The problem of object tracking is a problem arising in domains such as computer vision (video surveillance for instance) and cinematographic post-production (special effects). There are two major classes of solution to this problem: region of interest tracking, which indicates a coarse tracking, and space-time segmentation, which corresponds to a precise tracking of the region of interest's contour. In both cases, the region of interest must be selected beforehand on the first, and possibly on the last image of the video sequence. In this thesis, we propose two tracking methods (one of each type). We propose also a fast implementation of an existing tracking method on Graphics Processing Unit (GPU). The first method is based on the analysis...
The growing number of video data makes often difficult, even impossible, any attemptof watching them...
The general field of this study is digital signal processing applied to imagesequences for multimedi...
International audienceIn this paper, we proposed a Markov Random field sequence segmentation and reg...
The problem of object tracking is a problem arising in domains such as computer vision (video survei...
This paper addresses the problem of motion tracking in a sequence of monocular images. We want to es...
Object segmentation and tracking is a challenging area of ongoing research in computer vision. One i...
This PhD work is to be seen within the context of autonomous vehicle perception, in which the detect...
Many computer vision applications require the extraction and tracking of the different video objects...
We study the challenging problem of tracking an arbitrary object in video sequences with no prior kn...
Detecting and following the main objects of a video is necessary to describe its content in order to...
18 pages. Quelques films de résultats sont disponible sur: http://www.ceremade.dauphine.fr/~pelletie...
In this thesis we propose novel algorithms for video analysis. The first contribution of this thesis...
The automatic analysis of crowded areas in video sequences is particularly difficult because ofthe l...
With the increasing need for automated video analysis, visual object tracking became an important ta...
The growing number of video data makes often difficult, even impossible, any attemptof watching them...
The general field of this study is digital signal processing applied to imagesequences for multimedi...
International audienceIn this paper, we proposed a Markov Random field sequence segmentation and reg...
The problem of object tracking is a problem arising in domains such as computer vision (video survei...
This paper addresses the problem of motion tracking in a sequence of monocular images. We want to es...
Object segmentation and tracking is a challenging area of ongoing research in computer vision. One i...
This PhD work is to be seen within the context of autonomous vehicle perception, in which the detect...
Many computer vision applications require the extraction and tracking of the different video objects...
We study the challenging problem of tracking an arbitrary object in video sequences with no prior kn...
Detecting and following the main objects of a video is necessary to describe its content in order to...
18 pages. Quelques films de résultats sont disponible sur: http://www.ceremade.dauphine.fr/~pelletie...
In this thesis we propose novel algorithms for video analysis. The first contribution of this thesis...
The automatic analysis of crowded areas in video sequences is particularly difficult because ofthe l...
With the increasing need for automated video analysis, visual object tracking became an important ta...
The growing number of video data makes often difficult, even impossible, any attemptof watching them...
The general field of this study is digital signal processing applied to imagesequences for multimedi...
International audienceIn this paper, we proposed a Markov Random field sequence segmentation and reg...