Interpolation of three views based on epipolar geometry

M. Kimura, Hideo Saito

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

1 Citation (Scopus)

Abstract

In this paper, we propose a method for generating arbitrary view image by interpolating images between three cameras using epipolar geometry. Projective geometry has recently been used in the field of computer vision, because projective geometry can be easily determined compararing with Euclidean geometry. In the proposed method, three input camera images are rectified so that the vertical and horizontal directions can be completely aligned to the epipolar planes between the cameras. This rectification provides Projective Voxel Space (PVS), in which the three axes are aligned with the direction of camera's projection. Such alignment simplifies the procedure for projection and back projection between the 3D space and the image planes. First, we apply shape-from-silhouette with taking advantage of PVS. The consistency of color value between the images is evaluated for final determination of the object surface voxel. Therefore, consistent matching in three images is estimated and images can be interpolated from the matching information. Synthesized images are based on 3D shape in PVS, so the occlusion of the object is reproduced in the generated images, however it requires only weak calibration.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsB. Girod, C.A. Bouman, E.G. Steinbach
Pages218-227
Number of pages10
Volume4310
DOIs
Publication statusPublished - 2001
EventVisual Communications and Image Processing 2001 - San Jose, CA, United States
Duration: 2001 Jan 242001 Jan 26

Other

OtherVisual Communications and Image Processing 2001
CountryUnited States
CitySan Jose, CA
Period01/1/2401/1/26

Fingerprint

interpolation
Interpolation
Cameras
Geometry
geometry
projective geometry
cameras
projection
Computer vision
Calibration
Color
Euclidean geometry
occlusion
computer vision
rectification
alignment
color

Keywords

  • Fundamental matrix
  • Interpolation
  • Projective geometry
  • Shape reconstruction

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Kimura, M., & Saito, H. (2001). Interpolation of three views based on epipolar geometry. In B. Girod, C. A. Bouman, & E. G. Steinbach (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 4310, pp. 218-227) https://doi.org/10.1117/12.411799

Interpolation of three views based on epipolar geometry. / Kimura, M.; Saito, Hideo.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / B. Girod; C.A. Bouman; E.G. Steinbach. Vol. 4310 2001. p. 218-227.

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

Kimura, M & Saito, H 2001, Interpolation of three views based on epipolar geometry. in B Girod, CA Bouman & EG Steinbach (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 4310, pp. 218-227, Visual Communications and Image Processing 2001, San Jose, CA, United States, 01/1/24. https://doi.org/10.1117/12.411799
Kimura M, Saito H. Interpolation of three views based on epipolar geometry. In Girod B, Bouman CA, Steinbach EG, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 4310. 2001. p. 218-227 https://doi.org/10.1117/12.411799
Kimura, M. ; Saito, Hideo. / Interpolation of three views based on epipolar geometry. Proceedings of SPIE - The International Society for Optical Engineering. editor / B. Girod ; C.A. Bouman ; E.G. Steinbach. Vol. 4310 2001. pp. 218-227
@inproceedings{8cc01c5cccf048028b069a0c2e896eb9,
title = "Interpolation of three views based on epipolar geometry",
abstract = "In this paper, we propose a method for generating arbitrary view image by interpolating images between three cameras using epipolar geometry. Projective geometry has recently been used in the field of computer vision, because projective geometry can be easily determined compararing with Euclidean geometry. In the proposed method, three input camera images are rectified so that the vertical and horizontal directions can be completely aligned to the epipolar planes between the cameras. This rectification provides Projective Voxel Space (PVS), in which the three axes are aligned with the direction of camera's projection. Such alignment simplifies the procedure for projection and back projection between the 3D space and the image planes. First, we apply shape-from-silhouette with taking advantage of PVS. The consistency of color value between the images is evaluated for final determination of the object surface voxel. Therefore, consistent matching in three images is estimated and images can be interpolated from the matching information. Synthesized images are based on 3D shape in PVS, so the occlusion of the object is reproduced in the generated images, however it requires only weak calibration.",
keywords = "Fundamental matrix, Interpolation, Projective geometry, Shape reconstruction",
author = "M. Kimura and Hideo Saito",
year = "2001",
doi = "10.1117/12.411799",
language = "English",
volume = "4310",
pages = "218--227",
editor = "B. Girod and C.A. Bouman and E.G. Steinbach",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Interpolation of three views based on epipolar geometry

AU - Kimura, M.

AU - Saito, Hideo

PY - 2001

Y1 - 2001

N2 - In this paper, we propose a method for generating arbitrary view image by interpolating images between three cameras using epipolar geometry. Projective geometry has recently been used in the field of computer vision, because projective geometry can be easily determined compararing with Euclidean geometry. In the proposed method, three input camera images are rectified so that the vertical and horizontal directions can be completely aligned to the epipolar planes between the cameras. This rectification provides Projective Voxel Space (PVS), in which the three axes are aligned with the direction of camera's projection. Such alignment simplifies the procedure for projection and back projection between the 3D space and the image planes. First, we apply shape-from-silhouette with taking advantage of PVS. The consistency of color value between the images is evaluated for final determination of the object surface voxel. Therefore, consistent matching in three images is estimated and images can be interpolated from the matching information. Synthesized images are based on 3D shape in PVS, so the occlusion of the object is reproduced in the generated images, however it requires only weak calibration.

AB - In this paper, we propose a method for generating arbitrary view image by interpolating images between three cameras using epipolar geometry. Projective geometry has recently been used in the field of computer vision, because projective geometry can be easily determined compararing with Euclidean geometry. In the proposed method, three input camera images are rectified so that the vertical and horizontal directions can be completely aligned to the epipolar planes between the cameras. This rectification provides Projective Voxel Space (PVS), in which the three axes are aligned with the direction of camera's projection. Such alignment simplifies the procedure for projection and back projection between the 3D space and the image planes. First, we apply shape-from-silhouette with taking advantage of PVS. The consistency of color value between the images is evaluated for final determination of the object surface voxel. Therefore, consistent matching in three images is estimated and images can be interpolated from the matching information. Synthesized images are based on 3D shape in PVS, so the occlusion of the object is reproduced in the generated images, however it requires only weak calibration.

KW - Fundamental matrix

KW - Interpolation

KW - Projective geometry

KW - Shape reconstruction

UR - http://www.scopus.com/inward/record.url?scp=0035062091&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035062091&partnerID=8YFLogxK

U2 - 10.1117/12.411799

DO - 10.1117/12.411799

M3 - Conference contribution

AN - SCOPUS:0035062091

VL - 4310

SP - 218

EP - 227

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

A2 - Girod, B.

A2 - Bouman, C.A.

A2 - Steinbach, E.G.

ER -