Underwater shipwreck target detection based on audio-visual heterogeneous data

Tian Rong; Chen Xu Wang; Qing Hua Luo; Ying Chun Li

doi:10.1109/OCEANSLimerick52467.2023.10244537

Underwater shipwreck target detection based on audio-visual heterogeneous data

Tian Rong^*
, Chen Xu Wang
, Qing Hua Luo
, Ying Chun Li

^*Corresponding author for this work

School of Astronautics, Harbin Institute of Technology
Harbin Institute of Technology Weihai

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

As marine exploration continues to grow, the frequency of maritime emergency contingencies increases year by year. It is crucial to enhance marine surveillance to effectively detect underwater maritime shipwreck targets. Based on the excellent target detection performance of the YOLO5 model, we constructed the pure visual image dataset, pure sonar image dataset, and audio-visual heterogeneous dataset. We also trained the YOLOv5m model with a personal computer using the visual image dataset, sonar image dataset, and the hybrid audio-visual image dataset of maritime shipwrecks respectively. The test results show that the detection accuracy of the model trained with the hybrid maritime wrecks audio-visual image dataset is higher than that of the model trained with pure visual and sonar image datasets. This method may have an inspiration to future research.

Original language	English
Title of host publication	OCEANS 2023 - Limerick, OCEANS Limerick 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350332261
DOIs	https://doi.org/10.1109/OCEANSLimerick52467.2023.10244537
State	Published - 2023
Externally published	Yes
Event	2023 OCEANS Limerick, OCEANS Limerick 2023 - Limerick, Ireland Duration: 5 Jun 2023 → 8 Jun 2023

Publication series

Name	OCEANS 2023 - Limerick, OCEANS Limerick 2023

Conference

Conference	2023 OCEANS Limerick, OCEANS Limerick 2023
Country/Territory	Ireland
City	Limerick
Period	5/06/23 → 8/06/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 14 Life Below Water

Keywords

YOLOv5m
audio-visual image dataset
maritime shipwreck
sonar
target detection
visual

Access to Document

10.1109/OCEANSLimerick52467.2023.10244537

Cite this

@inproceedings{7afc927a17474a9facc52e0641d07732,

title = "Underwater shipwreck target detection based on audio-visual heterogeneous data",

abstract = "As marine exploration continues to grow, the frequency of maritime emergency contingencies increases year by year. It is crucial to enhance marine surveillance to effectively detect underwater maritime shipwreck targets. Based on the excellent target detection performance of the YOLO5 model, we constructed the pure visual image dataset, pure sonar image dataset, and audio-visual heterogeneous dataset. We also trained the YOLOv5m model with a personal computer using the visual image dataset, sonar image dataset, and the hybrid audio-visual image dataset of maritime shipwrecks respectively. The test results show that the detection accuracy of the model trained with the hybrid maritime wrecks audio-visual image dataset is higher than that of the model trained with pure visual and sonar image datasets. This method may have an inspiration to future research.",

keywords = "YOLOv5m, audio-visual image dataset, maritime shipwreck, sonar, target detection, visual",

author = "Tian Rong and Wang, \{Chen Xu\} and Luo, \{Qing Hua\} and Li, \{Ying Chun\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 OCEANS Limerick, OCEANS Limerick 2023 ; Conference date: 05-06-2023 Through 08-06-2023",

year = "2023",

doi = "10.1109/OCEANSLimerick52467.2023.10244537",

language = "英语",

series = "OCEANS 2023 - Limerick, OCEANS Limerick 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "OCEANS 2023 - Limerick, OCEANS Limerick 2023",

address = "美国",

}

Rong, T, Wang, CX , Luo, QH & Li, YC 2023, Underwater shipwreck target detection based on audio-visual heterogeneous data. in OCEANS 2023 - Limerick, OCEANS Limerick 2023. OCEANS 2023 - Limerick, OCEANS Limerick 2023, Institute of Electrical and Electronics Engineers Inc., 2023 OCEANS Limerick, OCEANS Limerick 2023, Limerick, Ireland, 5/06/23. https://doi.org/10.1109/OCEANSLimerick52467.2023.10244537

Underwater shipwreck target detection based on audio-visual heterogeneous data. / Rong, Tian; Wang, Chen Xu ; Luo, Qing Hua et al.
OCEANS 2023 - Limerick, OCEANS Limerick 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (OCEANS 2023 - Limerick, OCEANS Limerick 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Underwater shipwreck target detection based on audio-visual heterogeneous data

AU - Rong, Tian

AU - Wang, Chen Xu

AU - Luo, Qing Hua

AU - Li, Ying Chun

PY - 2023

Y1 - 2023

N2 - As marine exploration continues to grow, the frequency of maritime emergency contingencies increases year by year. It is crucial to enhance marine surveillance to effectively detect underwater maritime shipwreck targets. Based on the excellent target detection performance of the YOLO5 model, we constructed the pure visual image dataset, pure sonar image dataset, and audio-visual heterogeneous dataset. We also trained the YOLOv5m model with a personal computer using the visual image dataset, sonar image dataset, and the hybrid audio-visual image dataset of maritime shipwrecks respectively. The test results show that the detection accuracy of the model trained with the hybrid maritime wrecks audio-visual image dataset is higher than that of the model trained with pure visual and sonar image datasets. This method may have an inspiration to future research.

AB - As marine exploration continues to grow, the frequency of maritime emergency contingencies increases year by year. It is crucial to enhance marine surveillance to effectively detect underwater maritime shipwreck targets. Based on the excellent target detection performance of the YOLO5 model, we constructed the pure visual image dataset, pure sonar image dataset, and audio-visual heterogeneous dataset. We also trained the YOLOv5m model with a personal computer using the visual image dataset, sonar image dataset, and the hybrid audio-visual image dataset of maritime shipwrecks respectively. The test results show that the detection accuracy of the model trained with the hybrid maritime wrecks audio-visual image dataset is higher than that of the model trained with pure visual and sonar image datasets. This method may have an inspiration to future research.

KW - YOLOv5m

KW - audio-visual image dataset

KW - maritime shipwreck

KW - sonar

KW - target detection

KW - visual

UR - https://www.scopus.com/pages/publications/85173681022

U2 - 10.1109/OCEANSLimerick52467.2023.10244537

DO - 10.1109/OCEANSLimerick52467.2023.10244537

M3 - 会议稿件

AN - SCOPUS:85173681022

T3 - OCEANS 2023 - Limerick, OCEANS Limerick 2023

BT - OCEANS 2023 - Limerick, OCEANS Limerick 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 OCEANS Limerick, OCEANS Limerick 2023

Y2 - 5 June 2023 through 8 June 2023

ER -

Underwater shipwreck target detection based on audio-visual heterogeneous data

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this