An Optimized {DBN}-Based Mode-Focussing Particle Filter

Séverine Dubuisson 1 Christophe Gonzales 2
1 PEQUAN - Performance et Qualité des Algorithmes Numériques
LIP6 - Laboratoire d'Informatique de Paris 6
2 DECISION
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : We propose an original particle filtering-based approach combining optimization and decomposition techniques for sequential non-parametric density estimation defined in high-dimensional state spaces. Our method relies on Annealing to focus on the correct distributions and on probabilistic conditional independences defined by Dynamic Bayesian Networks to focus samples on their modes. After proving its theoretical correctness and showing its complexity, we highlight its ability to track single and multiple articulated objects both on synthetic and real video sequences. We show that our approach is particularly effective, both in terms of estimation errors and computation times.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01270034
Contributor : Lip6 Publications <>
Submitted on : Friday, February 5, 2016 - 3:39:42 PM
Last modification on : Thursday, March 21, 2019 - 2:42:11 PM

Identifiers

Citation

Séverine Dubuisson, Christophe Gonzales. An Optimized {DBN}-Based Mode-Focussing Particle Filter. International Conference on Computer Vision and Pattern Recognition (CVPR'12), Jun 2012, Providence, United States. International Conference on Computer Vision and Pattern Recognition (CVPR'12), pp.1934-1939, 〈10.1109/CVPR.2012.6247894〉. 〈hal-01270034〉

Share

Metrics

Record views

72