EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SAW-YOLOv8l: An Enhanced Sewer Pipe Defect Detection Model for Sustainable Urban Drainage Infrastructure Management

Linna Hu, Hao Li, Jiahao Guo, Penghao Xue, Weixian Zha, Shihan Sun, Bin Guo, Yanping Kang

Sustainability · 08.04.2026 · 18 (8) · 3685

DOI: 10.3390/su18083685 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sustainability, online erschienen am 08.04.2026. Verfasst von Linna Hu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jiangsu Provincial Department of Water Resources, Jiangsu hydraulic research institute, Jinling Institute of Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Urban underground sewage pipelines often suffer from defects such as cracks, irregular joint misalignment, and stratified sedimentation blockages, which may lead to pipeline bursts, sewage overflow, and water pollution. Timely detection of abnormal defects in sewage pipelines is critical to ensuring public health and environmental sustainability. Vision-based sewage pipeline defect detection plays a crucial role in modern urban wastewater treatment systems. However, it still faces challenges such as limited feature extraction capabilities, insufficient multi-scale defect characterization, and poor positioning stability when dealing with low-contrast images and in environments with severe background interference. To address this issue, this study proposes an enhanced SAW-YOLOv8l model that integrates RT-DETR (real-time detection Transformer) with CNN (convolutional neural network) architecture. First, a C2f_SCA module improves the long-distance feature extraction capability and localization precision. Second, an AIFI-PRBN module enhances global feature correlation through attention-mechanism-based intra-scale feature interaction and reduces computational complexity using lightweight techniques. Finally, an adaptive dynamic weighted loss function based on Wise-IoU (weighted intersection over union) further improves training convergence and robustness by balancing the gradient distribution of samples. Experiments on a mixed dataset comprising Sewer-ML and industrial images demonstrate that the SAW-YOLOv8l model achieved mAP@0.5 of 86.2% and precision of 84.4%, which were improvements of 2.4% and 6.6% respectively over the baseline model, significantly enhancing the detection performance of abnormal defects in sewage pipelines.

Förderung

  • Jiangsu Provincial Department of Water Resources
  • Jiangsu hydraulic research institute
  • Jinling Institute of Technology
  • Jiangsu Province Industry-Academia-Research Collaboration Projects

Zitieren

APA

Hu, L., Li, H., Guo, J., Xue, P., Zha, W., Sun, S., Guo, B., & Kang, Y. (2026). SAW-YOLOv8l: An Enhanced Sewer Pipe Defect Detection Model for Sustainable Urban Drainage Infrastructure Management. Sustainability, 18(8), 3685. https://doi.org/10.3390/su18083685

Vancouver

Hu L, Li H, Guo J, Xue P, Zha W, Sun S, et al. SAW-YOLOv8l: An Enhanced Sewer Pipe Defect Detection Model for Sustainable Urban Drainage Infrastructure Management. Sustainability. 2026;18(8):3685. doi:10.3390/su18083685

BibTeX
@article{Hu2026,
  author = {Hu, Linna and Li, Hao and Guo, Jiahao and Xue, Penghao and Zha, Weixian and Sun, Shihan and Guo, Bin and Kang, Yanping},
  title = {SAW-YOLOv8l: An Enhanced Sewer Pipe Defect Detection Model for Sustainable Urban Drainage Infrastructure Management},
  journal = {Sustainability},
  year = {2026},
  volume = {18},
  number = {8},
  pages = {3685},
  doi = {10.3390/su18083685}
}
Kostenlos starten →