DMCA
Coupled hidden Markov models for complex action recognition (1996)
Cached
Download Links
| Citations: | 501 - 22 self |
BibTeX
@MISC{Brand96coupledhidden,
author = {Matthew Brand and Nuria Oliver and Alex Pentland},
title = {Coupled hidden Markov models for complex action recognition},
year = {1996}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We present algorithms for coupling and training hidden Markov models (HMMs) to model interacting processes, and demonstrate their superiority to conventional HMMs in a vision task classifying two-handed actions. HMMs are perhaps the most successful framework in perceptual computing for modeling and classifying dynamic behaviors, popular because they offer dynamic time warping, a training algorithm, and a clear Bayesian semantics. However, the Markovian framework makes strong restrictive assumptions about the system generating the signal---that it is a single process having a small number of states and an extremely limited state memory. The single-process model is often inappropriate for vision (and speech) applications, resulting in low ceilings on model performance. Coupled HMMs provide an efficient way to resolve many of these problems, and offer superior training speeds, model likelihoods, and robustness to initial conditions. 1. Introduction Computer vision is turning to problems...
Keyphrases
hidden markov model complex action recognition conventional hmms two-handed action superior training speed introduction computer vision efficient way model likelihood clear bayesian semantics vision task strong restrictive assumption dynamic behavior limited state memory low ceiling perceptual computing model performance initial condition single-process model small number markovian framework dynamic time warping single process successful framework training algorithm
