Pixel-level automatic detection and quantification of running bands on rail surfaces

Abstract

The running band on the rail surface serves as a crucial indicator of the wheel-rail contact relationship, making quantitative detection of the running band vital for railroad inspection and maintenance. However, current rail running band detection methods remain manual, and leveraging state-of-the-art deep learning technology can significantly enhance detection efficiency and minimize the reliance on human labor. This paper presents an improved version of ShuttleNet, called ShuttleNetM2T, for rail surface running band detection, emphasizing high stability. Efficient self-attention in ShuttleNetM2T captures global information, maintaining efficiency and rectifying issues like misrecognition and incomplete edges. Experimental results show ShuttleNetM2T achieves 0.9823 average F-measure and 0.9653 average Intersection-Over-Union on test images. For automatic running band width detection, we propose a pixel-to-physical distance conversion-based calculation, yielding just 0.625% relative error. Overall, the findings in this paper facilitate accurate detection and automatic calculation of the running band width, with promising applications in intelligent rail surface detection.