The main focus in this project is to virtualize video services utilizing container and other virtualization techniques. Containers allow lightweight virtualization of a smaller or larger component with very little computing overhead, while traditional virtualization techniques allow virtualization of full server computer including the whole Operating System. There are plenty of different video services, which need to be started rapidly, scaled up or down, or moved to another computing platform.
Virtualization is a key technology, which enables flexible usage of different computing platforms. Computing platforms may be private or public cloud solutions, or in some cases those may be inside a telco network, for example in the form of edge computing platforms.
The goal of the project is to define a flexible approach to implement video services, which:
Those goals can be achieved by utilizing the most recent advancements in cloud, virtualisation and video delivery techniques. The project will research and implement the video services, but also analyse the business case for selected video services. Virtualization techniques will be utilized in several video related use cases. Initially use cases are related to cloud gaming, video analytics and surveillance, video conferencing, cable TV and video streaming (live and video-on-demand) services.
... standardization document info 1..
... standardization document info 2..
... standardization document info 3..
A. Altonen, M. Viitanen, J. Räsänen, A. Mercat and J. Vanne, "Public and Open HEVC Encoding Service in Cloud," MMSys'2019, Amherst, MA, USA, June 18-21, 2019.
T. Aihkisalo and E. Ovaska, "Identifying Architectural Design Trade-offs in Service Registry Features," IEEE SOSE 2017, Apr. 6-9, San Francisco, USA, 2017.
J. J. G. Aranda, M. G. Casquete, M. C. Cueto, J. N. Salmerón and F. G. Vidal, "Logarithmical hopping encoding: a low computational complexity algorithm for image compression," IET Image Processing, vol. 9, no. 8, pp. 643–651, 2015.
D. Becker, M. Schmidt, F. Bombardelli da Silva, S. Gül, C. Hellge, O. Sawade and I. Radusch, "Visual Object Tracking in a Parking Garage using Compressed Domain analysis," In Proc. ACM MMsys conference (MMSys), Amsterdam, Holland, 2018.
F. Bombardelli, Serhan Gül, Daniel Becker, Matthias Schmidt and Cornelius Hellge, "Efficient Object Tracking in Compressed Video Streams with Graph Cuts," in Proc. Int. Workshop on Multimedia Signal Processing (MMSP), Vancouver, Canada, 2018.
F. Bombardelli da Silva, S. Gül and C. Hellge, "Compressed-Domain Video Object Tracking using Markov Random Fields with Graph Cuts Optimization," in Proc. German Conf. on Pattern Recognition (GCPR), Stuttgart, Germany, 2018.
V. Cristian, B. Cristian and H. Ijaz, "Collaborative Object Recognition for Parking Management," eLSE 2019,Bucharest, Romania, Apr. 2019.
S. Ghosh, P. Amon, A. Hutter and A. Kaup, "Pedestrian Counting Using Deep Models Trained on Synthetically Generated Images,", in Proc. International Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), Porto, Portugal, Feb./Mar. 2017.
S. Ghosh, P. Amon, A. Hutter and A. Kaup, "Detecting Closely Spaced and Occluded Pedestrians Using Specialized Deep Models for Counting," in Proc. IEEE Visual Communications and Image Processing, St Petersburg, FL, USA, Dec. 2017.
S. Ghosh, P. Amon, A. Hutter and A. Kaup, "Reliable Pedestrian Detection Using a Deep Neural Network Trained on Pedestrian Counts," in Proc. Int. Conf. on Image Processing (ICIP), Beijing, China, Sep. 2017.
S. Ghosh, P. Amon, A. Hutter and A. Kaup, "Robustness of Deep Convoluational Neural Networks for Image Degradations," in Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Canada, Apr. 2018.
S. Ghosh, P. Amon, A. Hutter and A. Kaup, "Deep Counting Model Extensions with Segmentation for Person Detection," ICASSP'2019, Brighton, UK, May 2019.
S. Gül, J. T. Meyer, C. Hellge, T. Schierl and W. Samek, "Hybrid video object tracking in h. 265/hevc video streams," in Multimedia Signal Processing (MMSP), 2016 IEEE 18th International Workshop on, pp. 1–5, IEEE, 2016.
A. Heikkinen, P. Pääkkönen, M. Viitanen, J. Vanne, T. Riikonen and K. Bakanoglu, "Fast and Easy Live Video Service Setup Using Lightweight Virtualization," MMSys’18, June 12 – 15, Amsterdam, The Netherlands, 2018.
A. Heikkinen, "Network-assisted DASH by Utilizing Local Caches at Network Edge," SoftCOM 2018 September 13-15, Split, Croatia, 2018.
A. Mercat, A. Lemmetti, M. Viitanen and J. Vanne, "Acceleration of Kvazaar HEVC intra encoder with machine learning," ICIP'2019, Taipei, Taiwan, Sept. 22-25, 2019.
T. Ojanperä and H. Kokkoniemi-Tarkkanen, "Experimental Evaluation of a Wireless Bandwidth Management System for Multiple DASH Clients," IEEE Globecom 2016, Dec. 4-8, Washington DC, USA, 2016.
T. Ojanperä and H. Kokkoniemi-Tarkkanen, "Wireless Bandwidth Management for Multiple Video Clients through Network-assisted DASH," IEEE WoWMoM 2016, Jun. 21-24, Coimbra, Portugal, 2016.
P. Pääkkönen, A. Heikkinen and T. Aihkisalo, "Online architecture for predicting live video transcoding resources," Journal of Cloud Computing, Springer, 2019.
P. Pääkkönen, A. Heikkinen and T. Aihkisalo, "Architecture for Predicting Live Video Transcoding Performance on Docker Containers," IEEE SCC 2018, July 2– 7, San Francisco, USA, 2018.
J. Räsänen, M. Viitanen, J. Vanne and T. D. Hämäläinen, "Live demonstration: Kvazzup 4K HEVC video call," in Proc. IEEE Int. Symp. Multimedia, Taichung, Taiwan, Dec. 2018.
J. Räsänen, M. Viitanen, J. Vanne and T. D. Hämäläinen, "Kvazzup: open software for HEVC video calls," in Proc. IEEE Int. Symp. Multimedia, Taichung, Taiwan, Dec. 2017.
J. Sainio, A. Mercat and J. Vanne, "Hardware Deceleration of Kvazaar HEVC Encoder," SAMOS'2019, Samos, Greece, July 7-11, 2019.
V. Srinivasan, S. Gül, Bosse, J. T. Meyer, T. Schierl, C. Hellge and W. Samek, “On the robustness of action recognition methods in compressedand pixel domain,” in Visual Information Processing (EUVIP), 2016 6th European Workshop on, pp. 1–6, IEEE, 2016.
V. Srinivasan, S. Lapuschkin, C. Hellge, K. R. Müller and W. Samek, "Interpretable human action recognition in compressed domain," in Prcc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing(ICASSP), pp. 1692–1696, March 2017.
G. Suciu, M. Anwar, A. Pasat, C. M. Balaceanu and R. Matei, "VIRTUALIZED VIDEO CONFERENCING FOR eLEARNING," eLSE 2018, Bucharest, Romania, April 19-20, 2018.
G. Suciu, M. Anwar and R. Mihalcioiu, "Virtualized Video and Cloud Computing for Efficient e-Learning," in The International Scientific Conference eLearning and Software for Education, "Carol I" National Defence University, vol. 2, pp. 205-212, 2017.
M. Uitto and A. Heikkinen, "SAND-assisted encoding control for energy-aware MPEG-DASH live streaming," SoftCOM 2016, Sep. 22-24, Split, Croatia, 2016.
J. Vehkaperä and A. Heikkinen: "Pop-up CDN with smart monitoring and management," SmartCom16, May 16-17, Oulu, Finland, 2016.
M. Viitanen, A. Koivula, A. Lemmetti, A. Ylä-Outinen, J. Vanne, and T. D. Hämäläinen, "Kvazaar: open-source HEVC/H.265 encoder", in Proc. ACM Int. Conf. Multimedia, Amsterdam, The Netherlands, Oct. 2016.
T. Wiegand, (Keynote) "Image compression, processing, and machine learning" in German Conference on Pattern Recognition (GCPR), Hannover, Germany, September 2016.
T. Wiegand, "The convergence of communication and machine learning" in ICTs for a Sustainable World, ITU Kaleidoscope Academic Conference, Bangkok, Thailand, November 2016.
... Document name here ..
Jose Javier Garcia Aranda, Nokia Spain