DocumentCode
398442
Title
Head pose localization based on multicue fusion*
Author
Wei, Yucheng ; Tan, Tieniu ; Wang, Yunhong
Author_Institution
Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China
Volume
2
fYear
2003
fDate
14-17 Sept. 2003
Abstract
User´s face localization and head pose estimation play an essential role in the application of face-to-face human-computer interactive systems. In this paper, we formulate pose localization in a Bayesian framework by particle sampling. Proposal distribution fusing multiple cues such as color, shape and motion is defined to realize pose localization and tracking, which effectively enhances the performance of particle sampling. Experiment results on static images and real videos show the efficiency of our algorithm.
Keywords
face recognition; human computer interaction; image enhancement; image sampling; Bayesian framework; distribution fusing multiple cue; face-face human-computer interactive system; head pose estimation; head pose localization; image enhancement; image sampling; multicue fusion; pose tracking; real video; static image; user face localization; Bayesian methods; Face detection; Head; Image sampling; Interactive systems; Particle tracking; Probability; Proposals; Shape; Videos;
fLanguage
English
Publisher
ieee
Conference_Titel
Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on
ISSN
1522-4880
Print_ISBN
0-7803-7750-8
Type
conf
DOI
10.1109/ICIP.2003.1246823
Filename
1246823
Link To Document