An Improved YOLOv11n Algorithm with Conv2Former and PW-IoU for UAV Inspection of Power Line Insulators
Received: 21 August 2025 | Revised: 8 October 2025 and 18 October 2025 | Accepted: 21 October 2025 | Online: 1 November 2025
Corresponding author: Niwat Angkawisittpan
Abstract
Detecting insulator defects accurately and efficiently is vital for maintaining the reliability of power transmission systems, particularly during Unmanned Aerial Vehicle (UAV)-based inspections. In order to improve local and global feature extraction and detect minor, low-visibility flaws in complex settings, this paper suggests C2F-YOLOv11n, a lightweight detection framework that incorporates the Conv2Former attention mechanism. Experiments on a self-built insulator dataset show that C2F-YOLOv11n achieves 91.7% precision, 83.1% recall, 89.4% mAP50, and 58.9% mAP50-95, with inference speed at 194 FPS and a compact 2.70 MB model size, outperforming YOLOv8n and YOLOv10n. Additionally, a novel regression loss function, PW-IoU, combining PIoUv2's boundary-aware localization and WIoUv3's adaptive gradient reweighting, is introduced to address bounding box regression challenges. By integrating PW-IoU, the model achieves higher performance with precision reaching 92.6%, recall at 87.5%, mAP50 at 90.8%, and mAP50-95 at 59.3%, outperforming conventional Complete IoU (CIoU) and other IoU-related loss functions. PW-IoU enhances localization accuracy and convergence stability, especially for small targets in complex backgrounds. Furthermore, comparative experiments on the publicly available Chinese Power Line Insulator Dataset (CPLID) confirm the model's strong generalization, achieving competitive detection performance on both normal and defective insulators.
Keywords:
Conv2Former, PW-IoU, insulator defect detection, small target detectionDownloads
References
E. Antwi-Bekoe, G. Liu, J.-P. Ainam, G. Sun, and X. Xie, "A deep learning approach for insulator instance segmentation and defect detection," Neural Computing and Applications, vol. 34, no. 9, pp. 7253–7269, May 2022. DOI: https://doi.org/10.1007/s00521-021-06792-z
Y. Ma, Q. Li, L. Chu, Y. Zhou, and C. Xu, "Real-Time Detection and Spatial Localization of Insulators for UAV Inspection Based on Binocular Stereo Vision," Remote Sensing, vol. 13, no. 2, Jan. 2021, Art. no. 230. DOI: https://doi.org/10.3390/rs13020230
D. Doufene, S. Benharat, S. Bouazabia, and S. A. Bessedik, "Hybrid Grey Wolf and Finite Element Method (GWO-FEM) Algorithm for Enhancing High Voltage Insulator String Performance in Wet Pollution Conditions," Engineering, Technology & Applied Science Research, vol. 12, no. 3, pp. 8765–8771, June 2022. DOI: https://doi.org/10.48084/etasr.4978
S. Deng, L. Chen, and Y. He, "Insulator defect detection from aerial images in adverse weather conditions," Applied Intelligence, vol. 55, no. 6, Jan. 2025, Art. no. 365. DOI: https://doi.org/10.1007/s10489-025-06280-0
Z. Deng, X. Li, and R. Yang, "RML-YOLO: An Insulator Defect Detection Method for UAV Aerial Images," Applied Sciences, vol. 15, no. 11, June 2025, Art. no. 6117. DOI: https://doi.org/10.3390/app15116117
S. A. Ahmed, E. H. Khalifa, A. F. A. Mahmoud, F. A. Abdalla, M. Nawaz, and A. Sulman, "Real Time Electrical Load Prediction and Management through Deep Learning and Reinforcement Learning Techniques," Engineering, Technology & Applied Science Research, vol. 15, no. 2, pp. 21061–21067, Apr. 2025. DOI: https://doi.org/10.48084/etasr.9559
Z.-Q. Zhao, P. Zheng, S.-T. Xu, and X. Wu, "Object Detection With Deep Learning: A Review," IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 11, pp. 3212–3232, Nov. 2019. DOI: https://doi.org/10.1109/TNNLS.2018.2876865
Z. Cai and N. Vasconcelos, "Cascade R-CNN: Delving Into High Quality Object Detection," in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 6154–6162. DOI: https://doi.org/10.1109/CVPR.2018.00644
R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Region-Based Convolutional Networks for Accurate Object Detection and Segmentation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 1, pp. 142–158, Jan. 2016. DOI: https://doi.org/10.1109/TPAMI.2015.2437384
R. Girshick, "Fast R-CNN," in 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015, pp. 1440–1448. DOI: https://doi.org/10.1109/ICCV.2015.169
S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137–1149, June 2017. DOI: https://doi.org/10.1109/TPAMI.2016.2577031
Y. Liu, D. Liu, X. Huang, and C. Li, "Insulator defect detection with deep learning: A survey," IET Generation, Transmission & Distribution, vol. 17, no. 16, pp. 3541–3558, Aug. 2023. DOI: https://doi.org/10.1049/gtd2.12916
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," in 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 779–788. DOI: https://doi.org/10.1109/CVPR.2016.91
W. Liu et al., "SSD: Single Shot MultiBox Detector," in 14th European Conference on Computer Vision, Amsterdam, Netherlands, 2016, pp. 21–37. DOI: https://doi.org/10.1007/978-3-319-46448-0_2
C. Liu, Y. Wu, J. Liu, and J. Han, "MTI-YOLO: A Light-Weight and Real-Time Deep Neural Network for Insulator Detection in Complex Aerial Images," Energies, vol. 14, no. 5, Mar. 2021, Art. no. 1426. DOI: https://doi.org/10.3390/en14051426
Z. Yang, Z. Xu, and Y. Wang, "Bidirection-Fusion-YOLOv3: An Improved Method for Insulator Defect Detection Using UAV Image," IEEE Transactions on Instrumentation and Measurement, vol. 71, 2022, Art. no. 3521408. DOI: https://doi.org/10.1109/TIM.2022.3201499
G. Han, M. He, M. Gao, J. Yu, K. Liu, and L. Qin, "Insulator Breakage Detection Based on Improved YOLOv5," Sustainability, vol. 14, no. 10, May 2022, Art. no. 6066. DOI: https://doi.org/10.3390/su14106066
J. Zheng, H. Wu, H. Zhang, Z. Wang, and W. Xu, "Insulator-Defect Detection Algorithm Based on Improved YOLOv7," Sensors, vol. 22, no. 22, Nov. 2022, Art. no. 8801. DOI: https://doi.org/10.3390/s22228801
L. Zhang, B. Li, Y. Cui, Y. Lai, and J. Gao, "Research on improved YOLOv8 algorithm for insulator defect detection," Journal of Real-Time Image Processing, vol. 21, no. 1, Jan. 2024, Art. no. 22. DOI: https://doi.org/10.1007/s11554-023-01401-9
J. Han, S. Hao, S. Li, and J. He, "Improved YOLOv9-Based Insulation Breakage Detection of Column Transformer," in 2025 2nd International Conference on Smart Grid and Artificial Intelligence, Changsha, China, 2025, pp. 844–848. DOI: https://doi.org/10.1109/SGAI64825.2025.11010027
M. Wu, G. Wang, W. Zhang, L. Wen, and H. Qu, "Bi-YOLOv10: Sample Imbalance-Aware Feature Fusion-Based Object Detection for Power Inspection," in 2024 IEEE First International Conference on Data Intelligence and Innovative Application, Nanning, China, 2024, pp. 1–6. DOI: https://doi.org/10.1109/DIIA62678.2024.10871263
Y. Ji, D. Zhang, Y. He, J. Zhao, X. Duan, and T. Zhang, "Improved YOLO11 Algorithm for Insulator Defect Detection in Power Distribution Lines," Electronics, vol. 14, no. 6, Mar. 2025, Art. no. 1201. DOI: https://doi.org/10.3390/electronics14061201
Y. Chai, X. Yao, M. Chen, and S. Shan, "FPFS-YOLO: An Insulator Defect Detection Model Integrating FasterNet and an Attention Mechanism," Sensors, vol. 25, no. 13, July 2025, Art. no. 4165. DOI: https://doi.org/10.3390/s25134165
Q. Hou, C.-Z. Lu, M.-M. Cheng, and J. Feng, "Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 12, pp. 8274–8283, Dec. 2024. DOI: https://doi.org/10.1109/TPAMI.2024.3401450
C. Liu, K. Wang, Q. Li, F. Zhao, K. Zhao, and H. Ma, "Powerful-IoU: More straightforward and faster bounding box regression loss with a nonmonotonic focusing mechanism," Neural Networks, vol. 170, pp. 276–284, Feb. 2024. DOI: https://doi.org/10.1016/j.neunet.2023.11.041
Z. Tong, Y. Chen, Z. Xu, and R. Yu, "Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism." arXiv, Apr. 08, 2023.
J. Liu, M. Hu, J. Dong, and X. Lu, "Summary of insulator defect detection based on deep learning," Electric Power Systems Research, vol. 224, Nov. 2023, Art. no. 109688. DOI: https://doi.org/10.1016/j.epsr.2023.109688
Y. Ye et al., "TSSSKD-YOLO: an intelligent classification and defect detection method of insulators on transmission lines by fusing knowledge distillation in multiple scenarios," Multimedia Systems, vol. 31, no. 3, Apr. 2025, Art. no. 183. DOI: https://doi.org/10.1007/s00530-025-01772-y
X. Tao, D. Zhang, Z. Wang, X. Liu, H. Zhang, and D. Xu, "Detection of Power Line Insulator Defects Using Aerial Images Analyzed With Convolutional Neural Networks," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 50, no. 4, pp. 1486–1498, Apr. 2020. DOI: https://doi.org/10.1109/TSMC.2018.2871750
T. Jiang, X. Hou, and M. Wang, "Insulator Defect Detection Based on the CDDCR–YOLOv8 Algorithm," International Journal of Computational Intelligence Systems, vol. 17, no. 1, Sept. 2024, Art. no. 245. DOI: https://doi.org/10.1007/s44196-024-00654-x
L. Lu, L. Liu, J. Chen, J. Liu, and X. Wu, "YOLO-Lite: Lightweight Object Detection Algorithm Design and Optimization in Power System Inspection," Signal, Image and Video Processing, vol. 19, no. 9, June 2025, Art. no. 716. DOI: https://doi.org/10.1007/s11760-025-04312-3
Q. Zhang, J. Zhang, Y. Li, C. Zhu, and G. Wang, "IL-YOLO: An Efficient Detection Algorithm for Insulator Defects in Complex Backgrounds of Transmission Lines," IEEE Access, vol. 12, pp. 14532–14546, 2024. DOI: https://doi.org/10.1109/ACCESS.2024.3358205
Q. Zhang, J. Zhang, Y. Li, C. Zhu, and G. Wang, "ID-YOLO: A Multimodule Optimized Algorithm for Insulator Defect Detection in Power Transmission Lines," IEEE Transactions on Instrumentation and Measurement, vol. 74, 2025, Art. no. 3505611. DOI: https://doi.org/10.1109/TIM.2025.3527530
Downloads
How to Cite
License
Copyright (c) 2025 Bin Zheng, Niwat Angkawisittpan, Lu Huang, Somchat Sonasang
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
