Big Data Analysis for Media Production

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 un...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the IEEE 2016-11, Vol.104 (11), p.2085-2113
Main Authors: Blat, Josep, Smrz, Pavel, Hilton, Adrian, Pitas, Ioannis, Evans, Alun, Kim, Hansung, Imre, Evren, Polok, Lukas, Ila, Viorela, Nikolaidis, Nikos, Zemcik, Pavel, Tefas, Anastasios
Format: Article
Language:English
Subjects:
Acceleration
Anthropocentric semantic video analysis
Big data
big media data analysis and integration
Cameras
Computer applications
Data analysis
Data management
Data visualization
graph processing acceleration
Lasers
Monitoring
Motion pictures
multimodal data processing
outdoor 3-D reconstruction
Semantics
Three-dimensional displays
Visualization
web 3-D visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0018-9219
1558-2256
DOI:10.1109/JPROC.2015.2496111