Online video synthesis for removing occluding objects using multiple uncalibrated cameras via plane sweep algorithm

Takahide Hosokawa, Songkran Jarusirisawad, Hideo Saito

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

3 Citations (Scopus)

Abstract

We present an online rendering system which removes occluding objects in front of the objective scene from an input video using multiple videos taken with multiple cameras. To obtain geometrical relations between all cameras, we use projective grid space (PGS) defined by epipolar geometry between two basis cameras. Then we apply plane-sweep algorithm for generating depth image in the input camera. By excluding the area of occluding objects from the volume of the sweeping planes, we can generate the depthmap without the occluding objects. Using this depthmap, we can render the image without obstacles from all the multiple camera videos. Since we use graphics processing unit (GPU) for computation, we can achieve realtime online rendering using a normal spec PC and multiple USB cameras.

Original languageEnglish
Title of host publication2009 3rd ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC 2009
DOIs
Publication statusPublished - 2009
Event2009 3rd ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC 2009 - Como, Italy
Duration: 2009 Aug 302009 Sep 2

Other

Other2009 3rd ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC 2009
CountryItaly
CityComo
Period09/8/3009/9/2

Fingerprint

Cameras
Video cameras
Geometry

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Hosokawa, T., Jarusirisawad, S., & Saito, H. (2009). Online video synthesis for removing occluding objects using multiple uncalibrated cameras via plane sweep algorithm. In 2009 3rd ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC 2009 [5289380] https://doi.org/10.1109/ICDSC.2009.5289380

Online video synthesis for removing occluding objects using multiple uncalibrated cameras via plane sweep algorithm. / Hosokawa, Takahide; Jarusirisawad, Songkran; Saito, Hideo.

2009 3rd ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC 2009. 2009. 5289380.

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

Hosokawa, T, Jarusirisawad, S & Saito, H 2009, Online video synthesis for removing occluding objects using multiple uncalibrated cameras via plane sweep algorithm. in 2009 3rd ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC 2009., 5289380, 2009 3rd ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC 2009, Como, Italy, 09/8/30. https://doi.org/10.1109/ICDSC.2009.5289380
Hosokawa T, Jarusirisawad S, Saito H. Online video synthesis for removing occluding objects using multiple uncalibrated cameras via plane sweep algorithm. In 2009 3rd ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC 2009. 2009. 5289380 https://doi.org/10.1109/ICDSC.2009.5289380
Hosokawa, Takahide ; Jarusirisawad, Songkran ; Saito, Hideo. / Online video synthesis for removing occluding objects using multiple uncalibrated cameras via plane sweep algorithm. 2009 3rd ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC 2009. 2009.
@inproceedings{37fd1bd014ab4665ba4d82629f03debf,
title = "Online video synthesis for removing occluding objects using multiple uncalibrated cameras via plane sweep algorithm",
abstract = "We present an online rendering system which removes occluding objects in front of the objective scene from an input video using multiple videos taken with multiple cameras. To obtain geometrical relations between all cameras, we use projective grid space (PGS) defined by epipolar geometry between two basis cameras. Then we apply plane-sweep algorithm for generating depth image in the input camera. By excluding the area of occluding objects from the volume of the sweeping planes, we can generate the depthmap without the occluding objects. Using this depthmap, we can render the image without obstacles from all the multiple camera videos. Since we use graphics processing unit (GPU) for computation, we can achieve realtime online rendering using a normal spec PC and multiple USB cameras.",
author = "Takahide Hosokawa and Songkran Jarusirisawad and Hideo Saito",
year = "2009",
doi = "10.1109/ICDSC.2009.5289380",
language = "English",
isbn = "9781424446209",
booktitle = "2009 3rd ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC 2009",

}

TY - GEN

T1 - Online video synthesis for removing occluding objects using multiple uncalibrated cameras via plane sweep algorithm

AU - Hosokawa, Takahide

AU - Jarusirisawad, Songkran

AU - Saito, Hideo

PY - 2009

Y1 - 2009

N2 - We present an online rendering system which removes occluding objects in front of the objective scene from an input video using multiple videos taken with multiple cameras. To obtain geometrical relations between all cameras, we use projective grid space (PGS) defined by epipolar geometry between two basis cameras. Then we apply plane-sweep algorithm for generating depth image in the input camera. By excluding the area of occluding objects from the volume of the sweeping planes, we can generate the depthmap without the occluding objects. Using this depthmap, we can render the image without obstacles from all the multiple camera videos. Since we use graphics processing unit (GPU) for computation, we can achieve realtime online rendering using a normal spec PC and multiple USB cameras.

AB - We present an online rendering system which removes occluding objects in front of the objective scene from an input video using multiple videos taken with multiple cameras. To obtain geometrical relations between all cameras, we use projective grid space (PGS) defined by epipolar geometry between two basis cameras. Then we apply plane-sweep algorithm for generating depth image in the input camera. By excluding the area of occluding objects from the volume of the sweeping planes, we can generate the depthmap without the occluding objects. Using this depthmap, we can render the image without obstacles from all the multiple camera videos. Since we use graphics processing unit (GPU) for computation, we can achieve realtime online rendering using a normal spec PC and multiple USB cameras.

UR - http://www.scopus.com/inward/record.url?scp=72149100451&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72149100451&partnerID=8YFLogxK

U2 - 10.1109/ICDSC.2009.5289380

DO - 10.1109/ICDSC.2009.5289380

M3 - Conference contribution

AN - SCOPUS:72149100451

SN - 9781424446209

BT - 2009 3rd ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC 2009

ER -