A Deep-Learning Method to Predicting Traffic Accidents Due to Drowse

Abstract

Many accidents occur as a result of driving sleepiness. It is becoming one of the leading causes of traffic accidents. According to recent data, many accidents were caused by driver tiredness. Thousands of people are killed in car accidents caused by drowsy driving. Drowsiness is responsible for more than 30 percent of all accidents. Driver sleepiness is one of the leading causes of accidents worldwide. Detecting the driver's sleepiness is one of the most reliable methods of determining driver weariness. To avoid this, a device that detects sleepiness and informs the driver is necessary, perhaps saving a life. In this study, we describe a system for detecting driver sleepiness. In this case, the driver is constantly observed through the camera. This model employs image processing algorithms that primarily concentrate on the car's motorist's face and eyes. The software analyzes the motorist's face and forecasts the motorist's eye blinking based on the eye area. To calculate Per close, we employ an algorithm that tracks and analyses drivers' features and eyes. If the blinking rate is too fast, the system notifies the driver with a sound.