ADAPTIVE APPROACH TO VIDEO TRACKING.

Mansur R. Kabuka, E. McVey, P. Shironoshita

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

A video tracking system based on the principles of optimalizing control is presented. This system is designed such that expensive segmentation procedures are not necessary, and is well suited for fast hardware implementation. At the image received from the camera a perturbation procedure is performed, simulating the variations on the intensity values that would occur if the camera were moved. An index of performance (IP) is evaluated at the results of this perturbation; this IP does not need to detect the position of the tracked object accurately, but rather varies in such a way as to detect the motion of the object with respect to the camera. Algorithms for translation and scaling of the tracking object have been developed using area, centroid, and template matching as indices of performance. Software simulation experiments show that the control law developed yields good results even under variations in background and illumination and under multidimensional motion.

Original languageEnglish
Pages (from-to)228-236
Number of pages9
JournalIEEE journal of robotics and automation
Volume4
Issue number2
DOIs
StatePublished - Apr 1 1988

Fingerprint

Cameras
Template matching
Lighting
Hardware
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

ADAPTIVE APPROACH TO VIDEO TRACKING. / Kabuka, Mansur R.; McVey, E.; Shironoshita, P.

In: IEEE journal of robotics and automation, Vol. 4, No. 2, 01.04.1988, p. 228-236.

Research output: Contribution to journalArticle

Kabuka, Mansur R. ; McVey, E. ; Shironoshita, P. / ADAPTIVE APPROACH TO VIDEO TRACKING. In: IEEE journal of robotics and automation. 1988 ; Vol. 4, No. 2. pp. 228-236.
@article{807d9265ac33422c991c0715b45b75cc,
title = "ADAPTIVE APPROACH TO VIDEO TRACKING.",
abstract = "A video tracking system based on the principles of optimalizing control is presented. This system is designed such that expensive segmentation procedures are not necessary, and is well suited for fast hardware implementation. At the image received from the camera a perturbation procedure is performed, simulating the variations on the intensity values that would occur if the camera were moved. An index of performance (IP) is evaluated at the results of this perturbation; this IP does not need to detect the position of the tracked object accurately, but rather varies in such a way as to detect the motion of the object with respect to the camera. Algorithms for translation and scaling of the tracking object have been developed using area, centroid, and template matching as indices of performance. Software simulation experiments show that the control law developed yields good results even under variations in background and illumination and under multidimensional motion.",
author = "Kabuka, {Mansur R.} and E. McVey and P. Shironoshita",
year = "1988",
month = "4",
day = "1",
doi = "10.1109/56.2088",
language = "English",
volume = "4",
pages = "228--236",
journal = "IEEE journal of robotics and automation",
issn = "0882-4967",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - ADAPTIVE APPROACH TO VIDEO TRACKING.

AU - Kabuka, Mansur R.

AU - McVey, E.

AU - Shironoshita, P.

PY - 1988/4/1

Y1 - 1988/4/1

N2 - A video tracking system based on the principles of optimalizing control is presented. This system is designed such that expensive segmentation procedures are not necessary, and is well suited for fast hardware implementation. At the image received from the camera a perturbation procedure is performed, simulating the variations on the intensity values that would occur if the camera were moved. An index of performance (IP) is evaluated at the results of this perturbation; this IP does not need to detect the position of the tracked object accurately, but rather varies in such a way as to detect the motion of the object with respect to the camera. Algorithms for translation and scaling of the tracking object have been developed using area, centroid, and template matching as indices of performance. Software simulation experiments show that the control law developed yields good results even under variations in background and illumination and under multidimensional motion.

AB - A video tracking system based on the principles of optimalizing control is presented. This system is designed such that expensive segmentation procedures are not necessary, and is well suited for fast hardware implementation. At the image received from the camera a perturbation procedure is performed, simulating the variations on the intensity values that would occur if the camera were moved. An index of performance (IP) is evaluated at the results of this perturbation; this IP does not need to detect the position of the tracked object accurately, but rather varies in such a way as to detect the motion of the object with respect to the camera. Algorithms for translation and scaling of the tracking object have been developed using area, centroid, and template matching as indices of performance. Software simulation experiments show that the control law developed yields good results even under variations in background and illumination and under multidimensional motion.

UR - http://www.scopus.com/inward/record.url?scp=0023999563&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0023999563&partnerID=8YFLogxK

U2 - 10.1109/56.2088

DO - 10.1109/56.2088

M3 - Article

VL - 4

SP - 228

EP - 236

JO - IEEE journal of robotics and automation

JF - IEEE journal of robotics and automation

SN - 0882-4967

IS - 2

ER -