%0 Conference Paper %1 carmi-gaussian-mixture-mcmc-2009 %A Carmi, Avishy %A Septier, Francois %A Godsill, Simon J. %B 2009 12th International Conference on Information Fusion, FUSION 2009, July 6, 2009 - July 9, 2009 %C Seattle, WA, United states %D 2009 %I IEEE Computer Society %K clustering dynamic %P 1179--1186 %T The Gaussian mixture MCMC particle algorithm for dynamic cluster tracking %X We present a new filtering algorithm for tracking multiple clusters of coordinated targets. Based on a Markov Chain Monte Carlo (MCMC) mechanism, the new algorithm propagates a discrete approximation of the underlying filtering density. A dynamic Gaussian mixture model is utilized for representing the time-varying clustering structure. This involves point process formulations of typical behavioral moves such as birth and death of clusters as well as merging and splitting. Following our previous work, we adopt here two strategies for increasing the sampling efficiency of the basic MCMC scheme: an evolutionary stage which allows improved exploration of the sample space, and an EM-based method for making optimized proposals based on the frame likelihood. The algorithm's performance is assessed and demonstrated in both synthetic and real tracking scenarios. 2009 ISIF. %Z Compilation and indexing terms, Copyright 2009 Elsevier Inc.

@inproceedings{carmi-gaussian-mixture-mcmc-2009, abstract = {We present a new filtering algorithm for tracking multiple clusters of coordinated targets. Based on a Markov Chain Monte Carlo {(MCMC)} mechanism, the new algorithm propagates a discrete approximation of the underlying filtering density. A dynamic Gaussian mixture model is utilized for representing the time-varying clustering structure. This involves point process formulations of typical behavioral moves such as birth and death of clusters as well as merging and splitting. Following our previous work, we adopt here two strategies for increasing the sampling efficiency of the basic {MCMC} scheme: an evolutionary stage which allows improved exploration of the sample space, and an {EM-based} method for making optimized proposals based on the frame likelihood. The algorithm's performance is assessed and demonstrated in both synthetic and real tracking scenarios. 2009 {ISIF.}}, added-at = {2011-10-17T12:07:34.000+0200}, address = {Seattle, {WA,} United states}, annote = {Compilation and indexing terms, Copyright 2009 Elsevier Inc.}, author = {Carmi, Avishy and Septier, Francois and Godsill, Simon J.}, biburl = {https://www.bibsonomy.org/bibtex/2d58cd017b4fa38fc81136d77401ed605/mhwombat}, booktitle = {2009 12th International Conference on Information Fusion, {FUSION} 2009, July 6, 2009 - July 9, 2009}, citeulike-article-id = {8156548}, interhash = {75ccacd291b5d9eaca330b3a4a4ba091}, intrahash = {d58cd017b4fa38fc81136d77401ed605}, keywords = {clustering dynamic}, pages = {1179--1186}, posted-at = {2010-10-31 22:52:06}, priority = {2}, publisher = {{IEEE} Computer Society}, series = {2009 12th International Conference on Information Fusion, {FUSION} 2009}, timestamp = {2016-07-12T19:25:30.000+0200}, title = {The Gaussian mixture {MCMC} particle algorithm for dynamic cluster tracking}, year = 2009 }