DBN-Based Combinatorial Resampling for Articulated Object Tracking

Severine Dubuisson, Christophe Gonzales, Xuan Son NGuyen
Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence, PMLR R10:235-244, 2012.

Abstract

Particle Filter is an effective solution to track objects in video sequences in complex situations. Its key idea is to estimate the density over the possible states of the object using a weighted sample whose elements are called particles. One of its crucial step is a resampling step in which particles are resampled to avoid some degeneracy problem. In this paper, we introduce a new resampling method called Combinatorial Resampling that exploits some features of articulated objects to resample over an implicitly created sample of an exponential size better representing the density to estimate. We prove that it is sound and, through experimentations both on challenging synthetic and real video sequences, we show that it outperforms all classical resampling methods both in terms of the quality of its results and in terms of response times.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR10-dubuisson12a, title = {{DBN}-Based Combinatorial Resampling for Articulated Object Tracking}, author = {Dubuisson, Severine and Gonzales, Christophe and NGuyen, Xuan Son}, booktitle = {Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence}, pages = {235--244}, year = {2012}, editor = {de Freitas, Nando and Murphy, Kevin}, volume = {R10}, series = {Proceedings of Machine Learning Research}, month = {14--18 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r10/main/assets/dubuisson12a/dubuisson12a.pdf}, url = {https://proceedings.mlr.press/r10/dubuisson12a.html}, abstract = {Particle Filter is an effective solution to track objects in video sequences in complex situations. Its key idea is to estimate the density over the possible states of the object using a weighted sample whose elements are called particles. One of its crucial step is a resampling step in which particles are resampled to avoid some degeneracy problem. In this paper, we introduce a new resampling method called Combinatorial Resampling that exploits some features of articulated objects to resample over an implicitly created sample of an exponential size better representing the density to estimate. We prove that it is sound and, through experimentations both on challenging synthetic and real video sequences, we show that it outperforms all classical resampling methods both in terms of the quality of its results and in terms of response times.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T DBN-Based Combinatorial Resampling for Articulated Object Tracking %A Severine Dubuisson %A Christophe Gonzales %A Xuan Son NGuyen %B Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2012 %E Nando de Freitas %E Kevin Murphy %F pmlr-vR10-dubuisson12a %I PMLR %P 235--244 %U https://proceedings.mlr.press/r10/dubuisson12a.html %V R10 %X Particle Filter is an effective solution to track objects in video sequences in complex situations. Its key idea is to estimate the density over the possible states of the object using a weighted sample whose elements are called particles. One of its crucial step is a resampling step in which particles are resampled to avoid some degeneracy problem. In this paper, we introduce a new resampling method called Combinatorial Resampling that exploits some features of articulated objects to resample over an implicitly created sample of an exponential size better representing the density to estimate. We prove that it is sound and, through experimentations both on challenging synthetic and real video sequences, we show that it outperforms all classical resampling methods both in terms of the quality of its results and in terms of response times. %Z Reissued by PMLR on 04 October 2026.
APA
Dubuisson, S., Gonzales, C. & NGuyen, X.S.. (2012). DBN-Based Combinatorial Resampling for Articulated Object Tracking. Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R10:235-244 Available from https://proceedings.mlr.press/r10/dubuisson12a.html. Reissued by PMLR on 04 October 2026.

Related Material