Algorithms of Particle Swarm Optimizer Tracking Based on DSP Parallel System

doi:null

您当前的位置：

首页 >

文章列表页 >

Algorithms of Particle Swarm Optimizer Tracking Based on DSP Parallel System

Article | 更新时间：2020-08-12

- Algorithms of Particle Swarm Optimizer Tracking Based on DSP Parallel System
- Optics and Precision Engineering Vol. 17, Issue 9, Pages: 2236-2240(2009)
- 作者机构：
  
  北京理工大学
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Received：02 September 2008，
  
  Revised：29 October 2008，
  
  Published Online：25 September 2009，
  
  Published：25 September 2009
- 稿件说明：
移动端阅览
许廷发（理工）. DSP并行系统的并行粒子群优化目标跟踪[J]. 光学精密工程, 2009,17(9):2236-2240

Algorithms of Particle Swarm Optimizer Tracking Based on DSP Parallel System[J]. Optics and precision engineering, 2009, 17(9): 2236-2240.
许廷发（理工）. DSP并行系统的并行粒子群优化目标跟踪[J]. 光学精密工程, 2009,17(9):2236-2240 DOI：

Algorithms of Particle Swarm Optimizer Tracking Based on DSP Parallel System[J]. Optics and precision engineering, 2009, 17(9): 2236-2240. DOI：

摘要

摘要：针对串行粒子群优化（Particle Swarm Optimizer

PSO）算法存在计算量大、速度慢的问题，给出了一种基于DSP并行系统的并行PSO跟踪算法。在研制的4个DSP并行系统上，采用基于消息传递模型及单种群的Master-Slave模式设计实现并行PSO跟踪算法。DSP-A实现初始化设置，其他3个DSP-B、DSP-C、DSP-D并行计算每个粒子的适应值。最后，DSP-A比较每个粒子的适应值与其个体极值的优劣，选择较好的个体极值和比较选择整个种群的最优解，更新每个粒子的位置与速度。利用系统采集实际序列图像进行了算法仿真验证，与串行PSO跟踪算法相比，加速比提高2.525，效率提高63.13％。关键词：目标跟踪；并行PSO算法；DSP；并行系统

Abstract

Abstract： Aiming at the existent question that serial PSO algorithms has big calculation and speed slow

we propose a parallel PSO algorithms based on DSP parallel system. The algorithm adopts the information transfer model and single population Master-Slave model in 4 DSP parallel system.The initialize setting is realized by DSP-A

the adapt value of every particle are parallel computed by DSP-B

DSP-C and DSP-D.Finally

by DSP-A to compare to the adapt value of every particle and it’s individual extremum

and to choice better individual extremum and compare to choice best solution of entire population

and the update every particle position and speed.The simulation experiments show that the algorithms is compare to serial PSO algorithms that get 2.525 acceleration and 63.13% deficiency Keywords：Target tracking; Parallel PSO algorithms; DSP; Parallel system

关键词

Keywords

references

Views

446

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multimode composite guidance data fusion method and its experimental validation

Unbiased estimation of target motion analyze based on non-maneuvering single station

Compensation of hysteresis effect of piezoelectric fast steering mirror in dynamic target tracking of ground-based large aperture telescope system

High-precision photoelectric acquisition and tracking based on cascade sliding mode control

TLD particle swarm optimization target tracking using a sample deletion mechanism

Related Author

LIU Shuxin

WU Hui

WANG Daihua

SHE Junchao

LIN Jianjun

WANG Rangyuhan

BAN Xiaojun

LU Hongqian

Related Institution

Southwest Institute of Technical Physics

College of Optoelectronic Engineering， Chongqing University

School of Astronautics， Harbin Institute of Technology

College of Aerospace and Civil Engineering， Harbin Engineering of University

Changchun Institute of Optics，Fine Mechanics and Physics，Chinese Academy of Sciences

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰