赵锴,李继东,黄佳,郑静媛,张淞杰
ZHAO Kai,LI Jidong,HUANG Jia,ZHENG Jingyuan,ZHANG Songjie

• 1:国网北京市电力公司
• 2:浙江大学电气学院

摘要(Abstract)：

绝大部分的配电网线路故障都是架空线路故障,而鸟害一直是导致架空线路故障高发的主要原因,仅次于雷害与外力破坏。并且由于输电线路人工巡检成本较大,电网公司缺乏有效的应对措施。近年来,随着深度学习技术的不断发展,基于深度学习方法的目标检测与定位识别技术已经达到不错的效果,并开始大规模应用于产业。因此提出了一种基于Cascade R-CNN的配电网鸟巢检测方法,实验结果证明,该方法可以为配电网提供一种相对稳定、高效的鸟巢检测结果。
Of the distribution line faults, the best part occurs on overhead lines. Bird damage, only second to lightning strike and external damage, is a major reason for overhead line fault. Given the high cost of manual inspection on transmission lines, power grid enterprises lack effective solutions. With the continuous development of deep learning technologies in recent years, object detection and location recognition based on deep learning methods have excellent performance and have been applied in the industry. This paper proposes a method for bird nest detection on distribution networks based on Cascade R-CNN. The experiment results show that the method can provide a stable and efficient bird nest detection on the distribution network.

关键词(KeyWords)： 配电网;鸟巢检测;深度学习;目标检测;卷积神经网络
distribution network;bird nest detection;deep learning;object detection;convolutional neural network

Abstract:

Keywords:

基金项目(Foundation): 国家电网有限公司科技项目(52020518005F)

作者(Author): 赵锴,李继东,黄佳,郑静媛,张淞杰
ZHAO Kai,LI Jidong,HUANG Jia,ZHENG Jingyuan,ZHANG Songjie

DOI: 10.19585/j.zjdl.202103011

参考文献(References)：

• [1]李天友,金文龙,徐丙垠.配电技术[M].北京：中国电力出版社,2008.
• [2]马士聪,高厚磊,徐丙垠,等.配电网故障定位技术综述[J].电力系统保护与控制,2009,37(11):119-124.
• [3]刘若溪,吴迪,任健聪,等.架空配电网鸟害现状分析与预防措施研究[J].电气应用,2015,34(增刊1):32-35.
• [4]FRAZIER S D.Birds,Substations,and transmission[C]//2001IEEE Power Engineering Society Winter Meeting.Ohio,USA.IEEE,2001:355-358.
• [5]郭伟跃.美国输电线路和变电站电气设备防鸟害措施[J].中国电力,2006,39(8):82-84.
• [6]王桢.基于视频图像处理技术的输电线路杆塔鸟巢识别[D].北京：华北电力大学,2013.
• [7]段旺旺,唐鹏,金炜东,等.基于关键区域HOG特征的铁路接触网鸟巢检测[J].中国铁路,2015(8):73-77.
• [8]WU X,YUAN P,PENG Q,et al.Detection of bird nests in overhead catenary system images for high-speed rail[J].Pattern Recognition,2016,51:242-254.
• [9]徐晶,韩军,童志刚,等.一种无人机图像的铁塔上鸟巢检测方法[J].计算机工程与应用,2017,53(6):231-235.
• [10]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition(ICCV).Columbus,Ohio,USA.IEEE,2014:580-587.
• [11]HE K,ZHANG X,REN S,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE transactions on pattern analysis and machine intelligence,2015,37(9):1904-1916.
• [12]GIRSHICK R.Fast r-cnn[C]//Proceedings of the IEEE international conference on computer vision(ICCV).Santiago,Chile:IEEE,2015:1440-1448.
• [13]REN S,HE K,GIRSHICK R,et al.Faster r-cnn:Towards real-time object detection with region proposal networks[C]//Advances in neural information processing systems.IEEE,2015:91-99.
• [14]LOWE D G.Distinctive image features from scale-invariant keypoints[J].International journal of computer vision,2004,60(2):91-110.
• [15]DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//Proceedings of International Conference on Computer Vision&Pattern Recognition(CVPR).San Diego,US. IEEE,2005:886-893.
• [16]OSUNA E,FREUND R,GIROSIT F.Training support vector machines:an application to face detection[C]//Proceedings of IEEE computer society conference on computer vision and pattern recognition.San Juan,USA.IEEE,1997:130-136.
• [17]HUANG G B,ZHU Q Y,SIEW C K.Extreme learning machine:Theory and applications[J].Neurocomputing,2006,70(1):489-501.
• [18]周自强,纪扬,苏烨,等.基于迁移学习卷积神经网络的电缆隧道锈蚀识别算法[J].中国电力,2019,52(4):104-110.