ABSTRACT
Over-the-top (OTT) streaming services like YouTube and Netflix induce massive amounts of video data, hereby putting substantial pressure on network infrastructure. This paper describes a demonstration of the object-based video (OBV) methodology that allows for the quality-variant MPEG-DASH streaming of respectively the background and foreground object(s) of a video scene. The OBV methodology is inspired by research into human visual attention and foveated compression, in that it allows to adaptively and dynamically assign bitrate to those portions of the visual scene that have the highest utility in terms of perceptual quality. Using a content corpus of interview-like video footage, the described demonstration proves the OBV methodology's potential to downsize video bitrate requirements while incurring at most marginal perceptual impact (i.e., in terms of subjective video quality). Thanks to its standards-compliant Web implementation, the OBV methodology is directly and broadly deployable without requiring capital expenditure.
- Ingar M. Arntzen and Njål T. Borch. 2016. Data-independent Sequencing with the Timing Object: A JavaScript Sequencer for Single-device and Multi-device Web Media. In Proceedings of the 7th International Conference on Multimedia Systems (MMSys '16). ACM, Article 24, bibinfonumpages10 pages. https://doi.org/10.1145/2910017.2910614Google Scholar
- Robert B Goldstein, Russell Woods, and Eli Peli. 2007. Where people look when watching movies: Do all viewers look at the same place? Computers in Biology and Medicine , Vol. 37, 7 (08 2007), 957--964. https://doi.org/10.1016/j.compbiomed.2006.08.018Google ScholarDigital Library
- Giuseppe Boccignone , Angelo Marcelli, Paolo Napoletano , Gianluca Di Fiore, Giovanni Iacovoni , and Salvatore Morsa. 2008. Bayesian Integration of Face and Low-Level Cues for Foveated Video Coding. IEEE Transactions on Circuits and Systems for Video Technology , Vol. 18, 12 (December 2008), 1727--1740. https://doi.org/10.1109/TCSVT.2008.2005798Google Scholar
- Njål T. Borch, Ingar M. Arntzen, and Francc ois Daoust. 2018. Timing Object -- Draft Community Group Report. Online, http://webtiming.github.io/timingobject/.Google Scholar
- Cisco. 2019. Visual Networking Index: Forecast and Trends, 2017 - 2022. Online, https://www.cisco.com/c/en/us/solutions/collateral/service-provider/visual-networking-index-vni/white-paper-c11--741490.html.Google Scholar
- dash.js. 2019. A reference client implementation for the playback of MPEG DASH via Javascript and compliant browsers . Online, https://dashif.org/dash.js/.Google Scholar
- Michael Dorr, Thomas Martinetz, Karl R. Gegenfurtner, and Erhardt Barth. 2010. Variability of eye movements when viewing dynamic natural scenes . Journal of Vision , Vol. 10, 10 (August 2010), 1--17. https://doi.org/10.1167/10.10.28Google ScholarCross Ref
- Ulrich Engelke, Hagen Kaprykowsky, Hans-Jürgen Zepernick, and Patrick Ndjiki-Nya. 2011. Visual Attention in Quality Assessment. IEEE Signal Processing Magazine , Vol. 28, 6 (November 2011), 50--59. https://doi.org/10.1109/MSP.2011.942473Google ScholarCross Ref
- Ulrich Engelke, Romuald Pépion, Patrick Le Callet, and Hans-Jürgen Zepernick. 2010. Linking Distortion Perception and Visual Saliency in H.264/AVC Coded Video Containing Packet Loss. In Proceedings of Visual Communications and Image Processing (VCIP 2010). https://doi.org/10.1117/12.863508Google ScholarCross Ref
- Michael Evans, Tristan Ferne, Zillah Watson, Frank Melchior, Matthew Brooks, Phil Stenton, Ian Forrester, and Chris Baume. 2017. Creating Object-Based Experiences in the Real World. SMPTE Motion Imaging Journal , Vol. 126, 6 (August 2017), 1--7. https://doi.org/10.5594/JMI.2017.2709859Google ScholarCross Ref
- FFmpeg. 2019. Encode/H.264. Online, https://trac.ffmpeg.org/wiki/Encode/H.264.Google Scholar
- Rafael C. Gonzalez and Richard E. Woods. 2018. Digital Image Processing, 4th Edition .Pearson.Google Scholar
- Jie Li, Thomas Röggla, Maxine Glancy, Jack Jansen, and Pablo Cesar. 2018. A New Production Platform for Authoring Object-based Multiscreen TV Viewing Experiences. In Proceedings of the 2018 ACM International Conference on Interactive Experiences for TV and Online Video (TVX '18). ACM, 115--126. https://doi.org/10.1145/3210825.3210834Google ScholarDigital Library
- Sandvine. 2018. Global Internet Phenomena Report . Online, https://www.sandvine.com/2018-internet-phenomena-report.Google Scholar
- Meijun Sun, Ziqi Zhou, Dong Zhang, and Zheng Wang. 2018. Hybrid convolutional neural networks and optical flow for video visual attention prediction. Multimedia Tools and Applications , Vol. 77, 22 (November 2018), 29231--29244. https://doi.org/10.1007/s11042-018--5793-zGoogle ScholarCross Ref
- Marian F. Ursu, Ian C. Kegel, Doug Williams, Maureen Thomas, Harald Mayer, Vilmos Zsombori, and Mika L. Tuomola. 2008. ShapeShifting TV: interactive screen media narratives. Multimedia Systems , Vol. 14, 2 (July 2008), 115--132. https://doi.org/10.1007/s00530-008-0119-zGoogle ScholarDigital Library
- Maarten Wijnants, Sven Coppers, Gustavo Rovelo Ruiz, Peter Quax, and Wim Lamotte. 2019. Talking Video Heads: Saving Streaming Bitrate by Adaptively Applying Object-based Video Principles to Interview-like Footage. In Proceedings of the 27th ACM International Conference on Multimedia (MM '19, to appear). ACM.Google ScholarDigital Library
- Maarten Wijnants, Gustavo Rovelo, Peter Quax, and Wim Lamotte. 2016. A Pragmatically Designed Adaptive and Web-compliant Object-based Video Streaming Methodology: Implementation and Subjective Evaluation. In Proceedings of the 24th ACM International Conference on Multimedia (MM '16). ACM, 1267--1276. https://doi.org/10.1145/2964284.2964300Google ScholarDigital Library
Index Terms
- Split & Dual Screen Comparison of Classic vs Object-based Video
Recommendations
Talking Video Heads: Saving Streaming Bitrate by Adaptively Applying Object-based Video Principles to Interview-like Footage
MM '19: Proceedings of the 27th ACM International Conference on MultimediaOver-the-top (OTT) streaming services like YouTube and Netflix induce massive amounts of video traffic. To combat the resulting network load, this article empirically explores the use of the object-based video (OBV) methodology that allows for the ...
Multi-codec DASH dataset
MMSys '18: Proceedings of the 9th ACM Multimedia Systems ConferenceThe number of bandwidth-hungry applications and services is constantly growing. HTTP adaptive streaming of audio-visual content accounts for the majority of today's internet traffic. Although the internet bandwidth increases also constantly, audio-...
A Pragmatically Designed Adaptive and Web-compliant Object-based Video Streaming Methodology: Implementation and Subjective Evaluation
MM '16: Proceedings of the 24th ACM international conference on MultimediaThe bulk of contemporary online video traffic is encoded in a traditional manner, hereby neglecting most, if not all, of the semantics of the underlying visual scene. One essential piece of semantic information in the context of video streaming is ...
Comments