Drowsy Driver Detection Using Haar and PAC

Abstract

Drowsy driver detection system is one of the potential applications of intelligent vehicle systems. Previous approaches to drowsiness detection primarily make pre-assumptions about the relevant behavior, focusing on blink rate, eye closure, and yawning. Driver drowsiness contributes to many car crashes and fatalities in our country. Machine learning algorithms have shown to help in detecting driver drowsiness. In our proposed method Haar classifier and Probably Approximately Correct(PAC)are used for detecting driver drowsiness. It is one of the few object detection methods with the ability to detect faces. Haar classifier used for face recognition most probably eye detection and can optimize frequently used face measures by using PAC. The main idea behind this method is to develop a system which can detect fatigue of the driver and issue a timely warning. Existing method reveals that 78%, 68% and 68% accuracy by using SVM, Naive Bayes and PERCLOS algorithm. Our proposed method reveals that 89% and 84.6% accuracy respectively by using Haar and PAC algorithm. Its seems to be that our proposed methods are better than the existing method.