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...
The aim of this paper is to propose efficient tools for analysing shape families using morphological operators. The developments include the definition of shape statistics (mean a...
We are researching for real-time hand shape estimation, which we are going to apply to user interface and interactive applications. We have employed a computer vision approach, sin...
We describe the BodySpace system, which uses inertial sensing and pattern recognition to allow the gestural control of a music player by placing the device at different parts of t...
Steven Strachan, Roderick Murray-Smith, M. Sile O'...