The project is a collaboration between University of Alberta, the city of Edmonton, and the Edmonton Police Service.

The University of Alberta is leading a three-week pilot project that will use artificial intelligence to detect automobile drivers at the wheel with a cell phone in their hand. The project will assess the extent of such distracted driving in the city of Edmonton and also whether AI deployed could nab offenders. Sensors will be installed at strategic Edmonton locations to capture images of these drivers, even through windshields. The technology has been provided by Australian-based company Acusensus which said it had been used in Australia and several locations in the United States. (CBC)

AI and distracted driving

Acusensus general manager Tony Parrino described how the company trained the AI to identify distracted driving. First, the algorithm is shown examples of distracted driving, and then later, examples of driving that is not distracted. The algorithm learns from these images and once deployed, analyses the images taken by the sensors.

If the technology flags an image of a driver suspected of distracted driving, the picture is reviewed by a human being. If distracted driving is confirmed, the police department would issue a citation within 48 hours supported by photographic evidence from the sensor.

“With distracted driving, you can see the evidence in the photo,” said Parrino. “There’s no dispute, it’s not like a speeding ticket where you have to determine whether or not the system is working properly. It’s pretty obvious that the system is working properly for distracted driving when you could see somebody’s phone in their hand.”

According to the Edmonton Journal, most of the pilot project funding is from the University of Alberta and Edmonton Police Service through a seed grant.

Related Story: AI Cameras In Amazon Delivery Vehicles Unfairly Penalize Drivers