Advanced Eye State Analysis for Bus Driver Fatigue Detection

Abstract

By using this method, we want to increase road safety by reducing the number of accidents caused by drowsy driving. The automatic identification of driving weariness is handled by this technology, which is based on optical data and artificial intelligence. We locate, track, and look at the driver's face and eyes to measure PERCLOS (% of eye closure) with Soft Max for the neural transfer function. Driver fatigue is one of the major contributing factors in traffic accidents, especially for drivers of large vehicles (such as buses and heavy trucks), because of prolonged driving hours and boredom in congested areas. When a driver nods off, they lose control of the car, which frequently leads to a collision with another car or any other object. There is a method being developed to stop these fatal collisions; with this system, a driver's level of tiredness is being tracked. This research proposes a computer vision-based smart drowsiness system that uses the characteristics of eye pixels in video frames to determine a driver's eye condition. To determine a driver's level of tiredness in real time, a camera can be mounted at the intersection of the front mirror on one side of the car. This allows for continuous video acquisition.