Share Email Print

Proceedings Paper

Action classification using a discriminative non-parametric Hidden Markov Model
Author(s): Natraj Raman; S. J. Maybank; Dell Zhang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We classify human actions occurring in videos, using the skeletal joint positions extracted from a depth image sequence as features. Each action class is represented by a non-parametric Hidden Markov Model (NP-HMM) and the model parameters are learnt in a discriminative way. Specifically, we use a Bayesian framework based on Hierarchical Dirichlet Process (HDP) to automatically infer the cardinality of hidden states and formulate a discriminative function based on distance between Gaussian distributions to improve classification performance. We use elliptical slice sampling to efficiently sample parameters from the complex posterior distribution induced by our discriminative likelihood function. We illustrate our classification results for action class models trained using this technique.

Paper Details

Date Published: 24 December 2013
PDF: 5 pages
Proc. SPIE 9067, Sixth International Conference on Machine Vision (ICMV 2013), 906710 (24 December 2013); doi: 10.1117/12.2051084
Show Author Affiliations
Natraj Raman, Univ. of London (United Kingdom)
S. J. Maybank, Univ. of London (United Kingdom)
Dell Zhang, Univ. of London (United Kingdom)

Published in SPIE Proceedings Vol. 9067:
Sixth International Conference on Machine Vision (ICMV 2013)
Branislav Vuksanovic; Antanas Verikas; Jianhong Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top