Collaborative PHD filter for fast multi-target tracking

Feng Yang; Yong Qi Wang; Yan Liang; Quan Pan

doi:10.3969/j.issn.1001-506X.2014.11.01

Collaborative PHD filter for fast multi-target tracking

Feng Yang, Yong Qi Wang, Yan Liang, Quan Pan

School of Automation

Northwestern Polytechnical University Xian

Research output: Contribution to journal › Article › peer-review

3 Scopus citations

Abstract

Considering the difference of dynamic evolution between the survival target and the newborn targets collaborative probability hypothesis density (CoPHD) filter framework for fast multi-target tracking is proposed. The framework strives to improve the systematic implementing efficiency as well as guarantee the tracking accuracy by dynamically partitioning the measurement set into two parts, survival and newborn target measurement sets in which PHD groups are updated respectively, and constituting an interactive and collaborative mechanism for the processing modules. In addition, the framework has the ability of state self-extracting by utilizing PHD group processing, and the implementation via the sequential Monte Carlo (SMC) method is presented. Simulation results show that the proposed SMC-CoPHD filter has greatly-reduced computation cost and significantly-improved state-extraction accuracy.

Original language	English
Pages (from-to)	2113-2121
Number of pages	9
Journal	Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics
Volume	36
Issue number	11
DOIs	https://doi.org/10.3969/j.issn.1001-506X.2014.11.01
State	Published - 1 Nov 2014

Keywords

Collaboration
Interaction
Multi-target tracking
Probability hypothesis density (PHD) filter
Sequential Monte Carlo (SMC) method
State extraction

Access to Document

10.3969/j.issn.1001-506X.2014.11.01

Cite this

@article{2d08587d84f94d3292401a63fffd5ba9,

title = "Collaborative PHD filter for fast multi-target tracking",

abstract = "Considering the difference of dynamic evolution between the survival target and the newborn targets collaborative probability hypothesis density (CoPHD) filter framework for fast multi-target tracking is proposed. The framework strives to improve the systematic implementing efficiency as well as guarantee the tracking accuracy by dynamically partitioning the measurement set into two parts, survival and newborn target measurement sets in which PHD groups are updated respectively, and constituting an interactive and collaborative mechanism for the processing modules. In addition, the framework has the ability of state self-extracting by utilizing PHD group processing, and the implementation via the sequential Monte Carlo (SMC) method is presented. Simulation results show that the proposed SMC-CoPHD filter has greatly-reduced computation cost and significantly-improved state-extraction accuracy.",

keywords = "Collaboration, Interaction, Multi-target tracking, Probability hypothesis density (PHD) filter, Sequential Monte Carlo (SMC) method, State extraction",

author = "Feng Yang and Wang, {Yong Qi} and Yan Liang and Quan Pan",

year = "2014",

month = nov,

day = "1",

doi = "10.3969/j.issn.1001-506X.2014.11.01",

language = "英语",

volume = "36",

pages = "2113--2121",

journal = "Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics",

issn = "1001-506X",

publisher = "Chinese Institute of Electronics",

number = "11",

}

TY - JOUR

T1 - Collaborative PHD filter for fast multi-target tracking

AU - Yang, Feng

AU - Wang, Yong Qi

AU - Liang, Yan

AU - Pan, Quan

PY - 2014/11/1

Y1 - 2014/11/1

N2 - Considering the difference of dynamic evolution between the survival target and the newborn targets collaborative probability hypothesis density (CoPHD) filter framework for fast multi-target tracking is proposed. The framework strives to improve the systematic implementing efficiency as well as guarantee the tracking accuracy by dynamically partitioning the measurement set into two parts, survival and newborn target measurement sets in which PHD groups are updated respectively, and constituting an interactive and collaborative mechanism for the processing modules. In addition, the framework has the ability of state self-extracting by utilizing PHD group processing, and the implementation via the sequential Monte Carlo (SMC) method is presented. Simulation results show that the proposed SMC-CoPHD filter has greatly-reduced computation cost and significantly-improved state-extraction accuracy.

AB - Considering the difference of dynamic evolution between the survival target and the newborn targets collaborative probability hypothesis density (CoPHD) filter framework for fast multi-target tracking is proposed. The framework strives to improve the systematic implementing efficiency as well as guarantee the tracking accuracy by dynamically partitioning the measurement set into two parts, survival and newborn target measurement sets in which PHD groups are updated respectively, and constituting an interactive and collaborative mechanism for the processing modules. In addition, the framework has the ability of state self-extracting by utilizing PHD group processing, and the implementation via the sequential Monte Carlo (SMC) method is presented. Simulation results show that the proposed SMC-CoPHD filter has greatly-reduced computation cost and significantly-improved state-extraction accuracy.

KW - Collaboration

KW - Interaction

KW - Multi-target tracking

KW - Probability hypothesis density (PHD) filter

KW - Sequential Monte Carlo (SMC) method

KW - State extraction

UR - http://www.scopus.com/inward/record.url?scp=84911482992&partnerID=8YFLogxK

U2 - 10.3969/j.issn.1001-506X.2014.11.01

DO - 10.3969/j.issn.1001-506X.2014.11.01

M3 - 文章

AN - SCOPUS:84911482992

SN - 1001-506X

VL - 36

SP - 2113

EP - 2121

JO - Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics

JF - Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics

IS - 11

ER -

Collaborative PHD filter for fast multi-target tracking

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this