New preceding vehicle tracking algorithm based on optimal unbiased finite memory filter

In Hwan Choi, Jung Min Pak, Choon Ki Ahn, Young Hak Mo, Myo Taeg Lim, Moon Kyou Song

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Abstract In recent years, visual object tracking technologies have been used to track preceding vehicles in advanced driver assistance systems (ADASs). The accurate positioning of preceding vehicles in camera images allows drivers to avoid collisions with the preceding vehicle. Tracking systems typically take advantage of state estimators, such as the Kalman filter (KF) and the particle filter (PF), in order to suppress noises in measurements. In particular, the KF is popular in visual object tracking, because of its computational efficiency. However, the visual tracker based on the KF, referred to as the Kalman tracker (KT), has the drawback that its performance can decrease due to modeling and computational errors. To overcome this drawback, we propose a novel visual tracker based on the optimal unbiased finite memory filter (OUFMF) in the formulation of a linear matrix inequality (LMI) and a linear matrix equality (LME). We call the proposed visual tracker the finite memory tracker (FMT), and it is applied to the preceding vehicle tracking. Through extensive experiments, we demonstrate the FMT's performance that is superior to that of the KT and other filter-based tracker.

Original languageEnglish
Article number3368
Pages (from-to)262-274
Number of pages13
JournalMeasurement: Journal of the International Measurement Confederation
Volume73
DOIs
Publication statusPublished - 2015 Jun 14

Fingerprint

Vehicle Tracking
Kalman filters
Kalman Filter
Visual Tracking
vehicles
driver
Object Tracking
Filter
filters
Data storage equipment
Advanced driver assistance systems
performance
equality
Driver Assistance
assistance
Particle Filter
Tracking System
Computational efficiency
Linear matrix inequalities
Computational Efficiency

Keywords

  • Finite measurements
  • Finite memory tracker (FMT)
  • Optimal unbiased finite memory filter (OUFMF)
  • Preceding vehicle tracking

ASJC Scopus subject areas

  • Condensed Matter Physics
  • Applied Mathematics

Cite this

New preceding vehicle tracking algorithm based on optimal unbiased finite memory filter. / Choi, In Hwan; Pak, Jung Min; Ahn, Choon Ki; Mo, Young Hak; Lim, Myo Taeg; Song, Moon Kyou.

In: Measurement: Journal of the International Measurement Confederation, Vol. 73, 3368, 14.06.2015, p. 262-274.

Research output: Contribution to journalArticle

@article{3c78f51ba2564cdbaed79e51adde1322,
title = "New preceding vehicle tracking algorithm based on optimal unbiased finite memory filter",
abstract = "Abstract In recent years, visual object tracking technologies have been used to track preceding vehicles in advanced driver assistance systems (ADASs). The accurate positioning of preceding vehicles in camera images allows drivers to avoid collisions with the preceding vehicle. Tracking systems typically take advantage of state estimators, such as the Kalman filter (KF) and the particle filter (PF), in order to suppress noises in measurements. In particular, the KF is popular in visual object tracking, because of its computational efficiency. However, the visual tracker based on the KF, referred to as the Kalman tracker (KT), has the drawback that its performance can decrease due to modeling and computational errors. To overcome this drawback, we propose a novel visual tracker based on the optimal unbiased finite memory filter (OUFMF) in the formulation of a linear matrix inequality (LMI) and a linear matrix equality (LME). We call the proposed visual tracker the finite memory tracker (FMT), and it is applied to the preceding vehicle tracking. Through extensive experiments, we demonstrate the FMT's performance that is superior to that of the KT and other filter-based tracker.",
keywords = "Finite measurements, Finite memory tracker (FMT), Optimal unbiased finite memory filter (OUFMF), Preceding vehicle tracking",
author = "Choi, {In Hwan} and Pak, {Jung Min} and Ahn, {Choon Ki} and Mo, {Young Hak} and Lim, {Myo Taeg} and Song, {Moon Kyou}",
year = "2015",
month = "6",
day = "14",
doi = "10.1016/j.measurement.2015.04.015",
language = "English",
volume = "73",
pages = "262--274",
journal = "Measurement",
issn = "1536-6367",
publisher = "Elsevier",

}

TY - JOUR

T1 - New preceding vehicle tracking algorithm based on optimal unbiased finite memory filter

AU - Choi, In Hwan

AU - Pak, Jung Min

AU - Ahn, Choon Ki

AU - Mo, Young Hak

AU - Lim, Myo Taeg

AU - Song, Moon Kyou

PY - 2015/6/14

Y1 - 2015/6/14

N2 - Abstract In recent years, visual object tracking technologies have been used to track preceding vehicles in advanced driver assistance systems (ADASs). The accurate positioning of preceding vehicles in camera images allows drivers to avoid collisions with the preceding vehicle. Tracking systems typically take advantage of state estimators, such as the Kalman filter (KF) and the particle filter (PF), in order to suppress noises in measurements. In particular, the KF is popular in visual object tracking, because of its computational efficiency. However, the visual tracker based on the KF, referred to as the Kalman tracker (KT), has the drawback that its performance can decrease due to modeling and computational errors. To overcome this drawback, we propose a novel visual tracker based on the optimal unbiased finite memory filter (OUFMF) in the formulation of a linear matrix inequality (LMI) and a linear matrix equality (LME). We call the proposed visual tracker the finite memory tracker (FMT), and it is applied to the preceding vehicle tracking. Through extensive experiments, we demonstrate the FMT's performance that is superior to that of the KT and other filter-based tracker.

AB - Abstract In recent years, visual object tracking technologies have been used to track preceding vehicles in advanced driver assistance systems (ADASs). The accurate positioning of preceding vehicles in camera images allows drivers to avoid collisions with the preceding vehicle. Tracking systems typically take advantage of state estimators, such as the Kalman filter (KF) and the particle filter (PF), in order to suppress noises in measurements. In particular, the KF is popular in visual object tracking, because of its computational efficiency. However, the visual tracker based on the KF, referred to as the Kalman tracker (KT), has the drawback that its performance can decrease due to modeling and computational errors. To overcome this drawback, we propose a novel visual tracker based on the optimal unbiased finite memory filter (OUFMF) in the formulation of a linear matrix inequality (LMI) and a linear matrix equality (LME). We call the proposed visual tracker the finite memory tracker (FMT), and it is applied to the preceding vehicle tracking. Through extensive experiments, we demonstrate the FMT's performance that is superior to that of the KT and other filter-based tracker.

KW - Finite measurements

KW - Finite memory tracker (FMT)

KW - Optimal unbiased finite memory filter (OUFMF)

KW - Preceding vehicle tracking

UR - http://www.scopus.com/inward/record.url?scp=84931281684&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84931281684&partnerID=8YFLogxK

U2 - 10.1016/j.measurement.2015.04.015

DO - 10.1016/j.measurement.2015.04.015

M3 - Article

VL - 73

SP - 262

EP - 274

JO - Measurement

JF - Measurement

SN - 1536-6367

M1 - 3368

ER -