Computer vision for hunting stability inspection of high-speed trains

Abstract

The existing online inspection methods for hunting motion of high-speed trains are mainly based on processing the acceleration of bogie frames, which cannot directly and reliably reflect the safety conditions. This paper proposes a novel computer vision (CV) method, named the virtual point tracking (VPT) method, to detect the hunting motion by processing the dynamic wheel-rail contact video. First, some virtual points are defined on each frame of the captured video, then the coordinates of these virtual points are automatically located by a deep learning model, and finally, the relative displacement between these coordinates is calculated. Two experiments demonstrate that the VPT method can accurately determine the hunting frequency and detect changes in the pixel coordinates corresponding to key positions of the wheel and the rail. Besides, a VPT method with Canny edge detection is introduced for comparison, and the results demonstrate that the VPT method is superior.