First AI-based video analytics system for railroad crossing safety deployed
Nokia has deployed its first AI-based video analytics system designed to improve railroad crossing safety in Europe. The system, dubbed Scene Analytics, was field tested in collaboration with railway safety company Schweizer Electronics and Baselland Transport (BLT). It was installed in the Swiss municipality of Münchenstein.
Scene Analytics weaves together computer vision and machine learning, allowing a company such as BLT to unleash algorithms on their CCTV data. This, then, enables the system to learn how to detect anomalous situations. These anomalies are then reported in real-time, while the platform recognises and stores all the relevant incident information. As such Scene Analytics can both improve response time and lead to new insights in operational efficiencies. The system functions with an array of standard industry camera’s, eliminating the need for additional investments.
“Level crossings are notoriously difficult areas to ensure the safety of passengers, pedestrians, train operators and motorists. This deployment, in collaboration with Nokia represents an encouraging step towards using analytics as another layer of protection in dangerous areas”, said BLT’s head of electrical systems maintenance Michael Theiler.
“By combining level crossing systems and Scene Analytics within a simple interface, this project with Nokia and BLT enabled us to automate the interaction between level crossing systems and alarms for enhanced safety”, Schweizer Electronics’ Roland Liem added.
Nokia points to European statistics that indicate that some 250 people die every year at level crossings across member states. Other estimates give almost double that figure for road-rail level crossings.