Over the last few years, driver drowsiness has emerged as a major cause of road accidents, resulting in fatalities, grave injuries, and significant economic losses. To mitigate this issue, researchers have explored multiple measures to detect drowsiness in drivers, including vehicle-based, behavioural, and physiological measures. However, existing systems face limitations, necessitating a comprehensive, and hybrid approach that combines non-invasive physiological measures with other methods for accurate drowsiness detection. Recent advances in embedded technologies and artificial intelligence hold promise in developing real-time driver monitoring systems. This endeavour involves development of a real-time drowsiness detection model that automatically detects driver fatigue using webcam images and notifies the driver with an alarm and emergency alerts if needed, aiming to improve overall driving safety. With an accuracy of 96.54%, this system underscores the significance of precise crash prevention technologies and identifies potential areas for further investigation and optimization, contributing to the creation of a safer road environment.