KOTEK, Ondřej and Šimon ŘEŘUCHA. Visual Diagnostics of Vehicle Driver. In AiM2008. Trenčín: Faculty of Mechatronics, Alexander Dubcek University of Trencin, Slovakia. p. 65-70. ISBN 978-80-8075-359-7. 2008.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name Visual Diagnostics of Vehicle Driver
Name in Czech Vizuální diagnostika řidiče vozidel
Authors KOTEK, Ondřej (203 Czech Republic) and Šimon ŘEŘUCHA (203 Czech Republic, guarantor).
Edition Trenčín, AiM2008, p. 65-70, 6 pp. 2008.
Publisher Faculty of Mechatronics, Alexander Dubcek University of Trencin, Slovakia
Other information
Original language English
Type of outcome Proceedings paper
Field of Study 10201 Computer sciences, information science, bioinformatics
Country of publisher Czech Republic
Confidentiality degree is not subject to a state or trade secret
RIV identification code RIV/00216224:14330/08:00027079
Organization unit Faculty of Informatics
ISBN 978-80-8075-359-7
Keywords in English image processing; HMI; fatigue detection; attention
Tags attention, fatigue detection, HMI, image processing
Tags International impact, Reviewed
Changed by Changed by: Mgr. Šimon Řeřucha, Ph.D., učo 60382. Changed: 30/4/2009 00:28.
Abstract
The statistics has proven that the major cause of traffic accidents is insufficient attention paid to the traffic situation by the driver. One of the most common causes of decreased attention is fatigue and the probably most serious consequence is a microsleep. Our objective is to propose a robust method for diagnostics of drivers' level of attention by the means of visual recognition; this method is intended to be used with conjunction with other methods (e.g. EEG assessment) to achieve better accuracy. This contribution presents the our concept of "visual diagnostics" and our preliminary experiments with AAM method. We have sought for optimal parameters and training set for the AAM model creation and tested them against certain states that were expected to have significant impact on the recognition results. We have identified several factors that have significant negative impact on the accuracy and proposed guidelines to build the model. We also concluded that the parameters influence the accuracy and the robustness against particular phenomenons depends actually less than the respective training set. The results indicates that the method is suitable for target environment and can reliably provide desired information with sufficient reliability.
Abstract (in Czech)
Tento příspěvek představuje myšlenku "Vizuální diagnostiky", tj. metody, kdy je na základě obrazovéhp záznamu řidiče vyhodnocována míra únavy řidiče, a první experimenty s metodou Active Appearance Models (AAM), která je základem zpracování. Pomocí těchto experimentů jsme hledali optimální parametry trénovaní a zpracování a testovali je oproti situacím, u kterých jsme předpokládali významný dopad na úspěšnost rozpoznání obrazu. Ve výsledku jsme identifikovali sadu faktorů, které mají negativní vliv a navrhli základní vodítka pro stavbu modelu. Výsledky naznačují, že obecně se metoda chová velmi robustně a spolehlivě.
Links
ME 949, research and development projectName: Analysis of negative impacts on driver attention
Investor: Ministry of Education, Youth and Sports of the CR, Research and Development Programme KONTAKT (ME)
PrintDisplayed: 19/4/2024 16:11