TY - GEN
T1 - Incorporating global and local observation models for human pose tracking
AU - Cho, Nam Gyu
AU - Lee, Seong Whan
PY - 2013
Y1 - 2013
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84889585978&partnerID=8YFLogxK
U2 - 10.1109/ROMAN.2013.6628526
DO - 10.1109/ROMAN.2013.6628526
M3 - Conference contribution
AN - SCOPUS:84889585978
SN - 9781479905072
T3 - Proceedings - IEEE International Workshop on Robot and Human Interactive Communication
SP - 25
EP - 30
BT - 22nd IEEE International Symposium on Robot and Human Interactive Communication
T2 - 22nd IEEE International Symposium on Robot and Human Interactive Communication: "Living Together, Enjoying Together, and Working Together with Robots!", IEEE RO-MAN 2013
Y2 - 26 August 2013 through 29 August 2013
ER -