TY - JOUR
T1 - Tracking people in three dimensions using a hierarchical model of dynamics
AU - Karaulova, I A
AU - Hall, P M
AU - Marshall, A D
N1 - ID number: ISI:000177523600012
PY - 2002/8
Y1 - 2002/8
N2 - We propose a novel hierarchical model of human dynamics for view independent tracking of a human figure in monocular video sequences. The model is trained using real data from a collection of people. The top of the hierarchy contains information about the whole body. The lower levels of the hierarchy contain more detailed information about possible poses of some subpart of the body. In this article we describe our model and present experiments that show we can recover 3D human figures from 2D images in a view independent manner, and also track people the system has not been trained on. (C) 2002 Elsevier Science B.V. All rights reserved.
AB - We propose a novel hierarchical model of human dynamics for view independent tracking of a human figure in monocular video sequences. The model is trained using real data from a collection of people. The top of the hierarchy contains information about the whole body. The lower levels of the hierarchy contain more detailed information about possible poses of some subpart of the body. In this article we describe our model and present experiments that show we can recover 3D human figures from 2D images in a view independent manner, and also track people the system has not been trained on. (C) 2002 Elsevier Science B.V. All rights reserved.
UR - http://dx.doi.org/10.1016/S0262-8856(02)00059-8
UR - https://www.scopus.com/pages/publications/0036683236
U2 - 10.1016/S0262-8856(02)00059-8
DO - 10.1016/S0262-8856(02)00059-8
M3 - Article
SN - 0262-8856
VL - 20
SP - 691
EP - 700
JO - Image and Vision Computing
JF - Image and Vision Computing
IS - 9-10
ER -