Detection of Power Devices and Abnormal Objects in Transmission Lines Based on Improved CenterNet

被引：0
|
作者：
Li L. [1 ]
Chen P. [1 ]
Zhang Y. [1 ]
Mei B. [1 ]
Gong P. [2 ]
Yu H. [3 ]
机构：
[1] Hubei Engineering Research Center for Safety Monitoring of New Energy and Power Grid Equipment, Hubei University of Technology, Wuhan
[2] School of Computer Science and Engineering, Wuhan University of Technology, Wuhan
[3] State Grid Hubei Power Transmission and Transformation Engineering Co., Ltd., Wuhan
来源：
Gaodianya Jishu/High Voltage Engineering | 2023年 / 49卷 / 11期
基金：
中国国家自然科学基金;
关键词：
attention feature fusion; CenterNet; deep learning; feature enhancement; light-weighting; power inspection;
D O I：
10.13336/j.1003-6520.hve.20221672
中图分类号：
学科分类号：
摘要：
In order to realize fast and accurate detection of components and abnormal targets in power lines, a target detection algorithm based on the improved CenterNet is proposed. Firstly, the lightweight MobileNetV2 was used as the feature extraction network for CenterNet, and the number of channels in the decoding network was reduced, so as to improve the detection speed. Secondly, a multi-channel feature enhancement structure was constructed and the low-level detailed information was introduced to solve the problem of low detection accuracy caused by CenterNet only utilizing a single feature. Thirdly, an equal-scale residual attention feature fusion module was designed to replace the fusion method of directly adding features during the upsampling process, in order to fit the same level features from different branches. Finally, the elliptical Gaussian scattering kernel was introduced to optimize label encoding and improve the quality of bounding box regression. Experiments were conducted on the improved CenterNet algorithm. The results show that the algorithm achieves an average accuracy of 96% on the constructed dataset, a forward inference speed of 13 ms/frame, and a model parameter size of approximately 5.9 MB. All indicators are superior to mainstream detection algorithms such as FCOS and YOLOX. The combination of this method with drones can provide reference for intelligent inspection of power grids. © 2023 Science Press. All rights reserved.
引用
收藏
页码：4757 / 4768
页数：11
相关论文
共 24 条
  • [1] LIU Kaipei, LI Boqiang, QIN Liang, Et al., Review of application research of deep learning object detection algorithms in insulator defect detection of overhead transmission lines, High Voltage Engineering, 49, 9, pp. 3584-3595, (2023)
  • [2] LI Lirong, ZHANG Yunliang, CHEN Peng, Et al., Detection method of insulator breakage based on context augmentation and feature refinement, High Voltage Engineering, 49, 8, pp. 3405-3414, (2023)
  • [3] WU X W, SAHOO D, HOI S C H., Recent advances in deep learning for object detection[J], Neurocomputing, 396, pp. 39-64, (2020)
  • [4] LI F, XIN J B, CHEN T, Et al., An automatic detection method of bird’s nest on transmission line tower based on faster_RCNN[J], IEEE Access, 8, pp. 164214-164221, (2020)
  • [5] 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, 6, pp. 1137-1149, (2017)
  • [6] YAN Hongwen, CHEN Jinxin, Insulator string positioning and state recognition method based on improved YOLOv3 algorithm, High Voltage Engineering, 46, 2, pp. 423-431, (2020)
  • [7] REDMON J, FARHADI A., YOLOv3:an incremental improvement
  • [8] ZHOU X Y, WANG D Q, KRAHENBUHL P., Objects as points
  • [9] GE Z, LIU S T, WANG F, Et al., YOLOX:exceeding YOLO series in 2021
  • [10] TIAN Z, SHEN C H, CHEN H, Et al., FCOS:fully convolutional one-stage object detection, Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, pp. 9626-9635, (2019)
123