This article was published in Scientific American’s former blog network and reflects the views of the author, not necessarily those of Scientific American
On supporting science journalism
If you're enjoying this article, consider supporting our award-winning journalism by subscribing. By purchasing a subscription you are helping to ensure the future of impactful stories about the discoveries and ideas shaping our world today.
Several automakers have recently come to agree that their high-end vehicles should include a warning system to keep drivers from falling asleep, a problem that causes at least 100,000 crashes annually, according to the U.S. National Highway Traffic Safety Administration.
The automakers disagree, however, on the best way for a car to "know" when its driver is dozing off behind the wheel.
One team of researchers is proposing a simple clue—the yawn.
Whereas different auto makes and models rely primarily on cameras and sensors that keep a close eye on the car itself, as well as the road around it, researchers at Vanderbilt University, Siksha 'O' Anusandhan University's Institute of Technical Education and Research (ITER) in India and the Indian Institute of Technology Kharagpur's electrical engineering department are devising a model that can detect this most obvious sign of fatigue.
In a study published in the July issue of the International Journal of Computational Vision and Robotics, the researchers propose a driver-safety system that can detect a driver's yawn by the change in the contours of that person's lips. Such a system would include image-processing software that could even analyze the "deformation occurring on the driver's face and accurately identify the yawn from other types of mouth opening such as talking and singing," according to the study.
This approach most closely resembles the Lane Monitoring System that Toyota offers with several of its luxury Lexus models. (The company introduced an earlier version of this system in certain Japanese models in 2002.) The Lexus system uses a miniature camera on the steering column to determine whether the driver has stopped looking ahead and uses radar and stereo cameras to detect if the car is getting too close to another object. If so, the system will sound an alarm and gently apply the brakes.
Other driver-warning systems focus more on external factors, as opposed to driver posture or behavior. Volvo's Driver Alert Control (DAC)—a feature that has been available on some models since the end of 2007—kicks in when the car exceeds 65 kilometers per hour and keeps working as long as the car's speed exceeds 60 kilometers per hour. Volvo's approach is to monitor the car's movements and assess whether the vehicle is being driven in a controlled or uncontrolled way. It does this through a camera, mounted between the windshield and the interior rear-view mirror, that continuously measures the distance between the car and the road lane markings. If the DAC senses the driver is getting too close to these markings (or another car), an alarm sounds. (BMW's Lane Departure Warning system—standard on 5 Series sedans and 6 Series coupes—likewise uses a camera to monitor the lines on the road ahead, but it makes the steering wheel rumble if a driver crosses a line without a turn signal.)
"We often get questions about why we have chosen this concept instead of monitoring the driver's eyes," Daniel Levin, project manager for Driver Alert Control at Volvo Cars, said in a 2007 company press release. "The answer is that we don't think that the technology of monitoring the driver's eyes is mature enough yet."
The Mercedes Attention Assist system, standard on its 2010 E-class models, is designed to keep tabs on a driver's behavior through sensors that monitor steering, braking and acceleration. In a Big Brother sort of way, the car studies the driver's behavior throughout a trip and builds a driver profile based on the sensor inputs. When the system detects a significant deviation from the profile (drifting into another lane, for example), it will reference this against the time of day, duration of the trip and even the weather to determine if a driver might be distracted or falling asleep behind the wheel. If the system is satisfied that it's got an inattentive driver, it will sound warning chimes.
Image ©iStockphoto.com/ Vladimir Mucibabic
