Drivers’ Drowsiness Detection and Warning Systems for Critical Infrastructures

Road traffic accidents, due to driver fatigue, tend to inflict high mortality rates comparing with accidents involving rested drivers. Currently there is an emerging automotive industry trend towards equipping vehicles with various driver-assistance technologies. Third parties also started producing complementary systems, including ones that can detect the driver's degree of fatigue, but this growing field requires further research and development. The main purpose of this paper is the development and implementation of a system capable to detecting and alert, in real-time, the driver's level of fatigue. A system like this is expected to make the driver aware of the assumed danger when his level of driving and taking decisions are reduced and is indicating a sleep break as the necessary approach. By monitoring the state of the human eyes, it is assumed that the signs of driver fatigue can be detected early enough to prevent a possible road accident, which could result in severe injuries or ultimately, in fatalities. Hence, in this work the authors are focused on the video monitoring of the driver face, especially on his eyes position in time, when open or closed, using a machine learning object detection algorithm, the Haar Cascade. Two pretrained Haar classifiers, a face cascade, and an eye cascade were imported from the OpenCV GitHub repository. The OpenCV library, as well as other required packages, were installed on a BeagleBone Black Wireless development board. The software implementation, in order to achieve the driver's drowsiness detection, was made through the Python software program. The proposed system manages to alert if the eyes of the driver are being kept closed for more than a certain amount of time by triggering a set of warning lights and sounds. The large-scale implementation of this type of system will drop the number of road accidents caused by the drivers' fatigue, thus saving countless lives and bringing a reduction of the socio-economic costs associated with these tragic events.