New algorithms can detect when people text and drive

Toronto: Researchers have developed computer algorithms that can accurately determine when drivers are texting or engaged in other distracting activities.

The system uses cameras and Artificial Intelligence (AI) to detect hand movements that deviate from normal driving behaviour and grades or classifies them in terms of possible safety threats, according to the research presented at the 14th International Conference on Image Analysis and Recognition in Montreal, Canada.

That information could be used to improve road safety by warning or alerting drivers when they are dangerously distracted, said Fakhri Karray, Professor at University of Waterloo in Ontario, Canada.

And as advanced self-driving features are increasingly added to conventional cars, signs of serious driver distraction could be employed to trigger protective measures, he said.

“The car could actually take over driving if there was imminent danger, even for a short while, in order to avoid crashes,” Karray said.

Algorithms at the heart of the technology were trained using machine-learning techniques to recognise actions such as texting, talking on a cellphone or reaching into the backseat to retrieve something. Leading car makers and technology giants are making an entry into the automated driving sector, that operates completely on the particulars of the algorithms running the car.

The seriousness of the action is assessed based on duration and other factors.

IANS