Detection and Isolation of Switches in Point Clouds of the German Railway Network

In order to obtain an automated system of railway management, it is necessary to automatically detect, isolate and identify all switches in a point cloud which represents the railway. To realize this automated system of detection, a set of pre-processing steps is applied. The system begins by detecting and isolating tracks through application of a mask on each section of the point cloud. Then, it does a denoising through mathematical morphology and a compression in replacing a group of points by their centroid. Finally, it closes tracks holes through extrapolation. After that, the system does a low-level processing to search for all intersections between tracks, and records information on these intersections. Finally, the system builds switches (with intersections) and classifies them (with information). This automated system leads to a successful result of detection and classification, with a success of higher than 95%.