Academic Journals Database
Disseminating quality controlled scientific knowledge

Unsupervised Posture Modeling and Recognition based on Gaussian Mixture Model and EM Estimation

ADD TO MY LIST
 
Author(s): zhu xijun | Wang Chuanxu

Journal: Journal of Software
ISSN 1796-217X

Volume: 6;
Issue: 8;
Start page: 1445;
Date: 2011;
Original page

Keywords: NERF C-means | posture modeling | posture recognition | GMM

ABSTRACT
In this paper, we proposed an unsupervised posture modeling method based on Gaussian Mixture Model (GMM). Specifically, each learning posture is described based on its movement features by a set of spatial-temporal interest points (STIPs), salient postures are then clustered from these training samples by an unsupervised algorithm, here we give the comparison of four candidate classification methods and find the optimal one. Furthermore, each clustered posture type is modeled with GMM according to Expectation Maximization (EM) estimation. The experiment results proved that our method can effectively model postures and can be used for posture recognition in video.
Affiliate Program      Why do you need a reservation system?