A Fast Detection Method for Safety States of Power Receiving Device on High-Speed Rail Based on Deep Learning

被引：0
|
作者：
Feng Y. [1 ]
Song T. [2 ]
Qian X. [2 ]
机构：
[1] Electric Business Headquarter, CRRC Qingdao Sifang Rolling Stock Research Institute Co. Ltd., Qingdao, 266000, Shandong
[2] School of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an
来源：
Hsi-An Chiao Tung Ta Hsueh/Journal of Xi'an Jiaotong University | 2019年 / 53卷 / 10期
关键词：
Deep learning; Detection; High speed railway; Pantograph; Safety state;
D O I：
10.7652/xjtuxb201910015
中图分类号：
学科分类号：
摘要：
A fast and accurate method to detect and locate pantographs is proposed to solve the safety problem of railways caused by pantograph missing or serious deformation. The deep learning based method firstly uses 10,000 images captured by the camera in front of the high-speed rail pantograph as training samples to perform offline training and to generate a CNN prediction model. Then the model and the improved YOLOv2 are used to implement online testing to the pantograph through the image captured by the camera. Test results are finally returned by a program and an early warning of phenomenons of pantograph loss or severe deformation is provided. Results show that the proposed method detects the pantograph in real time with a detection speed of 55 frames per second on a CPU platform while the average accurate rate is 93.1%. © 2019, Editorial Office of Journal of Xi'an Jiaotong University. All right reserved.
引用
收藏
页码：109 / 114
页数：5
相关论文
共 18 条
  • [1] Yang D., Qian X., An Arc detection approach for pantograph of electric locomotive using classification learning, Journal of Xi'an Jiaotong University, 51, 2, pp. 79-83, (2017)
  • [2] Yuan H., Lin J., Li Y., Image processing based pantograph arc object extraction, Information & Communication, 159, 3, pp. 36-37, (2016)
  • [3] Ma L., Wang Z., Gao X., Et al., Application of image processing in detecting the pantograph sliding, Electric Drive for Locomotives, 5, pp. 48-52, (2009)
  • [4] Han Z., Liu Z., Zhang G., Et al., Overview of non-contact image detection technology for pantograph-catenary monitoring, Journal of the China Railway Society, 35, 6, pp. 40-47, (2013)
  • [5] Yao L., Xiao J., Pantograph slide cracks detection method based on fuzzy entropy and Hough transform, Journal of the China Railway Society, 35, 5, pp. 58-63, (2014)
  • [6] Pu W., Chen T., Liu B., Et al., Study of pantograph and catenary arc detection system based on ultraviolet light, Instrument Technique and Sensor, 7, pp. 64-67, (2014)
  • [7] Zeng P., Wang J., Deng J., Et al., Image recognition of slide abrasion for locomotive pantograph, Wireless Internet Technology, 7, 4, pp. 104-106, (2016)
  • [8] Zhang H., Luo L., Wang L., Et al., Improved multi-scale wavelet in pantograph slide edge detection, Information Technology, 3, pp. 190-193, (2015)
  • [9] Redmon J., Divvala S., Girshick R., Et al., You only look once: unified, real-time object detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, (2016)
  • [10] Ren S., He K., Girshick R., Et al., Faster R-CNN: towards real-time object detection with region proposal networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 6, pp. 1137-1149, (2016)
12