System-On Based Driver Drowsiness Detection and Warning System

Abstract

The aim of this project is to detect the drowsiness level of the driver in the vehicle, to warn the driver and to prevent possible accidents. Percentage Eye Closure (PERCLOS) and Convolutional Neural Network (CNN) are used to detect drowsiness. The system is implemented on Xilinx PYNQ-Z2 development board. The system is tested under real world conditions in real time. A high accuracy rate of 92% and a fast working system with 0.8 s is achieved. A speaker is activated to warn the driver when drowsiness is detected. Moreover, the drowsiness information is sent to the cloud by using a Wi-Fi module.