UCD-LFE: An Underwater Crack Detection Model for Hydraulic Structures in Complex Environments via Lightweight Design and Feature Enhancement
Water · 30.10.2026 · 18 (21) · 2719
DOI: 10.3390/w18212719 ↗Kurz gefasst
Fachartikel in der Zeitschrift Water, online erschienen am 30.10.2026. Verfasst von Xiaohu Chen und 3 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Independent Innovation Research Program of Changjiang Survey, Planning, Design and Research Co., Ltd..
Abstract (Originalsprache)
Underwater crack detection in hydraulic structures is difficult in complex underwater environments, where blur, uneven illumination, low contrast, and rough surface textures can weaken crack cues and introduce background interference, while multiple cracks further increase detection complexity. Practical inspection also requires compact models with low computational demand. To address these coupled challenges, this study develops UCD-LFE, an underwater crack detection model combining lightweight design with feature enhancement. StarNet and a shared-convolution detection head reduce redundant computation, while C2f_Star_CAA enhances crack feature representation during multiscale fusion. The model was evaluated using ROV-acquired images from an operating hydraulic project and a separate held-out set of 93 complex-scene images excluded from model development. UCD-LFE achieved 80.01% mAP@0.5 while reducing computation from 8.1 to 5.5 GFLOPs and model size from 6.0 to 3.8 MB relative to YOLOv8n. On the complex-scene set, mAP@0.5 reached 78.49%, 7.90 percentage points above the baseline, with substantially less performance degradation. Feature-response visualizations covering a clear reference and four challenging scene types—blur and uneven illumination, low contrast, rough texture, and multi-crack scenes—showed more continuous and spatially concentrated responses along crack regions, with fewer dispersed background responses. These results demonstrate that lightweight design and feature enhancement can improve robust crack detection in complex underwater environments while reducing model complexity.
Förderung
- National Natural Science Foundation of China
- National Key Research and Development Program of China
- Independent Innovation Research Program of Changjiang Survey, Planning, Design and Research Co., Ltd.
Zitieren
APA
Chen, X., Jia, X., Xu, T., & Zhu, Y. (2026). UCD-LFE: An Underwater Crack Detection Model for Hydraulic Structures in Complex Environments via Lightweight Design and Feature Enhancement. Water, 18(21), 2719. https://doi.org/10.3390/w18212719
Vancouver
Chen X, Jia X, Xu T, Zhu Y. UCD-LFE: An Underwater Crack Detection Model for Hydraulic Structures in Complex Environments via Lightweight Design and Feature Enhancement. Water. 2026;18(21):2719. doi:10.3390/w18212719
BibTeX
@article{Chen2026,
author = {Chen, Xiaohu and Jia, Xiaonan and Xu, Tao and Zhu, Yantao},
title = {UCD-LFE: An Underwater Crack Detection Model for Hydraulic Structures in Complex Environments via Lightweight Design and Feature Enhancement},
journal = {Water},
year = {2026},
volume = {18},
number = {21},
pages = {2719},
doi = {10.3390/w18212719}
}
EUVIMED