A deep learning approach to detect drowsy drivers in real time

Abstract

Fatigue and microsleep are the reasons behind many severe road accidents. These can be avoided if the symptoms of fatigue are detected on time. This paper describes a real-time system for monitoring driver vigilance. Driver drowsiness detection algorithms in the past have proven to work in controlled environments but have not been implemented on a wide scale as of yet. Algorithms in the past suggest calculating a scalar value known as Eye Aspect Ratio (EAR) and detect drowsiness by comparing its instantaneous value with a previously configured value. We propose a generalised approach using Convolution Neural Networks (CNN) in this paper. Our algorithm tracks the driver's eyes and feeds it into a pre-trained that predicts the state of the eye. Once the prediction is obtained, we would be able to detect if the driver is drowsy or not. The main components of our system include a camera, for real time image acquisition, a processor for running algorithms to process the acquired image and an alarm system to warn the driver when the symptoms are detected in order to avoid potential accidents. © 2019 IEEE.