This thesis addresses the question of how to introduce prior knowledge about the shape of an object to be detected in the general framework of object recognition from images. We illustrate this idea with the problem of line network extraction from satellite and aerial images. We use the framework of active contours and we introduce a whole new class of active contours, named "higher-order active contours". This class allows us to define new models that incorporate sophisticated prior geometric knowledge describing, rather than a specific shape, a general family of shapes. We first study a particular case of a geometric quadratic energy that favours network structures composed of arms of roughly constant width joined at junctions. This energ...
This thesis addresses the problem of the unsupervised extraction of line networks (roads, rivers, et...
National audiencePreviously, marked point process models have been successfully applied to solve pro...
This paper addresses the segmentation from an image of entities that have the form of a 'network', i...
This thesis addresses the question of how to introduce prior knowledge about the shape of an object ...
We present a novel method for the incorporation of shape information into active contour models, an...
Cette thèse aborde le problème de l'introduction d'une connaissance a priori sur la géométrie de l'o...
We introduce a new class of active contour models that hold great promise for region and shape model...
We introduce a new class of active contour models that hold great promise for region and shape model...
L objectif de cette thèse est de développer et valider des approches robustes d extraction semi-auto...
The manuscript in Chinese can be downloaded at: http://kepler.ia.ac.cn/publications/thesis/tpeng_the...
The original publication is available at www.springerlink.comInternational audienceThis paper addres...
International audienceThis paper addresses the segmentation from an image of entities that have the ...
This paper addresses the segmentation from an image of entities that have the form of a ‘network’, i...
This paper addresses the segmentation from an image of entities that have the form of a 'network', i...
The representation and modelling of regions is an important topic in computer vision. In this paper,...
This thesis addresses the problem of the unsupervised extraction of line networks (roads, rivers, et...
National audiencePreviously, marked point process models have been successfully applied to solve pro...
This paper addresses the segmentation from an image of entities that have the form of a 'network', i...
This thesis addresses the question of how to introduce prior knowledge about the shape of an object ...
We present a novel method for the incorporation of shape information into active contour models, an...
Cette thèse aborde le problème de l'introduction d'une connaissance a priori sur la géométrie de l'o...
We introduce a new class of active contour models that hold great promise for region and shape model...
We introduce a new class of active contour models that hold great promise for region and shape model...
L objectif de cette thèse est de développer et valider des approches robustes d extraction semi-auto...
The manuscript in Chinese can be downloaded at: http://kepler.ia.ac.cn/publications/thesis/tpeng_the...
The original publication is available at www.springerlink.comInternational audienceThis paper addres...
International audienceThis paper addresses the segmentation from an image of entities that have the ...
This paper addresses the segmentation from an image of entities that have the form of a ‘network’, i...
This paper addresses the segmentation from an image of entities that have the form of a 'network', i...
The representation and modelling of regions is an important topic in computer vision. In this paper,...
This thesis addresses the problem of the unsupervised extraction of line networks (roads, rivers, et...
National audiencePreviously, marked point process models have been successfully applied to solve pro...
This paper addresses the segmentation from an image of entities that have the form of a 'network', i...