Active 3D modeling by recursive viewpoint selection based on symmetry

Kazunori Yoshida, Hiromi T. Tanaka, Jun Ohya, Fumio Kishino

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

2 Citations (Scopus)

Abstract

This paper proposes a new method for creating 3D models of objects efficiently from the silhouettes of objects in images acquired by an active camera whose viewpoints are selected recursively based on symmetry planes of the observed silhouettes. In the proposed method, to obtain the initial view point, we use the assumption that an object takes a stable pose under the influence of gravity by having a symmetry plane to which the direction of gravity is constrained. We choose a point in the direction of the gravity as the initial viewpoint. Then, the new view points are determined based on information about the symmetry plane, where the symmetry plane is obtained from the center of gravity and the axis of inertia of the observed silhouette. This process is repeated until no new view point is selected. Then, the 3D shape of the object is reconstructed by processing voxel data based on the silhouette information acquired at the selected view points. Finally, textures acquired by the observations are mapped to the reconstructed 3D shape. We present some experimental results that show the effectiveness of the proposed method.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsDavid P. Casasent
Pages326-336
Number of pages11
Volume2588
Publication statusPublished - 1995
Externally publishedYes
EventIntelligent Robots and Computer Vision XIV: Algorithms, Techniques, Active Vision, and Materials Handling - Philadelphia, PA, USA
Duration: 1995 Oct 231995 Oct 26

Other

OtherIntelligent Robots and Computer Vision XIV: Algorithms, Techniques, Active Vision, and Materials Handling
CityPhiladelphia, PA, USA
Period95/10/2395/10/26

Fingerprint

Gravitation
symmetry
gravitation
center of gravity
inertia
textures
Textures
Cameras
cameras

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Yoshida, K., Tanaka, H. T., Ohya, J., & Kishino, F. (1995). Active 3D modeling by recursive viewpoint selection based on symmetry. In D. P. Casasent (Ed.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 2588, pp. 326-336)

Active 3D modeling by recursive viewpoint selection based on symmetry. / Yoshida, Kazunori; Tanaka, Hiromi T.; Ohya, Jun; Kishino, Fumio.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / David P. Casasent. Vol. 2588 1995. p. 326-336.

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

Yoshida, K, Tanaka, HT, Ohya, J & Kishino, F 1995, Active 3D modeling by recursive viewpoint selection based on symmetry. in DP Casasent (ed.), Proceedings of SPIE - The International Society for Optical Engineering. vol. 2588, pp. 326-336, Intelligent Robots and Computer Vision XIV: Algorithms, Techniques, Active Vision, and Materials Handling, Philadelphia, PA, USA, 95/10/23.
Yoshida K, Tanaka HT, Ohya J, Kishino F. Active 3D modeling by recursive viewpoint selection based on symmetry. In Casasent DP, editor, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 2588. 1995. p. 326-336
Yoshida, Kazunori ; Tanaka, Hiromi T. ; Ohya, Jun ; Kishino, Fumio. / Active 3D modeling by recursive viewpoint selection based on symmetry. Proceedings of SPIE - The International Society for Optical Engineering. editor / David P. Casasent. Vol. 2588 1995. pp. 326-336
@inproceedings{b99e0911ef63483690f402cf49b4e003,
title = "Active 3D modeling by recursive viewpoint selection based on symmetry",
abstract = "This paper proposes a new method for creating 3D models of objects efficiently from the silhouettes of objects in images acquired by an active camera whose viewpoints are selected recursively based on symmetry planes of the observed silhouettes. In the proposed method, to obtain the initial view point, we use the assumption that an object takes a stable pose under the influence of gravity by having a symmetry plane to which the direction of gravity is constrained. We choose a point in the direction of the gravity as the initial viewpoint. Then, the new view points are determined based on information about the symmetry plane, where the symmetry plane is obtained from the center of gravity and the axis of inertia of the observed silhouette. This process is repeated until no new view point is selected. Then, the 3D shape of the object is reconstructed by processing voxel data based on the silhouette information acquired at the selected view points. Finally, textures acquired by the observations are mapped to the reconstructed 3D shape. We present some experimental results that show the effectiveness of the proposed method.",
author = "Kazunori Yoshida and Tanaka, {Hiromi T.} and Jun Ohya and Fumio Kishino",
year = "1995",
language = "English",
isbn = "0819419524",
volume = "2588",
pages = "326--336",
editor = "Casasent, {David P.}",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Active 3D modeling by recursive viewpoint selection based on symmetry

AU - Yoshida, Kazunori

AU - Tanaka, Hiromi T.

AU - Ohya, Jun

AU - Kishino, Fumio

PY - 1995

Y1 - 1995

N2 - This paper proposes a new method for creating 3D models of objects efficiently from the silhouettes of objects in images acquired by an active camera whose viewpoints are selected recursively based on symmetry planes of the observed silhouettes. In the proposed method, to obtain the initial view point, we use the assumption that an object takes a stable pose under the influence of gravity by having a symmetry plane to which the direction of gravity is constrained. We choose a point in the direction of the gravity as the initial viewpoint. Then, the new view points are determined based on information about the symmetry plane, where the symmetry plane is obtained from the center of gravity and the axis of inertia of the observed silhouette. This process is repeated until no new view point is selected. Then, the 3D shape of the object is reconstructed by processing voxel data based on the silhouette information acquired at the selected view points. Finally, textures acquired by the observations are mapped to the reconstructed 3D shape. We present some experimental results that show the effectiveness of the proposed method.

AB - This paper proposes a new method for creating 3D models of objects efficiently from the silhouettes of objects in images acquired by an active camera whose viewpoints are selected recursively based on symmetry planes of the observed silhouettes. In the proposed method, to obtain the initial view point, we use the assumption that an object takes a stable pose under the influence of gravity by having a symmetry plane to which the direction of gravity is constrained. We choose a point in the direction of the gravity as the initial viewpoint. Then, the new view points are determined based on information about the symmetry plane, where the symmetry plane is obtained from the center of gravity and the axis of inertia of the observed silhouette. This process is repeated until no new view point is selected. Then, the 3D shape of the object is reconstructed by processing voxel data based on the silhouette information acquired at the selected view points. Finally, textures acquired by the observations are mapped to the reconstructed 3D shape. We present some experimental results that show the effectiveness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=0029504820&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029504820&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029504820

SN - 0819419524

SN - 9780819419521

VL - 2588

SP - 326

EP - 336

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Casasent, David P.

ER -