计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (6A): 250600110-7.doi: 10.11896/jsjkx.250600110

• 图像处理&多媒体技术 • 上一篇    下一篇

基于多尺度特征融合注意力与跨层聚合的输电线路金具缺陷检测

陈典龙1, 刘腾彬1, 高雄1, 田子坚1, 朱文兵1, 邹顺1, 王强2   

  1. 1 中国长江电力股份有限公司 湖北 宜昌 443002
    2 浙江大华系统工程有限公司 杭州 310000
  • 出版日期:2026-06-16 发布日期:2026-06-12
  • 通讯作者: 王强(18106517351@163.com)
  • 作者简介:(chen_dianlong@ctg.com.cn)
  • 基金资助:
    中国长江电力股份有限公司资助项目(Z532302050)

Defect Detection of Transmission Line Fittings Based on Multiscale Feature Fusion Attention and Cross-layer Aggregation

CHEN Dianlong1, LIU Tengbin1, GAO Xiong1, TIAN Zijian1, ZHU Wenbing1, ZOU Shun1, WANG Qiang2   

  1. 1 China Yangtze Power Co.,Ltd.,Yichang,Hubei 443002,China
    2 Zhejiang DAHUA Technology Co.,Ltd.,Hangzhou 310000,China
  • Published:2026-06-16 Online:2026-06-12
  • About author:CHEN Dianlong,born in 1990,bachelor,senior engineer.His main research interest is the operation,maintenance,and technical management of hydroelectric generator units.
    WANG Qiang,born in 1985,master,senior engineer.His main research interests include human-machine and environmental engineering,and machine vision.
  • Supported by:
    China Yangtze Power Co.,Ltd.(Z532302050).

PDF (PC)

32

摘要： 在You Only Look Once(YOLO)系列模型通用框架基础上提出了一种基于多尺度特征融合注意力与跨层聚合的输电线路金具缺陷检测方法。针对输电线路金具在复杂环境下缺陷检测精度不高的问题,在网络的特征提取部分引入了多尺度双分支注意力(MDA)机制,用于捕捉多尺度特征跨维度的交互关系,构建维度间的长距离依赖关系,有效提高检测性能。同时,针对特征传输过程细节易丢失的问题,提出了跨层聚合模块(CLA),通过将骨干网络的多级特征层与检测颈部的多级检测层进行跨层聚合,保留了特征传输过程中可能丢失的多级细粒度信息。相较于其他先进的目标检测模型,所提方法在真实输电线路金具缺陷数据集上取得了较高的检测精度,特别是在小目标缺陷检测和复杂背景抑制方面表现优异,展示了其在输电线路维护中的实际应用价值。

关键词: 输电线路金具, 缺陷检测, 多尺度特征, YOLO, 注意力机制, 特征融合

Abstract: This paper proposes a transmission line fitting defect detection method based on multiscale feature fusion attention and cross-layer aggregation,built upon the general framework ofthe YOLO series model.To address the issue of low detection accuracy of transmission line fittings in complex environments,a Multiscale Dual-branch Attention(MDA) mechanism is introduced into the feature extraction part of the network.This mechanism captures cross-dimensional interactions of multiscale features,establishing long-term dependencies between dimensions,thereby significantly improving detection performance.Additionally,to mitigate the loss of detail during feature transfer,a Cross-Layer Aggregation(CLA) module is proposed.This module aggregates multilevel feature layers from the backbone network with multilevel detection layers in the detection neck,preserving fine-grained information that might be lost during feature transmission.Compared to other state-of-the-art object detection models,the proposed method achieves higher detection accuracy on real-world transmission line fitting defect datasets,particularly excelling in small target defect detection and background noise suppression,demonstrating its practical value in transmission line maintenance.

Key words: Transmission line fittings, Defect detection, Multiscale features, YOLO, Attention mechanism, Feature fusion

中图分类号: 

  • TP391.4
[1] SHI Q,LIU Y W,FANG Y H,et al.Interpretation of the New Edition of “Code of Condition-Based Maintenance & Test for Electric Equipment”[J].Modern Electric Power,2022,39(5):623-630.
[2] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenetclassification with deep convolutional neural networks[J].Advances in Neural Information Processing Systems,2012,25.
[3] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unified,real-time object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2016:779-788.
[4] REN S,HE K,GIRSHICK R,et al.Faster r-cnn:Towards real-time object detection with region proposal networks[J].Advances in Neural Information Processing Systems,2015,28.
[5] LIU W,ANGUELOV D,ERHAN D,et al.Ssd:Single shotmultibox detector[C]//European Conference on Computer Vision(ECCV).2016:21-37.
[6] CHEN Z,CHEN K,LIN W,et al.Piou loss:Towards accurate oriented object detection in complex environments[C]//European Conference on Computer Vision(ECCV).2020:195-211.
[7] SONG Z W,HUANG X B,JI C,et al.Transmission Line Connection Fittings and Corrosion Detection MethodBased on PCSA-YOLOv7 Former[J].Electric Power,2024,57(6):141-152.
[8] LIU Z,LIN Y,CAO Y,et al.Swin transformer:Hierarchical vision transformer using shifted windows[C]//IEEE International Conference on Computer Vision(ICCV).2021:10012-10022.
[9] LIU L L,WAN X D,WANG Z G,et al.Transmission line defect detection method based on super-resolution reconstruction and multi-scale feature fusion[J].Journal of Electronic Measurement and Instrumentation,2023,37(1):130-139.
[10] LI L R,CHEN P,ZHANG Y L,et al.Insulator Defect Detection Based on Multi-Scale Feature Coding and Dual Attention Fusion [J].Laser & Optoelectronics Progress,2022,59(24):73-82.
[11] ZHAO Z B,WANG F F,LIU L S,et al.Transmission line image fitting detection method based on attention feature fusion YOLOv5 model [J].Electrical Measurement & Instrumentation,2023,60(3):145-152.
[12] YE F,LUO X Z,SONG Y C.Research on defect inspection of power small fittings based on improved R-CNN and double feature fusion[J].Journal of Electronic Measurement and Instrumentation,2023,37(7):213-220.
[13] LI B,QU L Y,ZHU X S,et al.Insulator Defect Detection Based on Multi-Scale Feature Fusion [J].Transactions of China Electrotechnical Society,2023,38(1):60-70.
[14] WU C M,WANG D J.Study on Defect Algorithm of Transmission Lines in Complex Background [J].Computer Science,2024,51(S1):547-552.
[15] HAO R,WANG H J,LI T R.Deep Neural Network Model forTransmission Line Defect Detection Based on Dual-branch Sequential Mixed Attention [J].Computer Science,2024,51(3):135-140.
[16] LU X,GAO C,JIANG C L,et al.Research on Bolt Defect Detection Based on Dual-attention Mechanism and Cascade Detection Framework[J].Machinery & Electronics,2024,42(1):63-70.
[17] LI G,CAI Z H,SUN H X,et al.Research on defect detection of transmission line fittings based on improved YOLOv8 and semantic knowledge fusion[J].Journal of Graphics,2024,45(5):979-986.
[18] TAN M,PANG R,LE Q V.Efficientdet:Scalable and efficient object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2020:10781-10790.
[19] LI C,LI L,JIANG H,et al.YOLOv6:A single-stage object detection framework for industrial applications[J].arXiv:2209.02976,2022.
[20] HOU Q,ZHOU D,FENG J.Coordinate attention for efficientmobile network design[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2021:13713-13722.
[21] WOO S,PARK J,LEE J Y,et al.Cbam:Convolutional block attention module[C]//European Conference on Computer Vision(ECCV).2018:3-19.
[22] PTL-AI Furnas Dataset:A Public Dataset for Fault Detection in Power Transmission Lines Using Aerial Images[DB/OL].https://github.com/freds0/PTL-AI_Furnas_Dataset.
[23] VIEIRA E S,ANDRE L B,et al.Insplad:A dataset and benchmark for power line asset inspection in uav images[J].International Journal of Remote Sensing,2023,44(23):7294-7320.
[24] SIMOES F,KOWERKO D,SCHLOSSER T,et al.Attentionmodules improve image-level anomaly detection for industrial inspection:A differnet case study[C]//IEEE/CVF Winter Conference on Applications of Computer Vision(WACV).2024:8246-8255.
[25] WANG C Y,YEH I H,MARK L H Y.Yolov9:Learning what you want to learn using programmable gradient information[C]//European Conference on Computer Vision(ECCV).2024:1-21.
[26] CARION N,MASSA F,SYNNAEVE G,et al.End-to-end object detection with transformers[C]//European Conference on Computer Vision(ECCV).2020:213-229.
[27] WANG Q,WU B,ZHU P,et al.ECA-Net:Efficient channel attention for deep convolutional neural networks[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2020:11534-11542.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发