IMPART: Big media data processing and analysis for film production

Josep Blat, Alun Evans, Javi Agenjo, Hansung Kim, Evren Imre, Adrian Hilton, Anastasios Tefas, Nikos Nikolaidis, Ioannis Pitas, Lukas Polok, Pavel Smrz, Pavel Zemcik

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

202 Downloads (Pure)

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). The EU project IMPART (impart.upf.edu) has been researching solutions that improve the integration and understanding of the quality of the multiple data sources to support creative decisions onset or near it, and an enhanced post-production as well. The
main results covered in this paper are: a public multisource production dataset made available for research purposes, monitoring and quality assurance of multicamera set-ups, multisource registration, anthropocentric visual analysis for
semantic content annotation, acceleration of 3D reconstruction, and integrated 2D-3D web visualization tools.
Original languageEnglish
Title of host publication2015 IEEE International Conference on Multimedia & Expo Workshops (ICMEW 2015)
Subtitle of host publicationProceedings of a meeting held 29 June - 3 July 2015, Turin, Italy
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1-5
ISBN (Print)9781479970803
DOIs
Publication statusPublished - Sep 2015
EventIEEE International Conference on Multimedia Expo Workshops (ICMEW) - Torino, Italy
Duration: 29 Jun 20153 Jul 2015

Conference

ConferenceIEEE International Conference on Multimedia Expo Workshops (ICMEW)
Country/TerritoryItaly
CityTorino
Period29/06/153/07/15

Keywords

  • Multi-modal data processing
  • big media data analysis
  • web 3D visualization

Fingerprint

Dive into the research topics of 'IMPART: Big media data processing and analysis for film production'. Together they form a unique fingerprint.

Cite this