Non-intrusive drowsiness detection system- design,analysis and evaluation of non-intrusive driver drowsiness system using a Support Vector Machine and fault diagnosis system

Ashardi Abas

QR Code Link :
Type :	Thesis
Subject :	TL Motor vehicles. Aeronautics. Astronautics
Main Author :	Ashardi Abas
Title :	Non-intrusive drowsiness detection system- design,analysis and evaluation of non-intrusive driver drowsiness system using a Support Vector Machine and fault diagnosis system
Hits :	32

Place of Production :	Tanjong Malim
Publisher :	Fakulti Komputeran dan META-Teknologi
Year of Publication :	2011
Corporate Name :	Perpustakaan Tuanku Bainun
PDF Guest :	Click to view PDF file
PDF Full Text :	You have no permission to view this item.

Abstract : Perpustakaan Tuanku Bainun

The development of technologies for preventing drowsiness at the wheel is a major challenge in the_ field of accident avoidance systems. Preventing drowsiness during driving requires a method for_ accurately detecting a decline in driver alertness and a method for alerting and refreshing the_ driver. As a detection method, the authors have developed a system that uses image processing_ technology to analyse images of the road lane with a video camera integrated with steering wheel_ angle data collection from a car simulation system. The main contribution of this study is a novel_ algorithm_ for drowsiness detection and tracking, which is based on the incorporation of_ information from a road vision system and vehicle performance parameters. Refinement of the_ algorithm is more precisely detected the level of drowsiness by the implementation of a support_ vector machine classification for robust and accurate drowsiness warning system. The Support Vector_ Machine (SYM) classification technique diminished drowsiness level by using non intrusive systems,_ using standard equipment sensors, aim to reduce these road accidents caused by drowsiness drivers._ This detection system provides a non-contact technique for judging various levels of driver_ alertness and facilitates early detection of a decline in alertness during driving. The presented_ results are based on a selection of drowsiness database, which covers almost 60 hours of driving_ data collection measurements. All the parameters extracted from vehicle parameter data arc_ collected in a driving simulator. With all the features from a real vehicle, a SYM drowsiness_ detection model is constructed. After several improvements, the classification results showed a_ very good indication of drowsiness by using those systems. _

This material may be protected under Copyright Act which governs the making of photocopies or reproductions of copyrighted materials.
You may use the digitized material for private study, scholarship, or research.

Back to search page