Abstract
We propose a machine vision system for the inspection of the railway track condition. Key stages of an algorithm for detecting gauge marks that serve to identify mechanical stresses of a continuous welded rail track are described. In the final section of the article, we discuss some peculiarities found in real exploitation conditions: effects of the rail surface defects on the algorithm performance and false detection of railway infrastructure elements similar to gauge marks.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have