An Approach to Detect Driver Drowsiness in Real Time using Facial Landmarks

Abstract

According to studies, 21% i.e., one-fourth of serious roadway accidents are caused due to the drowsiness of the drivers. Some of the most significant reasons that cause fatigueness in drivers are lack of sleep, heavy exertion and drunken driving. Heavy vehicle drivers who travel long distances despite their lack of sleep are more prone to road accidents. This research proposes a system that detects the drowsiness of the drivers like duration of eye closure and yawning. This system is built using Python and its libraries, such as OpenCV, dlib, pygame, etc. which would be integrated into a web application made with the help of flask in Python. This system in real-time determines if a person driving a car is drowsy or not, if the driver is drowsy, then the system alarms him by sound alerts.