Keywords: LiDAR, cloud point, random forest, vegetation management, maintenance automation, railway maintenance.

The vegetation near railway catenary wires can have various impacts on both the safety and efficiency of the railway system. If vegetation is too close to the catenary wires, it increases the risk of fire, especially during dry periods. Excessive vegetation near catenary wires can lead to electrical interference. This can disrupt the proper functioning of the railway electrical system, affecting trains’ power supply quality. LiDAR plays a crucial role in the detection and analysis of vegetation. This work leverages LiDAR to identify geographical areas where vegetation is close to the catenaries and thus may pose a risk of damaging them. This information will facilitate organizing maintenance and preventing incidents related to vegetation. The process involves the following steps: Determine, within the point cloud, the wire points corresponding to the contact wire and the vegetation points using a classification algorithm. For each vegetation point, compute a deviation corresponding to the shortest distance between the vegetation point and the nearest wire point. Estimate the number of vegetation points associated with deviations lower than a specified threshold distance in order to evaluate the maintenance need at each longitudinal section of the railway track.

download the full-text of this paper (PDF, 9 pages, 1448 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description