TLINet: A defects detection method for insulators of overhead transmission lines using partially transformer block
PLOS One · 25.06.2025 · 20 (6) · e0327139
DOI: 10.1371/journal.pone.0327139 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 25.06.2025. Verfasst von Xun Li und 6 weiteren Autor:innen. Beteiligte Einrichtung: Xi'an Key Laboratory of Advanced Photo-electronics Materials and Energy Conversion Device, School of Electronic Information, Xijing University, Xi'an…. Hauptthemen laut MEDLINE: Wireless Technology. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Basic Research Plan in Shaanxi Province of China, Natural Science Foundation of Shaanxi Province, Key Program of the National Social Science Foundation of China.
Abstract (Originalsprache)
The defects of insulators exhibit characteristics such as complex backgrounds, multi-scale variations, and small object sizes. Therefore, accurately focusing on these defects in dynamic and complex natural environments while maintaining inference speed remains a pressing challenge. To address this issue, this paper proposes an innovative insulator defect detection network, TLINet. First, a Multi-Branch Partially Transformer Block (MBPTB) is designed to enhance the backbone’s capability in capturing global features. Next, a Dynamic Downsampling Module (DyDown) is introduced to mitigate the issue of small-scale defect information blurring. Furthermore, considering the multi-scale variations of insulator defects, this paper proposes a Context-Guided Feature Fusion Network (CGFFN). This module enables fine-grained fusion of features at different scales, allowing the model to generate adaptive responses to defects of various sizes. Compared to the baseline model, the proposed method improves mAP50 by 5.3% on our self-constructed Insulator-DET dataset. On CPLID-D and CPLID-N, it achieves mAP50-95 improvements of 7.9% and 12.1%, respectively. Additionally, to verify the robustness of the proposed algorithm, TLINet is evaluated on the VOC07 + 12 dataset. Compared to the baseline model, TLINet improves mAP50 by 0.4% while reducing the number of parameters by 1/6. These results demonstrate the effectiveness of TLINet in addressing the complexities of insulator defect detection in power transmission lines. The code is available at https://github.com/mazilishang/TLINet .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Xi'an Key Laboratory of Advanced Photo-electronics Materials and Energy Conversion Device, School of Electronic Information, Xijing University, Xi'an, China.
- Xi'an Key Laboratory of High Precision Industrial Intelligent Vision Measurement Technology, Xijing University, Xi'an, Shaanxi, China.
- Xi'an Key Laboratory of Intelligent Sensing and Autonomous Navigation for Low Altitude Vehicles, Xijing University, Xi'an, Shaanxi, China.
ORCID-Profile: Yuzhen Zhao
Förderung
- Natural Science Basic Research Plan in Shaanxi Province of China
- Natural Science Foundation of Shaanxi Province
- Key Program of the National Social Science Foundation of China
- Shaanxi Provincial Science and Technology Plan Project
Zitieren
APA
Li, X., Zhao, Y., Zhao, Y., Guo, Z., Zhang, Y., Jiao, X., & Yuan, B. (2025). TLINet: A defects detection method for insulators of overhead transmission lines using partially transformer block. PLOS One, 20(6), e0327139. https://doi.org/10.1371/journal.pone.0327139
Vancouver
Li X, Zhao Y, Zhao Y, Guo Z, Zhang Y, Jiao X, et al. TLINet: A defects detection method for insulators of overhead transmission lines using partially transformer block. PLOS One. 2025;20(6):e0327139. doi:10.1371/journal.pone.0327139
BibTeX
@article{Li2025,
author = {Li, Xun and Zhao, Yuzhen and Zhao, Yang and Guo, Zhun and Zhang, Yongming and Jiao, Xiangke and Yuan, Baoxi},
title = {TLINet: A defects detection method for insulators of overhead transmission lines using partially transformer block},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {6},
pages = {e0327139},
doi = {10.1371/journal.pone.0327139}
}
EUVIMED