Sensor fusion for vehicle tracking based on the estimated probability

Chang Joo Lee, Kyeong Eun Kim, Myo Taeg Lim

Research output: Contribution to journalArticle

Abstract

The track-to-track fusion (T2TF) algorithm is currently an attractive fusion methodology in the industry because the algorithm can reflect the reliability of sensor tracks. However, the T2TF algorithm cannot be applied when the probability information of the sensor is unknown. The aim of this study is to exploit the T2TF algorithm even in the absence of the probability information of the sensor. The covariance is estimated using the recursive equations of the Kalman filter. In addition, a novel track-association approach using the total similarity is developed to improve association performance. The total similarity complements the defects of the track disposition and the estimated track history. Finally, by fusing the associated tracks using the estimated covariance, the T2TF algorithm is successfully applied to sensors with an unknown covariance. The fusion results are then evaluated using the correct association rate and the optimal subpattern assignment metric. The simulation results obtained show the superiority of the proposed algorithm under three scenarios.

Original languageEnglish
Pages (from-to)1386-1395
Number of pages10
JournalIET Intelligent Transport Systems
Volume12
Issue number10
DOIs
Publication statusPublished - 2018 Dec 1

Fingerprint

Fusion reactions
sensor
Sensors
Kalman filter
Kalman filters
disposition
defect
vehicle
scenario
Defects
simulation
methodology
industry
history
performance
Industry

ASJC Scopus subject areas

  • Transportation
  • Environmental Science(all)
  • Mechanical Engineering
  • Law

Cite this

Sensor fusion for vehicle tracking based on the estimated probability. / Lee, Chang Joo; Kim, Kyeong Eun; Lim, Myo Taeg.

In: IET Intelligent Transport Systems, Vol. 12, No. 10, 01.12.2018, p. 1386-1395.

Research output: Contribution to journalArticle

Lee, Chang Joo ; Kim, Kyeong Eun ; Lim, Myo Taeg. / Sensor fusion for vehicle tracking based on the estimated probability. In: IET Intelligent Transport Systems. 2018 ; Vol. 12, No. 10. pp. 1386-1395.
@article{83917a4487544f70903109848724bc84,
title = "Sensor fusion for vehicle tracking based on the estimated probability",
abstract = "The track-to-track fusion (T2TF) algorithm is currently an attractive fusion methodology in the industry because the algorithm can reflect the reliability of sensor tracks. However, the T2TF algorithm cannot be applied when the probability information of the sensor is unknown. The aim of this study is to exploit the T2TF algorithm even in the absence of the probability information of the sensor. The covariance is estimated using the recursive equations of the Kalman filter. In addition, a novel track-association approach using the total similarity is developed to improve association performance. The total similarity complements the defects of the track disposition and the estimated track history. Finally, by fusing the associated tracks using the estimated covariance, the T2TF algorithm is successfully applied to sensors with an unknown covariance. The fusion results are then evaluated using the correct association rate and the optimal subpattern assignment metric. The simulation results obtained show the superiority of the proposed algorithm under three scenarios.",
author = "Lee, {Chang Joo} and Kim, {Kyeong Eun} and Lim, {Myo Taeg}",
year = "2018",
month = "12",
day = "1",
doi = "10.1049/iet-its.2018.5024",
language = "English",
volume = "12",
pages = "1386--1395",
journal = "IET Intelligent Transport Systems",
issn = "1751-956X",
publisher = "Institution of Engineering and Technology",
number = "10",

}

TY - JOUR

T1 - Sensor fusion for vehicle tracking based on the estimated probability

AU - Lee, Chang Joo

AU - Kim, Kyeong Eun

AU - Lim, Myo Taeg

PY - 2018/12/1

Y1 - 2018/12/1

N2 - The track-to-track fusion (T2TF) algorithm is currently an attractive fusion methodology in the industry because the algorithm can reflect the reliability of sensor tracks. However, the T2TF algorithm cannot be applied when the probability information of the sensor is unknown. The aim of this study is to exploit the T2TF algorithm even in the absence of the probability information of the sensor. The covariance is estimated using the recursive equations of the Kalman filter. In addition, a novel track-association approach using the total similarity is developed to improve association performance. The total similarity complements the defects of the track disposition and the estimated track history. Finally, by fusing the associated tracks using the estimated covariance, the T2TF algorithm is successfully applied to sensors with an unknown covariance. The fusion results are then evaluated using the correct association rate and the optimal subpattern assignment metric. The simulation results obtained show the superiority of the proposed algorithm under three scenarios.

AB - The track-to-track fusion (T2TF) algorithm is currently an attractive fusion methodology in the industry because the algorithm can reflect the reliability of sensor tracks. However, the T2TF algorithm cannot be applied when the probability information of the sensor is unknown. The aim of this study is to exploit the T2TF algorithm even in the absence of the probability information of the sensor. The covariance is estimated using the recursive equations of the Kalman filter. In addition, a novel track-association approach using the total similarity is developed to improve association performance. The total similarity complements the defects of the track disposition and the estimated track history. Finally, by fusing the associated tracks using the estimated covariance, the T2TF algorithm is successfully applied to sensors with an unknown covariance. The fusion results are then evaluated using the correct association rate and the optimal subpattern assignment metric. The simulation results obtained show the superiority of the proposed algorithm under three scenarios.

UR - http://www.scopus.com/inward/record.url?scp=85057065163&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057065163&partnerID=8YFLogxK

U2 - 10.1049/iet-its.2018.5024

DO - 10.1049/iet-its.2018.5024

M3 - Article

VL - 12

SP - 1386

EP - 1395

JO - IET Intelligent Transport Systems

JF - IET Intelligent Transport Systems

SN - 1751-956X

IS - 10

ER -