The present paper considers the supplement of prior knowledge about joint angle configurations in the scope of 3-D human pose tracking. Training samples obtained from an industrial...
Thomas Brox, Bodo Rosenhahn, Uwe G. Kersting, Dani...
In this paper, we suggest to model priors on human motion by means of nonparametric kernel densities. Kernel densities avoid assumptions on the shape of the underlying distribution...
Thomas Brox, Bodo Rosenhahn, Daniel Cremers, Hans-...
An interactive human segmentation approach is described. Given regions of interest provided by users, the approach iteratively estimates segmentation via a generalized EM algorith...
Zhe Lin, Larry S. Davis, David S. Doermann, Daniel...
Discriminative approaches for human pose estimation model the functional mapping, or conditional distribution, between image features and 3D pose. Learning such multi-modal models ...
In this paper, we make two contributions to the field of level set based image segmentation. Firstly, we propose shape dissimilarity measures on the space of level set functions wh...