Effective Multi-Vehicle Tracking in Nighttime Condition Using Imaging Sensors

Hanseok Ko, Ilkwang Lee, Jihyo Lee, David Han

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we develop an image-based tracking algorithm of multiple vehicles performing effective detection and tracking of moving objects under adverse environmental conditions. In particular, we employ low cost commercial off-the-shelf IR or CCD image sensor for generating continuous images of multiple moving vehicles. The motion in image sequences is first detected by adaptive background estimation and then tracked by Kalman filtering with the attribute information being updated by data association. Upon applying a modified Retinex procedure as preprocessing to reduce the illumination effects, we proceed with a two-step tracking algorithm. The first step achieves blob grouping and then judicially selects the true targets for tracking using data association through information registration. In the second stage, all blobs detected go through a validation for screening as well as for occlusion reasoning, and those found pertinent to the real object survive to become the 'Object' state for stable tracking. The results of representative tests confirm its effectiveness in vehicle tracking under both daylight and nighttime conditions while resolving occlusions.

Original languageEnglish
Pages (from-to)1887-1895
Number of pages9
JournalIEICE Transactions on Information and Systems
VolumeE86-D
Issue number9
Publication statusPublished - 2003 Sep 1

Fingerprint

Imaging techniques
Sensors
Charge coupled devices
Image sensors
Screening
Lighting
Costs

Keywords

  • CCD
  • IR
  • Multi-vehicle tracking
  • Nighttime condition
  • Two-step tracking

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Information Systems
  • Software

Cite this

Effective Multi-Vehicle Tracking in Nighttime Condition Using Imaging Sensors. / Ko, Hanseok; Lee, Ilkwang; Lee, Jihyo; Han, David.

In: IEICE Transactions on Information and Systems, Vol. E86-D, No. 9, 01.09.2003, p. 1887-1895.

Research output: Contribution to journalArticle

Ko, Hanseok ; Lee, Ilkwang ; Lee, Jihyo ; Han, David. / Effective Multi-Vehicle Tracking in Nighttime Condition Using Imaging Sensors. In: IEICE Transactions on Information and Systems. 2003 ; Vol. E86-D, No. 9. pp. 1887-1895.
@article{3a806045692d4fdabcbd98535f89a4c5,
title = "Effective Multi-Vehicle Tracking in Nighttime Condition Using Imaging Sensors",
abstract = "In this paper, we develop an image-based tracking algorithm of multiple vehicles performing effective detection and tracking of moving objects under adverse environmental conditions. In particular, we employ low cost commercial off-the-shelf IR or CCD image sensor for generating continuous images of multiple moving vehicles. The motion in image sequences is first detected by adaptive background estimation and then tracked by Kalman filtering with the attribute information being updated by data association. Upon applying a modified Retinex procedure as preprocessing to reduce the illumination effects, we proceed with a two-step tracking algorithm. The first step achieves blob grouping and then judicially selects the true targets for tracking using data association through information registration. In the second stage, all blobs detected go through a validation for screening as well as for occlusion reasoning, and those found pertinent to the real object survive to become the 'Object' state for stable tracking. The results of representative tests confirm its effectiveness in vehicle tracking under both daylight and nighttime conditions while resolving occlusions.",
keywords = "CCD, IR, Multi-vehicle tracking, Nighttime condition, Two-step tracking",
author = "Hanseok Ko and Ilkwang Lee and Jihyo Lee and David Han",
year = "2003",
month = "9",
day = "1",
language = "English",
volume = "E86-D",
pages = "1887--1895",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "9",

}

TY - JOUR

T1 - Effective Multi-Vehicle Tracking in Nighttime Condition Using Imaging Sensors

AU - Ko, Hanseok

AU - Lee, Ilkwang

AU - Lee, Jihyo

AU - Han, David

PY - 2003/9/1

Y1 - 2003/9/1

N2 - In this paper, we develop an image-based tracking algorithm of multiple vehicles performing effective detection and tracking of moving objects under adverse environmental conditions. In particular, we employ low cost commercial off-the-shelf IR or CCD image sensor for generating continuous images of multiple moving vehicles. The motion in image sequences is first detected by adaptive background estimation and then tracked by Kalman filtering with the attribute information being updated by data association. Upon applying a modified Retinex procedure as preprocessing to reduce the illumination effects, we proceed with a two-step tracking algorithm. The first step achieves blob grouping and then judicially selects the true targets for tracking using data association through information registration. In the second stage, all blobs detected go through a validation for screening as well as for occlusion reasoning, and those found pertinent to the real object survive to become the 'Object' state for stable tracking. The results of representative tests confirm its effectiveness in vehicle tracking under both daylight and nighttime conditions while resolving occlusions.

AB - In this paper, we develop an image-based tracking algorithm of multiple vehicles performing effective detection and tracking of moving objects under adverse environmental conditions. In particular, we employ low cost commercial off-the-shelf IR or CCD image sensor for generating continuous images of multiple moving vehicles. The motion in image sequences is first detected by adaptive background estimation and then tracked by Kalman filtering with the attribute information being updated by data association. Upon applying a modified Retinex procedure as preprocessing to reduce the illumination effects, we proceed with a two-step tracking algorithm. The first step achieves blob grouping and then judicially selects the true targets for tracking using data association through information registration. In the second stage, all blobs detected go through a validation for screening as well as for occlusion reasoning, and those found pertinent to the real object survive to become the 'Object' state for stable tracking. The results of representative tests confirm its effectiveness in vehicle tracking under both daylight and nighttime conditions while resolving occlusions.

KW - CCD

KW - IR

KW - Multi-vehicle tracking

KW - Nighttime condition

KW - Two-step tracking

UR - http://www.scopus.com/inward/record.url?scp=1642394926&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1642394926&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:1642394926

VL - E86-D

SP - 1887

EP - 1895

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 9

ER -