Deploying artificial intelligence to spot fare dodgers

SPAIN: The use of a system 'based on artificial intelligence' to spot passengers attempting to avoid payment by following other users through ticket barriers is being tested by Catalan regional operator FGC and Barcelona-based Awaait Artificial Intelligence.

Named Detector, the system uses a camera to watch the gate area, and sends an alert to an inspector with a mobile terminal if it spots someone following another passenger through the gate. The inspector can then decide whether to intercept the passenger and ask them for their ticket. If the passenger cannot produce a valid ticket, they can be fined.

Detector does not get in the way of other travellers, and makes it possible to replace mass ticket checks with selective checks by smaller inspection teams. It also automatically generates statistics in real time so that changes can be monitored: FGC estimates current fare-dodging rates at 0·041%.

FGC and AWAAIT have agreed to co-operate to market the system, with AWAAIT supplying the technology and FGC offering consulting services to make the best use of it.

Following the pilot project at FGC’s Provença station, the technology is to be rolled out at Catalunya and Muntaner later this year.