Machine Vision for Automating Visual Condition Monitoring of Railway Sleepers

S. Yella (Sweden, UK), M. Dougherty (Sweden), and N.K. Gupta (UK)


Machine vision, Pattern recognition, Condition monitoring, Railway sleepers, Rail transportation.


This paper summarises the results of using machine vision approach for automating condition monitoring of wooden railway sleepers. Railway sleeper inspections are currently done manually; visual inspection being the most common approach, with some deeper examination using an axe to judge the condition. Digital images of the sleepers were acquired to compensate for the human visual capabilities. Appropriate image analysis techniques were applied to further process the images and necessary features were extracted. In this particular work, crack detection was focused and features such as, number of cracks, average length of the crack and width of the crack on each sleeper were calculated and used for further pattern recognition task. In the current work, though image analysis techniques reveal important information concerning the condition of the sleeper, it cannot be directly used for classifying the condition. Hence, a pattern recognition approach has been adopted to further classify the condition of the sleeper into classes (good or bad). A Support Vector Machine (SVM) using a Gaussian kernel has achieved good classification rate (82.35%) in the current case.

Important Links:

Go Back