Big Data Analysis for Media Production

Abstract

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 post-production 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 multi-camera set-ups, multisource registration and acceleration of 3D reconstruction, anthropocentric visual analysis techniques for semantic content annotation, and integrated 2D-3D 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.

Desafios para a Computação Energeticamente Eficiente

“…Olhando para o presente e o futuro próximo, o tamanho de dados de aplicativos futuros só pode aumentar. À medida que a automação substitui a fabricação e os serviços, a quantidade de dados que podem ser coletados e analisados pode alcançar facilmente a escala dos terabytes [Jun et al 2017, Blat et al 2016, Algur and Sakri 2015.…”

A pipeline for the creation of progressively rendered web 3D scenes

“…The majority of the previous work in the feld of web 3D transmission focuses on the compression of meshes [12], which consist of positon and index data, with an optonal normal vector, colour, and texture coordinate data. In parallel, 3D point clouds are increasingly available and used, due to the widespread use of 3D scanning (see for instance [23][24][25]), and volumetric rendering is central when dealing with 3D representaton of medical data [26].…”