Nokia tests AI safety at Japan rail crossing

Japan’s Odakyu Electric Railway is using Nokia’s SpaceTime scene analytics to identify ways of improving rail crossing safety. 
By Ben Spencer February 27, 2020 Read time: 1 min
Rail crossings can be hazardous for pedestrians and drivers (Source: © Gregory Brault | Dreamstime.com)

Nokia says its analytics detect abnormal events by applying machine learning-based artificial intelligence to available camera images. It can operate at reduced bandwidth in remote sites which may have limited connectivity. 

John Harrington, head of Nokia Japan, says: “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 realised in a wide variety of settings – with rail crossings a particularly relevant use case.”

According to Nokia, the analytics can provide real-time alerts for unauthorised entry into remote facilities. The product can also alert supervisors when personnel or equipment access unsafe locations in industrial settings or when heavy machinery is out of position creating a hazard, the company adds. 

Odakyu has 229 crossing points across 120.5km of rail track, with 137 radar systems for object detection. 


 

Enforcement

For more information on companies in this article

Related Content

  • Roadside monitoring used to target non-compliant trucks
    March 9, 2016
    The UK’s DVSA is utilising existing technology to identify non-compliant commercial vehicles and target repeat offenders while avoiding law-abiding companies. Enforcing the compliance of commercial vehicles (goods vehicles over 3.5 tonnes and vehicles with eight or more passenger seats) on the UK’s roads is the responsibility of the DVSA (the Driver and Vehicle Standards Agency). The Department for Transport created the executive agency about 18 months ago by merging the Driving Standards Agency (DSA) and t
    Read More
  • Daimler’s double take sees machine vision move in-vehicle
    December 13, 2013
    Jason Barnes looks at Daimler’s Intelligent Drive programme to consider how machine vision has advanced the state of the art of vision-based in-vehicle systems. Traditionally, radar was the in-vehicle Driver Assistance System (DAS) technology of choice, particularly for applications such as adaptive cruise control and pre-crash warning generation. Although vision-based technology has made greater inroads more recently, it is not a case of ‘one sensor wins’. Radar and vision are complementary and redundancy
    Read More
  • IntelliDrive and HOT lanes - the next generation?
    January 30, 2012
    Janet Banner, Metropolitan Transportation Commission, and Christopher Hill, Mixon Hill, Inc., outline efforts to explore the use of IntelliDrive technologies in HOT lane applications. On 21 October last year more than 100 transportation professionals came together for a workshop, either in person or via a webinar, to discuss the potential role of IntelliDriveSM technologies in enhancing the operations of High-Occupancy Toll (HOT) lanes. The discussions focused on a White Paper, commissioned by the Metropoli
    Read More
  • New solutions for catching texting drivers
    October 28, 2016
    Many countries have laws prohibiting texting while driving but enforcement is proving difficult – David Crawford looks at some new approaches being tried by authorities. Finding definitive solutions – technological, regulatory and educational - to the potentially lethal practice of people driving while using mobile phones is proving elusive, while the stakes grow higher.
    Read More

Highlighted Content