电力设备的红外图像故障区域分割方法  

Infrared image fault region segmentation method for electric power equipment

作　　者：席琳 高强[1] 李栋[1] XI Lin;GAO Qiang;LI Dong(Tianjin Key Laboratory for Control Theory&Applications in Complicated Systems,Tianjin University of Technology,Tianjin 300384,China;School of Electrical Engineering and Automation,Tianjin University of Technology,Tianjin 300384,China)

机构地区：[1]天津理工大学天津市复杂系统控制理论与应用重点实验室,天津300384 [2]天津理工大学电气工程与自动化学院,天津300384

出　　处：《天津理工大学学报》2024年第3期97-103,共7页Journal of Tianjin University of Technology

基　　金：天津市教委科研计划项目(2018KJ133)。

摘　　要：电力设备故障红外图像区域分割是电力设备故障处理与分析的基础步骤。针对区域生长法分割适应性弱,导致分割准确性低的问题,文中提出以温度最高点为种子点,并且引入类间方差函数对生长阈值进行优选的改进区域生长方法,有效提高故障区域分割的准确性。通过改进方法与其他方法的对比实验,结果表明:文中所提出的方法准确率高于传统方法23.94%。所提出的改进区域生长法有效提高了电力设备的红外图像故障区域分割准确性。Infrared image region segmentation of power equipment fault is the basic step of electric power equipment fault treatment and analysis.Aiming at the problem of low segmentation accuracy caused by weak adaptability of region growing method,this paper proposes an improved region growing method,which takes the highest temperature point as the seed point and introduces inter-class variance function to optimize the growth threshold,so as to effectively improve the segmentation accuracy of fault region.By comparing the improved method with other methods,the results show that the accuracy of the proposed method is 23.94%higher than that of the traditional method.The improved region growing method proposed in this paper improves the accuracy of fault region segmentation in infrared images of electric power equipment.

关 键 词：信息处理 图像分割 区域生长 电力设备 红外图像 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]