The article presents a vision system for detecting elements of railway track. Four types of fasteners, wooden and concrete sleepers, rails, and turnouts can be recognized by our system. In addition, it is possible to determine the degree of sleeper ballast coverage. Our system is also able to work when the track is moderately covered by snow. We used a Fully Convolutional Neural Network with 8 times upsampling (FCN-8) to detect railway track elements. In order to speed up training and improve performance of the model, a pre-trained deep convolutional neural network developed by Oxford’s Visual Geometry Group (VGG16) was used as a framework for our system. We also verified the invariance of our system to changes in brightness. To do this, we artificially varied the brightness of images. We performed two types of tests. In the first test, we changed the brightness by a constant value for the whole analyzed image. In the second test, we changed the brightness according to a predefined distribution corresponding to Gaussian function.

Railway automatics systems have a significant impact on ensuring an adequate level of safety. Therefore, it is very important to strive to achieve the high reliability of these systems. Modern railway automatics systems commonly use information technologies that enable events logging and self-diagnostics. However, there are no standards in the field of data acquisition mechanisms and their analysis, which results that manufacturers of railway automatics systems apply various solutions in this regard. The problem of unifying diagnostic methods, and the way for data representation and their analysis is very important, as it can significantly facilitate building of modern diagnostic centers. In the paper the Bayesian inference and SNMP technology, as a tool to solve diagnostic and unifying problems, were presented.