A neural-network-based system for monitoring driver fatigue

Abstract

A driver's lack of attention due to fatigue or sleepiness is one of the major reasons for traffic accidents. As a result, over the past ten years there has been an increased interest in the methods, techniques and technologies for developing driver-fatigue monitoring systems. In this paper we describe a prototype of a neural-network-based system for monitoring driver fatigue. The system consists of a combination of neural-network-based modules for the extraction of visual bio-behavioural features and a knowledge-based decision module. The prototype of the system was tested under laboratory conditions and the results of the experiment are presented.