Head detection of the car occupant based on contour models and support vector machines

Authors:
Yong-Guk Kim;Jeong-Eom Lee;Sang-Jun Kim;Soo-Mi Choi;Gwi-Tae Park
Affiliations:
School of Computer Engineering, Sejong University, Seoul, Korea;Dept. of Electrical Engineering, Korea University, Seoul, Korea;Dept. of Electrical Engineering, Korea University, Seoul, Korea;School of Computer Engineering, Sejong University, Seoul, Korea;Dept. of Electrical Engineering, Korea University, Seoul, Korea
Venue:
IEA/AIE'2005 Proceedings of the 18th international conference on Innovations in Applied Artificial Intelligence
Year:
2005

Citing 2
Cited 1

Digital image processing: principles and applications

Digital image processing: principles and applications
The nature of statistical learning theory

The nature of statistical learning theory

Head detection and tracking for the car occupant’s pose recognition

IEA/AIE'06 Proceedings of the 19th international conference on Advances in Applied Artificial Intelligence: industrial, Engineering and Other Applications of Applied Intelligent Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Head detection is a relatively well studied problem in computer vision. Several methods for head detection are proposed such as motion based method [6], disparity map [7], skin color method [8] and a head-shoulder contour [9]. Those methods are mainly based on stereo vision and color information for detecting the head. Our application domain is the telematics, especially within the car. In such environment, the illumination level is very variable. Moreover, we may need to use infrared illumination to capture the occupant in the night. Therefore, it is difficult to utilize the color information.