Fully automated extraction of railtop centerline from mobile laser scanning data

Digitization is an important part of efficient infrastructure maintenance. Means to achieve a digital asset database include precise 3D surveys of the physical assets and advanced automated recognition of objects of interest for documenting, maintenance and further analysis purposes. To this end, fast data collection of railway infrastructure environments can be obtained using a mobile laser scanner mounted on a service locomotive, permitting uninterruptive service. This paper presents an algorithm that extracts the railtop centerlines of up to seven parallel tracks with a single measurement pass and achieves an accuracy of 0.3 cm to 0.8 cm on non-intersecting rails, which improves the state of the art by 55%–85%. On intersecting rails, the railtop location accuracy is comparable to that of existing methods. The proposed method uses only geometric data and performs in real time in two-track railroad configurations. • Centimeter scale of rail width raises digitization accuracy requirements. • Locomotive-mounted mobile laser scanner permits uninterruptive data collection. • Local profile fitting enables sub-centimeter accuracy in rail modeling. • Guiding track centerline estimate aids runtime performance.