EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fog-Adaptive-YOLO: A lightweight model for insulator defect detection

Xiaoyuan Jin, Yuzhen Zhao iD, Wangyu Shen, Zhun Guo, Jianjing Gao, Baoxi Yuan, Xiyuan Zhu

PLOS One · 11.06.2026 · 21 (6) · e0351054

DOI: 10.1371/journal.pone.0351054 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 11.06.2026. Verfasst von Xiaoyuan Jin und 6 weiteren Autor:innen. Beteiligte Einrichtung: Shaanxi Key Laboratory of Liquid Crystal Polymer Intelligent Display, Technological Institute of Materials & Energy Science (TIMES), Xijing Universit…. Hauptthemen laut MEDLINE: Weather, Models, Theoretical. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Insulator defect detection under foggy conditions suffers from complex backgrounds, small targets, weak features, and severe weather interference, remaining a challenging task for UAV-based inspection. To address these issues, this paper proposes Fog-Adaptive-YOLO, a lightweight fog-adaptive detection network. The FogEnhance module suppresses fog noise and enhances weak defect features; the C3MSGR and C2fMSGR modules optimize lightweight multi-scale feature extraction and aggregation. Experimental results show that on the self-constructed InsDef-Fog dataset, the proposed model achieves 65.4% mAP50 with only 2.74M parameters. It obtains 60.3% mAP50 on the public IDID_FOG dataset and 80.2% mAP50 on the real-world WM-FOG dataset. The model also maintains stable precision on the cross-scene RTTS foggy dataset. These results demonstrate that Fog-Adaptive-YOLO achieves a favorable balance between detection accuracy and lightweight efficiency, well-suited for practical foggy insulator defect detection tasks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

WeatherModels, TheoreticalDetection AlgorithmsAlgorithmsUnmanned Aerial Devices

Autor:innen und Institutionen

  • Shaanxi Key Laboratory of Liquid Crystal Polymer Intelligent Display, Technological Institute of Materials & Energy Science (TIMES), Xijing University, Xi'an, China.
  • School of Electronic Information, Xijing University, Xi'an, China.

ORCID-Profile: Yuzhen Zhao

Zitieren

APA

Jin, X., Zhao, Y., Shen, W., Guo, Z., Gao, J., Yuan, B., & Zhu, X. (2026). Fog-Adaptive-YOLO: A lightweight model for insulator defect detection. PLOS One, 21(6), e0351054. https://doi.org/10.1371/journal.pone.0351054

Vancouver

Jin X, Zhao Y, Shen W, Guo Z, Gao J, Yuan B, et al. Fog-Adaptive-YOLO: A lightweight model for insulator defect detection. PLOS One. 2026;21(6):e0351054. doi:10.1371/journal.pone.0351054

BibTeX
@article{Jin2026,
  author = {Jin, Xiaoyuan and Zhao, Yuzhen and Shen, Wangyu and Guo, Zhun and Gao, Jianjing and Yuan, Baoxi and Zhu, Xiyuan},
  title = {Fog-Adaptive-YOLO: A lightweight model for insulator defect detection},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {6},
  pages = {e0351054},
  doi = {10.1371/journal.pone.0351054}
}
Kostenlos starten →