A Student’s t Mixture Probability Hypothesis Density Filter for Multi-Target Tracking with Outliers
In multi-target tracking, the outliers-corrupted process and measurement noises can reduce the performance of the probability hypothesis density (PHD) filter severely. To solve the problem, this paper proposed a novel PHD filter, called Student’s t mixture PHD (STM-PHD) filter. The proposed filter m...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/18/4/1095 |
id |
doaj-bf182770ad8d4635b3859264588fb90e |
---|---|
record_format |
Article |
spelling |
doaj-bf182770ad8d4635b3859264588fb90e2020-11-24T22:36:06ZengMDPI AGSensors1424-82202018-04-01184109510.3390/s18041095s18041095A Student’s t Mixture Probability Hypothesis Density Filter for Multi-Target Tracking with OutliersZhuowei Liu0Shuxin Chen1Hao Wu2Renke He3Lin Hao4Information and Navigation College Air Force Engineering University, Xi’an 710077, ChinaInformation and Navigation College Air Force Engineering University, Xi’an 710077, ChinaInformation and Navigation College Air Force Engineering University, Xi’an 710077, ChinaInformation and Navigation College Air Force Engineering University, Xi’an 710077, ChinaUnit 93786, Chinese People’s Liberation Army (PLA), Zhangjiakou 075000, ChinaIn multi-target tracking, the outliers-corrupted process and measurement noises can reduce the performance of the probability hypothesis density (PHD) filter severely. To solve the problem, this paper proposed a novel PHD filter, called Student’s t mixture PHD (STM-PHD) filter. The proposed filter models the heavy-tailed process noise and measurement noise as a Student’s t distribution as well as approximates the multi-target intensity as a mixture of Student’s t components to be propagated in time. Then, a closed PHD recursion is obtained based on Student’s t approximation. Our approach can make full use of the heavy-tailed characteristic of a Student’s t distribution to handle the situations with heavy-tailed process and the measurement noises. The simulation results verify that the proposed filter can overcome the negative effect generated by outliers and maintain a good tracking accuracy in the simultaneous presence of process and measurement outliers.http://www.mdpi.com/1424-8220/18/4/1095multi-target trackingPHD filterStudent’s t mixtureoutliersrobustness |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhuowei Liu Shuxin Chen Hao Wu Renke He Lin Hao |
spellingShingle |
Zhuowei Liu Shuxin Chen Hao Wu Renke He Lin Hao A Student’s t Mixture Probability Hypothesis Density Filter for Multi-Target Tracking with Outliers Sensors multi-target tracking PHD filter Student’s t mixture outliers robustness |
author_facet |
Zhuowei Liu Shuxin Chen Hao Wu Renke He Lin Hao |
author_sort |
Zhuowei Liu |
title |
A Student’s t Mixture Probability Hypothesis Density Filter for Multi-Target Tracking with Outliers |
title_short |
A Student’s t Mixture Probability Hypothesis Density Filter for Multi-Target Tracking with Outliers |
title_full |
A Student’s t Mixture Probability Hypothesis Density Filter for Multi-Target Tracking with Outliers |
title_fullStr |
A Student’s t Mixture Probability Hypothesis Density Filter for Multi-Target Tracking with Outliers |
title_full_unstemmed |
A Student’s t Mixture Probability Hypothesis Density Filter for Multi-Target Tracking with Outliers |
title_sort |
student’s t mixture probability hypothesis density filter for multi-target tracking with outliers |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2018-04-01 |
description |
In multi-target tracking, the outliers-corrupted process and measurement noises can reduce the performance of the probability hypothesis density (PHD) filter severely. To solve the problem, this paper proposed a novel PHD filter, called Student’s t mixture PHD (STM-PHD) filter. The proposed filter models the heavy-tailed process noise and measurement noise as a Student’s t distribution as well as approximates the multi-target intensity as a mixture of Student’s t components to be propagated in time. Then, a closed PHD recursion is obtained based on Student’s t approximation. Our approach can make full use of the heavy-tailed characteristic of a Student’s t distribution to handle the situations with heavy-tailed process and the measurement noises. The simulation results verify that the proposed filter can overcome the negative effect generated by outliers and maintain a good tracking accuracy in the simultaneous presence of process and measurement outliers. |
topic |
multi-target tracking PHD filter Student’s t mixture outliers robustness |
url |
http://www.mdpi.com/1424-8220/18/4/1095 |
work_keys_str_mv |
AT zhuoweiliu astudentstmixtureprobabilityhypothesisdensityfilterformultitargettrackingwithoutliers AT shuxinchen astudentstmixtureprobabilityhypothesisdensityfilterformultitargettrackingwithoutliers AT haowu astudentstmixtureprobabilityhypothesisdensityfilterformultitargettrackingwithoutliers AT renkehe astudentstmixtureprobabilityhypothesisdensityfilterformultitargettrackingwithoutliers AT linhao astudentstmixtureprobabilityhypothesisdensityfilterformultitargettrackingwithoutliers AT zhuoweiliu studentstmixtureprobabilityhypothesisdensityfilterformultitargettrackingwithoutliers AT shuxinchen studentstmixtureprobabilityhypothesisdensityfilterformultitargettrackingwithoutliers AT haowu studentstmixtureprobabilityhypothesisdensityfilterformultitargettrackingwithoutliers AT renkehe studentstmixtureprobabilityhypothesisdensityfilterformultitargettrackingwithoutliers AT linhao studentstmixtureprobabilityhypothesisdensityfilterformultitargettrackingwithoutliers |
_version_ |
1725721311050727424 |