Logo LVSN
EnglishAccueil
A proposPersonnesRecherchePublicationsEvenementsProfil
A propos
Publications

 

 

 

 

CERVIM

REPARTI

MIVIM

A Computer Vision System for Automatic Analysis of the Cephalo-Ocular Behaviour of Drivers


Frédéric Ntawiniga, Denis Laurendeau, Normand Teasdale and Martin Simoneau


Abstract - A computer vision system for automatic analysis of the cephalo-ocular behaviour of drivers is presented. Driving is an important activity for a large percentage of the population. In Canada, one out of five drivers is over 65 years old. In the US, there are indications that 50% of older drivers suffering from mild dementia still continue to drive for several years. In this context, our group is currently developing an intelligent system composed of a driving simulator offering a rich collection of scenarios for assessing driving abilities combined with a computer vision system for extracting information on cephalo-ocular behaviour and visual search patterns of drivers. This paper describes the head motion tracking algorithm in 3D space, which is an important component of the computer vision system that is responsible for estimating the driver's head pose as a function of time.

download document

Bibtex:

@article{Ntawiniga683,
    author    = { Frédéric Ntawiniga and Denis Laurendeau and Normand Teasdale and Martin Simoneau },
    title     = { A Computer Vision System for Automatic Analysis of the Cephalo-Ocular Behaviour of Drivers },
    publisher = { Fifth International Conference on INDUSTRIAL AUTOMATION },
    year      = { 2007 },
    month     = { June },
    journal   = { Fifth International Conference on INDUSTRIAL AUTOMATION },
    keywords  = { 3D head tracking, detection, tracking, stereo, matching, 3D reconstruction, monochrome, Kalman filter, neural network },
    location  = { Montreal, Quebec, Canada },
    language  = { English }
}

Dernière modification: 2007/06/16 par ntawini

     
   
   

©2002-. Laboratoire de Vision et Systèmes Numériques. Tous droits réservés