An Automatic Visual Monitoring System for Expansion Displacement of Switch Rail

Expansion displacement of switch rail is very important for the comfort and safety of the high-speed railway. For safety considerations, it is reasonable to take a noncontact measurement to monitor it online. The visual measurement method is suitable for the monitoring system of high-speed railway infrastructure. However, it is a big challenge to monitor such displacement in a visual system because of uneven illumination, low light, camera shake, and the constrained data acquisition condition in all-weather. In this paper, an Automatic Visual Monitoring System for Expansion Displacement of Switch Rail (AVMS-EDSR) is presented. First, AVMS-EDSR captures switch rail images through an image acquisition and transportation system. Then, a novel Spatial Support Convolutional Neural Networks (SSCNN) is proposed for ruler detection in switch rail images. At last, AVMS-EDSR outputs expansion displacement by Automatic Interpretation Method (AIM), which is faster and more precise than manual interpretation. Experimental results demonstrate that AVMS-EDSR can automatically monitor the expansion displacement of switch rail, report abnormal results, and interpret the ruler of the switch rail image in 1 s with the average difference less than 1 mm at a distance of 5 m, which can meet the requirement for real-time automatic monitoring of expansion displacement of switch rail.

[1]  Yuning Jiang,et al.  UnitBox: An Advanced Object Detection Network , 2016, ACM Multimedia.

[2]  Alexei A. Efros,et al.  Improving Spatial Support for Objects via Multiple Segmentations , 2007, BMVC.

[3]  Daniel T. Larose,et al.  Discovering Knowledge in Data: An Introduction to Data Mining , 2005 .

[4]  Ye Han,et al.  A CNN-Based Defect Inspection Method for Catenary Split Pins in High-Speed Railway , 2019, IEEE Transactions on Instrumentation and Measurement.

[5]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[6]  Agustin Sanchez-Lavega,et al.  Limb clouds and dust on Mars from images obtained by the Visual Monitoring Camera (VMC) onboard Mars Express , 2018 .

[7]  Qingyong Li,et al.  A Real-Time Visual Inspection System for Discrete Surface Defects of Rail Heads , 2012, IEEE Transactions on Instrumentation and Measurement.

[8]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  P. A. Gorry.  General least-squares smoothing and differentiation by the convolution (Savitzky-Golay) method , 1990 .

[10]  Shibin Gao,et al.  Deep Architecture for High-Speed Railway Insulator Surface Defect Detection: Denoising Autoencoder With Multitask Learning , 2019, IEEE Transactions on Instrumentation and Measurement.

[11]  Yi Li,et al.  R-FCN: Object Detection via Region-based Fully Convolutional Networks , 2016, NIPS.

[12]  Swarna Ramesh,et al.  Automatic interpretation of analog dials in driver's instrumentation panel , 2017, 2017 Third International Conference on Advances in Electrical, Electronics, Information, Communication and Bio-Informatics (AEEICB).

[13]  Xinlei Chen,et al.  Spatial Memory for Context Reasoning in Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[14]  Zainab Harbi,et al.  Automatic interpretation of clock drawings for computerised assessment of dementia , 2017 .

[15]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[16]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[17]  Nima Tajbakhsh,et al.  Automatic Interpretation of Carotid Intima-Media Thickness Videos Using Convolutional Neural Networks , 2017, Deep Learning for Medical Image Analysis.

[18]  A. Li Na Zhang,et al.  Development and validation of a visual image analysis for monitoring the body size of sheep , 2018 .

[19]  Jing Xiao,et al.  Detection Evolution with Multi-order Contextual Co-occurrence , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[21]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Michael J. Black,et al.  Occlusion Boundary Detection via Deep Exploration of Context , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.