Incorporating global and local observation models for human pose tracking

Tracking human pose is attractive to many applications such as Human Robot Interface (HRI), motion capture system, video surveillance, action recognition, etc. Though various methods were introduced during last decades, including both color and depth camera based, it is still considered that feature...

Full description

Saved in:
Bibliographic Details
Published in2013 IEEE RO-MAN pp. 25 - 30
Main Authors Nam-Gyu Cho, Seong-Whan Lee
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2013
Subjects
Graphical models
Histograms
Image color analysis
Image edge detection
Legged locomotion
Three-dimensional displays
Tracking
Online AccessGet full text

Cover

More Information
Summary:Tracking human pose is attractive to many applications such as Human Robot Interface (HRI), motion capture system, video surveillance, action recognition, etc. Though various methods were introduced during last decades, including both color and depth camera based, it is still considered that feature sets for them are not discriminative enough. In this paper, we propose a human pose tracking method based on a graphical model which incorporates global and local feature sets including Histogram of Oriented Gradients (HOG) and color distribution. HumanEva-I dataset is used for testing effectiveness of the proposed method.
ISSN:1944-9445
1944-9437
DOI:10.1109/ROMAN.2013.6628526