Image analysis for detecting the transverse profile of worn-out rails

Over its useful life a railway track is subject tomany mechanical and environmental stresses which graduallylead to its deterioration. Monitoring the wear condition of therailway superstructure is one of the key points to guarantee anadequate safety level of the railway transport system; in thisfield, the use of high-efficiency laser techniques has becomeconsolidated and implemented in diagnostic trains (e.g. the“Archimede train” and the “Talete train” ) which allow to detectthe track geometric parameters (gauge, alignment, longitudinallevel, cross level, superelevation defect, etc.) and the state of railwear (vertical, horizontal, 45-degree etc.) with very highaccuracy. The objective of this paper is to describe a new nonconventionalprocedure for detecting the transverse profile ofworn-out rails by means of image-processing technique. Thismethodological approach is based on the analysis of theinformation contained in high-resolution photographic images ofrails and on specific algorithms which allow to obtain the exactgeometric profile and the measurement of the relevant deviationscompared to new rails of the same typology.The analyses and the first results, obtained from laboratoryresearches, concern rails cross sections taken from railway linesunder upgrading. The procedure has shown high precision in thewear evaluation as well as great rapidity in being performed