Learning temporal structure for task based control

doi:10.1016/j.imavis.2005.08.010

Learning temporal structure for task based control

2008-01-01

1

PRE

AI

DOI：10.1016/j.imavis.2005.08.010

Original

Original request for help

Save

Abstract

En 中文

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. (c) 2006 Elsevier B.V. All rights reserved.

Keywords:

variable length Markov models

temporal learning

3-d tracking

data association

task-based control

Learning temporal structure for task based control

Abstract

AI Summary

Journal

Organization