An Accurate and Real-time Method of Self-blast Glass Insulator Location Based on Faster R-CNN and U-net with Aerial Images

作     者：Zenan Ling Dongxia Zhang Robert C.Qiu Zhijian Jin Yuhang Zhang Xing He Haichun Liu Zenan Ling;Dongxia Zhang;Robert C.Qiu;Zhijian Jin;Yuhang Zhang;Xing He;Haichun Liu

作者机构：Department of Electrical EngineeringCenter for Big Data and Artificial IntelligenceState Energy Smart Grid Research and Development CenterShanghai Jiao Tong UniversityShanghai 200240China China Electric Power Research InstituteBeijing 100192China Department of Electrical and Computer EngineeringTennessee Technological UniversityCookevilleTN 38505USA 

出 版 物：《CSEE Journal of Power and Energy Systems》 (中国电机工程学会电力与能源系统学报（英文）)

年 卷 期：2019年第5卷第4期

页      面：474-482页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work was supported in part by the National Natural Science Foundation of China(No.61571296) the National Science Foundation of USA(No.CNS-1619250) 

主　　题：Aerial images deep learning faster R-CNN insulators location real-time U-net 

摘      要：This paper proposes a new deep learning framework for the location of broken insulators(in particular the self-blast glass insulator)in aerial *** address the broken insulators location problem in a low signal-noise-ratio(SNR)*** deal with two modules:1)object detection based on Faster R-CNN,and 2)classification of pixels based on *** the first time,our paper combines the above two *** combination is motivated as follows:Faster R-CNN is used to improve SNR,while the U-net is used for classification of pixels.A diverse aerial image set measured by a power grid in China is tested to validate the proposed ***,a comparison is made among different methods and the result shows that our approach is accurate in real time.