Thesis Details

Algorithms for Automatic Spherical Image and Video Cropping

Master's Thesis Student: Ivančo Martin Academic Year: 2019/2020 Supervisor: Čadík Martin, doc. Ing., Ph.D.
Czech title
Algoritmy pro automatický ořez sférické fotografie a videa
Language
English
Abstract

The aim of this work is to provide a detailed overview of the research regarding spherical videos. Specifically, this work focuses on the task of creating a normal field of view video from a spherical one for viewing purposes. It provides an implementation of some of the available methods as well. So far, there have been three methods introduced by four papers tackling this challenge. All of them have brought promising results and this work examines two of them thoroughly. It also provides a baseline method leveraging well known techniques of automatic image cropping. This method serves as a good comparison tool which puts the improvements brought by the examined methods into perspective. Based on a thorough comparison via a user study this work concludes, that the best method for this task overall is a variation of the method by Pavel et al. [14] introduced in this work.

Keywords

Automatic 360° cinematography, automatic image cropping, spherical video, 360° video retargeting

Department
Degree Programme
Information Technology, Field of Study Computer Graphics and Multimedia
Files
Status
defended, grade B
Date
15 July 2020
Reviewer
Committee
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT), předseda
Bařina David, Ing., Ph.D. (DCGM FIT BUT), člen
Beran Vítězslav, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Grézl František, Ing., Ph.D. (DCGM FIT BUT), člen
Herout Adam, prof. Ing., Ph.D. (DCGM FIT BUT), člen
Křivka Zbyněk, Ing., Ph.D. (DIFS FIT BUT), člen
Citation
IVANČO, Martin. Algorithms for Automatic Spherical Image and Video Cropping. Brno, 2020. Master's Thesis. Brno University of Technology, Faculty of Information Technology. 2020-07-15. Supervised by Čadík Martin. Available from: https://www.fit.vut.cz/study/thesis/22563/
BibTeX
@mastersthesis{FITMT22563,
    author = "Martin Ivan\v{c}o",
    type = "Master's thesis",
    title = "Algorithms for Automatic Spherical Image and Video Cropping",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2020,
    location = "Brno, CZ",
    language = "english",
    url = "https://www.fit.vut.cz/study/thesis/22563/"
}
Back to top