Design of Real-Time Driver Drowsiness Detection Based Electromechanical Braking System for Heavy-Duty Vehicles

The increasing number of road accidents involving heavy vehicles due to driver drowsiness necessitates the development of advanced safety systems. This abstract presents a real-time driver-drowsiness-based electromechanical braking system designed specifically for heavy vehicles. The system uses a combination of sensors, including facial recognition cameras and fatigue monitoring sensors, to continuously monitor the driver's physiological and behavioral parameters. Machine learning algorithms analyze these data streams in real-time to identify signs of drowsiness, such as drooping eyelids, erratic steering behavior, and decreased responsiveness. Upon detecting drowsiness, the system triggers audible alerts, autonomous braking assistance, and remote monitoring and intervention. This method uses an electromechanical braking system to help stop the vehicle by determining the EAR (Eye Aspect Ratio) and LIP (Lip Aspect Ratio) using the haarcascade algorithm and Open CV. By integrating real-time drowsiness detection with proactive braking assistance, the proposed system aims to significantly reduce the risk of accidents caused by driver fatigue in heavy vehicles. When tiredness is identified, the project's implementation offers a possible way to improve road safety by warning drivers and activating braking devices.