Long short-term memory-based deep recurrent neural networks for target tracking

Chang Gao, Junkun Yan, Shenghua Zhou, Pramod Kumar Varshney, Hongwei Liu

Research output: Contribution to journalArticle

Abstract

Target tracking is a difficult estimation problem due to target motion uncertainty and measurement origin uncertainty. In this paper, we consider the target tracking problem in the presence of only target motion uncertainty. The traditional approaches to address this uncertainty, such as multiple model approaches, can suffer performance degradation when there is a model mismatch. The statistical accuracy of conventional model-based methods is also usually limited because of the measurement errors and insufficient data for the estimation. In this paper, deep neural network-based methods are proposed to handle target motion uncertainty due to their strong capability of fitting any mapping as long as there are sufficient training data. Specifically, a recurrent neural network-based structure is proposed to estimate the true states that is consistent with the sequential manner of target tracking. In addition, it is expected that better performance will be achieved due to access to true states during the training of the networks. We propose two networks that are based on different principles and are capable of real-time tracking. An approach to further reduce the computational load is also introduced. Simulation results show that the proposed methods can handle the target motion uncertainty well and provide better estimation accuracy.

Original languageEnglish (US)
Pages (from-to)279-296
Number of pages18
JournalInformation Sciences
Volume502
DOIs
StatePublished - Oct 1 2019

Fingerprint

Memory Term
Recurrent neural networks
Target Tracking
Recurrent Neural Networks
Target tracking
Uncertainty
Target
Motion
Multiple Models
Measurement errors
Measurement Error
Long short-term memory
Degradation
Neural Networks
Model-based
Sufficient
Real-time
Estimate
Simulation

Keywords

  • Deep neural network
  • Long short-term memory
  • Recurrent neural network
  • Target tracking

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Cite this

Long short-term memory-based deep recurrent neural networks for target tracking. / Gao, Chang; Yan, Junkun; Zhou, Shenghua; Varshney, Pramod Kumar; Liu, Hongwei.

In: Information Sciences, Vol. 502, 01.10.2019, p. 279-296.

Research output: Contribution to journalArticle

Gao, Chang ; Yan, Junkun ; Zhou, Shenghua ; Varshney, Pramod Kumar ; Liu, Hongwei. / Long short-term memory-based deep recurrent neural networks for target tracking. In: Information Sciences. 2019 ; Vol. 502. pp. 279-296.
@article{c9efe77cde9b4e769c011855bcd6bad8,
title = "Long short-term memory-based deep recurrent neural networks for target tracking",
abstract = "Target tracking is a difficult estimation problem due to target motion uncertainty and measurement origin uncertainty. In this paper, we consider the target tracking problem in the presence of only target motion uncertainty. The traditional approaches to address this uncertainty, such as multiple model approaches, can suffer performance degradation when there is a model mismatch. The statistical accuracy of conventional model-based methods is also usually limited because of the measurement errors and insufficient data for the estimation. In this paper, deep neural network-based methods are proposed to handle target motion uncertainty due to their strong capability of fitting any mapping as long as there are sufficient training data. Specifically, a recurrent neural network-based structure is proposed to estimate the true states that is consistent with the sequential manner of target tracking. In addition, it is expected that better performance will be achieved due to access to true states during the training of the networks. We propose two networks that are based on different principles and are capable of real-time tracking. An approach to further reduce the computational load is also introduced. Simulation results show that the proposed methods can handle the target motion uncertainty well and provide better estimation accuracy.",
keywords = "Deep neural network, Long short-term memory, Recurrent neural network, Target tracking",
author = "Chang Gao and Junkun Yan and Shenghua Zhou and Varshney, {Pramod Kumar} and Hongwei Liu",
year = "2019",
month = "10",
day = "1",
doi = "10.1016/j.ins.2019.06.039",
language = "English (US)",
volume = "502",
pages = "279--296",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier",

}

TY - JOUR

T1 - Long short-term memory-based deep recurrent neural networks for target tracking

AU - Gao, Chang

AU - Yan, Junkun

AU - Zhou, Shenghua

AU - Varshney, Pramod Kumar

AU - Liu, Hongwei

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Target tracking is a difficult estimation problem due to target motion uncertainty and measurement origin uncertainty. In this paper, we consider the target tracking problem in the presence of only target motion uncertainty. The traditional approaches to address this uncertainty, such as multiple model approaches, can suffer performance degradation when there is a model mismatch. The statistical accuracy of conventional model-based methods is also usually limited because of the measurement errors and insufficient data for the estimation. In this paper, deep neural network-based methods are proposed to handle target motion uncertainty due to their strong capability of fitting any mapping as long as there are sufficient training data. Specifically, a recurrent neural network-based structure is proposed to estimate the true states that is consistent with the sequential manner of target tracking. In addition, it is expected that better performance will be achieved due to access to true states during the training of the networks. We propose two networks that are based on different principles and are capable of real-time tracking. An approach to further reduce the computational load is also introduced. Simulation results show that the proposed methods can handle the target motion uncertainty well and provide better estimation accuracy.

AB - Target tracking is a difficult estimation problem due to target motion uncertainty and measurement origin uncertainty. In this paper, we consider the target tracking problem in the presence of only target motion uncertainty. The traditional approaches to address this uncertainty, such as multiple model approaches, can suffer performance degradation when there is a model mismatch. The statistical accuracy of conventional model-based methods is also usually limited because of the measurement errors and insufficient data for the estimation. In this paper, deep neural network-based methods are proposed to handle target motion uncertainty due to their strong capability of fitting any mapping as long as there are sufficient training data. Specifically, a recurrent neural network-based structure is proposed to estimate the true states that is consistent with the sequential manner of target tracking. In addition, it is expected that better performance will be achieved due to access to true states during the training of the networks. We propose two networks that are based on different principles and are capable of real-time tracking. An approach to further reduce the computational load is also introduced. Simulation results show that the proposed methods can handle the target motion uncertainty well and provide better estimation accuracy.

KW - Deep neural network

KW - Long short-term memory

KW - Recurrent neural network

KW - Target tracking

UR - http://www.scopus.com/inward/record.url?scp=85067524229&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067524229&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2019.06.039

DO - 10.1016/j.ins.2019.06.039

M3 - Article

AN - SCOPUS:85067524229

VL - 502

SP - 279

EP - 296

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

ER -