自适应权重粒子群优化的粒子滤波算法  

Particle Swarm Optimization Particle Filtering Algorithm Based on Adaptive Weight

作　　者：刘峰[1] 韩艳丽[2] 王铎[1] 

机构地区：[1]海军航空工程学院研究生管理大队,山东烟台264001 [2]海军航空工程学院控制工程系,山东烟台264001

出　　处：《计算机仿真》2013年第11期330-333,342,共5页Computer Simulation

摘　　要：由于粒子群粒子滤波方法存在粒子贫化易陷入局部最优,从而降低算法精度等问题。在目前PSO-PF算法的基础上,提出一种自适应权重法的PSO粒子滤波(AWPSO-PF)算法,能够很好地平衡PSO算法的全局搜索能力和局部搜索能力,使向全局最优位置靠近。在粒子滤波的框架下,建立采用粒子群优化算法思想的系统状态转移模型,建立加权颜色直方图信息,通过自适应改变权值对目标进跟踪。仿真结果表明,改进算法实时性强,与PF和PSO-PF算法相比,计算精度有较大提高。Particle Swarm Optimization Particle Filtering Algorithm has the problem of easy to fall into local opti- mum and reduce algorithm precision. On the basis of PS0-PF, this paper proposed a Particle Swarm Optimization Particle Filtering Algorithm Based on Adaptive Weight （AWPSO-PF） , it can well balance the global and local search capability and make it close to the global best position. We established the system state transition model based on the PSO and weighted color histogram information under the frame of PF. Through changing the weight adaptively, the target was tracked. Experimental resuh proves that the AWPSO-PF can remarkably improve the calculation accuracy compared with the PF and PSO-PF.

关 键 词：粒子群优化 粒子滤波 自适应权重 加权颜色直方图 目标跟踪 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]