The Car and Truck Fleet and Leasing Management Magazine

Tech Developed to Detect Distracted Driving

September 19, 2017

Photo by Intel Free Press via Wikimedia Commons.
Photo by Intel Free Press via Wikimedia Commons.

Engineering researchers at the University of Waterloo in Ontario, Canada, have developed computer algorithms that can accurately determine when drivers are texting or engaged in other distracting activities, according to the university.

The system uses cameras and artificial intelligence (AI) to detect hand movements that deviate from normal driving behavior and grades or classifies them as potential safety threats. The information could be used to improve road safety by warning or alerting drivers when they’re dangerously distracted, said Fakhri Karray, an electrical and computer engineering professor at Waterloo.

Additionally, in an emergency situation, an automated driving system might assume control of the vehicle.

“The car could actually take over driving if there was imminent danger, even for a short while, in order to avoid crashes,” said Karray, a university research chair and director of the Center for Pattern Analysis and Machine Intelligence (CPAMI) at Waterloo.

Algorithms at the heart of the technology were trained using machine-learning techniques to recognize such actions as texting, talking on a cell phone and reaching into the backseat to retrieve something. The system assesses the seriousness of the action based on duration and other factors.

This project builds on previous CPAMI research on recognizing the signs of drowsy driving. Head and face positioning are also important cues of distraction.

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

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

Another research project at CPAMI is exploring the use of sensors to measure physiological signals — such as eye-blinking rate, pupil size and heart rate variability — to help determine if a driver is paying adequate attention to the road.

Karray’s research was performed in collaboration with PhD candidates Arief Koesdwiady and Chaojie Ou and with post-doctoral fellow Safaa Bedawi. Their findings were recently presented at the 14th International Conference on Image Analysis and Recognition in Montreal.

Twitter Facebook Google+

Comments

Please note that comments may be moderated. 
Leave this field empty:
 
 

Fleet Incentives

Determine the actual cost of owning and running a vehicle in your fleet. Compare vehicles by class and model.

FleetFAQ

Fleet Tracking And Telematics

Todd Ewing from Fleetmatics will answer your questions and challenges

View All

 

Fleet Management And Leasing

Merchants Experts will answer your questions and challenges

View All

 

Sponsored by

BBL Fleet offers total fleet management solutions including acquisition, lease, financing, fuel and maintenance management, remarketing, accident, driver safety management, analytics, transactional data management, driver/fleet admin tools, reporting, and telematics.

Read more

Up Next

More From The World's Largest Fleet Publisher