Real Time Drowsiness Detection, Alerting and Reporting

Abstract

Driver drowsiness is one of the leading causes of motor vehicle crashes, an issue which the industry and academia wants to tackle. Currently, different methodologies focus on combining drowsiness detection technologies and machine learning. The proposed solution is a computer vision based solution for detecting drowsiness based on a video feed of the driver's face. This helps monitor a driver's fatigue condition in real-time. The system is based on a hybrid approach, combining the decision of far-edge and near-edge submodules to detect drowsiness signs of the truck driver. According to the drowsiness level, the system will trigger an alert, e.g., by sounding an alarm that will be installed in the truck's cabin. The proposed solution will be implemented in the Piraeus Container Terminal (PCT).