This paper presents a Bayesian framework for multi-cue 3D object tracking of deformable objects. The proposed spatio-temporal object representation involves a set of distinct linea...
Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the di...
Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the dis...
We derive a probabilistic framework for robust, realtime, visual tracking of multiple previously unseen objects from a moving camera. This framework models the discrete depth orde...
An original concept for computing instantaneous 3D pose and 3D velocity of fast moving objects using a single view is proposed, implemented and validated. It takes advantage of the...
Omar Ait-Aider, Nicolas Andreff, Jean-Marc Lavest,...