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.