To automate the wiring process for distribution network live-line operation robots, it is essential for visual sensors to accurately detect and locate the stripped areas of wires. However, due to the complex layout of power transmission lines and the varying outdoor lighting conditions, accurately identifying the stripped regions remains challenging. In this paper, we first construct a dataset of stripped wire areas and perform data augmentation to address the issue of limited samples. Subsequently, we apply a Transformer-based adaptive image enhancement model for image preprocessing, aiming to improve visual quality. Experimental results show that this model can enhance or correct lighting in a short time while preserving the primary color characteristics. Based on this, we design a stripped wire region detection model using an improved YOLOv7 algorithm, achieving high-precision, real-time detection in complex backgrounds. Tests with real-world data demonstrate an average detection accuracy exceeding 92%, effectively addressing the need for precise wire detection and localization during automated wiring in distribution networks, thereby advancing the development of smart grids.

1. [1] H. Zhao et al., “Autonomous live working robot navigation with real-time detection and motion planning system on distribution line,” High Voltage, Vol.7, No.6, pp. 1204-1216, 2022. https://doi.org/10.1049/hve2.12221
2. [2] M. Perez-Ramirez, G. Arroyo-Figueroa, and A. Ayala, “The use of a virtual reality training system to improve technical skill in the maintenance of live-line power distribution networks,” Interactive Learning Environments, Vol.29, No.4, pp. 527-544, 2021. https://doi.org/10.1080/10494820.2019.1587636
3. [3] X. Zhang et al., “Measurement and analysis of key influencing factors in the cost of equipment assets of distribution network operation and maintenance cost,” 7th Int. Symp. on Advances in Electrical, Electronics, and Computer Engineering (SPIE Proc. Vol.12294), Article No.122p41B, 2022. https://doi.org/10.1117/12.2640486
4. [4] B. Zhang, J. Song, Q. Liu, and Y. Yan, “Wear-YOLO: Research on detection methods of safety equipment for power personnel in substations,” 5th Int. Conf. on Clean Energy and Electric Power Engineering, pp. 274-278, 2024. https://doi.org/10.1109/ICCEPE62686.2024.10931509
5. [5] W. Jiang et al., “Research on key technologies of multi-task-oriented live maintenance robots for ultra high voltage multi-split transmission lines,” Industrial Robot, Vol.48, No.1, pp. 17-28, 2020. https://doi.org/10.1108/IR-03-2020-0066
6. [6] F. Shuang et al., “PLE: Power line extraction algorithm for UAV-based power inspection,” IEEE Sensors J., Vol.22, No.20, pp. 19941-19952, 2022. https://doi.org/10.1109/JSEN.2022.3202033
7. [7] Y. Chen et al., “Intelligent power distribution live-line operation robot systems based on stereo camera,” High Voltage, Vol.8, No.6, pp. 1306-1318, 2023. https://doi.org/10.1049/hve2.12349
8. [8] Y. Zhang, X. Shi, H. Zhang, Y. Cao, and V. Terzija, “Review on deep learning applications in frequency analysis and control of modern power system,” Int. J. of Electrical Power & Energy Systems, Vol.136, Article No.107744, 2022. https://doi.org/10.1016/j.ijepes.2021.107744
9. [9] X. Lei and Z. Sui, “Intelligent fault detection of high voltage line based on the Faster R-CNN,” Measurement, Vol.138, pp. 379-385, 2019. https://doi.org/10.1016/j.measurement.2019.01.072
10. [10] M. Liu, Z. Li, and G. Sheng, “Edge intelligent visual monitoring of substations based on lightweight object detection model,” IEEE Trans. on Instrumentation and Measurement, Vol.74, Article No.3533112, 2025. https://doi.org/10.1109/TIM.2025.3562970
11. [11] J. Li et al., “PEDNet: A lightweight detection network of power equipment in infrared image based on YOLOv4-Tiny,” IEEE Trans. on Instrumentation and Measurement, Vol.72, Article No.5004312, 2023. https://doi.org/10.1109/TIM.2023.3235416
12. [12] C. Liu, Y. Wu, J. Liu, and Z. Sun, “Improved YOLOv3 network for insulator detection in aerial images with diverse background interference,” Electronics, Vol.10, No.7, Article No.771, 2021. https://doi.org/10.3390/electronics10070771
13. [13] Z. Yang, Z. Xu, and Y. Wang, “Bidirection-fusion-YOLOv3: An improved method for insulator defect detection using UAV image,” IEEE Trans. on Instrumentation and Measurement, Vol.71, Article No.3521408, 2022. https://doi.org/10.1109/TIM.2022.3201499
14. [14] W. Cao et al., “Step-by-step: Efficient ship detection in large-scale remote sensing images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol.17, pp. 13426-13438, 2024. https://doi.org/10.1109/JSTARS.2024.3429395
15. [15] O. Ulucan, D. Karakaya, and M. Turkan, “Saturated region recovery in tone-mapped HDR images,” 2021 IEEE Int. Conf. on Image Processing, pp. 1774-1778, 2021. https://doi.org/10.1109/ICIP42928.2021.9506727
16. [16] K. Wei, Y. Fu, Y. Zheng, and J. Yang, “Physics-based noise modeling for extreme low-light photography,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.44, No.11, pp. 8520-8537, 2022. https://doi.org/10.1109/TPAMI.2021.3103114
17. [17] K. Li et al., “UniFormer: Unifying convolution and self-attention for visual recognition,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.45, No.10, pp. 12581-12600, 2023. https://doi.org/10.1109/TPAMI.2023.3282631
18. [18] A. Dosovitskiy et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv:2010.11929, 2020.
19. [19] C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,” 2023 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 7464-7475, 2023. https://doi.org/10.1109/CVPR52729.2023.00721
20. [20] N. Mukai et al., “Application of object grasping using dual-arm autonomous mobile robot—Path planning by spline curve and object recognition by YOLO—,” J. Robot. Mechatron., Vol.35, No.6, pp. 1524-1531, 2023. https://doi.org/10.20965/jrm.2023.p1524
21. [21] R. Gai, N. Chen, and H. Yuan, “A detection algorithm for cherry fruits based on the improved YOLO-v4 model,” Neural Computing and Applications, Vol.35, No.19, pp. 13895-13906, 2023. https://doi.org/10.1007/s00521-021-06029-z
22. [22] L. Yang, R.-Y. Zhang, L. Li, and X. Xie, “SimAM: A simple, parameter-free attention module for convolutional neural networks,” Proc. of the 38th Int. Conf. on Machine Learning, pp. 11863-11874, 2021.
23. [23] Y. Qi, Y. He, X. Qi, Y. Zhang, and G. Yang, “Dynamic snake convolution based on topological geometric constraints for tubular structure segmentation,” 2023 IEEE/CVF Int. Conf. on Computer Vision, pp. 6047-6056, 2023. https://doi.org/10.1109/ICCV51070.2023.00558
24. [24] K. Han et al., “GhostNet: More features from cheap operations,” 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 1577-1586, 2020. https://doi.org/10.1109/CVPR42600.2020.00165
25. [25] D. Costarelli, M. Seracini, and G. Vinti, “A comparison between the sampling Kantorovich algorithm for digital image processing with some interpolation and quasi-interpolation methods,” Applied Mathematics and Computation, Vol.374, Article No.125046, 2020. https://doi.org/10.1016/j.amc.2020.125046