By Topic

Human Pose Tracking Algorithm Based on Skeleton-Texture Model

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
$33 $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

2 Author(s)
Yi Ouyang ; Coll. of Comput. Sci., Zhejiang Univ., Hangzhou, China ; Sanyuan Zhang

In order to achieve good tracking results in single camera environment, the human pose of recognition, based on a skeleton and texture model of video algorithms to identify the body is proposed. Single-camera in the background and complexity of the environment, the target audience can only show 2-D information. The algorithm will be the first skeleton to the human body in accordance with the balance weighted tree modeling approach, combined with the skin texture characteristics of the skeleton structure, texture model. Particle filter used for detection and tracking human body. Experiments show that the skeleton model and texture of video algorithms to identify the body with a high recognition rate and robustness, and can do real-time interaction.

Published in:

Future Computer and Communication, 2009. FCC '09. International Conference on

Date of Conference:

6-7 June 2009