With the advancement of the intellectualization of power systems, visible light images captured by inspection robots have found extensive applications in the condition monitoring of transmission lines. However, two key challenges persist in real-world scenarios. First, critical components such as insulators and spacer dampers are frequently configured in dense and small-scale arrangements, rendering them prone to being overlooked by traditional detection methods owing to insufficient feature extraction or inadequate contextual modeling. Second, transmission corridors are often susceptible to various safety hazards, including encroaching vegetation, accumulated water, floating plastic films, and smoke from nearby fires, each posing a significant threat to operational reliability and the safe and stable operation of the power grid. Therefore, we propose a model named Mobile-RCNN that is capable of detecting both densely arranged and small-scale components as well as safety hazards. First, we constructed a safety hazard dataset through on-site photography. Second, we introduced the Q-linear-NMS post-processing method that replaced the non-maximum suppression (NMS) approach with Soft-NMS and incorporated a linear suppression control coefficient. Then, we replaced the intersection over union (IOU) evaluation method for overlapping detection boxes with the distance-IOU (DIOU) evaluation method and introduced an adjustment parameter for the degree of score suppression. Finally, to enable the backbone feature extraction network to better learn the characteristics of safety hazards and provide rich information for the subsequent detection network, we adopted MobileNetV3 as the feature extraction network for the Mobile-RCNN. The experimental results demonstrated that the proposed model detected densely arranged targets and accurately identified the locations of safety hazards, providing robust technical support for the construction of an intelligent, reliable, and all-weather operation and maintenance system for power systems.

1. [1] S. Yu, S. Zhou, and J. Qin, “Layout optimization of China’s power transmission lines for renewable power integration considering flexible resources and grid stability,” Int. J. of Electrical Power and Energy Systems, Vol.135, Article No.107507, 2022. https://doi.org/10.1016/j.ijepes.2021.107507
2. [2] “DTE energy highlights accelerating its investments to build a smarter grid,” Food and Beverage Close-Up, 2025.
3. [3] R. Girshick, J. Donahue, T. Darrell et al., “Rich feature hierarchies for accurate object detection and semantic segmentation,” Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 580-587, 2014. https://doi.org/10.1109/CVPR.2014.81
4. [4] K. He, X. Zhang, S. Ren et al., “Spatial pyramid pooling in deep convolutional networks for visual recognition,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.37, No.9, pp. 1904-1916, 2015. https://doi.org/10.1109/TPAMI.2015.2389824
5. [5] R. Girshick “Fast R-CNN,” Proc. of the IEEE Int. Conf. on Computer Vision, pp. 1440-1448, 2015. https://doi.org/10.1109/ICCV.2015.169
6. [6] S. Ren, K. He, R. Girshick et al., “Faster R-CNN: Towards real-time object detection with region proposal networks,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.39, No.6, pp. 1137-1149, 2017. https://doi.org/10.1109/TPAMI.2016.2577031
7. [7] Z. Cai and N. Vasconcelos, “Cascade R-CNN: Delving into high quality object detection,” Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 6154-6162, 2018. https://doi.org/10.1109/CVPR.2018.00644
8. [8] W. Liu, D. Anguelov, D. Erhan et al., “SSD: Single shot multibox detector,” 14th European Conf. on Computer Vision (ECCV 2016), pp. 21-37, 2016. https://doi.org/10.1007/978-3-319-46448-0_2
9. [9] J. Redmon, S. Divvala, R. Girshick et al., “You only look once: Unified, real-time object detection,” Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 779-788, 2016. https://doi.org/10.1109/CVPR.2016.91
10. [10] L. Mejias, J. F. Correa, I. Mondragón et al., “COLIBRI: A vision-guided UAV for surveillance and visual inspection,” Proc. 2007 IEEE Int. Conf. on Robotics and Automation, pp. 2760-2761, 2007. https://doi.org/10.1109/ROBOT.2007.363883
11. [11] C. Li, C. Wang, Y. Zhao et al., “Investigation into in situ computed tomography inspection technology for conductor connection structure of ultra-high voltage gas-insulated transmission lines,” Russian J. of Nondestructive Testing, Vol.61, No.3, pp. 353-365, 2025. https://doi.org/10.1134/S1061830925600133
12. [12] C. Shen, N. Chen, R. Tan et al., “Modeling and stability analysis of coarse – Fine composite mechatronic system in UAV multi-gimbal electro-optical pod,” Electronics, Vol.9, No.5, Article No.769, 2020. https://doi.org/10.3390/electronics9050769
13. [13] S. Zeng, J. Jia, T. Ma et al., “Application of AI Image Recognition in the Omnidirectional Monitoring System for Power Transmission Lines,” Advances in Multimedia, Vol.2023, Article No.9898403, 2021. https://doi.org/10.1155/2023/9898403
14. [14] H. Ni, M. Wang, and L. Zhao, “An improved faster R-CNN for defect recognition of key components of transmission line,” Mathematical Biosciences and Engineering, Vol.18, No.4, pp. 4679-4695, 2021. https://doi.org/10.3934/mbe.2021237
15. [15] L. Kong, “Research on Small Target Detection Algorithm for Transmission Lines Based on Convolutional Neural Network,” Master’s theses, Huazhong University of Science and Technology, 2019 (in Chinese).
16. [16] L. Hui, D. Yan, and L. Xiang, “Abnormal target detection method of transmission line based on two-stage deep network," Control Decis, Vol.37, pp. 1873-1882, 2022.
17. [17] Y. Xu, “Research on detection method of transmission line fittings based on knowledge reasoning,” Master’s theses, North China Electric Power University, 2024 (in Chinese).
18. [18] Z. Zhao, Y. Li, Y. Qi et al., “Insulator defect detection method based on dynamic focus loss function and sample balance method," Electric Power Automation Equipment, Vol.40, No.10, pp. 205-211, 2020 (in Chinese). https://doi.org/10.16081/j.epae.202010008
19. [19] W. He, J. Li, and W. Zhao, “Insulator anomaly detection based on improved faster RCNN,” Zhejiang Electric Power, Vol.40, No.8, pp. 40-46, 2021 (in Chinese). https://doi.org/10.19585/j.zjdl.202108006
20. [20] Z. Zhao, Y. Li, Z. Zhen et al., “Typical fittings detection method with faster R-CNN combining KL divergence and shape constraints,” High Voltage Technology, Vol.46, No.9, pp. 3018-3026, 2020. https://doi.org/10.13336/j.1003-6520.hve.20200507023
21. [21] H. Hu, Y. Liu, and H. Rong, “Detection of insulators on power transmission line based on an improved faster region-convolutional neural network,” Algorithms, Vol.15, Issue 3, Article No.83, 2022. https://doi.org/10.3390/a15030083
22. [22] J. Ou, J. Wang, J. Xue et al., “Infrared image target detection of substation electrical equipment using an improved faster R-CNN,” IEEE Trans. on Power Delivery, Vol.38, No.1, pp. 387-396, 2023. https://doi.org/10.1109/TPWRD.2022.3191694
23. [23] C. Dong, K. Zhang, Z. Xie et al., “An improved cascade RCNN detection method for key components and defects of transmission lines,” IET Generation, Transmission & Distribution, Vol.17, No.19, pp. 4277-4292, 2023. https://doi.org/10.1049/gtd2.12948
24. [24] N. Bodla, B. Singh, R. Chellappa, and L. S. Davis, “Soft-NMS—Improving object detection with one line of code,” Proc. of the IEEE Int. Conf. on Computer Vision, pp. 5561-5569, 2017. https://doi.org/10.1109/ICCV.2017.593
25. [25] Q. Wang, Z. Zhang, Q. Chen et al., “Lightweight transmission line fault detection method based on leaner YOLOv7-tiny,” Sensors, Vol.24, No.2, Article No.565, 2024. https://doi.org/10.3390/s24020565
26. [26] 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,” Proc. of the IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 7464-7475, 2023. https://doi.org/10.1109/CVPR52729.2023.00721
27. [27] Z.-y. Xu and X. Tang, “Transmission line insulator defect detection algorithm based on MAP-YOLOv8,” Scientific Reports, Vol.15, No.1, Article No.10288, 2025. https://doi.org/10.1038/s41598-025-92445-3