National audienceThe approach we investigate for point tracking combines within a stochastic filtering framework a dynamic model relying on the optical flow constraint and measurements provided by a matching technique. Based on this, two kinds of simple trackers are devised whose dynamic and measurements depend on image data. The first one is a linear tracker particularly well-suited to image sequences exhibiting global dominant motion situations. In this context, a conditional Kalman filter is derived through the use of a conditional linear minimum variance estimator. The second one is a nonlinear tracker built from a conditional particle filter. The two trackers allow us to deal with trajectories exhibiting abrupt changes. We present some...
Nous nous intéressons ici à la sélection automatique de points d'intérêt en vue de leur suivi dans u...
National audienceThis article presents a novel approach to person tracking within large-scale enviro...
National audienceThis paper presents an optimal parametric active contour method based on Fourier de...
National audienceThe approach we investigate for point tracking combines within a stochastic filteri...
National audienceIn this paper, we propose a new conditional formulation of classical filtering meth...
International audienceThe approach we investigate for point tracking combines within a stochastic fi...
International audienceIn this paper, a new conditional formulation of classical filtering methods is...
International audienceThe PIV characterization of flows on large fields of view requires an adaptati...
The automatic analysis of crowded areas in video sequences is particularly difficult because ofthe l...
A new conditional formulation of classical filtering methods is proposed. This formulation is dedi...
The problem of object tracking is a problem arising in domains such as computer vision (video survei...
The problem of object tracking is a problem arising in domains such as computer vision (video survei...
Particle filtering is now established as one of the most popular methods for visual tracking. Within...
National audienceThis paper proposes a method for the detection, separation, and tracking of objects...
Nous nous intéressons ici à la sélection automatique de points d'intérêt en vue de leur suivi dans u...
National audienceThis article presents a novel approach to person tracking within large-scale enviro...
National audienceThis paper presents an optimal parametric active contour method based on Fourier de...
National audienceThe approach we investigate for point tracking combines within a stochastic filteri...
National audienceIn this paper, we propose a new conditional formulation of classical filtering meth...
International audienceThe approach we investigate for point tracking combines within a stochastic fi...
International audienceIn this paper, a new conditional formulation of classical filtering methods is...
International audienceThe PIV characterization of flows on large fields of view requires an adaptati...
The automatic analysis of crowded areas in video sequences is particularly difficult because ofthe l...
A new conditional formulation of classical filtering methods is proposed. This formulation is dedi...
The problem of object tracking is a problem arising in domains such as computer vision (video survei...
The problem of object tracking is a problem arising in domains such as computer vision (video survei...
Particle filtering is now established as one of the most popular methods for visual tracking. Within...
National audienceThis paper proposes a method for the detection, separation, and tracking of objects...
Nous nous intéressons ici à la sélection automatique de points d'intérêt en vue de leur suivi dans u...
National audienceThis article presents a novel approach to person tracking within large-scale enviro...
National audienceThis paper presents an optimal parametric active contour method based on Fourier de...