基于量测分配的SMC-PHD 改进算法

樊鹏飞; 李鸿艳; 王雪

doi:10.15892/j.cnki.djzdxb.2017.04.029

2017 , Vol. 37 >Issue 4: 123 - 127

DOI: https://doi.org/10.15892/j.cnki.djzdxb.2017.04.029

摘要

序贯蒙特卡罗概率假设密度(SMC-PHD)滤波算法由于需要大量粒子参与,导致其存在效率低、估计精度不高等问题。文中以序贯蒙特卡罗概率假设密度滤波算法为框架,利用最新量测集中的量测信息与目标粒子的单步预测状态的似然值,通过概率选取量测值,之后进行概率假设滤波算法的更新。仿真的结果表明,与现有序列蒙特卡罗概率假设密度滤波算法相比,在相同仿真条件下新算法的估计精度显著提高。

关键词： 多目标跟踪; 粒子概率假设滤波; 量测分配

本文引用格式

樊鹏飞 , 李鸿艳 , 王雪 . 基于量测分配的SMC-PHD 改进算法[J]. 弹箭与制导学报, 2017 , 37(4) : 123 -127 . DOI: 10.15892/j.cnki.djzdxb.2017.04.029

Abstract

The sequence Monte Carlo probability hypothesis density(SMC-PHD) filter algorithm needed a large number of particles, which led to some problems, such as inefficiency, low estimation accuracy, etc. The sequence Monte Carlo probability hypothesis density filter algorithm was taken as framework in this paper, and the measurement value was selected by probability using the likelihood of the measurement information in the latest measurement set and the single step prediction state of target particle, then the probability hypothesis filtering algorithm was updated. The simulation results showed that compared with the existing sequence Monte Carlo probability hypothesis density filter algorithm, the estimation accuracy of the new algorithm was improved significantly under the same simulation conditions.

Key words： multiple target tracking; particle probability hypothesis filtering; distributions of measurements

[an error occurred while processing this directive]

参考文献

[1]	MAHLER R P S. Multitarget Bayes filtering via first-order multi-target moments[J]. IEEE Transactions on Aerospace and Electronic Systems,2003,39(4):1152-1178.
[2]	MAHLER R P S,Mahler. PHD filters of higher order in target number[J]. IEEE Transactions on Aerospace and Electronic Systems,2007,43(4):1523-1543.
[3]	VO Ba-Tuong,VO Ba-Ngu,ANTONIO Comtoni,et al. The cardinality balanced multi-target multi-bernoulli filter and its implementations[J]. IEEE Transactions on Signal Processing, 2009,57(2):409-423.
[4]	VO Ba-Ngu,SINGH S,DOUCET A,et al. Sequential Monte Carlo methods for multitarget filtering with random finite sets[J]. IEEE Transactions on Aerospace and Electronic Systems,2005,41(4):1224-1245.
[5]	VO Ba-Ngu,SINGH S,DOUCET A. Random finite sets and sequential Monte Carlo methods in multi-target tracking[C]//IEEE. 2003 Proceedings of the International Conference on Radar.[S.l.]: IEEE,2003: 486-491.
[6]	QUANG Pham Tran Anh,KIM Dong-Sung. Enhancing real-time delivery of gradient routing for industrial wireless sensor networks[J]. IEEE Transactions on Industrial Informatics, 2012,8(1):61-68.
[7]	MEISSNER D,REUTER S,STRIGEL E,et al. Intersection-based road user tracking using a classifying multiplemodel PHD filter[J]. IEEE Intelligent Transportation Systems Magazine,2014,6(2):21-33.
[8]	LI T,SUN S,SATTAR T P. High-speed Sigma-gating SMC-PHD filter[J]. Signal Processing,2013,93 (9):2586-2593.
[9]	RISTIC B,CLARK D,VO Ba-Ngu, et al. Adaptive target birth intensity for PHD and CPHD filters[J]. IEEE Transactions on Aerospace and Electronic Systems,2012,48(2):1656-1668.
[10]	SHI Zhiguo,ZHENG Yunmei,BIAN Xiaomeng,et al. Threshold-based resampling for high-speed particle PHD filter[J]. Progress in Electromagnetics Research,2013, 136: 369-383.
[11]	WANG Junjie,ZHAO Lingling,SU Xiaohong,et al. Cluster-based efficient particle PHD filter[C]//IEEE.2015 International Conference on Control,Automation and Information Sciences.[S.l.]: IEEE,2015: 219-224.
[12]	RISTIC B,CLARK D,VO Ba-Ngu,et al. Adaptive target birth intensity for PHD and CPHD filters[J]. IEEE Transactions on Aerospace and Electronic Systems,2012, 48(2):1656-1668.
[13]	徐从安,刘瑜,熊伟,等. 新生目标强度未知的双门限粒子PHD 滤波器[J]. 航空学报,2015,36 (12):3957-3969.
[14]	CLARK D E,BELL J. Multi-target state estimation and track continuity for the particle PHD filter[J]. IEEE Transactions on Aerospace and Electronic Systems,2007, 43(4):1441-1453.

Options

文章导航