文献类型：期刊文献

英文题名：Fast and accurate cable detection using CNN

作者：Dai, Zhiyong[1];Yi, Jianjun[1];Zhang, Yajun[1];Zhou, Bo[1];He, Liang[2,3]

机构：[1]East China Univ Sci & Technol, Sch Mech & Power Engn, Shanghai, Peoples R China;[2]Shanghai Aerosp Control Technol Inst, Shanghai 201109, Peoples R China;[3]Shanghai Key Lab Aerosp Intelligent Control Techn, Shanghai 201109, Peoples R China

年份：2020

卷号：50

期号：12

起止页码：4688

外文期刊名：APPLIED INTELLIGENCE

收录：;EI(收录号：20203209005891);WOS:【SCI-EXPANDED(收录号:WOS:000557090400001)】；

基金：This paper was supported by the Natural Science Fund of China (NSFC) under Grant Nos. 51575186, 51275173, and 50975088, Shanghai Software and IC industry Development Special Fund under Grant No. 180121, and Shanghai Science and Technology Action Plan under Grant No. 18DZ1204000, 18510745500, the Fundamental Research Funds for the Central Universities (50321041918013).

语种：英文

外文关键词：Cable detection; Convolutional neural networks; Deep learning

摘要：In recent years, unmanned aerial vehicle (UAV) based vision inspections have been widely applied in electricity systems for both efficiency improvement and labor cost saving. Cable detection is essential for both navigation and flight safety of aerial vehicles. However, power cable detection is widely regarded as a challenging task since the targets are very weak and very easy to be confused with cluttered backgrounds. Traditional line and edge detectors are lack of robustness to scene variations. Recent deep learning based methods also can not support fast and stable power cable detection well for onboard applications . In this paper, a new convolutional neural network (CNN) based cable detection method is proposed. First of all, we encode cables by groups of evenly distributed key points, which reduce the complexities of detection tasks. By this approach, the proposed model detect grouped key points of cables from aerial images directly and the detailed pixels of cables can be restore with the curve equations which are implicitly behind those grouped key points. Subsequently, new methods of data labeling and augmentation, sample matching, post clustering, and performance evaluation for cable key points detection are presented. Finally, comprehensive experimental results demonstrate the efficiency and accuracy of our proposed cable detection method.