[1] Li K, Yuan Z, Li J D. Key technology of UAV power line safety inspection[J]. China High and New Technology, 48-49(2022).

[2] Wang S Z, Zhao L, Shao M W et al. Insulator identification method of transmission line based on improved YOLOv5[J]. Electronic Measurement Technology, 45, 181-188(2022).

[3] Zhang S P, Yang Z, Huang X N et al. Defects detection and positioning for glass insulator from aerial images[J]. Journal of Terahertz Science and Electronic Information Technology, 11, 609-613(2013).

[4] Zhang H Y, Zhang G C, Qin Z Y. Application and analysis of UAV power autonomous inspection technology[J]. Rural Electrification, 51-53(2022).

[5] Song L Y, Liu S, Wang K et al. Identification method of power grid components and defects based on improved Efficient Det[J]. Transactions of China Electrotechnical Society, 37, 2241-2251(2022).

[6] Jiang B, Qu R K, Li Y D et al. Object detection in UAV imagery based on deep learning: review[J]. Acta Aeronautica et Astronautica Sinica, 42, 524519(2021).

[7] Redmon J, Divvala S, Girshick R et al. You only look once: unified, real-time object detection[C], 779-788(2016).

[8] Redmon J, Farhadi A. YOLO9000: better, faster, stronger[C], 6517-6525(2017).

[9] Redmon J, Farhadi A. YOLOv3: an incremental imp-rovement[EB/OL]. http://export.arxiv.org/abs/1804.02767

[10] Liu W, Anguelov D, Erhan D et al. SSD: single shot MultiBox detector[M]. Leibe B, Matas J, Sebe N, et al. Computer Vision-ECCV 2016. Lecture notes in computer science, 9905, 21-37(2016).

[11] Zheng W, Yang X H, Lü Z B et al. Real-time inspection model for key components of transmission lines based on improved YOLOv4[J]. Science Technology and Engineering, 21, 10393-10400(2021).

[12] Wang C S, Li W X, Zheng W L et al. An improved SSD method for power component identification of transmission lines[J]. Applied Science and Technology, 47, 75-81(2020).

[13] Girshick R, Donahue J, Darrell T et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C], 580-587(2014).

[14] Girshick R. Fast R-CNN[C], 1440-1448(2016).

[15] Ren S Q, He K M, Girshick R et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149(2017).

[16] Huang W Q, Zhang F Z, Li P et al. Exploration and application on faster R-CNN based insulator recognition[J]. Southern Power System Technology, 12, 22-27(2018).

[17] Cheng H Y, Zhai Y J, Chen R. Faster R-CNN based recognition of insulators in aerial images[J]. Modern Electronics Technique, 42, 98-102(2019).

[18] Ju M R, Luo H B, Wang Z B et al. Improved YOLO V3 algorithm and its application in small target detection[J]. Acta Optica Sinica, 39, 0715004(2019).

[19] Liu Z, Mao H Z, Wu C Y et al. A ConvNet for the 2020s[C], 11966-11976(2022).

[20] Hou Q B, Zhou D Q, Feng J S. Coordinate attention for efficient mobile network design[C], 13708-13717(2021).

[21] 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]. https://arxiv.org/abs/2207.02696