A lightweight cross-scale feature fusion model based on YOLOv8 for defect detection in sewer pipeline
PLOS One · 21.08.2025 · 20 (8) · e0330677
DOI: 10.1371/journal.pone.0330677 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 21.08.2025. Verfasst von Ruibo Sha und 3 weiteren Autor:innen. Beteiligte Einrichtung: Software Engineering College, Zhengzhou University of Light Industry, Zhengzhou, Henan, China. Hauptthemen laut MEDLINE: Sewage, Models, Theoretical. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Sewer pipeline defect detection is a critical task for ensuring the normal operation of urban infrastructure. However, the sewer environment often presents challenges such as multi-scale defects, complex backgrounds, lighting changes, and diverse defect morphologies. To address these issues, this paper proposes a lightweight cross-scale feature fusion model based on YOLOv8. First, the C2f module in the backbone network is replaced with the C2f-FAM module to enhance multi-scale feature extraction capabilities. Second, the HS-BiFPN module is adopted to replace the original structure, leveraging cross-layer semantic fusion and feature re-weighting mechanisms to improve the model’s ability to distinguish complex backgrounds and diverse defect morphologies. Finally, DySample is introduced to replace traditional sampling operations, enhancing the model’s ability to capture details in complex environments. This study uses the Sewer-ML dataset to train and evaluate the model, selecting 1,158 images containing six types of typical defects (CK, PL, SG, SL, TL, ZW), and expanding the dataset to 1,952 images through data augmentation. Experimental results show that compared to the YOLOv8n model, the improved model achieves a 3.8% increase in mAP, while reducing the number of parameters by 35%, floating-point operations by 21%, and model size by 33%. By improving detection accuracy while achieving model lightweighting, the model demonstrates potential for application in pipeline defect detection.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Software Engineering College, Zhengzhou University of Light Industry, Zhengzhou, Henan, China.
ORCID-Profile: Ruibo Sha, Zhifeng Zhang
Zitieren
APA
Sha, R., Zhang, Z., Cui, X., & Mu, Q. (2025). A lightweight cross-scale feature fusion model based on YOLOv8 for defect detection in sewer pipeline. PLOS One, 20(8), e0330677. https://doi.org/10.1371/journal.pone.0330677
Vancouver
Sha R, Zhang Z, Cui X, Mu Q. A lightweight cross-scale feature fusion model based on YOLOv8 for defect detection in sewer pipeline. PLOS One. 2025;20(8):e0330677. doi:10.1371/journal.pone.0330677
BibTeX
@article{Sha2025,
author = {Sha, Ruibo and Zhang, Zhifeng and Cui, Xiao and Mu, Qingzheng},
title = {A lightweight cross-scale feature fusion model based on YOLOv8 for defect detection in sewer pipeline},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {8},
pages = {e0330677},
doi = {10.1371/journal.pone.0330677}
}
EUVIMED