Abstract | ||
---|---|---|
We present an extension for variable length Markov models (VLMMs) to allow for modelling of continuous input data and show that the generative properties of these VLMMs are a powerful tool for dealing with real world tracking issues. We explore methods for addressing the temporal correspondence problem in the context of a practical hand tracker, which is essential to support expectation in task-based control using these behavioural models. The hand tracker forms a part of a larger multi-component distributed system, providing 3-D hand position data to a gesture recogniser client. We show how the performance of such a hand tracker can be improved by using feedback from the gesture recogniser client. In particular, feedback based on the generative extrapolation of the recogniser's internal models is shown to help the tracker deal with mid-term occlusion. We also show that VLMMs can be used as a means to inform the prior in an expectation maximisation (EM) process used for joint spatial and temporal learning of image features. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1016/j.imavis.2005.08.010 | Image Vision Comput. |
Keywords | Field | DocType |
3-d hand position data,gesture recogniser client,temporal learning,data association,temporal correspondence problem,variable length markov models,3-d tracking,task-based control,continuous input data,hand tracker,temporal structure,expectation maximisation,tracker deal,practical hand tracker,generative extrapolation,generative property,markov model,image features,internal model,correspondence problem,distributed system | Gesture,Computer science,Artificial intelligence,Temporal learning,Correspondence problem,Computer vision,Pattern recognition,Feature (computer vision),Markov model,Extrapolation,Data association,Generative grammar,Machine learning | Journal |
Volume | Issue | ISSN |
26 | 1 | Image and Vision Computing |
Citations | PageRank | References |
1 | 0.36 | 16 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kingsley Sage | 1 | 8 | 1.56 |
jon howell | 2 | 585 | 39.63 |
Hilary Buxton | 3 | 491 | 135.93 |
Antonis A. Argyros | 4 | 1684 | 104.99 |