Home > Archive>Volume 20, Issue 11, 2024 >681-688. DOI:https://doi.org/10.1007/s11801-024-3213-3
PDF HTML XML Export Cite reminder
Enhancing hyperspectral power transmission line defect and hazard identification with an improved YOLO-based model
CSTR:
[cstr]
Author:
Affiliation:

1. Ningbo Power Transmission and Transformation Construction Co., Ltd., Yongyao Technology Branch, Ningbo 315100, China;2. State Grid Ningbo Power Supply Company, Ningbo 315100, China

  • Article
    • | |
  • Metrics
    • |
  • Reference [21]
    • |
  • Related [20]
    • | | |
  • Comments
    Abstract:

    To address the challenges of inefficient manual inspections and time-consuming video monitoring for power transmission lines, this paper presents an innovative solution. It combines deep learning algorithms with visible light remote sensing images to detect defects and hazards. Deep learning offers enhanced robustness, significantly improving efficiency and accuracy. The study utilizes you only look once version 7 (YOLOv7) as a foundational framework, enhancing it with the Transformer algorithm, Triplet Attention mechanism, and smooth intersection over union (SIoU) loss function. Experimental results show a remarkable 92.3% accuracy and an 18.4 ms inference speed. This approach promises to revolutionize power transmission line maintenance, offering real-time, high-precision defect and hazard identification.

    Reference
    [1] NIE X T, TIAN J, WANG B, et al. Key technologies research on trimble ux5 vav photogrammetry[J]. Journal of North China University of Water Resources and Electric Power (natural science edition), 2020, 41(5):73-83. (in Chinese)
    [2] ZHOU X Y, WANG K, LI L Y. A survey of deep learning-based object detection algorithms[J]. Electronic measurement technology, 2017, 40(11):89-93. (in Chinese)
    [3] QIAN J J, WANG K, WANG R, et al. Task planning for intelligent substation robots[J]. Guangdong electric power, 2017, 30(2):143-149. (in Chinese)
    [4] YU Y X. The urgency and long-term implementation of smart grids power[J]. System protection and control, 2019, 47(17):1-5. (in Chinese)
    [5] NGUYEN V, JENSSEN R, ROVERSO D. Automatic autonomous vision-based power line inspection:a review of current status and the potential role of deep learning[J]. International journal of electrical power and energy systems, 2018, 99:107-120.
    [6] CHENG H, ZHAI Y, CHEN R, et al. Self-shattering defect detection of glass insulators based on spatial features[J]. Energies, 2019, 12(3):543.
    [7] PAN X, ZHAO J, XU J. An object-based and heterogeneous segment filter convolutional neural network for high-resolution remote sensing image classification[J]. International journal of remote sensing, 2019:1-25.
    [8] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2014, NW Washington, DC, USA. New York:IEEE, 2014:508-587.
    [9] YIN Y, CHENG X, SHI F, et al. An enhanced lightweight convolutional neural network for ship detection in maritime surveillance system[J]. IEEE journal of selected topics in applied earth observations and remote sensing, 2022, 15:5811-5825.
    [10] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7:trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-22, 2023, Vancouver, Canada. New York:IEEE, 2023:7464-7475.
    [11] ZHAO H, ZHANG H, ZHAO Y. YOLOv7-sea:object detection of maritime UAV images based on improved YOLOv7[C]//Proceedings of the 2023 IEEE/CVF Winter Conference on Applications of Computer Vision, January 2-7, 2023, Waikoloa, USA. New York:IEEE, 2023:233-238.
    [12] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7:trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[EB/OL]. (2022-07-06) [2023-08-22]. https://arxiv.org/abs/2207.
    02696.
    [13] BOCHKOVSKIY A, WANG C Y, LIAO H Y. YOLOv4:optimal speed and accuracy of object detection[EB/OL]. (2020-04-23) [2023-08-22]. https://arxiv.org/abs/2004.
    10934.
    [14] LIU Z, LIN Y, CAO Y, et al. Swin transformer:hierarchical vision transformer using shifted windows[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, October 10-17, 2021, Montreal, QC, Canada. New York:IEEE, 2021:10012-10022.
    [15] MISRA D, NALAMADA T, HOU Q, et al. Rotate to attend:convolutional triplet attention module[EB/OL]. (2020-10-06) [2023-08-22]. https://arxiv.org/abs/2010.03045v1.
    [16] GEVORGYAN Z. Siou loss:more powerful learning for bounding box regression[EB/OL]. (2022-05-25) [2023-08-22]. https://arxiv.org/abs/2205.12740.
    [17] HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2020:2011-2023.
    [18] WANG Q, WU B, ZHU P, et al. ECA-net:efficient channel attention for deep convolutional neural networks[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, October 10-17, 2021, Montreal, QC, Canada. New York:IEEE, 2021:11531-11539.
    [19] HENDERSON P, FERRARI V. End-to-end training of object class detectors for mean average precision[C]//13th Asian Conference on Computer Vision, November 20-24, 2016. Berlin, Heidelberg:Springer, 2017:198-213.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

WANG Meng, SUN Long, JIANG Jiong, YANG Jinsong, ZHANG Xingru. Enhancing hyperspectral power transmission line defect and hazard identification with an improved YOLO-based model[J]. Optoelectronics Letters,2024,20(11):681-688

Copy
Share
Article Metrics
  • Abstract:41
  • PDF: 0
  • HTML: 0
  • Cited by: 0
History
  • Received:October 07,2023
  • Revised:April 26,2024
  • Online: September 30,2024
Article QR Code
Phone：86-22-60214471
URL：http://www.oelett.com E-mail：oel@263.net
Supported by:Beijing E-Tiller Technology Development Co., Ltd.
® 2025 All Rights Reserved