Communications of the ACM
New Software Can Detect When People Text and Drive
New algorithms developed by University of Waterloo researchers can accurately determine when drivers are texting.
Credit: istockphoto
Researchers at the University of Waterloo in Canada have developed 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 are not associated with normal driving behavior and classify them in terms of possible safety threats.
The researchers say the system could be used to improve road safety by warning or alerting drivers when they are dangerously distracted. In addition, as advanced self-driving systems become more common, signs of serious driver distraction could be used 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," says the University of Waterloo's Fakhri Karray.
The algorithms were trained using machine-learning techniques to recognize actions such as texting, talking on a cellphone, or reaching into the backseat to retrieve something.
From University of Waterloo News
View Full Article
Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA
No entries found