360ViewPET: View Based Pose EsTimation for Ultra-Sparse 360-Degree Cameras

Qian Zhou, Bo Chen, Zhe Yang, Hongpeng Guo, Klara Nahrstedt

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

Abstract

Immersive virtual tours based on 360-degree cameras, showing famous outdoor scenery, are becoming more and more desirable due to travel costs, pandemics and other constraints. To feel immersive, a user must receive the view accurately corresponding to her position and orientation in the virtual space when she moves inside, and this requires cameras' orientations to be known. Outdoor tour contexts have numerous, ultra-sparse cameras deployed across a wide area, making camera pose estimation challenging. As a result, pose estimation techniques like SLAM, which require mobile or dense cameras, are not applicable. In this paper we present a novel strategy called 360ViewPET, which automatically estimates the relative poses of two stationary, ultra-sparse (15 meters apart) 360-degree cameras using one equirectangular image taken by each camera. Our experiments show that it achieves accurate pose estimation, with a mean error as low as 0.9 degree.

Original languageEnglish (US)
Title of host publicationProceedings - 23rd IEEE International Symposium on Multimedia, ISM 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-8
Number of pages8
ISBN (Electronic)9781665437349
DOIs
StatePublished - 2021
Externally publishedYes
Event23rd IEEE International Symposium on Multimedia, ISM 2021 - Virtual, Online, Italy
Duration: Nov 29 2021Dec 1 2021

Publication series

NameProceedings - 23rd IEEE International Symposium on Multimedia, ISM 2021

Conference

Conference23rd IEEE International Symposium on Multimedia, ISM 2021
Country/TerritoryItaly
CityVirtual, Online
Period11/29/2112/1/21

Keywords

  • 360 camera
  • pose estimation
  • virtual tourism

ASJC Scopus subject areas

  • Computer Science Applications
  • Human-Computer Interaction
  • Media Technology
  • Artificial Intelligence

Fingerprint

Dive into the research topics of '360ViewPET: View Based Pose EsTimation for Ultra-Sparse 360-Degree Cameras'. Together they form a unique fingerprint.

Cite this