Researchers Develop In-Car Camera That Can Spot a Drunk Driver

A person wearing a suit is driving a car at night. The image is taken from the backseat, showing the driver's back and hands on the steering wheel. City lights and out-of-focus traffic can be seen through the windshield and side windows.

Researchers have created new camera technology that can detect whether a driver is impaired by alcohol when they get behind the wheel of a vehicle.

A team of researchers at Edith Cowan University in Australia have developed an in-vehicle camera with a facial tracking system that can detect signs of alcohol intoxication in drivers before they hit the road.

In a paper published this year, the team revealed that the system utilizes data from standard RGB (red, green, and blue) camera footage to spot telltale facial cues that reveal whether the driver is drunk.

The researchers started by having 60 volunteers use an indoor driving simulator while a conventional RGB video camera recorded footage of their faces. Each person drove at three successive levels of intoxication: Sober, Low, and Severe.

Researchers then used a machine learning system that analyzes discernible cues from standard videos of the driver’s faces to gauge the degree of alcohol-related impairment. These included facial features, gaze direction, and head position.

According to the team’s research, the camera system was able to classify alcohol intoxication levels with an overall accuracy of 75% for the three levels of classification.

The researchers believe that the system could utilize driver-facing versions of the cameras such as those in dashcams — potentially not allowing the car to start if intoxication is detected.

“Our system has the capability to identify intoxication levels at the beginning of a drive, allowing for the potential prevention of impaired drivers from being on the road. This sets it apart from methods reliant on observable driving behaviors, which require extended active vehicle operation to identify impairment.” Edith Cowan University PhD student Ensiyeh Keshtkaran says in a statement.

Edith Cowan University Senior Lecturer Dr. Syed Zulqarnain Gilani adds that the new technology is the first to employ a standard RGB camera to detect alcohol intoxication levels based on signs of impairment in a driver’s face.

“This research confirms that it is possible to detect intoxication levels using just a simple camera,” Gilani says.

“The next step in our research is to define the image resolution needed to employ this algorithm. If low-resolution videos are proven sufficient, this technology can be employed by surveillance cameras installed on roadside, and law enforcement agencies can use this to prevent [drunk] driving.”

According to the National Highway Traffic Safety Administration (NHTSA), around 37 people in the U.S. die in drunk-driving crashes every day. In 2022, 13,524 people died in alcohol-impaired driving traffic deaths.


Image credits: Header photo licensed via Depositphotos.