Real-time visual tracking using geometric active contours and particle filters

Jincheol Ha, Eric Johnson, Allen Tannenbaum

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Image processing and filtering are essential elements for airborne visual tracking systems. This paper presents a visual tracking methodology based on particle filtering in the framework of the Chan-Vese active contour model. We describe a fast implementation of the algorithm which greatly improves the computational time of the segmentation process. We have tested particle filtering using this fast active contour model, and the filtering algorithm has shown the ability to robustly track an aerial target under varied conditions. The computational speed of the algorithm has allowed us to employ it for formation flight among several unmanned aircraft. This paper describes results from recent flight tests. We have also demonstrated the utility of the filtering algorithm for multiple target tracking in the presence of occlusions.

Original languageEnglish (US)
Pages (from-to)361-379
Number of pages19
JournalJournal of Aerospace Computing, Information and Communication
Volume5
Issue number10
DOIs
StatePublished - Oct 1 2008

Fingerprint

Target tracking
Image processing
Aircraft
Antennas

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

@article{84b3cc30939f4fc2bfd0746b508bc303,
title = "Real-time visual tracking using geometric active contours and particle filters",
abstract = "Image processing and filtering are essential elements for airborne visual tracking systems. This paper presents a visual tracking methodology based on particle filtering in the framework of the Chan-Vese active contour model. We describe a fast implementation of the algorithm which greatly improves the computational time of the segmentation process. We have tested particle filtering using this fast active contour model, and the filtering algorithm has shown the ability to robustly track an aerial target under varied conditions. The computational speed of the algorithm has allowed us to employ it for formation flight among several unmanned aircraft. This paper describes results from recent flight tests. We have also demonstrated the utility of the filtering algorithm for multiple target tracking in the presence of occlusions.",
author = "Jincheol Ha and Eric Johnson and Allen Tannenbaum",
year = "2008",
month = "10",
day = "1",
doi = "10.2514/1.35527",
language = "English (US)",
volume = "5",
pages = "361--379",
journal = "Journal of Aerospace Information Systems",
issn = "1542-9423",
publisher = "American Institute of Aeronautics and Astronautics Inc. (AIAA)",
number = "10",

}

Real-time visual tracking using geometric active contours and particle filters. / Ha, Jincheol; Johnson, Eric; Tannenbaum, Allen.

In: Journal of Aerospace Computing, Information and Communication, Vol. 5, No. 10, 01.10.2008, p. 361-379.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Real-time visual tracking using geometric active contours and particle filters

AU - Ha, Jincheol

AU - Johnson, Eric

AU - Tannenbaum, Allen

PY - 2008/10/1

Y1 - 2008/10/1

N2 - Image processing and filtering are essential elements for airborne visual tracking systems. This paper presents a visual tracking methodology based on particle filtering in the framework of the Chan-Vese active contour model. We describe a fast implementation of the algorithm which greatly improves the computational time of the segmentation process. We have tested particle filtering using this fast active contour model, and the filtering algorithm has shown the ability to robustly track an aerial target under varied conditions. The computational speed of the algorithm has allowed us to employ it for formation flight among several unmanned aircraft. This paper describes results from recent flight tests. We have also demonstrated the utility of the filtering algorithm for multiple target tracking in the presence of occlusions.

AB - Image processing and filtering are essential elements for airborne visual tracking systems. This paper presents a visual tracking methodology based on particle filtering in the framework of the Chan-Vese active contour model. We describe a fast implementation of the algorithm which greatly improves the computational time of the segmentation process. We have tested particle filtering using this fast active contour model, and the filtering algorithm has shown the ability to robustly track an aerial target under varied conditions. The computational speed of the algorithm has allowed us to employ it for formation flight among several unmanned aircraft. This paper describes results from recent flight tests. We have also demonstrated the utility of the filtering algorithm for multiple target tracking in the presence of occlusions.

UR - http://www.scopus.com/inward/record.url?scp=55249099587&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=55249099587&partnerID=8YFLogxK

U2 - 10.2514/1.35527

DO - 10.2514/1.35527

M3 - Article

VL - 5

SP - 361

EP - 379

JO - Journal of Aerospace Information Systems

JF - Journal of Aerospace Information Systems

SN - 1542-9423

IS - 10

ER -