Abstract | ||
---|---|---|
Region-based tracking in a temporal image sequence is described as a segmentation of current frame into a set of non-overlapping regions: the tracking regions and the non-tracking region. The segmentation is viewed to be a Markov labeling process. Based on the key idea of using a doubly stochastic prior model, the optimal estimation for the label field is found by the minimization of a differentiable function. We exploit the feature-spatial probabilistic representation of a region as the conditional distribution in the Bayesian framework, which makes our tracker robust to local deformation and partial occlusion. The continuity of the objective function leads to a much faster numerical implementation. Very promising experimental results on some real-world sequences are presented to illustrate the performance of the presented algorithm. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/ACVMOT.2005.100 | Proceedings - IEEE Workshop on Motion and Video Computing, MOTION 2005 |
Keywords | Field | DocType |
bayesian methods,stochastic processes,tracking,conditional distribution,objective function,robustness,hidden markov models,optimal estimation,labeling,information security,lattices,image segmentation | Computer vision,Conditional probability distribution,Pattern recognition,Segmentation,Computer science,Markov chain,Stochastic process,Optimal estimation,Image segmentation,Artificial intelligence,Probabilistic logic,Hidden Markov model | Conference |
Volume | Issue | ISSN |
null | null | null |
ISBN | Citations | PageRank |
0-7695-2271-8-2 | 0 | 0.34 |
References | Authors | |
6 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiao-Tong Yuan | 1 | 792 | 49.95 |
Shutang Yang | 2 | 20 | 5.09 |
Hongwen Zhu | 3 | 144 | 15.68 |