Driver’s real-time Drowsiness Detection using Adaptable Eye Aspect Ratio and Smart Alarm System

According to National Highway Traffic Safety Administration (NHTSA), drowsy driving leads to over 71,000 injuries, 1,500 deaths, and $ 12.5 billion in monetary losses per year. The main issue that needs to be addressed is that the driver should be warned well before time to take precautionary measures. This paper suggests a radical solution to the problem by proposing a system that can detect the driver's drowsiness and can issue a timely warning. This paper describes a non-intrusive approach that takes into consideration the Eye Aspect Ratio (EAR) and Mouth Aspect Ratio (MAR) to quantify drowsiness by locating, monitoring, and analyzing both eyes and mouth, even in the dark. The real-time EAR is compared with the initial EAR of the drive and the MAR is compared with a set threshold of 20. The system alerts the user by issuing text and audio warnings. We also propose a smart alarm system that can be turned off by detecting a hand gesture. The data is collected from the user in real-time to test the system. This system predicted 9 out of 10 cases accurately, both in dark and light conditions, with different facial features including spectacles.