Abstract | ||
---|---|---|
Objects can exhibit different dynamics at different spatio-temporal scales, a property that is often exploited by visual tracking algorithms. A local dynamic model is typically used to extract image features that are then used as inputs to a system for tracking the object using a global dynamic model. Approximate local dynamics may be brittle-point trackers drift due to image noise and adaptive background models adapt to foreground objects that become stationary-and constraints from the global model can make them more robust. We propose a probabilistic framework for incorporating knowledge about global dynamics into the local feature extraction processes. A global tracking algorithm can be formulated as a generative model and used to predict feature values thereby influencing the observation process of the feature extractor, which in turn produces feature values that are used in high-level inference. We combine such models utilizing a multichain graphical model framework. We show the utility of our framework for improving feature tracking as well as shape and motion estimates in a batch factorization algorithm. We also propose an approximate filtering algorithm appropriate for online applications and demonstrate its application to tasks in background subtraction, structure from motion and articulated body tracking. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1016/j.cviu.2006.11.022 | Computer Vision and Image Understanding |
Keywords | Field | DocType |
shape from motion,approximate models,global tracking algorithm,probabilistic graphical models,feature tracking,feature dynamic,image feature,global model,background subtraction,combining object,probabilistic tracking,generative model,feature value,global dynamic model,feature extractor,articulated body tracking,adaptive background model,predictive models,tracking,visual tracking,object recognition,artificial intelligence,feature extraction,object tracking,background noise,image noise,graphical models,ai,motion estimation,computer science,structure from motion,image features,hidden markov models | Background subtraction,Computer vision,Pattern recognition,Computer science,Feature (computer vision),Feature extraction,Artificial intelligence,Motion estimation,Probabilistic logic,Graphical model,Hidden Markov model,Generative model | Journal |
Volume | Issue | ISSN |
108 | 3 | Computer Vision and Image Understanding |
Citations | PageRank | References |
3 | 0.51 | 18 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Leonid Taycher | 1 | 240 | 19.37 |
John W. Fisher III | 2 | 878 | 74.44 |
Trevor Darrell | 3 | 22413 | 1800.67 |