An autonomous system capable of detecting actions which could suggest driver distractedness has been created by researchers at the university of waterloo. With the aid of machine learning algorithms it can detect patterns of behaviour when trained on enormous datasets to recognise the hand movements indicative of texting, talking on a phone, reaching into the backseat to retrieve an object and other actions which deviate from safe driving.
In addition to the machine-learning software , there are cameras to monitor the driver. It can classify the risky activities in terms of possible threat to road safety, based on the duration of the action and other factors.
According to director of the Centre for Pattern Analysis and Machine Intelligence at the University of Waterloo -Professor Fakhri Karray, this information could come in useful by warning or alerting drivers when they are dangerously distracted, improving road safety.
“If there is an imminent danger the car could take over driving, even for a short while, in order to avoid crashes,” said Professor Fakhri .
“(Driver distraction) has a huge impact on society,” said Professor Karray. Reports estimated that up to 75 per cent of all traffic accidents are caused by driver distraction. According to the World Health Organisation, in the year 2010 alone road accidents caused 1.25million deaths.
The engineer intend to combine the detection, processing and classification of these various signals of driver distractedness into a single automated safety system.