In this paper, we present a method of object classification within the context of Visual Surveillance. Our goal is the classification of tracked objects into one of the two classe...
John-Paul Renno, Dimitrios Makris, Graeme A. Jones
A new algorithm for performing classification with imperfectly labeled data is presented. The proposed approach is motivated by the insight that the average prediction of a group ...
We propose a method for human activity recognition in videos, based on shape analysis. We define local shape descriptors for interest points on the detected contour of the human a...
Abstract In this paper an approach for motion capture of dressed people is presented. A cloth draping method is incorporated in a silhouette based motion capture system. This leads...
Bodo Rosenhahn, Uwe G. Kersting, Katie Powell, Rei...
A Bayesian marked point process (MPP) model is developed
to detect and count people in crowded scenes. The
model couples a spatial stochastic process governing number
and placem...