EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Synergistic Multi-Model Fusion for Efficient–Accurate Multi-Defect Detection in Power Lines

Linfeng Xi, Tao Shen, Guanglong Zhao, Nan Wang, Zhi Li

Sensors · 18.05.2026 · 26 (10) · 3185

DOI: 10.3390/s26103185 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 18.05.2026. Verfasst von Linfeng Xi und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical Engineering, University of Jinan, Jinan 250022, China. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Science and Technology of Shandong Province, University of Jinan, Jinan Municipal Science and Technology Bureau.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In unmanned aerial vehicle (UAV)-based power line inspection, multi-scale defects and complex backgrounds challenge the balance between detection accuracy, speed, and model lightweighting, limiting automated grid inspection. This paper proposes a Multi-Scale Mamba Framework (MS-Mamba) for efficient and accurate defect perception. A drone inspection dataset containing 5137 images from 14 defect categories was constructed and divided into training and validation sets with an 8:2 split. To address the large scale variation among defects, the categories are decoupled into macroscopic, mesoscopic, and microscopic groups according to physical attributes and visual scales. As the core perception engine, a lightweight state-space mechanism is designed to balance accuracy and deployability. A spatial resolution-aware hierarchical reconstruction strategy and a dynamic feature selection mechanism are integrated to enhance feature extraction, reduce background redundancy, and improve small-target representation. Compared with the YOLOv5s baseline, MS-Mamba achieves an mAP@0.5 of 0.749, corresponding to a 15.6 percentage-point improvement, while reducing parameters by 0.13 M and computational cost by 1.7 GFLOPs. Ablation studies and visual analyses further confirm fewer missed and false detections in complex backgrounds. The developed end-to-end inspection system was validated through closed-loop engineering tests, demonstrating strong potential for industrial deployment.

Schlagwörter

Stichwörter der Autor:innen

C3_MambaUAV power line inspectionmulti-target defect detectionsynergistic multi-model fusion

Autor:innen und Institutionen

  • School of Electrical Engineering, University of Jinan, Jinan 250022, China.
  • School of Control Science and Engineering, Shandong University, Jinan 250061, China.

Förderung

  • Department of Science and Technology of Shandong Province
  • University of Jinan
  • Jinan Municipal Science and Technology Bureau
  • Shandong Provincial Natural Science Foundation
  • University of Jinan Young Excellence Program
  • Shandong Province Youth Innovation Team Talent Introduction and Education Program for Higher Education Institutions
  • Intelligent Sensing and Robotics Application Engineering Research Center
  • University of Jinan Disciplinary Cross-Convergence Construction Project 2024

Zitieren

APA

Xi, L., Shen, T., Zhao, G., Wang, N., & Li, Z. (2026). Synergistic Multi-Model Fusion for Efficient–Accurate Multi-Defect Detection in Power Lines. Sensors, 26(10), 3185. https://doi.org/10.3390/s26103185

Vancouver

Xi L, Shen T, Zhao G, Wang N, Li Z. Synergistic Multi-Model Fusion for Efficient–Accurate Multi-Defect Detection in Power Lines. Sensors. 2026;26(10):3185. doi:10.3390/s26103185

BibTeX
@article{Xi2026,
  author = {Xi, Linfeng and Shen, Tao and Zhao, Guanglong and Wang, Nan and Li, Zhi},
  title = {Synergistic Multi-Model Fusion for Efficient–Accurate Multi-Defect Detection in Power Lines},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {3185},
  doi = {10.3390/s26103185}
}
Kostenlos starten →