Vision-Based Position Deviation Measurement of Rail Corrugation Chord Measuring Points Under Bi-Linear Laser Assistance

Abstract

During the dynamic measurement of chord-based rail corrugation, with the interferences of curve rail and train snaking movement, it is hard to ensure that the measuring points on the rail surface can trace the railhead centerline well the whole time. This introduces the position deviations to the measurement system, and leads to the measurement results cannot reflect the true rail irregularity state. To solve the problem, a position deviation measurement method based on the assistance of bi-linear laser is proposed in this paper. First, by means of three verifications composed of color, dimension and position, the laser stripe regions on railhead are located from original image effectively. Then, by suppressing stripe highlight texture and modifying the traditional Steger algorithm with flexible-widths Gaussian template, we extract the laser stripe centerline accurately, and depict the railhead boundary fast. Last, by locating three chord-based measuring points and calculating the distances from them to the railhead centerline, we obtain the position deviations of each point. The efficiency and superiority of proposed method are verified by vast experiments. The results show that the accuracy of the position deviation of the chord-based measuring points is limited within 0.4mm.

Keywords

• Bi-linear laser assistance
• chord-based method
• vision-based measurement
• position deviation
• rail corrugation