Swapping-Based Partitioned Sampling for better complex density estimation: application to articulated object tracking - Sorbonne Université
Conference Papers Year : 2011

Swapping-Based Partitioned Sampling for better complex density estimation: application to articulated object tracking

Christophe Gonzales
Xuan Son Nguyen
  • Function : Author

Abstract

In this paper, we propose to better estimate high-dimensional distributions by exploiting conditional independences within the Particle Filter (PF) framework. We rst exploit Dynamic Bayesian Networks to determine conditionally independent subspaces of the state space, which allows us to independently perform propagations and corrections over smaller spaces. Second, we propose a swapping process to transform the weighted particle set provided by the update step of PF into a \new particle set" better focusing on high peaks of the posterior distribution. This new methodology, called Swapping-Based Partitioned Sampling, is successfully tested and validated for articulated object tracking
Fichier principal
Vignette du fichier
sum2011.pdf (481.98 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-00821841 , version 1 (13-05-2013)

Identifiers

Cite

Séverine Dubuisson, Christophe Gonzales, Xuan Son Nguyen. Swapping-Based Partitioned Sampling for better complex density estimation: application to articulated object tracking. 5th International Conference on Scalable Uncertainty Management (SUM'11), Oct 2011, Dayton, OH, United States. pp.525-538, ⟨10.1007/978-3-642-23963-2_41⟩. ⟨hal-00821841⟩
121 View
268 Download

Altmetric

Share

More