尤振飞,位一鸣,俞兴伟,宣科,邬凌云,王爱玉,张悦
YOU Zhenfei,WEI Yiming,YU Xingwei,XUAN Ke,WU Lingyun,WANG Aiyu,ZHANG Yue

• 1:国网浙江省电力有限公司舟山供电公司

摘要(Abstract)：

随着无人机成为电力巡检的重要方式，基于机器视觉技术的无人机图像分析方法可为电杆倾斜检测及风险评估提供辅助手段。提出一种基于语义分割与证据理论的电杆倾斜检测及风险评估方法。基于U-Net和连通区域标记算法的电杆图像分割方法，对图像按照语义类别进行逐像素分类，并利用连通区域标记算法消除非电杆区域。在构建电杆倾斜判据的基础上，提出基于证据理论的电杆倾斜检测方法，利用合成规则将多个判据的结论融合。给出电杆倾斜风险评估方法，并将倾斜等级作为评估结果。实验结果表明所提方法可提高检测的准确性。
Now that UAVs(unmanned aerial vehicles) have been widely used for power inspection, the UAV image analysis method based on computer vision technology can provide auxiliary means for pole tilt detection and risk assessment. This paper proposes a method of pole tilt detection and risk assessment based on semantic segmentation and evidence theory. The pole image segmentation method based on U-Net and connected component labeling algorithm is used to classify the images pixel by pixel according to semantic categories, and non-pole regions are eliminated by using the connected component labeling algorithm. By the construction of pole tilt criterion, a method for pole tilt detection based on evidence theory is proposed to fuse the conclusions of multiple criteria by using synthetic rules. The tilt risk assessment method is given, and the tilt level is taken as the assessment result. The experimental results show that the proposed method can improve detection accuracy.

关键词(KeyWords)： 语义分割;证据理论;形态特征;电杆倾斜;风险评估
semantic segmentation;evidence theory;morphological characteristics;pole tilt;risk assessment

Abstract:

Keywords:

基金项目(Foundation): 国网浙江省电力有限公司群创项目（5211ZS22000C）

作者(Author): 尤振飞,位一鸣,俞兴伟,宣科,邬凌云,王爱玉,张悦
YOU Zhenfei,WEI Yiming,YU Xingwei,XUAN Ke,WU Lingyun,WANG Aiyu,ZHANG Yue

DOI: 10.19585/j.zjdl.202304010

参考文献(References)：

• [1]陈强，王建，熊小伏，等.一种降雨诱发滑坡灾害下输电杆塔的监测与预警方法[J].电力系统保护与控制，2020,48(3):147-155.CHEN Qiang,WANG Jian,XIONG Xiaofu,et al.Monitoring and early warning method for transmission tower under rainfall-induced landslide disaster[J].Power System Protection and Control,2020,48(3):147-155.
• [2]朱凌，陈涛威，周晨，等.考虑风速风向联合分布的大风灾害下电力断线倒塔概率预测[J].电力系统保护与控制，2019,47(2):115-122.ZHU Ling,CHEN Taowei,ZHOU Chen,et al.Probability prediction of transmission line breakage and tower topple over under wind disaster considering the joint distribution of wind speed and wind direction[J].Power System Protection and Control,2019,47(2):115-122.
• [3]舒恺，郭高鹏，张洁，等.基于惯性传感器的电力线路杆塔倾斜监测装置设计[J].计算机测量与控制，2022,30(5):18-23.SHU Kai,GUO Gaopeng,ZHANG Jie,et al. Design of transmission tower inclination monitoring device based on inertial sensor[J]. Computer Measurement&Control,2022,30(5):18-23.
• [4]黄秀超，钟建伟，张建业，等.基于ZigBee技术的输电杆塔倾斜在线监测系统设计[J].现代电子技术，2019,42(5):95-99.HUANG Xiuchao,ZHONG Jianwei,ZHANG Jianye,et al.Design of transmission tower tilt on-line monitoring system based on ZigBee technology[J]. Modern Electronics Technique,2019,42(5):95-99.
• [5]高雪莲，李乐依，刘文琳.基于遥感卫星光学影像的杆塔倾斜在线监测方法[J].中国电机工程学报，2022,42(16):5971-5978.GAO Xuelian,LI Leyi,LIU Wenlin. On-line monitoring method of pole and tower tilt based on remote sensing satellite optical image[J].Proceedings of the CSEE,2022,42(16):5971-5978.
• [6]王学民，徐海奇，刘小寨，等.变电站智能巡检机器人塔杆倾斜识别深度研究[J].自动化与仪器仪表，2020(11):73-76.WANG Xuemin,XU Haiqi,LIU Xiaozhai,et al.Research on depth recognition depth of substation intelligent patrol robot tower[J]. Automation&Instrumentation,2020(11):73-76.
• [7]张春晓，陆志浩，刘相财.智慧变电站联合巡检技术及其应用[J].电力系统保护与控制，2021,49(9):158-164.ZHANG Chunxiao,LU Zhihao,LIU Xiangcai. Joint inspection technology and its application in a smart substation[J]. Power System Protection and Control,2021,49(9):158-164.
• [8]顾晓东，唐丹宏，黄晓华.基于深度学习的电网巡检图像缺陷检测与识别[J].电力系统保护与控制，2021,49(5):91-97.GU Xiaodong,TANG Danhong,HUANG Xiaohua.Deep learning-based defect detection and recognition of a power grid inspection image[J]. Power System Protection and Control,2021,49(5):91-97.
• [9]缪希仁，刘志颖，鄢齐晨.无人机输电线路智能巡检技术综述[J].福州大学学报（自然科学版），2020,48(2):198-209.MIAO Xiren,LIU Zhiying,YAN Qichen. Review on UAV intelligent technology for transmission line inspection[J]. Journal of Fuzhou University(Natural Science Edition),2020,48(2):198-209.
• [10]刘勇，陈海滨，刘方.基建现场巡检无人机智能感知系统的研究与应用[J].电力系统保护与控制，2018,46(15):155-161.LIU Yong,CHEN Haibin,LIU Fang.Research and application of intelligent perception system for unmanned aerial vehicle inspection at construction site[J]. Power System Protection and Control,2018,46(15):155-161.
• [11]史晋涛，李喆，顾超越，等.基于样本扩充的Faster RCNN电网异物监测技术[J].电网技术，2020,44(1):44-51.SHI Jintao,LI Zhe,GU Chaoyue,et al.Research on foreign matter monitoring of power grid with faster R-CNN based on sample expansion[J]. Power System Technology,2020,44(1):44-51.
• [12]缪希仁，林志成，江灏，等.基于深度卷积神经网络的输电线路防鸟刺部件识别与故障检测[J].电网技术，2021,45(1):126-133.MIAO Xiren,LIN Zhicheng,JIANG Hao,et al.Fault detection of power tower anti-bird spurs based on deep convolutional neural network[J].Power System Technology,2021,45(1):126-133.
• [13]陈珂锐，孟小峰.机器学习的可解释性[J].计算机研究与发展，2020,57(9):1971-1986.CHEN Kerui,MENG Xiaofeng.Interpretation and understanding in machine learning[J].Journal of Computer Research and Development,2020,57(9):1971-1986.
• [14] RONNEBERGER O,FISCHER P,BROX T.U-net:convolutional networks for biomedical image segmentation[M].Cham:Springer International Publishing,2015.
• [15]吕常魁，徐岩，罗冰心.基于游程的连通区域标记两次扫描快速算法[J].华南理工大学学报（自然科学版），2017,45(7):84-89.LYU Changkui,XU Yan,LUO Bingxin.A fast Run-based two-pass algorithm for connected components labeling[J].Journal of South China University of Technology(Natural Science Edition),2017,45(7):84-89.
• [16]邢晓敏，徐海瑞，廖孟柯，等.基于云模型和D-S证据理论的配电终端健康状态综合评估方法[J].电力系统保护与控制，2021,49(13):72-81.XING Xiaomin,XU Hairui,LIAO Mengke,et al.Comprehensive evaluation method of distribution terminal units health status based on a cloud model and D-S evidence theory[J].Power System Protection and Control,2021,49(13):72-81.