Stochastic filtering of level sets for curve tracking

Abstract : This paper focuses on the tracking of free curves using non-linear stochastic filtering techniques. It relies on a particle filter which includes color measurements. The curve and its velocity are defined through two coupled implicit level set representations. The stochastic dynamics of the curve is expressed directly on the level set function associated to the curve representation and combines a velocity field captured from the additional second level set attached to the past curve's points location. The curve's dynamics combines a lowdimensional noise model and a data-driven local force. We demonstrate how this approach allows the tracking of highly and rapidly deforming objects, such as convective cells in infra-red satellite images, while providing a location-dependent assessment of the estimation confidence.
Type de document :
Communication dans un congrès
20 th International Conference on Pattern Recognition (ICPR), Aug 2010, Istanbul, Turkey. 2010, 〈10.1109/ICPR.2010.867〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00619114
Contributeur : Ist Rennes <>
Soumis le : lundi 5 septembre 2011 - 14:44:09
Dernière modification le : mercredi 11 avril 2018 - 02:00:14

Identifiants

Collections

Citation

Christophe Avenel, Etienne Memin, Patrick Pérez. Stochastic filtering of level sets for curve tracking. 20 th International Conference on Pattern Recognition (ICPR), Aug 2010, Istanbul, Turkey. 2010, 〈10.1109/ICPR.2010.867〉. 〈inria-00619114〉

Partager

Métriques

Consultations de la notice

85