Model-based 3-D object tracking using projective invariance

Sung Woo Lee, Bum Jae You, Gregory Hager

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

This paper describes a method of three-dimensional object tracking by projective invariance. Usually, projective invariance has been used for object recognition and its property discards the need for cumbersome camera calibration to obtain metric information. We focus on the fact the projective invariance is not only regarded as recognition cues but also able to verify the status of a 3-D object for visual tracking. With projective invariance relevant to points, we develop a fast and reliable visual tracking strategy by combining a recognition module using projective invariance, window-based corner trackers for object's corner tracking and a visibility checking module. The proposed method is experimented in single IBM-PC platform successfully.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
PublisherIEEE
Pages1589-1594
Number of pages6
Volume2
StatePublished - 1999
Externally publishedYes
EventProceedings of the 1999 IEEE International Conference on Robotics and Automation, ICRA99 - Detroit, MI, USA
Duration: May 10 1999May 15 1999

Other

OtherProceedings of the 1999 IEEE International Conference on Robotics and Automation, ICRA99
CityDetroit, MI, USA
Period5/10/995/15/99

Fingerprint

Invariance
Object recognition
Visibility
Cameras
Calibration

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering

Cite this

Lee, S. W., You, B. J., & Hager, G. (1999). Model-based 3-D object tracking using projective invariance. In Proceedings - IEEE International Conference on Robotics and Automation (Vol. 2, pp. 1589-1594). IEEE.

Model-based 3-D object tracking using projective invariance. / Lee, Sung Woo; You, Bum Jae; Hager, Gregory.

Proceedings - IEEE International Conference on Robotics and Automation. Vol. 2 IEEE, 1999. p. 1589-1594.

Research output: Chapter in Book/Report/Conference proceedingChapter

Lee, SW, You, BJ & Hager, G 1999, Model-based 3-D object tracking using projective invariance. in Proceedings - IEEE International Conference on Robotics and Automation. vol. 2, IEEE, pp. 1589-1594, Proceedings of the 1999 IEEE International Conference on Robotics and Automation, ICRA99, Detroit, MI, USA, 5/10/99.
Lee SW, You BJ, Hager G. Model-based 3-D object tracking using projective invariance. In Proceedings - IEEE International Conference on Robotics and Automation. Vol. 2. IEEE. 1999. p. 1589-1594
Lee, Sung Woo ; You, Bum Jae ; Hager, Gregory. / Model-based 3-D object tracking using projective invariance. Proceedings - IEEE International Conference on Robotics and Automation. Vol. 2 IEEE, 1999. pp. 1589-1594
@inbook{4245c402d4614af08adc591f1b7cca84,
title = "Model-based 3-D object tracking using projective invariance",
abstract = "This paper describes a method of three-dimensional object tracking by projective invariance. Usually, projective invariance has been used for object recognition and its property discards the need for cumbersome camera calibration to obtain metric information. We focus on the fact the projective invariance is not only regarded as recognition cues but also able to verify the status of a 3-D object for visual tracking. With projective invariance relevant to points, we develop a fast and reliable visual tracking strategy by combining a recognition module using projective invariance, window-based corner trackers for object's corner tracking and a visibility checking module. The proposed method is experimented in single IBM-PC platform successfully.",
author = "Lee, {Sung Woo} and You, {Bum Jae} and Gregory Hager",
year = "1999",
language = "English (US)",
volume = "2",
pages = "1589--1594",
booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",
publisher = "IEEE",

}

TY - CHAP

T1 - Model-based 3-D object tracking using projective invariance

AU - Lee, Sung Woo

AU - You, Bum Jae

AU - Hager, Gregory

PY - 1999

Y1 - 1999

N2 - This paper describes a method of three-dimensional object tracking by projective invariance. Usually, projective invariance has been used for object recognition and its property discards the need for cumbersome camera calibration to obtain metric information. We focus on the fact the projective invariance is not only regarded as recognition cues but also able to verify the status of a 3-D object for visual tracking. With projective invariance relevant to points, we develop a fast and reliable visual tracking strategy by combining a recognition module using projective invariance, window-based corner trackers for object's corner tracking and a visibility checking module. The proposed method is experimented in single IBM-PC platform successfully.

AB - This paper describes a method of three-dimensional object tracking by projective invariance. Usually, projective invariance has been used for object recognition and its property discards the need for cumbersome camera calibration to obtain metric information. We focus on the fact the projective invariance is not only regarded as recognition cues but also able to verify the status of a 3-D object for visual tracking. With projective invariance relevant to points, we develop a fast and reliable visual tracking strategy by combining a recognition module using projective invariance, window-based corner trackers for object's corner tracking and a visibility checking module. The proposed method is experimented in single IBM-PC platform successfully.

UR - http://www.scopus.com/inward/record.url?scp=0032661327&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032661327&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:0032661327

VL - 2

SP - 1589

EP - 1594

BT - Proceedings - IEEE International Conference on Robotics and Automation

PB - IEEE

ER -