A team of Australian researchers has developed an intelligent system capable of detecting, via images provided by a camera, the level of drunkenness of motorists. Combined with surveillance cameras, this could make it a formidable tool for the authorities.
Researchers at Edith Cowan University (ECU) in Australia have developed visual tracking technology that can Detect drunk drivers using a simple camera to be able to drive safely. This technology uses machine learning to analyze different facial features, but also the position of the driver’s head and the direction of gaze to determine their level of intoxication. This is the first solution using a classic RGB camera to detect alcohol intoxication levels based on signs of impairment on the driver’s face.
To train their tool, these researchers used MiX by Powerfleet, a fleet management application that usually tracks driver behavior.
Participants, divided into three levels of alcohol intoxication (sober, slightly intoxicated and severely intoxicated) were recorded while they were driving on a simulator. It was these images that then fed into the intelligent tool they developed.
The first tests showed 75% accuracy in its behavioral analysis of drivers. Ultimately, This system could be integrated into road surveillance camerasoffering a quick and effective alternative to traditional drunk driver detection checks.
Technology soon to be deployed on the roads?
The next step will be to define the level of image resolution needed to use this algorithm so that it is as reliable as possible. The lower this resolution, the more its scope of action can be extended, particularly at the level of law enforcement surveillance cameras.
If this technology could one day be used in the context of unlocking his carsuch an approach could also be integrated with road camerasin the same way that these cameras can now detect the wearing of seat belts or the use of mobile phones.
In Australia (as in France), excess alcohol is a factor in almost one in three fatal accidents.
