Skip to main content

Vinci Highways and Invision AI light up motorway in Greece

New smart system adjusts road lighting to suit driving conditions and save energy
By David Arminas December 19, 2023 Read time: 2 mins
Vinci says the adaptive lighting system, combined with the energy performance of the LED lights, will reduce annual energy consumption for night lighting by up to 75% (image: Vinci Highways)

The Athens-Patras highway is the first in Greece to have a smart lighting system that automatically adapts the road lighting to the level of traffic

The system along a trial section of the tolled 218km-long highway - also known as Motorway 8 - adjusts the lighting to best suit the driving conditions, according to Vinci Highways, operator of the road. Vinci has committed to achieve operational net-zero emission on its network by 2050.

The system uses artificial intelligence and machine learning to determine the optimal lighting level by processing live data including traffic, weather and road incidents from multiple sources. Constant monitoring of the vehicle traffic at each interchange of the highway allows the system to calculate the total traffic and make forecasts for the next hour. When traffic decreases and predictive traffic remains low, the system progressively reduces intensity of lighting.

The system also includes real-time data from the highway’s weather stations and cameras to immediately increase lighting in case of a change in driving conditions. The system has been set up in a trial along the Elefsina to Corinth section and will be progressively implemented along the entire length of the highway.

Vinci says the adaptive lighting system, combined with the energy performance of the LED lights already set up along the complete length of the Athens-Patras highway, will reduce annual energy consumption for night lighting by up to 75%. It also reduces light pollution for people living close to the motorway.

The adaptive lighting system has been developed in collaboration with the National Technical University of Athens and specialist start-ups including Extrabit, Athens-based predictive weather forecasting company Ex Machina and Invision AI, which provides video-based AI solutions for transit and public safety applications.

Dutch firm Tvilight provided the luminaire controllers and software. 

Extrabit supplied the machine learning algorithm that accurately predicts the number of vehicles in predefined future intervals. The company also provided the communication protocols for interfacing with around 8,000 LED dimmable luminaires, as well as the visualisation and control of the complete system on a web-based platform.

For more information on companies in this article

Related Content

  • Will you allow winter weather to derail your transit operations?
    June 8, 2021
    JW Speaker's SmartHeat allows transportation managers to improve public transit safety
  • Telegra Lightway IQ LED lamps
    February 6, 2012
    The substantial energy saving capability of LED lamps over traditional lighting is now well recognised and Telegra's new Lightway IQ LED lamps are no exception. However, that's only part of the cost savings provided by these devices.
  • Big data and GPS combine to cut emergency response times
    April 2, 2014
    David Crawford looks at technologies for better emergency medical service delivery. Emergency medical services (EMS) play key roles in transporting, or bringing treatment to, patients who become ill through medical emergencies or are injured in road traffic accidents (RTAs). But awareness has been rising steadily, in the US and elsewhere, of the extent to which EMS can generate their own emergencies. The most common cause is vehicles causing or becoming involved in RTAs, as a result of driving fast under pr
  • Queensland extends emergency vehcile priority system
    December 18, 2014
    Following encouraging results from an initial small-scale trial of an emergency vehicle priority system in Queensland, Australia, the scheme is now being extended. In an emergency every second counts. Nowhere is this more graphically illustrated than by the survivability statistics for the time to cardiopulmonary resuscitation of pre-hospital cardiac arrest: at four minutes the survival rate is 22% but by 14 minutes the survival has dropped to 5% - as can be seen from the graph below. There is a similar tre