Driver fatigue monitoring method based on eyes state classification

An algorithm for eyes state classification based on radial basic function (RBF) neural network is proposed, and is used for driver fatigue monitoring. Firstly, after detecting the face, a method based on chroma space of color image is adopted to locate the eyes. Then the eigenvector relation to the...

Full description

Saved in:
Bibliographic Details
Published in2008 Chinese Control and Decision Conference pp. 2257 - 2260
Main Authors Yanli Liu, Heng Zhang, Juefu Liu
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2008
Subjects
Artificial neural networks
Classification algorithms
Driver circuits
Driver Fatigue
Fatigue
Feature extraction
Monitoring
Percent Eyelid Closure
Radial Basic Function
Road transportation
Online AccessGet full text

Cover

More Information
Summary:An algorithm for eyes state classification based on radial basic function (RBF) neural network is proposed, and is used for driver fatigue monitoring. Firstly, after detecting the face, a method based on chroma space of color image is adopted to locate the eyes. Then the eigenvector relation to the features of eyes region is extracted, and put into the RBF neural network to classify the eyes states: invigoration, sag or dormancy. With the classification results, the PERCLOS and blink frequency, which are the most effective parameters of fatigue detection, are figured out to judge the degree of the driver fatigue. The experiments results show that the proposed method is so fast and precise that it can be used to online driver fatigue monitoring.
ISBN:9781424417339
1424417333
ISSN:1948-9439
1948-9447
DOI:10.1109/CCDC.2008.4597725