RELATIVE PANORAMIC CAMERA POSITION ESTIMATION for IMAGE-BASED VIRTUAL REALITY NETWORKS in INDOOR ENVIRONMENTS

M. Nakagawa, K. Akano, T. Kobayashi, Y. Sekiguchi

Research output: Research - peer-reviewArticle

Abstract

Image-based virtual reality (VR) is a virtual space generated with panoramic images projected onto a primitive model. In imagebased VR, realistic VR scenes can be generated with lower rendering cost, and network data can be described as relationships among VR scenes. The camera network data are generated manually or by an automated procedure using camera position and rotation data. When panoramic images are acquired in indoor environments, network data should be generated without Global Navigation Satellite Systems (GNSS) positioning data. Thus, we focused on image-based VR generation using a panoramic camera in indoor environments. We propose a methodology to automate network data generation using panoramic images for an image-based VR space. We verified and evaluated our methodology through five experiments in indoor environments, including a corridor, elevator hall, room, and stairs. We confirmed that our methodology can automatically reconstruct network data using panoramic images for image-based VR in indoor environments without GNSS position data.

LanguageEnglish
Pages349-354
Number of pages6
JournalISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Volume4
Issue number2W4
DOIs
StatePublished - 2017 Sep 12

Fingerprint

Virtual reality
Cameras
panoramic cameras
virtual reality
indoor environment
methodology
Navigation
Satellites
satellite navigation systems
cameras
GNSS
Stairs
Elevators
Costs
Experiments
Rendering (computer graphics)
corridors
positioning
rooms
cost

Keywords

  • camera network
  • Image-based virtual reality
  • indoor environment
  • optical flow
  • panoramic image

ASJC Scopus subject areas

  • Earth and Planetary Sciences (miscellaneous)
  • Environmental Science (miscellaneous)
  • Instrumentation

Cite this

RELATIVE PANORAMIC CAMERA POSITION ESTIMATION for IMAGE-BASED VIRTUAL REALITY NETWORKS in INDOOR ENVIRONMENTS. / Nakagawa, M.; Akano, K.; Kobayashi, T.; Sekiguchi, Y.

In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 4, No. 2W4, 12.09.2017, p. 349-354.

Research output: Research - peer-reviewArticle

@article{ea005577b2534f63a2441d9cee896410,
title = "RELATIVE PANORAMIC CAMERA POSITION ESTIMATION for IMAGE-BASED VIRTUAL REALITY NETWORKS in INDOOR ENVIRONMENTS",
abstract = "Image-based virtual reality (VR) is a virtual space generated with panoramic images projected onto a primitive model. In imagebased VR, realistic VR scenes can be generated with lower rendering cost, and network data can be described as relationships among VR scenes. The camera network data are generated manually or by an automated procedure using camera position and rotation data. When panoramic images are acquired in indoor environments, network data should be generated without Global Navigation Satellite Systems (GNSS) positioning data. Thus, we focused on image-based VR generation using a panoramic camera in indoor environments. We propose a methodology to automate network data generation using panoramic images for an image-based VR space. We verified and evaluated our methodology through five experiments in indoor environments, including a corridor, elevator hall, room, and stairs. We confirmed that our methodology can automatically reconstruct network data using panoramic images for image-based VR in indoor environments without GNSS position data.",
keywords = "camera network, Image-based virtual reality, indoor environment, optical flow, panoramic image",
author = "M. Nakagawa and K. Akano and T. Kobayashi and Y. Sekiguchi",
year = "2017",
month = "9",
doi = "10.5194/isprs-annals-IV-2-W4-349-2017",
volume = "4",
pages = "349--354",
journal = "ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences",
issn = "2194-9042",
number = "2W4",

}

TY - JOUR

T1 - RELATIVE PANORAMIC CAMERA POSITION ESTIMATION for IMAGE-BASED VIRTUAL REALITY NETWORKS in INDOOR ENVIRONMENTS

AU - Nakagawa,M.

AU - Akano,K.

AU - Kobayashi,T.

AU - Sekiguchi,Y.

PY - 2017/9/12

Y1 - 2017/9/12

N2 - Image-based virtual reality (VR) is a virtual space generated with panoramic images projected onto a primitive model. In imagebased VR, realistic VR scenes can be generated with lower rendering cost, and network data can be described as relationships among VR scenes. The camera network data are generated manually or by an automated procedure using camera position and rotation data. When panoramic images are acquired in indoor environments, network data should be generated without Global Navigation Satellite Systems (GNSS) positioning data. Thus, we focused on image-based VR generation using a panoramic camera in indoor environments. We propose a methodology to automate network data generation using panoramic images for an image-based VR space. We verified and evaluated our methodology through five experiments in indoor environments, including a corridor, elevator hall, room, and stairs. We confirmed that our methodology can automatically reconstruct network data using panoramic images for image-based VR in indoor environments without GNSS position data.

AB - Image-based virtual reality (VR) is a virtual space generated with panoramic images projected onto a primitive model. In imagebased VR, realistic VR scenes can be generated with lower rendering cost, and network data can be described as relationships among VR scenes. The camera network data are generated manually or by an automated procedure using camera position and rotation data. When panoramic images are acquired in indoor environments, network data should be generated without Global Navigation Satellite Systems (GNSS) positioning data. Thus, we focused on image-based VR generation using a panoramic camera in indoor environments. We propose a methodology to automate network data generation using panoramic images for an image-based VR space. We verified and evaluated our methodology through five experiments in indoor environments, including a corridor, elevator hall, room, and stairs. We confirmed that our methodology can automatically reconstruct network data using panoramic images for image-based VR in indoor environments without GNSS position data.

KW - camera network

KW - Image-based virtual reality

KW - indoor environment

KW - optical flow

KW - panoramic image

UR - http://www.scopus.com/inward/record.url?scp=85031045088&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031045088&partnerID=8YFLogxK

U2 - 10.5194/isprs-annals-IV-2-W4-349-2017

DO - 10.5194/isprs-annals-IV-2-W4-349-2017

M3 - Article

VL - 4

SP - 349

EP - 354

JO - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

T2 - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

JF - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

SN - 2194-9042

IS - 2W4

ER -