基于改进的U-Net和YOLOv5的绝缘子掩模获取与缺陷检测  

Insulator Mask Acquisition and Defect Detection Based on Improved U-Net and YOLOv5

作　　者：唐小煜[1,2,3,4] 熊浩良 黄锐珊 林威霖 TANG Xiaoyu;XIONG Haoliang;HUANG Ruishan;LIN Weilin(School of Physics and Telecommunication Engineering,South China Normal University,Guangzhou 510006,China;Guangdong Provincial Key Laboratory of Quantum Engineering and Quantum Materials,Guangzhou 510006,China;Guangdong Provincial Engineering Technology Research Center for Optoelectronic Instrument,Guangzhou 510006,China;National Demonstration Center for Experimental Physics Education,South China Normal University,Guangzhou 510006,China)

机构地区：[1]华南师范大学物理与电信工程学院,广州510006 [2]广东省量子调控工程与材料重点实验室,广州510006 [3]广东省光电检测仪器工程技术研究中心,广州510006 [4]华南师范大学物理国家级实验教学示范中心,广州510006

出　　处：《数据采集与处理》2021年第5期1041-1049,共9页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(61371176)资助项目。

摘　　要：输电线路的绝缘子定期巡检是必不可少的一项任务,而传统的人工巡检存在着效率低、工作强度大等问题。因此,本文设计了一种改进的U-Net模型实现对绝缘子的分割,并使用改进的YOLOv5实现在复杂背景下对爆破绝缘子的定位。本文基于U-Net图像语义分割模型,提出一种改进的网络结构SERes-Unet。模型引入残差结构减少卷积过程中存在的梯度消失、结构信息损耗的影响,引入注意力机制对特征权重进行校正,从而提升网络性能。为实现对高分辨率图像的爆破绝缘子检测,提出将图片进行切割再进行检测,再通过非极大值抑制(Non-maximum suppression,NMS)进行筛选,获取图像全部爆破绝缘子的位置。本文设计的多组实验验证了模型的有效性和高效性。本文方法绝缘子分割精度达到0.96,爆破绝缘子检测精确率达到0.97,召回率达到0.99。Regular inspection of insulators of transmission lines is an indispensable task,while traditional manual inspections have problems such as low efficiency and high work intensity.Therefore,this paper designs an improved U-Net model to realize the segmentation of insulators,and uses an improved YOLOv5 to realize the positioning of blasting insulators in complex backgrounds.Based on the U-Net image semantic segmentation model,this paper proposes an improved network structure SERes-Unet.The model introduces residual structure to reduce the influence of gradient disappearance and structural information loss in the convolution process,and introduces an attention mechanism to correct feature weights,thereby improving network performance.In order to realize the detection of blasting insulators on high-resolution images,it is proposed to cut the pictures and then detect them,and then filter through NonMaximum suppression(NMS)to obtain the positions of all blasting insulators in the image.The article designs multiple sets of experimental controls to verify the effectiveness and efficiency of the model.In the end,the method achieves an insulator segmentation accuracy of 0.96,a blasting insulator detection accuracy of 0.97,and a recall rate of 0.99.

关 键 词：爆破绝缘子 图像语义分割 目标检测 U-Net模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]