Abstract | ||
---|---|---|
Usually a uniform observation strategy will result in frustrated tracking processes. To address this problem, we construct a flexible model with Hierarchical Dynamic Bayesian Network by introducing hidden variables to infer the intrinsic properties of the state and observation spaces. With this model, a dynamic-mapping is built between target state space and the observation space. Based on a decoupling based inference strategy, a tractable solution for this algorithm is proposed. Experiments of human face tracking under various poses and occlusions show promising results. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1007/978-3-540-30542-2_76 | PCM (2) |
Keywords | Field | DocType |
uniform observation strategy,hierarchical dynamic bayesian network,frustrated tracking process,inference strategy,human face tracking,intrinsic property,hidden variable,flexible model,observation space,target state space,visual tracking,hidden variables,monte carlo,face tracking,dynamic bayesian network,state space | Computer vision,Pattern recognition,Inference,Computer science,Decoupling (cosmology),Eye tracking,Artificial intelligence,Hidden variable theory,State space,Facial motion capture,Dynamic Bayesian network | Conference |
Volume | ISSN | ISBN |
3332 | 0302-9743 | 3-540-23977-4 |
Citations | PageRank | References |
0 | 0.34 | 9 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hua Li | 1 | 24 | 1.48 |
Rong Xiao | 2 | 559 | 36.27 |
Hong-Jiang ZHANG | 3 | 17378 | 1393.22 |
Lizhong Peng | 4 | 92 | 17.96 |