Implementation of the Sampling Importance Resampling Particle Filter Algorithm in Graphics Processing Unit

Date

2015-05-19

Author

Dülger, Özcan
Oğuztüzün, Mehmet Halit S.
Demirekler, Mübeccel

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

186
views

0
downloads

When the particle filter has too many particles, the computational cost increases and the sequential algorithms become inefficient in terms of the execution time. Recent developments in the graphics processing unit technology offer promising solutions for the speedup of the particle filter. In this study, Sampling Importance Resampling (SIR) particle filter method is implemented on the graphics processing unit. The speedup results are compared with results of the sequential and parallel implementations of the SIR particle filter on the central processing unit. The results show that the solution in the graphics processing unit obtains about 12 times speedup over the sequential algorithm. Furthermore, the importance of the parallel solution of the resampling step in the SIR particle filter is pointed out.

Subject Keywords

SIR particle filter, Graphics processing unit, CUDA

URI

https://hdl.handle.net/11511/54845

Conference Name

23nd Signal Processing and Communications Applications Conference (SIU)

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Solution of sparse systems on GPU architecture Lüleç, Andaç; Kurç, Özgür; Department of Civil Engineering (2011) The solution of the linear system of equations is one of the core aspects of Finite Element Analysis (FEA) software. Since large amount of arithmetic operations are required for the solution of the system obtained by FEA, the influence of the solution of linear equations on the performance of the software is very significant. In recent years, the increasing demand for performance in the game industry caused significant improvements on the performances of Graphical Processing Units (GPU). With their massive ...
Non-coalesced Access Patterns of Global Memory Load Transactions in Metropolis Resampling Implemented on Graphics Processing Unit Dülger, Özcan; Oğuztüzün, Mehmet Halit S. (2018-01-01) Due to having many particles, the particle filter has high computational cost. Owing to many cores in its architecture, graphics processing unit (GPU) offers promising solutions. The resampling stage of the particle filter has long execution time because of interactions among the particles. As Metropolis resampling does not need collective operations on particles, it avoids the numerical instability problem and performs fast. However, reading the weights from the global memory becomes serial as the number o...
Applications of hybrid discrete Fourier transform-moment method to the fast analysis of large rectangular dipole arrays printed on a thin grounded dielectric substrate Chou, HT; Ko, HK; Aydın Çivi, Hatice Özlem; ERTÜRK, VAKUR BEHÇET (2002-08-05) Recently a discrete Fourier transform-method of moments (DFT-MoM) scheme was developed for fast analysis of electrically large rectangular planar dipole arrays, which has been shown to be very efficient in terms of number reduction of unknown variables and computational complexity. The applications of this DFT-MoM to treat dipole arrays printed on a grounded dielectric substrate are examined in this Letter. Numerical results are presented to validate its efficiency and accuracy. (C) 2002 Wiley Periodicals, ...
Implementation and assessment of the generalized Riemann problem method in an unstructured solver Ayan, Ulaş Canberk; Baran, Özgür Uğraş; Aksel, Mehmet Haluk; Department of Mechanical Engineering (2022-9) High-order accuracy in the Computational Fluid Dynamics (CFD) solvers became an important necessity with increasing computational resources and algorithms. Resolving discontinuities and regions where high gradients formed accurately is the main topic for high-order schemes. The Generalized Riemann Problem (GRP) method came to the fore with its ability to improve the accuracy in these regions and discontinuities. With the GRP method, the second-order accuracy is not achieved by the piece-wise linear reconstr...
Compensation of Temperature and Acceleration effects on MEMS Gyroscope Ali, Muhammad (2016-01-16) This paper shows temperature and acceleration effects on Micro-Electro-Mechanical-Systems (MEMS) gyroscope and a practical solution is presented to mitigate effect of these errors using different methods (Polynomial Curve fitting and Neural Networks). Compensation is performed on the output bias drift data acquired from different MEMS gyroscopes. Performance of compensation techniques is also presented in this study. This paper presents novelty of integrated compensation for both factors (temperature and ac...

Citation Formats

Ö. Dülger, M. H. S. Oğuztüzün, and M. Demirekler, “Implementation of the Sampling Importance Resampling Particle Filter Algorithm in Graphics Processing Unit,” presented at the 23nd Signal Processing and Communications Applications Conference (SIU), Inonu University, Malatya, Turkey, 2015, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/54845.