A vision-based AR registration method utilizing edges and vertices of 3D model

Ryo Hirose, Hideo Saito

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

3 Citations (Scopus)

Abstract

The most important issue in AR (Augmented Reality) is accurate geometric registration between real world and virtual objects. We propose a hybrid registration method utilizing the edges and the vertices of a 3D model of the target object. We estimate camera position and orientation by detecting the vertices and true edges every frames. The influence of the misleading edges is reduced by considering multiple edge candidates and selecting the best one from them. Furthermore the magnetic sensor or a set of the artificial vision markers as a tool to obtain approximate camera position and orientation are also used when the tracking object goes out of the user's view point or the camera movement is too fast to track natural features. By considering multiple edge candidates and utilizing a magnetic sensor or vision markers, the accuracy of registration and the robustness of rapid camera movement can be improved.

Original languageEnglish
Title of host publicationACM International Conference Proceeding Series
Pages187-194
Number of pages8
Volume157
DOIs
Publication statusPublished - 2005
Event2005 International Conference on Augmented Tele-Existence, ICAT '05 - Christchurch, New Zealand
Duration: 2005 Dec 52005 Dec 8

Other

Other2005 International Conference on Augmented Tele-Existence, ICAT '05
CountryNew Zealand
CityChristchurch
Period05/12/505/12/8

Fingerprint

Augmented reality
Cameras
Magnetic sensors
Computer vision

Keywords

  • 3D object model
  • accurate geometric registration
  • augmented reality
  • magnetic 6DOF sensor/vision markers
  • natural features (edges and vertices)

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Hirose, R., & Saito, H. (2005). A vision-based AR registration method utilizing edges and vertices of 3D model. In ACM International Conference Proceeding Series (Vol. 157, pp. 187-194) https://doi.org/10.1145/1152399.1152433

A vision-based AR registration method utilizing edges and vertices of 3D model. / Hirose, Ryo; Saito, Hideo.

ACM International Conference Proceeding Series. Vol. 157 2005. p. 187-194.

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

Hirose, R & Saito, H 2005, A vision-based AR registration method utilizing edges and vertices of 3D model. in ACM International Conference Proceeding Series. vol. 157, pp. 187-194, 2005 International Conference on Augmented Tele-Existence, ICAT '05, Christchurch, New Zealand, 05/12/5. https://doi.org/10.1145/1152399.1152433
Hirose R, Saito H. A vision-based AR registration method utilizing edges and vertices of 3D model. In ACM International Conference Proceeding Series. Vol. 157. 2005. p. 187-194 https://doi.org/10.1145/1152399.1152433
Hirose, Ryo ; Saito, Hideo. / A vision-based AR registration method utilizing edges and vertices of 3D model. ACM International Conference Proceeding Series. Vol. 157 2005. pp. 187-194
@inproceedings{7ae8d8ee91ae450eab0d1a19a19922e7,
title = "A vision-based AR registration method utilizing edges and vertices of 3D model",
abstract = "The most important issue in AR (Augmented Reality) is accurate geometric registration between real world and virtual objects. We propose a hybrid registration method utilizing the edges and the vertices of a 3D model of the target object. We estimate camera position and orientation by detecting the vertices and true edges every frames. The influence of the misleading edges is reduced by considering multiple edge candidates and selecting the best one from them. Furthermore the magnetic sensor or a set of the artificial vision markers as a tool to obtain approximate camera position and orientation are also used when the tracking object goes out of the user's view point or the camera movement is too fast to track natural features. By considering multiple edge candidates and utilizing a magnetic sensor or vision markers, the accuracy of registration and the robustness of rapid camera movement can be improved.",
keywords = "3D object model, accurate geometric registration, augmented reality, magnetic 6DOF sensor/vision markers, natural features (edges and vertices)",
author = "Ryo Hirose and Hideo Saito",
year = "2005",
doi = "10.1145/1152399.1152433",
language = "English",
isbn = "0473106574",
volume = "157",
pages = "187--194",
booktitle = "ACM International Conference Proceeding Series",

}

TY - GEN

T1 - A vision-based AR registration method utilizing edges and vertices of 3D model

AU - Hirose, Ryo

AU - Saito, Hideo

PY - 2005

Y1 - 2005

N2 - The most important issue in AR (Augmented Reality) is accurate geometric registration between real world and virtual objects. We propose a hybrid registration method utilizing the edges and the vertices of a 3D model of the target object. We estimate camera position and orientation by detecting the vertices and true edges every frames. The influence of the misleading edges is reduced by considering multiple edge candidates and selecting the best one from them. Furthermore the magnetic sensor or a set of the artificial vision markers as a tool to obtain approximate camera position and orientation are also used when the tracking object goes out of the user's view point or the camera movement is too fast to track natural features. By considering multiple edge candidates and utilizing a magnetic sensor or vision markers, the accuracy of registration and the robustness of rapid camera movement can be improved.

AB - The most important issue in AR (Augmented Reality) is accurate geometric registration between real world and virtual objects. We propose a hybrid registration method utilizing the edges and the vertices of a 3D model of the target object. We estimate camera position and orientation by detecting the vertices and true edges every frames. The influence of the misleading edges is reduced by considering multiple edge candidates and selecting the best one from them. Furthermore the magnetic sensor or a set of the artificial vision markers as a tool to obtain approximate camera position and orientation are also used when the tracking object goes out of the user's view point or the camera movement is too fast to track natural features. By considering multiple edge candidates and utilizing a magnetic sensor or vision markers, the accuracy of registration and the robustness of rapid camera movement can be improved.

KW - 3D object model

KW - accurate geometric registration

KW - augmented reality

KW - magnetic 6DOF sensor/vision markers

KW - natural features (edges and vertices)

UR - http://www.scopus.com/inward/record.url?scp=77953493540&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953493540&partnerID=8YFLogxK

U2 - 10.1145/1152399.1152433

DO - 10.1145/1152399.1152433

M3 - Conference contribution

SN - 0473106574

SN - 9780473106577

VL - 157

SP - 187

EP - 194

BT - ACM International Conference Proceeding Series

ER -