Detail publikačního výsledku

Big Data Analysis for Media Production

BLAT, J.; EVANS, A.; KIM, H.; IMRE, E.; POLOK, L.; ILA, V.; NIKOLAIDIS, N.; ZEMČÍK, P.; TEFAS, A.; SMRŽ, P.; HILTON, A.; PITAS, I.

Originální název

Big Data Analysis for Media Production

Anglický název

Big Data Analysis for Media Production

Druh

Článek WoS

Originální abstrakt

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.

Anglický abstrakt

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.

Klíčová slova

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

Klíčová slova v angličtině

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

Autoři

BLAT, J.; EVANS, A.; KIM, H.; IMRE, E.; POLOK, L.; ILA, V.; NIKOLAIDIS, N.; ZEMČÍK, P.; TEFAS, A.; SMRŽ, P.; HILTON, A.; PITAS, I.

Rok RIV

2016

Vydáno

31.12.2015

Kniha

Proceedings of the IEEE - special issue on Big Data - Part 2

ISSN

1089-7798

Periodikum

IEEE COMMUNICATIONS LETTERS

Svazek

104

Číslo

11

Stát

Spojené státy americké

Strany od

2085

Strany do

2113

Strany počet

29

URL

http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7350093

BibTex

@article{BUT119929,
  author="Josep {Blat} and Alun {Evans} and Hansung {Kim} and Evren {Imre} and Lukáš {Polok} and Viorela Simona {Ila} and Nikos {Nikolaidis} and Pavel {Zemčík} and Anastasios {Tefas} and Pavel {Smrž} and Adrian {Hilton} and Ioannis {Pitas}",
  title="Big Data Analysis for Media Production",
  journal="IEEE COMMUNICATIONS LETTERS",
  year="2015",
  volume="104",
  number="11",
  pages="2085--2113",
  doi="10.1109/JPROC.2015.2496111",
  issn="1089-7798",
  url="http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7350093"
}