TY  - CONF
AU  - Wenjuan Gong
AU  - Andrew Bagdanov
AU  - Xavier Roca
AU  - Jordi Gonzalez
A2  - AMDO
PY  - 2010//
TI  - Automatic Key Pose Selection for 3D Human Action Recognition
BT  - 6th International Conference on Articulated Motion and Deformable Objects
SP  - 290–299
VL  - 6169
PB  - Springer Verlag
N2  - This article describes a novel approach to the modeling of human actions in 3D. The method we propose is based on a “bag of poses” model that represents human actions as histograms of key-pose occurrences over the course of a video sequence. Actions are first represented as 3D poses using a sequence of 36 direction cosines corresponding to the angles 12 joints form with the world coordinate frame in an articulated human body model. These pose representations are then projected to three-dimensional, action-specific principal eigenspaces which we refer to as aSpaces. We introduce a method for key-pose selection based on a local-motion energy optimization criterion and we show that this method is more stable and more resistant to noisy data than other key-poses selection criteria for action recognition.
SN  - 0302-9743
SN  - 978-3-642-14060-0
UR  - http://dx.doi.org/10.1007/978-3-642-14061-7_28
N1  - ISE
ID  - Wenjuan Gong2010
ER  -