A new framework for tracking by maintaining multiple global hypotheses for augmented reality

Kenichi Hayashi, Hirokazu Kato, Shogo Nishida

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Several tracking techniques for augmented reality have been proposed. In feature point tracking, a pose is computed by minimizing the error between the observed 2D feature points and the back-projected feature points from the 3D scene model. This minimization problem is usually solved by nonlinear optimization. The main advantage of this approach is its accuracy. However, it is difficult to compute the correct pose unless an appropriate initial value is used. In addition, when an observation contains some errors, this approach does not guarantee a correct pose even if it converges to the global minimum. Therefore, once an incorrect pose is computed in a frame, either the tracking in the next frame may fail or the result will deviate from the correct pose. In this paper, we propose a new tracking framework for augmented reality. The proposed method tracks features as multiple local hypotheses based on not just one pose but multiple poses that are computed from pose estimation in the previous frame. Since multiple poses are maintained as global hypotheses, as long as the correct pose is contained in the hypotheses, tracking can be continued even in difficult situations such as a simple iterative scene with high-speed movements.

Original languageEnglish
Title of host publicationProceedings 17th International Conference on Artificial Reality and Telexistence, ICAT 2007
Pages15-22
Number of pages8
DOIs
Publication statusPublished - 2007 Dec 1
Externally publishedYes
Event17th International Conference on Artificial Reality and Telexistence, ICAT 2007 - Esbjerg, Jylland, Denmark
Duration: 2007 Nov 282007 Nov 30

Other

Other17th International Conference on Artificial Reality and Telexistence, ICAT 2007
CountryDenmark
CityEsbjerg, Jylland
Period07/11/2807/11/30

Fingerprint

Augmented reality

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Control and Systems Engineering

Cite this

Hayashi, K., Kato, H., & Nishida, S. (2007). A new framework for tracking by maintaining multiple global hypotheses for augmented reality. In Proceedings 17th International Conference on Artificial Reality and Telexistence, ICAT 2007 (pp. 15-22). [4414611] https://doi.org/10.1109/ICAT.2007.9

A new framework for tracking by maintaining multiple global hypotheses for augmented reality. / Hayashi, Kenichi; Kato, Hirokazu; Nishida, Shogo.

Proceedings 17th International Conference on Artificial Reality and Telexistence, ICAT 2007. 2007. p. 15-22 4414611.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hayashi, K, Kato, H & Nishida, S 2007, A new framework for tracking by maintaining multiple global hypotheses for augmented reality. in Proceedings 17th International Conference on Artificial Reality and Telexistence, ICAT 2007., 4414611, pp. 15-22, 17th International Conference on Artificial Reality and Telexistence, ICAT 2007, Esbjerg, Jylland, Denmark, 07/11/28. https://doi.org/10.1109/ICAT.2007.9
Hayashi K, Kato H, Nishida S. A new framework for tracking by maintaining multiple global hypotheses for augmented reality. In Proceedings 17th International Conference on Artificial Reality and Telexistence, ICAT 2007. 2007. p. 15-22. 4414611 https://doi.org/10.1109/ICAT.2007.9
Hayashi, Kenichi ; Kato, Hirokazu ; Nishida, Shogo. / A new framework for tracking by maintaining multiple global hypotheses for augmented reality. Proceedings 17th International Conference on Artificial Reality and Telexistence, ICAT 2007. 2007. pp. 15-22
@inproceedings{3477bd22098a425fbed5cf2fdb5ae6a4,
title = "A new framework for tracking by maintaining multiple global hypotheses for augmented reality",
abstract = "Several tracking techniques for augmented reality have been proposed. In feature point tracking, a pose is computed by minimizing the error between the observed 2D feature points and the back-projected feature points from the 3D scene model. This minimization problem is usually solved by nonlinear optimization. The main advantage of this approach is its accuracy. However, it is difficult to compute the correct pose unless an appropriate initial value is used. In addition, when an observation contains some errors, this approach does not guarantee a correct pose even if it converges to the global minimum. Therefore, once an incorrect pose is computed in a frame, either the tracking in the next frame may fail or the result will deviate from the correct pose. In this paper, we propose a new tracking framework for augmented reality. The proposed method tracks features as multiple local hypotheses based on not just one pose but multiple poses that are computed from pose estimation in the previous frame. Since multiple poses are maintained as global hypotheses, as long as the correct pose is contained in the hypotheses, tracking can be continued even in difficult situations such as a simple iterative scene with high-speed movements.",
author = "Kenichi Hayashi and Hirokazu Kato and Shogo Nishida",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/ICAT.2007.9",
language = "English",
isbn = "0769530567",
pages = "15--22",
booktitle = "Proceedings 17th International Conference on Artificial Reality and Telexistence, ICAT 2007",

}

TY - GEN

T1 - A new framework for tracking by maintaining multiple global hypotheses for augmented reality

AU - Hayashi, Kenichi

AU - Kato, Hirokazu

AU - Nishida, Shogo

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Several tracking techniques for augmented reality have been proposed. In feature point tracking, a pose is computed by minimizing the error between the observed 2D feature points and the back-projected feature points from the 3D scene model. This minimization problem is usually solved by nonlinear optimization. The main advantage of this approach is its accuracy. However, it is difficult to compute the correct pose unless an appropriate initial value is used. In addition, when an observation contains some errors, this approach does not guarantee a correct pose even if it converges to the global minimum. Therefore, once an incorrect pose is computed in a frame, either the tracking in the next frame may fail or the result will deviate from the correct pose. In this paper, we propose a new tracking framework for augmented reality. The proposed method tracks features as multiple local hypotheses based on not just one pose but multiple poses that are computed from pose estimation in the previous frame. Since multiple poses are maintained as global hypotheses, as long as the correct pose is contained in the hypotheses, tracking can be continued even in difficult situations such as a simple iterative scene with high-speed movements.

AB - Several tracking techniques for augmented reality have been proposed. In feature point tracking, a pose is computed by minimizing the error between the observed 2D feature points and the back-projected feature points from the 3D scene model. This minimization problem is usually solved by nonlinear optimization. The main advantage of this approach is its accuracy. However, it is difficult to compute the correct pose unless an appropriate initial value is used. In addition, when an observation contains some errors, this approach does not guarantee a correct pose even if it converges to the global minimum. Therefore, once an incorrect pose is computed in a frame, either the tracking in the next frame may fail or the result will deviate from the correct pose. In this paper, we propose a new tracking framework for augmented reality. The proposed method tracks features as multiple local hypotheses based on not just one pose but multiple poses that are computed from pose estimation in the previous frame. Since multiple poses are maintained as global hypotheses, as long as the correct pose is contained in the hypotheses, tracking can be continued even in difficult situations such as a simple iterative scene with high-speed movements.

UR - http://www.scopus.com/inward/record.url?scp=48349086109&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48349086109&partnerID=8YFLogxK

U2 - 10.1109/ICAT.2007.9

DO - 10.1109/ICAT.2007.9

M3 - Conference contribution

AN - SCOPUS:48349086109

SN - 0769530567

SN - 9780769530567

SP - 15

EP - 22

BT - Proceedings 17th International Conference on Artificial Reality and Telexistence, ICAT 2007

ER -