Loughborough University
Browse
Ekmekcioglu_37.pdf (1.28 MB)

Predicting head trajectories in 360° virtual reality videos

Download (1.28 MB)
conference contribution
posted on 2018-03-27, 08:47 authored by Deniz Aladagli, Erhan Ekmekcioglu, Dmitri Jarnikov, Ahmet Kondoz
In this paper a fixation prediction based saliency algorithm is used in order to predict the head movements of viewers watching virtual reality (VR) videos, by modelling the relationship between fixation predictions and recorded head movements. The saliency algorithm is applied to viewings faithfully recreated from recorded head movements. Spherical cross-correlation analysis is performed between predicted attention centres and actual viewing centres in order to try and identify prevalent lengths of predictable attention and how early they can be predicted. The results show that fixation prediction based saliency analysis correlates with head movements only for limited durations. Therefore, further classification of durations where saliency analysis is predictive is required.

Funding

The work presented in this paper was carried out as part of CLOUDSCREENS, a Marie Curie Initial Training Networks action funded by the European Commissions 7th Framework Program under the Grant Number 608028.

History

School

  • Loughborough University London

Published in

2017 International Conference on 3D Immersion (IC3D)

Pages

1 - 6 (6)

Citation

ALADAGLI, A.D. ...et al., 2018. Predicting head trajectories in 360° virtual reality videos. Presented at the 2017 International Conference on 3D Immersion (IC3D), Brussels, Belgium, 11-12 Dec. 2017.

Publisher

© Institute of Electrical and Electronics Engineers (IEEE)

Version

  • AM (Accepted Manuscript)

Publication date

2018

Notes

Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

ISBN

9781538646557

eISSN

2379-1780

Language

  • en

Location

Brussels, Belgium

Usage metrics

    Loughborough Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC