Multi-Objective Optimization Based Multi-Bernoulli Sensor Selection for Multi-Target Tracking

被引：13

作者：

Zhu, Yun ^{[1
]}

Wang, Jun ^{[1
]}

Liang, Shuang ^{[2
]}

机构：

[1] Xidian Univ, Natl Lab Radar Signal Proc, Xian 710071, Shaanxi, Peoples R China

[2] Minist Educ, Key Lab Intelligent Percept & Image Understanding, Xian 710071, Shaanxi, Peoples R China

来源：

SENSORS | 2019年 / 19卷 / 04期

基金：

中国国家自然科学基金;

关键词：

multi-target tracking; sensor management; random finite set; multi-objective optimization; TARGET TRACKING; STATIC DOPPLER; PHD FILTERS; MANAGEMENT;

D O I：

10.3390/s19040980

中图分类号：

O65 [分析化学];

学科分类号：

070302 ; 081704 ;

摘要：

This paper presents a novel multi-objective optimization based sensor selection method for multi-target tracking in sensor networks. The multi-target states are modelled as multi-Bernoulli random finite sets and the multi-Bernoulli filter is used to propagate the multi-target posterior density. The proposed method is designed to select the sensor that provides the most reliable cardinality estimate, since more accurate cardinality estimate indicates more accurate target states. In the multi-Bernoulli filter, the updated multi-target density is a multi-Bernoulli random finite set formed by a union of legacy tracks and measurement-updated tracks. The legacy track and the measurement-updated track have different theoretical and physical meanings, and hence these two kinds of tracks are considered separately in the sensor management problem. Specifically, two objectives are considered: (1) maximizing the mean cardinality of the measurement-updated tracks, (2) minimizing the cardinality variance of the legacy tracks. Considering the conflicting objectives simultaneously is a multi-objective optimization problem. Tradeoff solutions between two conflicting objectives will be derived. Theoretical analysis and examples show that the proposed approach is effective and direct. The performance of the proposed method is demonstrated using two scenarios with different levels of observability of targets in the passive sensor network.

引用

页数：18

共 32 条

[1]

[Anonymous], 2003, Pomdp solution methods

[2] Void Probabilities and Cauchy-Schwarz Divergence for Generalized Labeled Multi-Bernoulli Models [J].

Beard, Michael ;

Vo, Ba-Tuong ;

Vo, Ba-Ngu ;

Arulampalam, Sanjeev .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2017, 65 (19) :5047-5061

[3]

Castañón DA, 2008, SIGNALS COMMUN TECHN, P7, DOI 10.1007/978-0-387-49819-5_2

[4] Constrained Sensor Control for Labeled Multi-Bernoulli Filter Using Cauchy-Schwarz Divergence [J].

Gostar, Amirali K. ;

Hoseinnezhad, Reza ;

Rathnayake, Tharindu ;

Wang, Xiaoying ;

Bab-Hadiashar, Alireza .

IEEE SIGNAL PROCESSING LETTERS, 2017, 24 (09) :1313-1317

[5] Sensor-Management for Multitarget Filters via Minimization of Posterior Dispersion [J].

Gostar, Amirali Khodadadian ;

Hoseinnezhad, Reza ;

Bab-Hadiashar, Alireza ;

Liu, Weifeng .

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2017, 53 (06) :2877-2884

[6]

Gostar AK, 2013, 2013 IEEE EIGHTH INTERNATIONAL CONFERENCE ON INTELLIGENT SENSORS, SENSOR NETWORKS AND INFORMATION PROCESSING, P312, DOI 10.1109/ISSNIP.2013.6529808

[7]

Hero AO, 2008, SIGNALS COMMUN TECHN, P33, DOI 10.1007/978-0-387-49819-5_3

[8]

Hoang HG, 2012, INT CONF CONTR AUTO, P7, DOI 10.1109/ICCAIS.2012.6466635

[9] The Cauchy-Schwarz Divergence for Poisson Point Processes [J].

Hung Gia Hoang ;

Ba-Ngu Vo ;

Ba-Tuong Vo ;

Mahler, Ronald .

IEEE TRANSACTIONS ON INFORMATION THEORY, 2015, 61 (08) :4475-4485

[10] Sensor management for multi-target tracking via multi-Bernoulli filtering [J].

Hung Gia Hoang ;

Ba Tuong Vo .

AUTOMATICA, 2014, 50 (04) :1135-1142

← 1 2 3 4 →