Improved Gaussian mixture PHD for close multi-target tracking

Author

Huanqing Zhang ; Hongwei Ge ; Jinlong Yang

Author_Institution

Sch. of Internet of Things Eng., Jiangnan Univ., Wuxi, China

fYear

2014

Firstpage

311

Lastpage

315

Abstract

Probability hypothesis density (PHD) filter is an optimal Bayesian multi-target filter based on random finite set. Gaussian mixture is an approximation scheme of PHD filter, which is suitable for linear Gaussian case. In multi-target tracking, when targets are moving closely to each other, GM-PHD filter cannot correctly estimate the number of targets and target states in complex tracking environment. To solve the problem, we propose an improved algorithm in this paper. The improved algorithm uses a novel method for the redistribution of target weights. The simulation results demonstrate that the proposed approach can achieve better performance compared to the other existing methods.

Keywords

Bayes methods; Gaussian processes; mixture models; target tracking; tracking filters; Bayesian multitarget tracking filter; GM-PHD filter; Gaussian mixture PHD filter; linear Gaussian case; probability hypothesis density filter; random finite set; target weight redistribution; Clutter; Estimation; Filtering algorithms; Filtering theory; Information filters; Target tracking; Gaussian mixture PHD; multiple target tracking; probability hypothesis density; random finite set;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Technology and Artificial Intelligence Conference (ITAIC), 2014 IEEE 7th Joint International

Print_ISBN

978-1-4799-4420-0

Type

conf

DOI

10.1109/ITAIC.2014.7065057

Filename

7065057