| | |
Summary:
, ,
. , ,
. , Boosting,
. .
, ,
Part Detector Based Human Pose Estimation in Monocular Images and
Videos
Anonymous
Abstract Human pose estimation is an essential problem in computer vision area since it has many applications such as
human activity analysis, human computer interaction and visual surveillance. In this paper, we focus on the 2D human
estimation problem in monocular images and videos. Based on part based graph inference method, we improve the
observation model and the inference method. We design a rotation invariant EdgeField feature, based on which a boosting
classifier is learnt as the observation model. The human pose estimation is done by a particle based belief propagation
inference method. Experiments show the effectiveness and the speed of the proposed method.
Key words: human pose estimation, EdgeField feature, belief propagation
,
,
.
|
