Share Email Print

Proceedings Paper

Improvement of HMM-based action classification by using state transition probability
Author(s): Yuka Kitamura; Haruki Aruga; Manabu Hashimoto
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We propose a method to classify multiple similar actions which are contained in human behaviors by considering a weak-constrained order of “actions”. The proposed method regards the human behavior as a combination of “action” patterns which have order constrained weakly. In this method, actions are classified by using not only image features but also consistency of transitions between an action and next action. By considering such an action transition, our method can recognize human behavior even if image features of different action are similar to each other. Based on this idea, we have improved the previous HMM-based algorithm effectively. Through some experiments using test image sequences of human behavior appeared in a bathroom, we have confirmed that the average classification success rate is 97 %, which is about 53 % higher than the previous method.

Paper Details

Date Published: 30 April 2015
PDF: 7 pages
Proc. SPIE 9534, Twelfth International Conference on Quality Control by Artificial Vision 2015, 95340S (30 April 2015); doi: 10.1117/12.2182836
Show Author Affiliations
Yuka Kitamura, Chukyo Univ. (Japan)
Haruki Aruga, Chukyo Univ. (Japan)
Manabu Hashimoto, Chukyo Univ. (Japan)

Published in SPIE Proceedings Vol. 9534:
Twelfth International Conference on Quality Control by Artificial Vision 2015
Fabrice Meriaudeau; Olivier Aubreton, Editor(s)

© SPIE. Terms of Use
Back to Top