Analytic fusion of visual cues in model-based camera tracking

Hanhoon Park, Hideki Mitsumine, Masato Fujii, Jong-Il Park

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

2 Citations (Scopus)

Abstract

Model-based camera tracking is a technology that estimates a camera pose by tracking visual cues, i.e. points and edges on a known 3D scene model, in camera images. In model-based camera tracking, it has been a main challenge how to use the visual cues effectively for better performance. In this paper, we carefully analyze the dependency of the visual cues on tracking conditions (or environments) and propose a formula for integrating the visual cues cooperatively into a single framework based on the analysis. Then, we demonstrate that the analytic integration outperforms separate use of either cue and expedient integration of visual cues in arbitrary environments through experiments with synthetic camera images for which ground truth camera poses are given.

Original languageEnglish
Title of host publicationProceedings - VRCAI 2009
Subtitle of host publication8th International Conference on Virtual Reality Continuum and its Applications in Industry
Pages215-220
Number of pages6
DOIs
StatePublished - 2009 Dec 1
EventVRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry - Yokohama, Japan
Duration: 2009 Dec 142009 Dec 15

Publication series

NameProceedings - VRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry

Other

OtherVRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry
CountryJapan
CityYokohama
Period09/12/1409/12/15

Fingerprint

Fusion reactions
Cameras
Experiments

Keywords

  • Analytic fusion
  • Augmented reality
  • Model-based camera tracking

Cite this

Park, H., Mitsumine, H., Fujii, M., & Park, J-I. (2009). Analytic fusion of visual cues in model-based camera tracking. In Proceedings - VRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry (pp. 215-220). (Proceedings - VRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry). https://doi.org/10.1145/1670252.1670298
Park, Hanhoon ; Mitsumine, Hideki ; Fujii, Masato ; Park, Jong-Il. / Analytic fusion of visual cues in model-based camera tracking. Proceedings - VRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry. 2009. pp. 215-220 (Proceedings - VRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry).
@inproceedings{bf5d56914b45486a8b1f2cc020b4f0e2,
title = "Analytic fusion of visual cues in model-based camera tracking",
abstract = "Model-based camera tracking is a technology that estimates a camera pose by tracking visual cues, i.e. points and edges on a known 3D scene model, in camera images. In model-based camera tracking, it has been a main challenge how to use the visual cues effectively for better performance. In this paper, we carefully analyze the dependency of the visual cues on tracking conditions (or environments) and propose a formula for integrating the visual cues cooperatively into a single framework based on the analysis. Then, we demonstrate that the analytic integration outperforms separate use of either cue and expedient integration of visual cues in arbitrary environments through experiments with synthetic camera images for which ground truth camera poses are given.",
keywords = "Analytic fusion, Augmented reality, Model-based camera tracking",
author = "Hanhoon Park and Hideki Mitsumine and Masato Fujii and Jong-Il Park",
year = "2009",
month = "12",
day = "1",
doi = "10.1145/1670252.1670298",
language = "English",
isbn = "9781605589121",
series = "Proceedings - VRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry",
pages = "215--220",
booktitle = "Proceedings - VRCAI 2009",

}

Park, H, Mitsumine, H, Fujii, M & Park, J-I 2009, Analytic fusion of visual cues in model-based camera tracking. in Proceedings - VRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry. Proceedings - VRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry, pp. 215-220, VRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry, Yokohama, Japan, 09/12/14. https://doi.org/10.1145/1670252.1670298

Analytic fusion of visual cues in model-based camera tracking. / Park, Hanhoon; Mitsumine, Hideki; Fujii, Masato; Park, Jong-Il.

Proceedings - VRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry. 2009. p. 215-220 (Proceedings - VRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry).

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

TY - GEN

T1 - Analytic fusion of visual cues in model-based camera tracking

AU - Park, Hanhoon

AU - Mitsumine, Hideki

AU - Fujii, Masato

AU - Park, Jong-Il

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Model-based camera tracking is a technology that estimates a camera pose by tracking visual cues, i.e. points and edges on a known 3D scene model, in camera images. In model-based camera tracking, it has been a main challenge how to use the visual cues effectively for better performance. In this paper, we carefully analyze the dependency of the visual cues on tracking conditions (or environments) and propose a formula for integrating the visual cues cooperatively into a single framework based on the analysis. Then, we demonstrate that the analytic integration outperforms separate use of either cue and expedient integration of visual cues in arbitrary environments through experiments with synthetic camera images for which ground truth camera poses are given.

AB - Model-based camera tracking is a technology that estimates a camera pose by tracking visual cues, i.e. points and edges on a known 3D scene model, in camera images. In model-based camera tracking, it has been a main challenge how to use the visual cues effectively for better performance. In this paper, we carefully analyze the dependency of the visual cues on tracking conditions (or environments) and propose a formula for integrating the visual cues cooperatively into a single framework based on the analysis. Then, we demonstrate that the analytic integration outperforms separate use of either cue and expedient integration of visual cues in arbitrary environments through experiments with synthetic camera images for which ground truth camera poses are given.

KW - Analytic fusion

KW - Augmented reality

KW - Model-based camera tracking

UR - http://www.scopus.com/inward/record.url?scp=76749128965&partnerID=8YFLogxK

U2 - 10.1145/1670252.1670298

DO - 10.1145/1670252.1670298

M3 - Conference contribution

AN - SCOPUS:76749128965

SN - 9781605589121

T3 - Proceedings - VRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry

SP - 215

EP - 220

BT - Proceedings - VRCAI 2009

ER -

Park H, Mitsumine H, Fujii M, Park J-I. Analytic fusion of visual cues in model-based camera tracking. In Proceedings - VRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry. 2009. p. 215-220. (Proceedings - VRCAI 2009: 8th International Conference on Virtual Reality Continuum and its Applications in Industry). https://doi.org/10.1145/1670252.1670298