Intelligent Management Platform for Advanced Real-Time media processes

Czech title

IMPART - Intelligent Management Platform for Advanced Real-Time media processes

Type

grant

Keywords

information management; multimodal; metadata; real-time decision support; digital
media

Abstract

IMPART will research, develop and evaluate intelligent information management
solutions for "big data" problems in the field of digital cinema production. It
will find new ways of managing, visualising and analysing very large multimodal
data sets so that creative personnel can review three-dimensional scene
representations on the set, understand the data, identify errors, evaluate the
quality of the shot and take creative decisions in real time. We will research
and test solutions for the use case of large-scale movie production, with very
large research and evaluation datasets based on the latest industrial processes.
Results will be applicable to film production and more generally to commercial
and professional domains ranging from TV and on-line video to surveillance. The
project outcomes will include: - Architectures and file structures for
intelligent multimodal data and metadata management, presentation and browsing
linking data, metadata and advanced applications - Methods for automatically
selecting relevant subsets of data to allow rapid processing - Techniques for
processing, information extraction and analysis in distributed systems -
Multimodal content semantic and low-level analysis techniques for the automatic
derivation of metadata to support visualisation, decision support, management and
retrieval - On-set decision support, including tools for multimodal data
visualisation, data summarization, layout, registration and cross-referencing,
data and metadata search, virtual overlays and real-time previews of effects,
creative and technical decision support - A demonstrator system for professional
testing and evaluation, both on and off set - A documented xml interface that
allows third parties to develop compatible tools and processes - A published test
dataset of multimodal data and metadata captured in realistic film production
conditions for use by other researchers.

Team members

Smrž Pavel, doc. RNDr., Ph.D. (DCGM) – research leader
Ila Viorela Simona, Ph.D.
Kula Michal, Ing., Ph.D. (DCGM)
Polok Lukáš, Ing., Ph.D.
Seeman Michal, Ing., Ph.D.
Šolony Marek, Ing., Ph.D. (DCGM)
Zemčík Pavel, prof. Dr. Ing., dr. h. c. (DCGM)

Publications

2018

BAŘINA, D.; ZEMČÍK, P. Vectorization and Parallelization of 2-D Wavelet Lifting. Journal of Real-Time Image Processing, 2018, vol. 15, no. 2, p. 349-361. ISSN: 1861-8200. Detail

2017

ILA, V.; POLOK, L.; ŠOLONY, M.; SVOBODA, P. SLAM plus plus -A highly efficient and temporally scalable incremental SLAM framework. INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2017, vol. 2017, no. 1, p. 210-230. ISSN: 1741-3176. Detail

2015

BLAT, J.; EVANS, A.; HILTON, A.; IMRE, E.; KIM, H.; NIKOLAIDIS, N.; PITAS, I.; POLOK, L.; SMRŽ, P.; TEFAS, A.; ZEMČÍK, P. IMPART: Big media data processing and analysis for film production. In IEEE International Conference on Multimedia Expo Workshops (ICMEW). Torino: 2015. p. 1-5. ISBN: 978-1-4799-7079-7. Detail
BLAT, J.; EVANS, A.; KIM, H.; IMRE, E.; POLOK, L.; ILA, V.; NIKOLAIDIS, N.; ZEMČÍK, P.; TEFAS, A.; SMRŽ, P.; HILTON, A.; PITAS, I. Big Data Analysis for Media Production. IEEE Communication Letters, 2015, vol. 104, no. 11, p. 2085-2113. ISSN: 1089-7798. Detail
ILA, V.; POLOK, L.; ŠOLONY, M.; ZEMČÍK, P.; SMRŽ, P. Fast Covariance Recovery in Incremental Nonlinear Least Square Solvers. In Proceedings of IEEE International Conference on robotics and Automation. Seattle: IEEE Computer Society, 2015. p. 1-8. ISBN: 978-1-4799-6922-7. Detail
PABST, S.; KIM, H.; POLOK, L.; ILA, V.; WAINE, T.; HILTON, A.; CLIFFORD, J.; SMRŽ, P. Jigsaw - Multi-Modal Big Data Management in Digital Film Production. Los Angeles: 2015. p. 1-2. ISBN: 978-1-4503-3632-1. Detail
POLOK, L.; ILA, V.; SMRŽ, P. Fast Sparse Matrix Multiplication on GPU. In Proceedings of the 23rd High Performance Computing Symposium (HPC'15). Alexandria, Virginia: Association for Computing Machinery, 2015. p. 1-8. ISBN: 978-1-5108-0101-1. Detail
POLOK, L.; KLICNAR, L.; ZEMČÍK, P.; BERAN, V.; SMRŽ, P. Quality Assurance in Large Collections of Video Sequences. In Proceedings - International Conference on Image Processing, ICIP. Québec: IEEE Computer Society Press, 2015. p. 3580-3584. ISBN: 978-1-4799-8339-1. Detail
POLOK, L.; ŠOLONY, M.; ILA, V.; SMRŽ, P.; ZEMČÍK, P.; CLIFFORD, J.; PABST, S. A GPU-Accelerated Bundle Adjustment Solver. San Jose: NVIDIA, 2015. p. 1 (1 s.). Detail
POLOK, L.; VINCENT, L.; ILA, V.; DRUMMOND, T.; MAHONY, R. The effect of different parameterisations in incremental structure from motion. In Proceedings of 2015 Australasian Conference on Robotics and Automation, ACRA 2015; Australian National UniversityCanberra; Australia. Australasian Conference on Robotics and Automation, ACRA. Canberra: Australian National University, 2015. p. 1-9. ISSN: 1448-2053. Detail
ŠOLONY, M.; IMRE, E.; ILA, V.; POLOK, L.; KIM, H.; ZEMČÍK, P. Fast and Accurate Refinement Method for 3D Reconstruction from Stereo Spherical Images. In Proceedings of the 10th International Conference on Computer Vision Theory and Applications. Berlin: Institute of Electrical and Electronics Engineers, 2015. p. 1-8. ISBN: 978-989-8425-47-8. Detail

2014

BAŘINA, D.; ZAHRÁDKA, J.; ZEMČÍK, P. Wavelet Representation of Optical System Distortion. In International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG). Plzeň: Union Agency, 2014. p. 11-16. ISBN: 978-80-86943-71-8. Detail
BAŘINA, D.; ZEMČÍK, P. Diagonal Vectorisation of 2-D Wavelet Lifting. In International Conference on Image Processing (ICIP). Paris: IEEE Signal Processing Society, 2014. p. 2978-2982. ISBN: 978-1-4799-5751-4. Detail
POLOK, L.; ILA, V.; SMRŽ, P. Fast Radix Sort for Sparse Linear Algebra on GPU. Proceedings of the 22nd High Performance Computing Symposium (HPC'14). Tampa: Association for Computing Machinery, 2014. p. 1-8. ISBN: 1-56555-353-5. Detail

2013

BAŘINA, D.; ZEMČÍK, P. Minimum Memory Vectorisation of Wavelet Lifting. In Advanced Concepts for Intelligent Vision Systems (ACIVS). Lecture Notes in Computer Science (LNCS) 8192. Poznan: Springer London, 2013. p. 91-101. ISBN: 978-3-319-02894-1. Detail
BAŘINA, D.; ZEMČÍK, P. Wavelet Lifting on Application Specific Vector Processor. In GraphiCon'2013. Vladivostok: GraphiCon Scientific Society, 2013. p. 83-86. ISBN: 978-5-8044-1402-4. Detail
ILA, V.; POLOK, L.; SMRŽ, P.; ŠOLONY, M.; ZEMČÍK, P. Incremental Block Cholesky Factorization for Nonlinear Least Squares in Robotics. In proceedings of The Robotics: Science and Systems 2013 Conference. Berlín: MIT Press, 2013. p. 1-8. ISBN: 978-981-07-3937-9. Detail
ILA, V.; POLOK, L.; SMRŽ, P.; ŠOLONY, M.; ZEMČÍK, P. Incremental Cholesky Factorization for Least Squares Problems in Robotics. Proceedings of The 2013 IFAC Intelligent Autonomous Vehicles Symposium. Gold Coast: IEEE Computer Society, 2013. p. 1-8. ISBN: 978-3-902823-36-6. Detail
POLOK, L.; ILA, V.; SMRŽ, P. Cache Efficient Implementation for Block Matrix Operations. Proceedings of the 21st High Performance Computing Symposium (HPC'13). San Diego: Association for Computing Machinery, 2013. p. 698-706. ISBN: 1-56555-350-0. Detail
VRÁBELOVÁ, P.; BAŘINA, D.; ŠKODA, P.; VÁŽNÝ, J.; ZENDULKA, J. Classification of Spectra of Emission-line Stars Using Feature Extraction Based on Wavelet Transform. In Proceedings of 23rd Annual Astronomical Data Analysis Software and Systems (ADASS) Conference. San Francisco: Astronomical Society of the Pacific, 2013. p. 177-180. ISBN: 978-1-58381-854-1. Detail
VRÁBELOVÁ, P.; BAŘINA, D.; ŠKODA, P.; ZENDULKA, J.; VÁŽNÝ, J. Classification of Be Stars Using Feature Extraction Based on Discrete Wavelet Transform. Proceedings of conferences Datakon and Znalosti 2013. Ostrava: VŠB-Technical University of Ostrava, 2013. p. 95-102. ISBN: 978-80-248-3189-3. Detail