Multi-Module Fusion Model for Submarine Pipeline Identification Based on YOLOv5

In recent years, the surge in marine activities has increased the frequency of submarine pipeline failures. Detecting and identifying the buried conditions of submarine pipelines has become critical. Sub-bottom profilers (SBPs) are widely employed for pipeline detection, yet manual data interpretati...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of marine science and engineering Ročník 12; číslo 3; s. 451
Hlavní autoři: Duan, Bochen, Wang, Shengping, Luo, Changlong, Chen, Zhigao
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.03.2024
Témata:
Acoustics
Automation
Computer networks
Data collection
Data interpretation
Data processing
Datasets
Deep learning
Detection
Efficiency
Geology
Localization
Modules
Pipe lines
pipeline detection
Profilers
Sediments
Sensors
Software
sub-bottom profiler (SBP) system
Submarine pipelines
subsea pipelines
Telecommunication systems
Underwater pipelines
Underwater structures
YOLOv5 object detection algorithm
China
United States > US
ISSN:2077-1312, 2077-1312
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In recent years, the surge in marine activities has increased the frequency of submarine pipeline failures. Detecting and identifying the buried conditions of submarine pipelines has become critical. Sub-bottom profilers (SBPs) are widely employed for pipeline detection, yet manual data interpretation hampers efficiency. The present study proposes an automated detection method for submarine pipelines using deep learning models. The approach enhances the YOLOv5s model by integrating Squeeze and Excitation Networks (SE-Net) and S2-MLPv2 attention modules into the backbone network structure. The Slicing Aided Hyper Inference (SAHI) module is subsequently introduced to recognize original large-image data. Experimental results conducted in the Yellow Sea region demonstrate that the refined model achieves a precision of 82.5%, recall of 99.2%, and harmonic mean (F1 score) of 90.0% on actual submarine pipeline data detected using an SBP. These results demonstrate the efficiency of the proposed method and applicability in real-world scenarios.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2077-1312
2077-1312
DOI:10.3390/jmse12030451