The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON INFORMATION SCIENCE AND APPLICATIONS
Transactions ID Number: 89-774
Full Name: Xiaoyan Wang
Position: Lecturer
Age: ON
Sex: Female
Address: College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou,310023
Country: CHINA
Tel:
Tel prefix:
Fax:
E-mail address: xiaoyanwang@zjut.edu.cn
Other E-mails: wangxiaoyan817@gmail.com
Title of the Paper: A Head Pose and Facial Actions Tracking Method Based on Effecient Online Appearance Models
Authors as they appear in the Paper: Xiaoyan Wang, Xiangsheng Huang, Huiwen Cai, Xin Wang
Email addresses of all the authors: xiaoyanwang@zjut.edu.cn, xiangshenghuang@gmail.com, huiwen.cai@ia.ac.cn, xinw@zjut.edu.cn
Number of paper pages: 11
Abstract: Target modeling and model fitting are the two important parts of the problem of object tracking. The former has to provide a good reference for the latter. Online appearance models (OAM) has been successfully used for facial features tracking on account of their strong ability to adapt to variations, however, it suffers from time-consuming model fitting. Inverse Compositional Image Alignment (ICIA) algorithm has been proved to be an efficient, robust and accurate fitting algorithm. In this work, we introduce an efficient online appearance models based on ICIA, and apply it to track head pose and facial actions in video. A 3d parameterized model, CANDIDE model, is used to model the face and facial expression, a weak perspective projection method is used to model the head pose, an adaptive appearance model is built on shape free texture, and then the efficient fitting algorithm is taken to track parameters of head pose and facial actions. Experiments demonstrate that!
the tracking algorithm is robust and efficient.
Keywords: Object tracking, Online appearance models, Inverse Compositional Image Alignment, model learning, facial feature tracking
EXTENSION of the file: .pdf
Special (Invited) Session: Effecient Online Appearance Models For Object Tracking
Organizer of the Session: 637-312
How Did you learn about congress:
IP ADDRESS: 221.12.171.116
