Automated Extraction of 3-D Railway Tracks from Mobile Laser Scanning Point Clouds

Abstract

The demand for automated railway tracks extraction is driven by the importance of maintaining and updating the fundamental geographic data of railway tracks for railway engineering. Mobile laser scanning (MLS), which is a promising technology for the rapid 3-D mapping of railways, provides a good means to capture details along the corridors, including tracks, clearance of overhanging wires, natural obstructions (e.g., trees and rock faces), and tunnel/bridge clearances. This paper presents an automated method to detect tracks from MLS point clouds. Both the geometry and intensity data of railway tracks are utilized to extract track points and to model tracks. Experiments were undertaken to evaluate the validity of the proposed method based on the test dataset captured by Optech’s Lynx Mobile Mapper System, proving it a promising solution to extract 3-D tracks from MLS point clouds.