Railway track inspection software could save £10m a year

After two-and-a-half years in a Knowledge Transfer Partnership a machine-learning technology has been developed to digitalise and automate the way in which railway line inspections are carried out.

Project aims for self-powered railway track monitoring in real time

In use, inspections are carried out by a camera attached to the front of a train, which captures high-definition images of the rail track to generate data that is analysed for inaccuracies and faults. In addition, the technology assists in identifying where faults may occur, allowing preventative measures to be taken.

“These machine vision technologies for high-speed rail inspection will improve the reliability of the railway network, reduce costs and increase the safety of manual inspection,” said Prof Richard Wilson, lead researcher on the project from the Department of Computer Science at York University. “The computer vision and machine learning technologies provide automated inspection of complex assets such as junctions and crossings.”