Intelligence series: Image Recognition Systems for Rail

Image recognition systems utilise various image processing techniques (image manipulation to enhance image quality, restoration, compression and decompression) and machine learning, to accurately identify objects or people from photos or video feeds. Typically, they consist of a high resolution CCTV system combined with pattern recognition computer software.

Image author: Feliciano Guimarães from Guimarães, Portugal.

Image recognition systems can be used in the rail industry at the Platform Train Interface (PTI) for object, motion and accident detection. This can allow station staff and train drivers to be automatically alerted about dangerous situations (e.g. passengers falling between the platform and the train), improving safety and security.
Image recognition systems can also be used to track passengers using facial recognition and behavioural analysis to monitor their movements; beyond immediate policing usage, this technology is one of the main enablers in some gateless ticketing systems. Flow analysis and crowd density estimations can be implemented to provide data of passenger flow through a station.
Driverless train technology or future driver assist systems will also heavily rely on image and pattern recognition (e.g. sign and obstacle recognition on the track).


Banner image author: Shady59.
Log in or register to keep reading
Register for free individual access
  • Unlock research, articles and more
  • Get updates on RSSB’s activities





Need some help?
To talk to us about accessing RSSB content or corporate membership:
Cookies help us improve your website experience.
By using our website, you agree to our use of cookies.