2008
Driver Fatigue Detection Using Video Recording of Face
ŘEŘUCHA, Šimon a Ondřej KOTEKZákladní údaje
Originální název
Driver Fatigue Detection Using Video Recording of Face
Název česky
Detekce únavy řidičů pomocí videozáznamu
Název anglicky
Driver Fatigue Detection Using Video Recording of Face
Autoři
ŘEŘUCHA, Šimon (203 Česká republika, garant) a Ondřej KOTEK (203 Česká republika)
Vydání
Praha, Driver Car Interaction & Interface 2008, 4 s. 2008
Nakladatel
Prague: Academy of Sciences of CR, Institute of Computer Science
Další údaje
Jazyk
čeština
Typ výsledku
Stať ve sborníku
Obor
10201 Computer sciences, information science, bioinformatics
Stát vydavatele
Česká republika
Utajení
není předmětem státního či obchodního tajemství
Kód RIV
RIV/00216224:14330/08:00027934
Organizační jednotka
Fakulta informatiky
ISBN
978-80-87136-04-1
Klíčová slova anglicky
fatigue detection; Active Appearance Model; man-machine system; operator support; statistics
Příznaky
Mezinárodní význam
Změněno: 30. 4. 2009 00:43, Mgr. Šimon Řeřucha, Ph.D.
V originále
The safety of road transportation is still a topical issue. The principal problem we aim at is the detection of states when the driver's attention is not sufficient for safe driving using the analysis of video recording that captures driver's face. Our technique divides into several steps that use various methods to solve a part of the problem. The most fundamental is AAM for landmark point extraction, geometric methods for head posture computation, statistic methods for event detection and finally a rule-based expert system for final assessment. Our contribution presents the concept of "visual diagnostics" of a vehicle driver, describe particular steps and discuss methodology and introduce the experiments that validate the function of our approach. The results indicate that the method is suitable for target environment and can reliably provide desired information with sufficient reliability.
Anglicky
The safety of road transportation is still a topical issue. The principal problem we aim at is the detection of states when the driver's attention is not sufficient for safe driving using the analysis of video recording that captures driver's face. Our technique divides into several steps that use various methods to solve a part of the problem. The most fundamental is AAM for landmark point extraction, geometric methods for head posture computation, statistic methods for event detection and finally a rule-based expert system for final assessment. Our contribution presents the concept of "visual diagnostics" of a vehicle driver, describe particular steps and discuss methodology and introduce the experiments that validate the function of our approach. The results indicate that the method is suitable for target environment and can reliably provide desired information with sufficient reliability.
Návaznosti
| ME 949, projekt VaV |
|