Parralelization of non-linear non-Gaussian Bayesian state estimators (Particle filters)

Parralelization of non-linear non-Gaussian Bayesian state estimators (Particle filters). Jarrah, A., Jamali, M. M., Hosseini, S. S. S., Astola, J., & Gabbouj, M. In 2015 23rd European Signal Processing Conference (EUSIPCO), pages 2506-2510, Aug, 2015.
doi abstract bibtex

Particle filter has been proven to be a very effective method for identifying targets in non-linear and non-Gaussian environment. However, particle filter is computationally intensive and may not achieve the real time requirements. So, it's desirable to implement it on parallel platforms by exploiting parallel and pipelining architecture to achieve its real time requirements. In this work, an efficient implementation of particle filter in both FPGA and GPU is proposed. Particle filter has also been implemented using MATLAB Parallel Computing Toolbox (PCT). Experimental results show that FPGA and GPU architectures can significantly outperform an equivalent sequential implementation. The results also show that FPGA implementation provides better performance than the GPU implementation. The achieved execution time on dual core and quad core Dell PC using PCT were higher than FPGAs and GPUs as was expected.

@InProceedings{7362836,
  author = {A. Jarrah and M. M. Jamali and S. S. S. Hosseini and J. Astola and M. Gabbouj},
  booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)},
  title = {Parralelization of non-linear non-Gaussian Bayesian state estimators (Particle filters)},
  year = {2015},
  pages = {2506-2510},
  abstract = {Particle filter has been proven to be a very effective method for identifying targets in non-linear and non-Gaussian environment. However, particle filter is computationally intensive and may not achieve the real time requirements. So, it's desirable to implement it on parallel platforms by exploiting parallel and pipelining architecture to achieve its real time requirements. In this work, an efficient implementation of particle filter in both FPGA and GPU is proposed. Particle filter has also been implemented using MATLAB Parallel Computing Toolbox (PCT). Experimental results show that FPGA and GPU architectures can significantly outperform an equivalent sequential implementation. The results also show that FPGA implementation provides better performance than the GPU implementation. The achieved execution time on dual core and quad core Dell PC using PCT were higher than FPGAs and GPUs as was expected.},
  keywords = {field programmable gate arrays;graphics processing units;parallel architectures;particle filtering (numerical methods);quad core Dell PC;dual core Dell PC;MATLAB PCT;MATLAB Parallel Computing Toolbox;GPU;FPGA;pipelining architecture;parallel architecture;parallel platforms;particle filter;Particle filters;Field programmable gate arrays;Graphics processing units;Parallel processing;Instruction sets;Particle measurements;MATLAB;Field Programmable Gate Array (FPGA);Graphic Processing Unit (GPU);Parallel Architecture;Particle Filter;MATLAB Parallel Computing Toolbox (PCT)},
  doi = {10.1109/EUSIPCO.2015.7362836},
  issn = {2076-1465},
  month = {Aug},
}

Downloads: 0

{"_id":"pLsp6oxRS3ofsqpKF","bibbaseid":"jarrah-jamali-hosseini-astola-gabbouj-parralelizationofnonlinearnongaussianbayesianstateestimatorsparticlefilters-2015","downloads":0,"creationDate":"2016-01-08T22:33:13.754Z","title":"Parralelization of non-linear non-Gaussian Bayesian state estimators (Particle filters)","author_short":["Jarrah, A.","Jamali, M. M.","Hosseini, S. S. S.","Astola, J.","Gabbouj, M."],"year":2015,"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2015url.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["A."],"propositions":[],"lastnames":["Jarrah"],"suffixes":[]},{"firstnames":["M.","M."],"propositions":[],"lastnames":["Jamali"],"suffixes":[]},{"firstnames":["S.","S.","S."],"propositions":[],"lastnames":["Hosseini"],"suffixes":[]},{"firstnames":["J."],"propositions":[],"lastnames":["Astola"],"suffixes":[]},{"firstnames":["M."],"propositions":[],"lastnames":["Gabbouj"],"suffixes":[]}],"booktitle":"2015 23rd European Signal Processing Conference (EUSIPCO)","title":"Parralelization of non-linear non-Gaussian Bayesian state estimators (Particle filters)","year":"2015","pages":"2506-2510","abstract":"Particle filter has been proven to be a very effective method for identifying targets in non-linear and non-Gaussian environment. However, particle filter is computationally intensive and may not achieve the real time requirements. So, it's desirable to implement it on parallel platforms by exploiting parallel and pipelining architecture to achieve its real time requirements. In this work, an efficient implementation of particle filter in both FPGA and GPU is proposed. Particle filter has also been implemented using MATLAB Parallel Computing Toolbox (PCT). Experimental results show that FPGA and GPU architectures can significantly outperform an equivalent sequential implementation. The results also show that FPGA implementation provides better performance than the GPU implementation. The achieved execution time on dual core and quad core Dell PC using PCT were higher than FPGAs and GPUs as was expected.","keywords":"field programmable gate arrays;graphics processing units;parallel architectures;particle filtering (numerical methods);quad core Dell PC;dual core Dell PC;MATLAB PCT;MATLAB Parallel Computing Toolbox;GPU;FPGA;pipelining architecture;parallel architecture;parallel platforms;particle filter;Particle filters;Field programmable gate arrays;Graphics processing units;Parallel processing;Instruction sets;Particle measurements;MATLAB;Field Programmable Gate Array (FPGA);Graphic Processing Unit (GPU);Parallel Architecture;Particle Filter;MATLAB Parallel Computing Toolbox (PCT)","doi":"10.1109/EUSIPCO.2015.7362836","issn":"2076-1465","month":"Aug","bibtex":"@InProceedings{7362836,\n author = {A. Jarrah and M. M. Jamali and S. S. S. Hosseini and J. Astola and M. Gabbouj},\n booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)},\n title = {Parralelization of non-linear non-Gaussian Bayesian state estimators (Particle filters)},\n year = {2015},\n pages = {2506-2510},\n abstract = {Particle filter has been proven to be a very effective method for identifying targets in non-linear and non-Gaussian environment. However, particle filter is computationally intensive and may not achieve the real time requirements. So, it's desirable to implement it on parallel platforms by exploiting parallel and pipelining architecture to achieve its real time requirements. In this work, an efficient implementation of particle filter in both FPGA and GPU is proposed. Particle filter has also been implemented using MATLAB Parallel Computing Toolbox (PCT). Experimental results show that FPGA and GPU architectures can significantly outperform an equivalent sequential implementation. The results also show that FPGA implementation provides better performance than the GPU implementation. The achieved execution time on dual core and quad core Dell PC using PCT were higher than FPGAs and GPUs as was expected.},\n keywords = {field programmable gate arrays;graphics processing units;parallel architectures;particle filtering (numerical methods);quad core Dell PC;dual core Dell PC;MATLAB PCT;MATLAB Parallel Computing Toolbox;GPU;FPGA;pipelining architecture;parallel architecture;parallel platforms;particle filter;Particle filters;Field programmable gate arrays;Graphics processing units;Parallel processing;Instruction sets;Particle measurements;MATLAB;Field Programmable Gate Array (FPGA);Graphic Processing Unit (GPU);Parallel Architecture;Particle Filter;MATLAB Parallel Computing Toolbox (PCT)},\n doi = {10.1109/EUSIPCO.2015.7362836},\n issn = {2076-1465},\n month = {Aug},\n}\n\n","author_short":["Jarrah, A.","Jamali, M. M.","Hosseini, S. S. S.","Astola, J.","Gabbouj, M."],"key":"7362836","id":"7362836","bibbaseid":"jarrah-jamali-hosseini-astola-gabbouj-parralelizationofnonlinearnongaussianbayesianstateestimatorsparticlefilters-2015","role":"author","urls":{},"keyword":["field programmable gate arrays;graphics processing units;parallel architectures;particle filtering (numerical methods);quad core Dell PC;dual core Dell PC;MATLAB PCT;MATLAB Parallel Computing Toolbox;GPU;FPGA;pipelining architecture;parallel architecture;parallel platforms;particle filter;Particle filters;Field programmable gate arrays;Graphics processing units;Parallel processing;Instruction sets;Particle measurements;MATLAB;Field Programmable Gate Array (FPGA);Graphic Processing Unit (GPU);Parallel Architecture;Particle Filter;MATLAB Parallel Computing Toolbox (PCT)"],"metadata":{"authorlinks":{}},"downloads":0},"search_terms":["parralelization","non","linear","non","gaussian","bayesian","state","estimators","particle","filters","jarrah","jamali","hosseini","astola","gabbouj"],"keywords":["field programmable gate arrays;graphics processing units;parallel architectures;particle filtering (numerical methods);quad core dell pc;dual core dell pc;matlab pct;matlab parallel computing toolbox;gpu;fpga;pipelining architecture;parallel architecture;parallel platforms;particle filter;particle filters;field programmable gate arrays;graphics processing units;parallel processing;instruction sets;particle measurements;matlab;field programmable gate array (fpga);graphic processing unit (gpu);parallel architecture;particle filter;matlab parallel computing toolbox (pct)"],"authorIDs":[],"dataSources":["eov4vbT6mnAiTpKji","knrZsDjSNHWtA9WNT"]}