IMPART: Big media data processing and analysis for film 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). 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.

[1]  Richard Szeliski,et al.  Modeling the World from Internet Photo Collections , 2008, International Journal of Computer Vision.

[2]  Jean-Yves Guillemaut,et al.  Through-the-Lens Multi-camera Synchronisation and Frame-Drop Detection for 3D Reconstruction , 2012, 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission.

[3]  Alun Evans,et al.  Web-based visualisation of on-set point cloud data , 2014, CVMP.

[4]  Guillaume Lavoué,et al.  Streaming compressed 3D data on the web using JavaScript and WebGL , 2013, Web3D '13.

[5]  Anastasios Tefas,et al.  A distributed framework for trimmed Kernel k-Means clustering , 2015, Pattern Recognit..

[6]  Anastasios Tefas,et al.  Symmetric Subspace Learning for Image Analysis , 2014, IEEE Transactions on Image Processing.

[7]  Adrian Hilton,et al.  Coverage evaluation of camera networks for facilitating big-data management in film production , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[8]  Adrian Hilton,et al.  Jigsaw: multi-modal big data management in digital film production , 2015, SIGGRAPH Posters.

[9]  Alexandros Iosifidis,et al.  Minimum Class Variance Extreme Learning Machine for Human Action Recognition , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

[10]  Barry W. Peyton,et al.  Block sparse Cholesky algorithms on advanced uniprocessor computers , 1991 .

[11]  Stefan Decker,et al.  On the design of a Dual-Mode User Interface for accessing 3D content on the World Wide Web , 2013, Int. J. Hum. Comput. Stud..

[12]  Alexandros Iosifidis,et al.  Exploiting subclass information in one-class support vector machine for video summarization , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).