Complex virtual environments can be simulated with physical or procedural motion. Physical motion is more realistic, but requires the integration of an ordinary differential equat...
In this paper, we propose a 2D visual motion estimation method which can be exploited to achieve a dynamic positioning (eg. by gaze control) with respect to a sea-bottom area of i...
This paper presents an iterative maximum likelihood framework for motion segmentation via the pairwise checking of pixel blocks. We commence from a characterisation of the motion ...
We present methods for learning and tracking human motion in video. We estimate a statistical model of typical activities from a large set of 3D periodic human motion data by segm...
Dirk Ormoneit, Hedvig Sidenbladh, Michael J. Black...
Even if the problem of human action categorization from videos has received a lot of attention during the past decade, it remains a challenging problem in operative conditions due...