Robust target detection and tracking through integration of motion, color, and geometry

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

Vision-based tracking is a basic elementary task in many computer vision-based applications such as video surveillance and monitoring, sensing and navigation in robotics, video compression, video annotation, and many more. However, reliable recovery of targets and their trajectories in an uncontrolled environment is affected by a wide range of conditions exhibited by the environment such as sudden illumination changes and clutter. This work addresses the problem of (i) combining information from a set of cues in order to obtain reasonably accurate estimates of multiple targets in uncontrolled environments and (ii) a collection of data association methods for cues containing less information for robust tracking through persistent clutter. Specifically, we introduce a novel geometric template constrained data association method for robust tracking of point features, while using the Joint Probabilistic Data Association (JPDA) method for blob cue measurements. Extensive experimental validation of the tracking and the data association framework is presented in the work for several real-world outdoor traffic intersection image sequences.

Original languageEnglish (US)
Pages (from-to)121-138
Number of pages18
JournalComputer Vision and Image Understanding
Volume103
Issue number2
DOIs
StatePublished - Aug 1 2006

Fingerprint

Image compression
Target tracking
Computer vision
Navigation
Robotics
Lighting
Trajectories
Color
Recovery
Geometry
Monitoring

Keywords

  • Data association
  • Expectation maximization
  • Measurement error estimation
  • Multiple cue combination

Cite this

Robust target detection and tracking through integration of motion, color, and geometry. / Veeraraghavan, Harini; Schrater, Paul R; Papanikolopoulos, Nikolaos P.

In: Computer Vision and Image Understanding, Vol. 103, No. 2, 01.08.2006, p. 121-138.

Research output: Contribution to journalArticle

@article{f74f859c3b674a50bef69a9a56f6fe86,
title = "Robust target detection and tracking through integration of motion, color, and geometry",
abstract = "Vision-based tracking is a basic elementary task in many computer vision-based applications such as video surveillance and monitoring, sensing and navigation in robotics, video compression, video annotation, and many more. However, reliable recovery of targets and their trajectories in an uncontrolled environment is affected by a wide range of conditions exhibited by the environment such as sudden illumination changes and clutter. This work addresses the problem of (i) combining information from a set of cues in order to obtain reasonably accurate estimates of multiple targets in uncontrolled environments and (ii) a collection of data association methods for cues containing less information for robust tracking through persistent clutter. Specifically, we introduce a novel geometric template constrained data association method for robust tracking of point features, while using the Joint Probabilistic Data Association (JPDA) method for blob cue measurements. Extensive experimental validation of the tracking and the data association framework is presented in the work for several real-world outdoor traffic intersection image sequences.",
keywords = "Data association, Expectation maximization, Measurement error estimation, Multiple cue combination",
author = "Harini Veeraraghavan and Schrater, {Paul R} and Papanikolopoulos, {Nikolaos P}",
year = "2006",
month = "8",
day = "1",
doi = "10.1016/j.cviu.2006.04.003",
language = "English (US)",
volume = "103",
pages = "121--138",
journal = "Computer Vision and Image Understanding",
issn = "1077-3142",
publisher = "Academic Press Inc.",
number = "2",

}

TY - JOUR

T1 - Robust target detection and tracking through integration of motion, color, and geometry

AU - Veeraraghavan, Harini

AU - Schrater, Paul R

AU - Papanikolopoulos, Nikolaos P

PY - 2006/8/1

Y1 - 2006/8/1

N2 - Vision-based tracking is a basic elementary task in many computer vision-based applications such as video surveillance and monitoring, sensing and navigation in robotics, video compression, video annotation, and many more. However, reliable recovery of targets and their trajectories in an uncontrolled environment is affected by a wide range of conditions exhibited by the environment such as sudden illumination changes and clutter. This work addresses the problem of (i) combining information from a set of cues in order to obtain reasonably accurate estimates of multiple targets in uncontrolled environments and (ii) a collection of data association methods for cues containing less information for robust tracking through persistent clutter. Specifically, we introduce a novel geometric template constrained data association method for robust tracking of point features, while using the Joint Probabilistic Data Association (JPDA) method for blob cue measurements. Extensive experimental validation of the tracking and the data association framework is presented in the work for several real-world outdoor traffic intersection image sequences.

AB - Vision-based tracking is a basic elementary task in many computer vision-based applications such as video surveillance and monitoring, sensing and navigation in robotics, video compression, video annotation, and many more. However, reliable recovery of targets and their trajectories in an uncontrolled environment is affected by a wide range of conditions exhibited by the environment such as sudden illumination changes and clutter. This work addresses the problem of (i) combining information from a set of cues in order to obtain reasonably accurate estimates of multiple targets in uncontrolled environments and (ii) a collection of data association methods for cues containing less information for robust tracking through persistent clutter. Specifically, we introduce a novel geometric template constrained data association method for robust tracking of point features, while using the Joint Probabilistic Data Association (JPDA) method for blob cue measurements. Extensive experimental validation of the tracking and the data association framework is presented in the work for several real-world outdoor traffic intersection image sequences.

KW - Data association

KW - Expectation maximization

KW - Measurement error estimation

KW - Multiple cue combination

UR - http://www.scopus.com/inward/record.url?scp=33746083573&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33746083573&partnerID=8YFLogxK

U2 - 10.1016/j.cviu.2006.04.003

DO - 10.1016/j.cviu.2006.04.003

M3 - Article

VL - 103

SP - 121

EP - 138

JO - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

SN - 1077-3142

IS - 2

ER -