%0 Journal Article
%T Action-specific motion prior for efficient bayesian 3D human body tracking
%A Ignasi Rius
%A Jordi Gonzalez
%A J. Varona
%A Xavier Roca
%J Pattern Recognition
%D 2009
%V 42
%N 11
%@ 0031-3203
%F Ignasi Rius2009
%O ISE
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=1159), last updated on Tue, 04 Mar 2014 10:07:33 +0100
%X In this paper, we aim to reconstruct the 3D motion parameters of a human bodymodel from the known 2D positions of a reduced set of joints in the image plane.Towards this end, an action-specific motion model is trained from a database of realmotion-captured performances. The learnt motion model is used within a particlefiltering framework as a priori knowledge on human motion. First, our dynamicmodel guides the particles according to similar situations previously learnt. Then, the solution space is constrained so only feasible human postures are accepted as valid solutions at each time step. As a result, we are able to track the 3D configuration of the full human body from several cycles of walking motion sequences using only the 2D positions of a very reduced set of joints from lateral or frontal viewpoints.
%U http://dx.doi.org/10.1016/j.patcog.2009.02.012
%P 2907–2921