DocumentCode :
2998409
Title :
A new rapid algorithm for driver face organ detection
Author :
Guo, Keyou ; Yu, Guizhen ; Li, Zhenhua
Author_Institution :
Coll. of Mech. Eng. & Autom., Beijing Technol. & Bus. Univ., Beijing
fYear :
2008
fDate :
1-3 Sept. 2008
Firstpage :
1502
Lastpage :
1506
Abstract :
The monitoring and warning system for the driverpsilas driving behavior plays an important role in enhancing the safety of vehicles. Monitoring and analyzing the driverpsilas facial status by using the machine vision is one of hotspots in the assistant safe driving system. The face detection and face organ location technology of the system are discussed firstly. By analyzing the actual drivers state , the driver face location was obtained using the Gray Variance algorithm. From the extreme points of the projective curve we may divide the face areas, and then can get the accurate face organ location based on OSTU algorithm. The samples proved that the algorithm was real-time and efficient. The research was the foundation for further information-collecting and state-analyzing of driverpsilas eyes.
Keywords :
computer vision; driver information systems; face recognition; human factors; monitoring; object detection; road safety; OSTU algorithm; assistant safe driving system; driver face location; driver face organ detection; driving behavior monitoring; driving behavior warning system; image gray variance algorithm; machine vision; projective curve; vehicle safety; Alarm systems; Algorithm design and analysis; Automation; Computerized monitoring; Condition monitoring; Educational institutions; Face detection; Machine vision; Surveillance; Vehicle safety; Driver Behaviour Surveillance; Face Organ Detection; Machine Vision; Real-Time;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Automation and Logistics, 2008. ICAL 2008. IEEE International Conference on
Conference_Location :
Qingdao
Print_ISBN :
978-1-4244-2502-0
Electronic_ISBN :
978-1-4244-2503-7
Type :
conf
DOI :
10.1109/ICAL.2008.4636391
Filename :
4636391
Link To Document :
بازگشت