Trials are running from last Friday (February 14) into March at Tamagawa Gakuenmae No.8 railroad crossing in Machida City, Tokyo.
Nokia’s scene analytics will analyse available image feeds, generated by conventional railroad crossing cameras, to detect abnormal events by applying machine-learning based artificial intelligence. This should identify potential issues in real-time.
The software runs on edge computing resources, which can reduce required bandwidth at remote sites and better manage limited connectivity.
The Odakyu Electric Railway has said it is committed to advancing innovative technology in order to make the Odakyu Line the safest rail company in Japan, enabling its customers to travel with complete peace of mind. It has 229 crossing points across 120.5 kilometers of rail track, with 137 radar systems for object detection.
John Harrington, head of Nokia Japan, said, “Odakyu Electric Railway is renowned for being an early adopter of new technology and this trial illustrates the role that AI can play in delivering enhanced levels of vigilance. This is a critical milestone for Nokia to help contribute not only to railway safety improvement but also to decrease operational costs and enhance performance.
“Network connected cameras are one of the most prolific sources of IoT data that can provide valuable insights to help promote high safety standards. By running machine learning analytics on camera feeds, and sending solely relevant scenes and events to operators, the full benefits of video surveillance can be realized in a wide variety of settings – with rail crossings a particularly relevant use case.”
SpaceTime scene analytics, developed by Nokia Bell Labs, can provide real-time alerts for unauthorised entry into remote facilities. It can detect and alert supervisors when personnel or equipment enter unsafe locations.
