road traffic
Caption: Artificial intelligence allows better detection of road traffic disturbances in real-time. Credit: Nabeel Syed on Unsplash

A test carried out by the Finnish Transport Agency and Tieto has indicated that artificial intelligence (AI) enables better detection of road traffic disturbances in real-time without significantly adding costs.

The two organisations carried out a proof-of-concept experiment in the spring of 2018, which saw LiDAR (Light Detection and Ranging) measurement technology combined with sensor fusion and artificial intelligence techniques deployed to analyse traffic flows.

The automatic monitoring of any traffic disturbances is currently based on camera surveillance and even the most sophisticated solutions primarily focus on the security of tunnels.

Artificial intelligence and sensor data systems are not widely used for real-time monitoring of traffic disturbances.

However, data analysis systems that use sensor fusion and artificial intelligence can offer new opportunities for traffic management centres to get a wider real-time view of road conditions and any irregularities as they occur.

The test was carried out at the Mestarintunneli tunnel in Leppävaara, Espoo.

“This approach shows that even a smaller set of observations can be used to build virtually functional artificial intelligence solutions.”

LiDAR sensors were installed in the tunnel intended to detect stalled vehicles and other disturbances such as people or animals on the road.

The test allowed organisations to gather data from normal traffic flow, but the small number of abnormal situations recorded during the measurement period made it difficult to develop an artificial intelligence solution.

Tieto data-driven businesses chief data scientist Ari Rantanen said: “In order to model traffic flows, we decided to build a tailored machine learning model based on sensor fusion, and one that also recognises traffic anomalies by comparing them with the normal traffic model.

“This approach shows that even a smaller set of observations can be used to build virtually functional artificial intelligence solutions.”

Finnish Transport Agency senior officer Kalle Ruottinen said: “Automatic recognition of traffic disturbances is a key requirement for a secure road network. Based on current functional requirements, the most cost-effective system has been traffic camera surveillance with a built-in disturbance detection system.

“However, we are constantly monitoring the market and introducing new technologies to seek new opportunities and cost-effectiveness.”

The project also indicated that automated analysis of traffic flows can generate near real-time information for different stakeholder requirements without needing any significant investments in sensors.