Advanced deep learning framework for underwater object detection with multibeam forward-looking sonar
Structural Health Monitoring · 2025-07 · 24 (4) · 1991-2007
DOI: 10.1177/14759217241235637 ↗Kurz gefasst
Fachartikel in der Zeitschrift Structural Health Monitoring, online erschienen am 24.03.2024. Verfasst von Liangfu Ge und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Civil and Environmental Engineering, The Western Academy for Advanced Research, Western University, London, ON, Canada. Die Arbeit wurde bisher 42-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada.
Abstract (Originalsprache)
Underwater object detection (UOD) is an essential activity in maintaining and monitoring underwater infrastructure, playing an important role in their efficient and low-risk asset management. In underwater environments, sonar, recognized for overcoming the limitations of optical imaging in low-light and turbid conditions, has increasingly gained popularity for UOD. However, due to the low resolution and limited foreground-background contrast in sonar images, existing sonar-based object detection algorithms still face challenges regarding precision and transferability. To solve these challenges, this article proposes an advanced deep learning framework for UOD that uses the data from multibeam forward-looking sonar. The framework is adapted from the network architecture of YOLOv7, one of the state-of-the-art vision-based object detection algorithms, by incorporating unique optimizations in three key aspects: data preprocessing, feature fusion, and loss functions. These improvements are extensively tested on a dedicated public dataset, showing superior object classification performance compared to the selected existing sonar-based methods. Through experiments conducted on an underwater remotely operated vehicle, the proposed framework validates significant enhancements in target classification, localization, and transfer learning capabilities. Since the engineering structures have similar geometric shapes to the objects tested in this study, the proposed framework presents potential applicability to underwater structural inspection and monitoring, and autonomous asset management.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Civil and Environmental Engineering, The Western Academy for Advanced Research, Western University, London, ON, Canada.
- Department of Civil and Environmental Engineering, Western University, London, ON, Canada.
ORCID-Profile: Ayan Sadhu
Förderung
- Natural Sciences and Engineering Research Council of Canada
Zitieren
APA
Ge, L., Singh, P., & Sadhu, A. (2025). Advanced deep learning framework for underwater object detection with multibeam forward-looking sonar. Structural Health Monitoring, 24(4), 1991-2007. https://doi.org/10.1177/14759217241235637
Vancouver
Ge L, Singh P, Sadhu A. Advanced deep learning framework for underwater object detection with multibeam forward-looking sonar. Structural Health Monitoring. 2025;24(4):1991-2007. doi:10.1177/14759217241235637
BibTeX
@article{Ge2025,
author = {Ge, Liangfu and Singh, Premjeet and Sadhu, Ayan},
title = {Advanced deep learning framework for underwater object detection with multibeam forward-looking sonar},
journal = {Structural Health Monitoring},
year = {2025},
volume = {24},
number = {4},
pages = {1991--2007},
doi = {10.1177/14759217241235637}
}
EUVIMED