detection, Underwater acoustics
0
0 ratings - Please login to submit your rating.
ACCESS DATASET CITE SHARE/EMBED

Abstract 

QiandaoEar22 is a high-quality noise dataset designed for identifying specific ships among multiple underwater acoustic targets using ship-radiated noise. This dataset includes 9 hours and 28 minutes of real-world ship-radiated noise data and 21 hours and 58 minutes of background noise data. Collected in June 2022 at Qiandao Lake, China, using digitalHyd SR-1 self-capacitance hydrophones in a real underwater acoustic environment, this dataset serves as a high-quality recording of ship-radiated noise. The experimental period coincided with the tourist season, resulting in recorded ship radiated noise primarily originating from sightseeing boats and speedboats. Due to the hydrophone's proximity to the navigation channel, passing vessels, including sightseeing boats, speedboats, and other watercraft, contribute to a composite radiated noise. Additional targets include large tour boats, cargo ships, sanitation vessels, small boats, research ships, and ambient noise. Moreover, mechanism of collection of data and its labeling are also discussed. Utilizing the QiandaoEar22 dataset, we built some sub-dataset which help us distinguish ship signals and background noise signals from the underwater acoustic data and successfully recognizes three specific types of ship signals—speedboats, KaiYuan, and UUV—from the multi-target ship signals.

Instructions: 

The dataset is in WAV format and contains mixed ship radiated noise from multiple vessels. Please refer to the documentation for data labels. The data can be utilized for tasks such as feature extraction and target classification.

Funding Agency: 
Natural Science Foundation of Shanghai, Youth Innovation Promotion Association CAS, Young Talent Cultivation Program of Shanghai Branch of CAS
Grant Number: 
22ZR1475700, 2021022

Dataset Files

LOGIN TO ACCESS DATASET FILES

Documentation

AttachmentSize
File QiandaoEar22_documentations.pdf208.52 KB

QUESTIONS?