EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Underwater Structural Multi-Defects Automatic Detection via Hybrid Neural Network

Chunyan Ma, Zhe Chen, Huibin Wang, Guangze Shen

Journal of Marine Science and Engineering · 22.10.2025 · 13 (11) · 2029

DOI: 10.3390/jmse13112029 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 22.10.2025. Verfasst von Chunyan Ma und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Jiangsu Province Young Scientific and Technological Talents Promotion Plan.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Detecting underwater structural defects is vital for hydraulic engineering safety. Diverse patterns of underwater structural defects, i.e., the morphology and scale characteristics, pose difficulties on feature representability during detection. Any single feature morphology is insufficient to fully characterize diverse types of underwater defect patterns. This paper proposes a novel hybrid neural network to enhance feature representation of underwater structural multi-defects, which in turn improves the accuracy and adaptability of underwater detection. Three types of convolution operations are combined to build Hybrid Aggregation Network (HanNet), enhancing the morphological representation for diverse defects. Considering the scale difference of diverse defects, the Multi-Scale Shared Feature Pyramid (MSFP) is proposed, facilitating adaptive representation for diverse sizes of structural defects. The defect detection module leverages an Adaptive Spatial-Aware Attention (ASAA) at the backend, enabling selective enhancement of salient defect features. For model training and evaluation, we, for the first time, build an underwater structural multi-defects sonar image dataset containing a wide range of typical defect types. Experimental results demonstrate that the proposed model outperforms state-of-the-art methods, significantly improving defect detection accuracy, and provides an effective solution for detecting diverse structural defects in complex underwater environments.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Jiangsu Province Young Scientific and Technological Talents Promotion Plan

Zitieren

APA

Ma, C., Chen, Z., Wang, H., & Shen, G. (2025). Underwater Structural Multi-Defects Automatic Detection via Hybrid Neural Network. Journal of Marine Science and Engineering, 13(11), 2029. https://doi.org/10.3390/jmse13112029

Vancouver

Ma C, Chen Z, Wang H, Shen G. Underwater Structural Multi-Defects Automatic Detection via Hybrid Neural Network. Journal of Marine Science and Engineering. 2025;13(11):2029. doi:10.3390/jmse13112029

BibTeX
@article{Ma2025,
  author = {Ma, Chunyan and Chen, Zhe and Wang, Huibin and Shen, Guangze},
  title = {Underwater Structural Multi-Defects Automatic Detection via Hybrid Neural Network},
  journal = {Journal of Marine Science and Engineering},
  year = {2025},
  volume = {13},
  number = {11},
  pages = {2029},
  doi = {10.3390/jmse13112029}
}
Kostenlos starten →