Diminished reality via multiple hand-held cameras

Songkran Jarusirisawad, Hideo Saito

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

4 Citations (Scopus)

Abstract

This paper proposes a novel method for calibrating multiple hand-held cameras target for Diminished Reality application. Our method does not require any special markers or information about camera parameters. Projective Grid Space (PGS) which is 3D space defined by epipolar geometry of two basis camera is used for dynamic cameras calibration. Geometrical relations among cameras in PGS are obtained from 2D-2D corresponding points between views. We utilize Scale Invariant Feature Transform (SIFT) for finding corresponding points in natural scene for registering cameras to PGS. Moving object is segmented via graph cut optimization. Finally, the reconstructed visual hull is used to synthesize free viewpoint video in which unwanted or occluding object is deliberately removed. In the experimental results, free viewpoint video without unwanted object which is captured by hand-held cameras is successfully synthesized using the proposed method.

Original languageEnglish
Title of host publication2007 1st ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC
Pages251-258
Number of pages8
DOIs
Publication statusPublished - 2007
Event2007 First ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC-07 - Vienna, Austria
Duration: 2007 Sep 252007 Sep 28

Other

Other2007 First ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC-07
CountryAustria
CityVienna
Period07/9/2507/9/28

Fingerprint

Cameras
Mathematical transformations
Calibration
Geometry

Keywords

  • 3D reconstruction
  • Cameras calibration
  • Diminished reality
  • Projective grid space

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition

Cite this

Jarusirisawad, S., & Saito, H. (2007). Diminished reality via multiple hand-held cameras. In 2007 1st ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC (pp. 251-258). [4357531] https://doi.org/10.1109/ICDSC.2007.4357531

Diminished reality via multiple hand-held cameras. / Jarusirisawad, Songkran; Saito, Hideo.

2007 1st ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC. 2007. p. 251-258 4357531.

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

Jarusirisawad, S & Saito, H 2007, Diminished reality via multiple hand-held cameras. in 2007 1st ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC., 4357531, pp. 251-258, 2007 First ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC-07, Vienna, Austria, 07/9/25. https://doi.org/10.1109/ICDSC.2007.4357531
Jarusirisawad S, Saito H. Diminished reality via multiple hand-held cameras. In 2007 1st ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC. 2007. p. 251-258. 4357531 https://doi.org/10.1109/ICDSC.2007.4357531
Jarusirisawad, Songkran ; Saito, Hideo. / Diminished reality via multiple hand-held cameras. 2007 1st ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC. 2007. pp. 251-258
@inproceedings{23a03ea9faf445108043e7c5af72405e,
title = "Diminished reality via multiple hand-held cameras",
abstract = "This paper proposes a novel method for calibrating multiple hand-held cameras target for Diminished Reality application. Our method does not require any special markers or information about camera parameters. Projective Grid Space (PGS) which is 3D space defined by epipolar geometry of two basis camera is used for dynamic cameras calibration. Geometrical relations among cameras in PGS are obtained from 2D-2D corresponding points between views. We utilize Scale Invariant Feature Transform (SIFT) for finding corresponding points in natural scene for registering cameras to PGS. Moving object is segmented via graph cut optimization. Finally, the reconstructed visual hull is used to synthesize free viewpoint video in which unwanted or occluding object is deliberately removed. In the experimental results, free viewpoint video without unwanted object which is captured by hand-held cameras is successfully synthesized using the proposed method.",
keywords = "3D reconstruction, Cameras calibration, Diminished reality, Projective grid space",
author = "Songkran Jarusirisawad and Hideo Saito",
year = "2007",
doi = "10.1109/ICDSC.2007.4357531",
language = "English",
isbn = "1424413540",
pages = "251--258",
booktitle = "2007 1st ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC",

}

TY - GEN

T1 - Diminished reality via multiple hand-held cameras

AU - Jarusirisawad, Songkran

AU - Saito, Hideo

PY - 2007

Y1 - 2007

N2 - This paper proposes a novel method for calibrating multiple hand-held cameras target for Diminished Reality application. Our method does not require any special markers or information about camera parameters. Projective Grid Space (PGS) which is 3D space defined by epipolar geometry of two basis camera is used for dynamic cameras calibration. Geometrical relations among cameras in PGS are obtained from 2D-2D corresponding points between views. We utilize Scale Invariant Feature Transform (SIFT) for finding corresponding points in natural scene for registering cameras to PGS. Moving object is segmented via graph cut optimization. Finally, the reconstructed visual hull is used to synthesize free viewpoint video in which unwanted or occluding object is deliberately removed. In the experimental results, free viewpoint video without unwanted object which is captured by hand-held cameras is successfully synthesized using the proposed method.

AB - This paper proposes a novel method for calibrating multiple hand-held cameras target for Diminished Reality application. Our method does not require any special markers or information about camera parameters. Projective Grid Space (PGS) which is 3D space defined by epipolar geometry of two basis camera is used for dynamic cameras calibration. Geometrical relations among cameras in PGS are obtained from 2D-2D corresponding points between views. We utilize Scale Invariant Feature Transform (SIFT) for finding corresponding points in natural scene for registering cameras to PGS. Moving object is segmented via graph cut optimization. Finally, the reconstructed visual hull is used to synthesize free viewpoint video in which unwanted or occluding object is deliberately removed. In the experimental results, free viewpoint video without unwanted object which is captured by hand-held cameras is successfully synthesized using the proposed method.

KW - 3D reconstruction

KW - Cameras calibration

KW - Diminished reality

KW - Projective grid space

UR - http://www.scopus.com/inward/record.url?scp=47349107935&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47349107935&partnerID=8YFLogxK

U2 - 10.1109/ICDSC.2007.4357531

DO - 10.1109/ICDSC.2007.4357531

M3 - Conference contribution

AN - SCOPUS:47349107935

SN - 1424413540

SN - 9781424413546

SP - 251

EP - 258

BT - 2007 1st ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC

ER -