By Topic

Video Human Motion Recognition Using Knowledge-Based Hybrid Method

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Myunghoon Suk ; Dept. of Comput. Sci., Univ. of Texas at Dallas, Richardson, TX, USA ; Ramadass, A. ; Yohan Jin ; Prabhakaran, B.

Human motion recognition in video data has several interesting applications in fields such as gaming, senior/assisted living environments, and surveillance. In these scenarios, we might have to consider adding new motion classes (i.e. new types of human motions to be recognized) as well as new training data (say, for handling different type of subjects). Hence, both accuracy of classification and training time for the machine learning algorithms become important performance parameters in these cases. In this paper, we propose a Knowledge Based Hybrid (KBH) method that can compute the probabilities for Hidden Markov Models (HMMs) associated with different human motion classes. This computation is facilitated by appropriately mixing features from two different media types (3D motion capture and 2D video). We conducted a variety of experiments comparing the proposed KBH for HMMs and the traditional Baum-Welch algorithms. With the advantage of computing the HMMs parameters in a non-iterative manner, the KBH method outperforms the Baum-Welch algorithm both in terms of accuracy as well as reduced training time.

Published in:

Multimedia (ISM), 2010 IEEE International Symposium on

Date of Conference:

13-15 Dec. 2010