Predicting head trajectories in 360° virtual reality videos

A. Deniz Aladagli; Erhan Ekmekcioglu; Dmitri Jarnikov; Ahmet Kondoz

doi:10.1109/IC3D.2017.8251913

Predicting head trajectories in 360° virtual reality videos

A. Deniz Aladagli, Erhan Ekmekcioglu, Dmitri Jarnikov, Ahmet Kondoz

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

30 Citations (Scopus)

1 Downloads (Pure)

Abstract

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.

Original language	English
Title of host publication	2017 International Conference on 3D Immersion, IC3D 2017 - Proceedings
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	1-6
Number of pages	6
ISBN (Electronic)	9781538646557
DOIs	https://doi.org/10.1109/IC3D.2017.8251913
Publication status	Published - 8 Jan 2018
Event	7th International Conference on 3D Immersion (IC3D 2017) - Brussels, Belgium Duration: 11 Dec 2017 → 12 Dec 2017 Conference number: 7

Conference

Conference	7th International Conference on 3D Immersion (IC3D 2017)
Abbreviated title	IC3D 2017
Country/Territory	Belgium
City	Brussels
Period	11/12/17 → 12/12/17

Keywords

360, VR
head
omnidirectional
prediction
saliency
video

Access to Document

10.1109/IC3D.2017.8251913

Cite this

@inproceedings{6114ae2bff4b4903849bcf38848b5045,

title = "Predicting head trajectories in 360° virtual reality videos",

abstract = "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.",

keywords = "360, VR, head, omnidirectional, prediction, saliency, video",

author = "Aladagli, {A. Deniz} and Erhan Ekmekcioglu and Dmitri Jarnikov and Ahmet Kondoz",

year = "2018",

month = jan,

day = "8",

doi = "10.1109/IC3D.2017.8251913",

language = "English",

pages = "1--6",

booktitle = "2017 International Conference on 3D Immersion, IC3D 2017 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "7th International Conference on 3D Immersion (IC3D 2017), IC3D 2017 ; Conference date: 11-12-2017 Through 12-12-2017",

}

Aladagli, AD, Ekmekcioglu, E, Jarnikov, D & Kondoz, A 2018, Predicting head trajectories in 360° virtual reality videos. in 2017 International Conference on 3D Immersion, IC3D 2017 - Proceedings. Institute of Electrical and Electronics Engineers, Piscataway, pp. 1-6, 7th International Conference on 3D Immersion (IC3D 2017), Brussels, Belgium, 11/12/17. https://doi.org/10.1109/IC3D.2017.8251913

Predicting head trajectories in 360° virtual reality videos. / Aladagli, A. Deniz; Ekmekcioglu, Erhan; Jarnikov, Dmitri et al.
2017 International Conference on 3D Immersion, IC3D 2017 - Proceedings. Piscataway: Institute of Electrical and Electronics Engineers, 2018. p. 1-6.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Predicting head trajectories in 360° virtual reality videos

AU - Aladagli, A. Deniz

AU - Ekmekcioglu, Erhan

AU - Jarnikov, Dmitri

AU - Kondoz, Ahmet

N1 - Conference code: 7

PY - 2018/1/8

Y1 - 2018/1/8

N2 - 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.

AB - 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.

KW - 360, VR

KW - head

KW - omnidirectional

KW - prediction

KW - saliency

KW - video

UR - http://www.scopus.com/inward/record.url?scp=85049434031&partnerID=8YFLogxK

U2 - 10.1109/IC3D.2017.8251913

DO - 10.1109/IC3D.2017.8251913

M3 - Conference contribution

SP - 1

EP - 6

BT - 2017 International Conference on 3D Immersion, IC3D 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 7th International Conference on 3D Immersion (IC3D 2017)

Y2 - 11 December 2017 through 12 December 2017

ER -

Predicting head trajectories in 360° virtual reality videos

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this