|
Published Articles >> Table of Contents >> Abstract
IEEE International Workshop on Analysis and Modeling of Faces and Gestures
p. 135
Multi-Modal Face Tracking Using Bayesian Network
Fang Liu, Tsinghua University, Beijing
Xueyin Lin, Tsinghua University, Beijing
Stan Z Li, Microsoft Research China, Beijing
Yuanchun Shi, Tsinghua University, Beijing
Full Article Text:
  
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/AMFG.2003.1240835
Send link to a friend
| Abstract |
|
This paper presents a Bayesian network based multi-modal
fusion method for robust and real-time face
tracking. The Bayesian network integrates a prior of
second order system dynamics, and the likelihood cues
from color, edge and face appearance. While different
modalities have different confidence scales, we encode
the environmental factors related to the confidences of
modalities into the Bayesian network, and develop a
Fisher discriminant analysis method for learning optimal
fusion.
The face tracker may track multiple faces under
different poses. It is made up of two stages. First
hypotheses are efficiently generated using a coarse-to-fine
strategy; then multiple modalities are integrated in
the Bayesian network to evaluate the posterior of each
hypothesis. The hypothesis that maximizes a posterior
(MAP) is selected as the estimate of the object state.
Experimental results demonstrate the robustness and
real-time performance of our face tracking approach.
|
 Additional Information
|
Citation:
Fang Liu, Xueyin Lin, Stan Z Li, Yuanchun Shi,
"Multi-Modal Face Tracking Using Bayesian Network,"
amfg,
p. 135,
IEEE International Workshop on Analysis and Modeling of Faces and Gestures,
2003
|
|
