This paper introduces a new feature-based technique for implicitly modelling objects in visual surveillance. Previous work has generally employed background subtraction and other ...
We propose a novel Active Volume Model (AVM) which deforms in a free-form manner to minimize energy. Unlike Snakes and level-set active contours which only consider curves or surfa...
Human movements are important cues for recognizing human actions, which can be captured by explicit modeling and tracking of actor or through space-time low-level features. Howeve...
We investigate the problem of learning the structure of an articulated object, i.e. its kinematic chain, from feature trajectories under affine projections. We demonstrate this po...
We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and p...
Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris...