Conference Agenda

Overview and details of the sessions of this conference. Please register as a participant for the conference (free!) and then Login in order to have access to downloads in the detailed view. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view.

 
 
Session Overview
Session
MCN2-P: Multimedia Communications and Networking 2
Time:
Thursday, 24/Sept/2020:
6:25pm - 6:40pm

Session Chair: Nicholas Mastronarde
Location: Virtual platform

Presentations
6:25pm - 6:30pm

ABR prediction using supervised learning algorithms

Hiba Yousef1, Jean Le Feuvre2, Alexandre Storelli3

1Streamroot, Telecom Paris; 2Telecom Paris; 3Streamroot

With the massive increase of video traffic over the internet, HTTP adaptive streaming has now become the main technique for infotainment content delivery.

In this context, many bandwidth adaptation algorithms have emerged, each aiming to improve the user QoE using different session information e.g. TCP throughput, buffer occupancy, download time... Notwithstanding the difference in their implementation, they mostly use the same inputs to adapt to the varying conditions of the media session.

In this paper, we show that it is possible to predict the bitrate decision of any ABR algorithm, thanks to machine learning techniques, and supervised classification in particular.

This approach has the benefit of being generic, hence it does not require any knowledge about the player ABR algorithm itself, but assumes that whatever the logic behind, it will use a common set of input features. Then, using machine learning feature selection, it is possible to predict the relevant features and then train the model over real observation. We test our approach using simulations on well-known ABR algorithms, then we verify the results on commercial closed-source players, using different VoD and Live realistic data sets.

The results show that both Random Forest and Gradient Boosting achieve a very high prediction accuracy among other ML-classifier.

Yousef-ABR prediction using supervised learning algorithms-207.pdf


6:30pm - 6:35pm

Evaluating the Performance of Apple's Low-Latency HLS

Kerem Durak, Mehmet N. Akcay, Yigit K. Erinc, Boran Pekel, Ali C. Begen

Ozyegin University, Turkey

In its annual developers conference in June 2019, Apple has announced a backwards-compatible extension to its popular HTTP Live Streaming (HLS) protocol to enable low-latency live streaming. This extension offers new features such as the ability to generate partial segments, use playlist delta updates, block playlist reload and provide rendition reports. Compared to the traditional HLS, these features require new capabilities on the origin servers and the caches inside a content delivery network. While HLS has been known to perform great at scale, its low-latency extension is likely to consume considerable server and network resources, and this may raise concerns about its scalability. In this paper, we make the first attempt to understand how this new extension works and performs. We also provide a 1:1 comparison against the low-latency DASH approach, which is the competing low-latency solution developed as an open standard.

Durak-Evaluating the Performance of Apples Low-Latency HLS-264.pdf


6:35pm - 6:40pm

Open-Source RTP Library for High-Speed 4K HEVC Video Streaming

Aaro Altonen, Joni Räsänen, Jaakko Laitinen, Marko Viitanen, Jarno Vanne

Tampere University, Finland

Efficient transport technologies for High Efficiency Video Coding (HEVC) are key enablers for economic 4K video transmission in current telecommunication networks. This paper introduces a novel open-source Real-time Transport Protocol (RTP) library called uvgRTP for high-speed 4K HEVC video streaming. Our library supports the latest RFC 3550 specification for RTP and an associated RFC 7798 RTP payload format for HEVC. It is written in C++ under a permissive 2-clause BSD license and supports both Linux and Windows operating systems with a user-friendly interface. The end-to-end uvgRTP architecture is composed of the carefully optimized uvgRTP sender and uvgRTP receiver ends. Our experiments on an Intel Core i7-4770 CPU show that uvgRTP is able to stream HEVC video at 5.0 Gb/s over a local 10 Gb/s network. It attains 4.4 times as high peak goodput and 92.1% lower latency than the state-of-the-art FFmpeg multimedia framework. Respectively, it outperforms LIVE555 with over double goodput and 82.3% lower latency. These results indicate that uvgRTP is currently the fastest open-source RTP library for 4K HEVC video streaming.

Altonen-Open-Source RTP Library for High-Speed 4K HEVC Video Streaming-280.pdf