Journal of Xidian University ›› 2019, Vol. 46 ›› Issue (5): 134-141.doi: 10.19665/j.issn1001-2400.2019.05.019

Previous Articles     Next Articles

Student’s t Distribution mixture CPHD filter with noise outliers

WANG Mingjie,JI Hongbing,LIU Long   

  1. School of Electronic Engineering, Xidian Univ., Xi’an 710071, China
  • Received:2019-04-12 Online:2019-10-20 Published:2019-10-30

Abstract:

In order to solve the performance degradation of the Gaussian mixture cardinalized probability hypothesis density (GM-CPHD) filter induced by the process and measurement noise outlier, a novel CPHD filter based Student’s t distribution is proposed. The method introduces the Student’s t distribution to model the heavy tailed process and measurement noise. By approximating the multi-target posterior intensity as a Student’s t distribution mixture form, the linear closed-form solution of the CPHD is derived. Furthermore, the moment matching algorithm is used to prevent the infinite growth of the degree of freedom of the student’s t distribution. Simulation results demonstrate that the proposed filter can achieve a better target tracking performance than the GM-CPHD filter and the Student’s t distribution mixture probability hypothesis density filter under process and measurement noise outliers.

Key words: noise outlier, multi-target tracking, cardinalized probability hypothesis density, Student’s t distribution

CLC Number: 

  • TN953