Particle filter target tracking algorithm based on wavelet transform

被引：2

作者：

Zhang F. ^{[1
,2
]}

Zhou X. ^{[1
]}

Chen X. ^{[3
]}

机构：

[1] Key Laboratory of Measurement and Control of CSE of Ministry of Education, Southeast University

[2] School of Electronics and Information, Jiangsu University of Science and Technology

[3] School of Automation, Nanjing University of Posts and Telecommunications

来源：

Dongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Southeast University (Natural Science Edition) | 2010年 / 40卷 / 02期

关键词：

Bearings-only; Multiresolution; Nonlinear filtering; Particle filter; Wavelet transform;

D O I：

10.3969/j.issn.1001-0505.2010.02.020

中图分类号：

学科分类号：

摘要：

Focusing on the natural computational complexity problem of particle filter in bearings-only passive target tracking problem, a new particle filter based on wavelet transform is proposed. Wavelet multiresolution decomposition is carried out on particle weights. By setting threshold to filter the highpassed particle weights, the reconstructed particle weights are used to remove the repeated particle and generate a new particle set to approximate posterior probability density function. Therefore, the number of particles is reduced and the computational efficiency is improved while maintaining filtering accuracy. The proposed particle filter is utilized to solve the bearings-only target motion analysis problem with the nonlinear and non-Gaussian characteristics, and to make a comparison in tracking efficiency with standard particle filter. Simulation results demonstrate that compared with standard particle filter algorithm, the proposed algorithm has comparable tracking accuracy and outclassed computational efficiency, and has enhanced real-time tracking performance. Moreover, the proposed algorithm is promising in expanding the application range of particle filter.

引用

页码：320 / 325

页数：5

共 14 条

[11] Hong L., Wicker D., A spatial-domain multiresolutional particle filter with thresholded wavelets, Signal Processing, 87, 6, pp. 1384-1401, (2007)
[12] Cui N., Hong L., Layne J.R., A comparison of nonlinear filtering approaches with application to ground target tracking, Signal Processing, 85, 8, pp. 1469-1492, (2005)
[13] Carmi A., Oshman Y., Fast particle filtering for attitude and angular-rate estimation from vector observations, Journal of Guidance, Control, and Dynamics, 32, 1, pp. 70-78, (2009)
[14] Driessen H., Boers Y., Efficient particle filter for jump Markov nonlinear systems, IEE Proceedings: Radar, Sonar and Navigation, 152, 5, pp. 323-326, (2005)

← 1 2 →