Insulator Defect Detection Based on Lightweight Network and Enhanced Multi-scale Feature Fusion

被引：0
|
作者：
Chen K. [1 ]
Liu X. [1 ]
Jia L. [1 ]
Fang Y. [1 ]
Zhao C. [2 ]
机构：
[1] School of Electrical Engineering, China University of Mining and Technology, Xuzhou
[2] Xuzhou Power Supply Company, State Grid Jiangsu Electric Power Co., Ltd., Xuzhou
来源：
Gaodianya Jishu/High Voltage Engineering | 2024年 / 50卷 / 03期
关键词：
insulator defect detection; lightweight; ShuffleNetV2; network; small target detection; UAV; YOLOv5;
D O I：
10.13336/j.1003-6520.hve.20221652
中图分类号：
学科分类号：
摘要：
With the development of target detection algorithm embedded in UAV for insulator inspection of transmission towers, a YOLOv5-3S-4PH model based on lightweight network and enhanced multi-scale feature fusion is proposed to detect insulator defects in real time in view of the low detection speed, high network complexity and the difficulty of accurate detection of small defect targets. Firstly, the reconstructed ShuffleNetV2-Stem-SPP(3S) network is used as the backbone of YOLOv5, which reduces the amount of network parameters and calculation significantly. Secondly, the enhanced multi-scale feature fusion network for small targets and four prediction heads(4PH) is added to enhance the network’s perception of insulator defects. Combined with Mosaic-9 data enhancement and CIoU loss function, the loss of detection accuracy caused by lightweight is further compensated. Finally, the YOLOv5-3S-4PH model is applied to the self-made insulator dataset for verification. The experimental results show that mean average precision(mAP) is increased by 3%, the detection speed is increased by 81.8%, and parameters and calculation are decreased by 82.4% and 67% compared to original YOLOv5 model. Therefore, the proposed model is more suitable for real-time monitoring of insulator defects deployed on UAV platforms. © 2024 Science Press. All rights reserved.
引用
下载
收藏
页码：1289 / 1301
页数：12
相关论文
共 27 条
  • [1] ZHAI Yongjie, WANG Di, ZHAO Zhenbing, Et al., Insulator string location method based on spatial configuration consistency feature, Proceedings of the CSEE, 37, 5, pp. 1568-1577, (2017)
  • [2] GIRSHICK R, DONAHUE J, DARRELL T, Et al., Rich feature hierarchies for accurate object detection and semantic segmentation, Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, (2014)
  • [3] GIRSHICK R., Fast R-CNN, Proceedings of 2015 IEEE International Conference on Computer Vision, pp. 1440-1448, (2015)
  • [4] REN S Q, HE K M, GIRSHICK R, Et al., Faster R-CNN: towards real-time object detection with region proposal networks, Proceedings of the 28th International Conference on Neural Information Processing Systems, pp. 91-99, (2015)
  • [5] ZHANG Ye, GAO Yuhan, HUANG Xinbo, Et al., Fault identification and evaluation of tower wading in 110~220 kV transmission line with fine mask RCNN, Power System Technology, 46, 6, pp. 2132-2140, (2022)
  • [6] XU Xiaobing, YUAN Jing, LIAO Yanqun, Et al., Autonomous diagnosis method for defects of cable accessories based on faster RCNN and mean-shift algorithm by infrared images, High Voltage Engineering, 46, 9, pp. 3070-3079, (2020)
  • [7] GUO Lei, WANG Qiulong, XUE Wei, Et al., A small object detection algorithm based on improved YOLOv5, Journal of University of Electronic Science and Technology of China, 51, 2, pp. 251-258, (2022)
  • [8] IEAMSAARD J, CHAROENSOOK S N, YAMMEN S., Deep learning-based face mask detection using YoloV5, Proceedings of 2021 9th International Electrical Engineering Congress (iEECON), pp. 428-431, (2021)
  • [9] LI Bin, LI Yalin, ZHU Xinshan, Et al., Multi-target detection in substation scence based on attention mechanism and feature balance, Power System Technology, 46, 6, pp. 2122-2131, (2022)
  • [10] HAO Shuai, MA Ruize, ZHAO Xinsheng, Et al., Fault detection of YOLOv3 transmission line based on convolutional block attention model, Power System Technology, 45, 8, pp. 2979-2987, (2021)
123