Publication Details

Big Data Analysis for Media Production

BLAT Josep, EVANS Alun, KIM Hansung, IMRE Evren, POLOK Lukáš, ILA Viorela S., NIKOLAIDIS Nikos, ZEMČÍK Pavel, TEFAS Anastasios, SMRŽ Pavel, HILTON Adrian and PITAS Ioannis. Big Data Analysis for Media Production. IEEE Communication Letters, vol. 104, no. 11, 2015, pp. 2085-2113. ISSN 1089-7798. Available from: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7350093
Czech title
Analýza velkých dat ve filmové produkci
Type
journal article
Language
english
Authors
Blat Josep (UPF)
Evans Alun (UPF)
Kim Hansung (USG)
Imre Evren (USG)
Polok Lukáš, Ing. (DCGM FIT BUT)
Ila Viorela S., Ing., Ph.D. (DCGM FIT BUT)
Nikolaidis Nikos (AUTH)
Zemčík Pavel, prof. Dr. Ing. (DCGM FIT BUT)
Tefas Anastasios (AUTH)
Smrž Pavel, doc. RNDr., Ph.D. (DCGM FIT BUT)
Hilton Adrian (USG)
Pitas Ioannis (AUTH)
URL
Keywords

Anthropocentric semantic video analysis; big media data analysis and integration; graph processing acceleration; multimodal data processing; outdoor 3-D reconstruction; web 3-D visualization

Abstract

A typical high-end film production generates several terabytes of data per day, either as footage from multiple cameras or as background information regarding the set (laser scans, spherical captures, etc). This paper presents solutions to improve the integration of the multiple data sources, and understand their quality and content, which are useful both to support creative decisions on-set (or near it) and enhance the postproduction process. The main cinema specific contributions, tested on a multisource production dataset made publicly available for research purposes, are the monitoring and quality assurance of multicamera set-ups, multisource registration and acceleration of 3-D reconstruction, anthropocentric visual analysis techniques for semantic content annotation, and integrated 2-D-3-D web visualization tools. We discuss as well improvements carried out in basic techniques for acceleration, clustering and visualization, which were necessary to deal with the very large multisource data, and can be applied to other big data problems in diverse application fields.

Published
2015
Pages
2085-2113
Journal
IEEE Communication Letters, vol. 104, no. 11, ISSN 1089-7798
Book
Proceedings of the IEEE - special issue on Big Data - Part 2
DOI
UT WoS
000386244000004
EID Scopus
BibTeX
@ARTICLE{FITPUB11045,
   author = "Josep Blat and Alun Evans and Hansung Kim and Evren Imre and Luk\'{a}\v{s} Polok and S. Viorela Ila and Nikos Nikolaidis and Pavel Zem\v{c}\'{i}k and Anastasios Tefas and Pavel Smr\v{z} and Adrian Hilton and Ioannis Pitas",
   title = "Big Data Analysis for Media Production",
   pages = "2085--2113",
   booktitle = "Proceedings of the IEEE - special issue on Big Data - Part 2",
   journal = "IEEE Communication Letters",
   volume = 104,
   number = 11,
   year = 2015,
   ISSN = "1089-7798",
   doi = "10.1109/JPROC.2015.2496111",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11045"
}
Back to top