TY - GEN
T1 - View invariant body pose estimation based on biased manifold learning
AU - Hur, Dongcheol
AU - Wallraven, Christian
AU - Lee, Seong Whan
PY - 2010
Y1 - 2010
N2 - In human body pose estimation, manifold learning is a popular technique for reducing the dimension of 2D images and 3D body configuration data. This technique, however, is especially vulnerable to silhouette variation such as caused by viewpoint changes. In this paper, we propose a novel approach that combines three separate manifolds for representing variations in viewpoint, pose and 3D body configuration. We use biased manifold learning to learn these manifolds with appropriately weighted distances. A set of four mapping functions are then learned by a generalized regression neural network for added robustness. Despite using only three manifolds, we show that this method can reliably estimate 3D body poses from 2D images with all learned viewpoints.
AB - In human body pose estimation, manifold learning is a popular technique for reducing the dimension of 2D images and 3D body configuration data. This technique, however, is especially vulnerable to silhouette variation such as caused by viewpoint changes. In this paper, we propose a novel approach that combines three separate manifolds for representing variations in viewpoint, pose and 3D body configuration. We use biased manifold learning to learn these manifolds with appropriately weighted distances. A set of four mapping functions are then learned by a generalized regression neural network for added robustness. Despite using only three manifolds, we show that this method can reliably estimate 3D body poses from 2D images with all learned viewpoints.
KW - Body pose analysis
KW - Manifold learning
KW - Non-linear dimensional reduction
KW - Supervised learning
KW - View-invariance
UR - http://www.scopus.com/inward/record.url?scp=78149483712&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78149483712&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2010.942
DO - 10.1109/ICPR.2010.942
M3 - Conference contribution
AN - SCOPUS:78149483712
SN - 9780769541099
T3 - Proceedings - International Conference on Pattern Recognition
SP - 3866
EP - 3869
BT - Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010
T2 - 2010 20th International Conference on Pattern Recognition, ICPR 2010
Y2 - 23 August 2010 through 26 August 2010
ER -