Diminished reality using plane-sweep algorithm with weakly-calibrated cameras

Songkran Jarusirisawad, Takahide Hosokawa, Hideo Saito

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

We present a plane-sweep algorithm for removing occluding objects in front of the objective scene from multiple weakly-calibrated cameras. Projective grid space (PGS), a weak cameras calibration framework, is used to obtain geometrical relations between cameras. Plane-sweep algorithm works by implicitly reconstructing the depth maps of the targeted view. By excluding the occluding objects from the volume of the sweeping planes, we can generate new views without the occluding objects. The results show the effectiveness of the proposed method and it is fast enough to run in several frames per second on a consumer PC by implementing the proposed plane-sweep algorithm in graphics processing unit (GPU).

Original languageEnglish
Pages (from-to)11-20
Number of pages10
JournalProgress in Informatics
Issue number7
Publication statusPublished - 2010 Mar

Fingerprint

Cameras
PC
Calibration
Graphics processing unit

Keywords

  • Diminished reality
  • Graphics processing unit (GPU)
  • Plane-sweep
  • Real-time
  • Video-based rendering

ASJC Scopus subject areas

  • Computer Science(all)
  • Library and Information Sciences

Cite this

Diminished reality using plane-sweep algorithm with weakly-calibrated cameras. / Jarusirisawad, Songkran; Hosokawa, Takahide; Saito, Hideo.

In: Progress in Informatics, No. 7, 03.2010, p. 11-20.

Research output: Contribution to journalArticle

Jarusirisawad, Songkran ; Hosokawa, Takahide ; Saito, Hideo. / Diminished reality using plane-sweep algorithm with weakly-calibrated cameras. In: Progress in Informatics. 2010 ; No. 7. pp. 11-20.
@article{9ab570f5eb404b129966d58d4205ce6c,
title = "Diminished reality using plane-sweep algorithm with weakly-calibrated cameras",
abstract = "We present a plane-sweep algorithm for removing occluding objects in front of the objective scene from multiple weakly-calibrated cameras. Projective grid space (PGS), a weak cameras calibration framework, is used to obtain geometrical relations between cameras. Plane-sweep algorithm works by implicitly reconstructing the depth maps of the targeted view. By excluding the occluding objects from the volume of the sweeping planes, we can generate new views without the occluding objects. The results show the effectiveness of the proposed method and it is fast enough to run in several frames per second on a consumer PC by implementing the proposed plane-sweep algorithm in graphics processing unit (GPU).",
keywords = "Diminished reality, Graphics processing unit (GPU), Plane-sweep, Real-time, Video-based rendering",
author = "Songkran Jarusirisawad and Takahide Hosokawa and Hideo Saito",
year = "2010",
month = "3",
language = "English",
pages = "11--20",
journal = "NII Journal",
issn = "1349-8614",
publisher = "National Institute of Informatics",
number = "7",

}

TY - JOUR

T1 - Diminished reality using plane-sweep algorithm with weakly-calibrated cameras

AU - Jarusirisawad, Songkran

AU - Hosokawa, Takahide

AU - Saito, Hideo

PY - 2010/3

Y1 - 2010/3

N2 - We present a plane-sweep algorithm for removing occluding objects in front of the objective scene from multiple weakly-calibrated cameras. Projective grid space (PGS), a weak cameras calibration framework, is used to obtain geometrical relations between cameras. Plane-sweep algorithm works by implicitly reconstructing the depth maps of the targeted view. By excluding the occluding objects from the volume of the sweeping planes, we can generate new views without the occluding objects. The results show the effectiveness of the proposed method and it is fast enough to run in several frames per second on a consumer PC by implementing the proposed plane-sweep algorithm in graphics processing unit (GPU).

AB - We present a plane-sweep algorithm for removing occluding objects in front of the objective scene from multiple weakly-calibrated cameras. Projective grid space (PGS), a weak cameras calibration framework, is used to obtain geometrical relations between cameras. Plane-sweep algorithm works by implicitly reconstructing the depth maps of the targeted view. By excluding the occluding objects from the volume of the sweeping planes, we can generate new views without the occluding objects. The results show the effectiveness of the proposed method and it is fast enough to run in several frames per second on a consumer PC by implementing the proposed plane-sweep algorithm in graphics processing unit (GPU).

KW - Diminished reality

KW - Graphics processing unit (GPU)

KW - Plane-sweep

KW - Real-time

KW - Video-based rendering

UR - http://www.scopus.com/inward/record.url?scp=77952893628&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77952893628&partnerID=8YFLogxK

M3 - Article

SP - 11

EP - 20

JO - NII Journal

JF - NII Journal

SN - 1349-8614

IS - 7

ER -