Nokia has deployed its AI-powered Scene Analytics solution for Baselland Transport (BLT) in Münchenstein, Switzerland, for real-time monitoring and analysis to ensure the safety of level crossings.
The computer vision and machine learning system is the first deployment of this kind in Europe, as Nokia’s collaboration with Schweizer Electronics and BLT looked to demonstrate the reliability of AI-based railroad safety solutions for daily use.
Safety of passengers and vehicles at level crossings remains a concern for rail authorities due to the threat of serious injury or loss of life in these areas. Statistics from the European Union identified around 250 fatalities and 300 serious injuries related to level crossings in the EU during 2018.
Even the best warning systems can be bypassed, and crossings obstructed, making it essential for train operators to be alerted of issues in real-time, the partnership said.
“Level crossings are notoriously difficult areas to ensure the safety of passengers, pedestrians, train operators and motorists,” explained Michael Theiler, head of maintenance electrical systems at BLT.
Integrating Nokia Scene Analytics enables BLT to use machine learning algorithms based on CCTV data to continually learn what is normal or irregular. In addition to reporting anomalies to railway security in real-time, the AI-based platform detects the object type which provides a more complete picture of the situation at hand.
Furthermore, event-based video clips, images and associated data are stored, enabling post-incident forensic analysis.
Besides improving safety and response time, the deployment of Scene Analytics on railroad crossings is designed to increases operational efficiencies by minimising downtime and delays.
Theiler continued: “This deployment, in collaboration with Nokia represents an encouraging step towards using analytics as another layer of protection in dangerous areas. Nokia Scene Analytics acts as an intelligent set of ‘eyes’ and, by providing critical information in real-time, to prevent or mitigate the impact of an incident.”
Its machine learning capability also reduces the time investment required by rail personnel to manually update the system. In doing so, Nokia Scene Analytics aims to provide train operators with much greater overall cost efficiency.
It can also be integrated with many standard industry cameras, reducing the total cost of ownership, and increasing the return on investment.
