New software could detect when people text and drive

Engineering researchers at Canada’s University of Waterloo are developing technology which 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.
September 20, 2017 Read time: 2 mins
Engineering researchers at Canada’s University of Waterloo are developing technology which 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.


Fakhri Karray, an electrical and computer engineering professor and director of the Centre for Pattern Analysis and Machine Intelligence (CPAMI) at Waterloo, said that information could be used to improve road safety by warning or alerting drivers when they are dangerously distracted. As advanced self-driving features are increasingly added to conventional cars, he said, signs of serious driver distraction could be employed to trigger protective measures.

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

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

That work builds on extensive previous research at CPAMI on the recognition of signs, including frequent blinking, that drivers are in danger of falling asleep at the wheel. Head and face positioning are also important cues of distraction.

Ongoing research at the centre now seeks to combine the detection, processing and grading of several different kinds of driver distraction in a single system.

“It has a huge impact on society,” said Karray, citing estimates that distracted drivers are to blame for up to 75 per cent of all traffic accidents worldwide.

Related Content

  • New research finds distracted driving on the rise on I-95
    May 12, 2014
    Transurban-Fluor and AAA Mid-Atlantic have released the second annual report on distracted drivers on I-95 in Northern Virginia, which found that despite major construction, distracted driving is a growing problem on the heavily travelled corridor. The report, part of the Orange Cones, No Phones campaign focused on reducing distracted driving in the 95 Express Lanes construction zone, found that the number of frequent I-95 drivers likely to use their cell phone while driving has increased from 56 percent i
    Read More
  • Deadlines approach for Europe’s automatic crash alert system
    September 15, 2016
    The EU-co-funded I_ HeERO (Infrastructure_ Harmonised eCall European Pilot) project is working to ensure the readiness of national networks of call centres - known as public safety answering posts (PSAPs) - to deal with automated crash alerts arriving via the continent-wide 112 emergency phone number. Following on from its HeERO and HeERO2 pre-deployment predecessors, which enjoyed €16m (US$17.76m) in EU funding, the new initiative runs from 1 January 2015 to 31 December 2017. It has €30.9 million (US$34.
    Read More
  • Knowing when to slow down
    August 8, 2018
    Level 2 driver assistance vehicles have little problem reading fixed metal signs at the roadside - but it’s a different story with VMS in tunnels, finds Alan Dron. Following a series of hands-free driving tests in tunnels, an Australian road authority believes that car manufacturers have to up their game before vehicles have the required levels of competence to consistently perform ‘assisted driving’ tasks. The trials, in the state of Victoria late last year, tested the ability of several vehicles to stay
    Read More
  • ‘Eating and drinking while driving almost as dangerous as using a mobile device’
    June 13, 2014
    According to new data released by driver safety solutions company Lytx Europe, eating or drinking while driving is nearly as dangerous as using a mobile device – whether handheld or hands-free - and greatly increases a driver’s risk of being in or causing a collision. Lytx (formerly DriveCam) found that drivers who eat and drink while driving are 3.6 times more likely to be involved in a collision than those who do not due to the distraction this causes. This is almost as high as the collisions resultin
    Read More

Highlighted Content