講演抄録/キーワード |
講演名 |
2018-06-01 12:45
Improving QoE of Viewport Adaptive 360-degree Video Streaming with Machine Learning ○Xiaolan Jiang・Yi-Han Chiang(NII)・Zhi Liu(Shizuoka Univ.)・Yusheng Ji(NII) CQ2018-26 |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
To prevent the delivery of entire 360-degree (or 360) videos from adversely affecting QoE, tile-based viewport adaptive streaming that divides 360 video chunks into tiles and conveys streams with differentiated quality levels to viewport and non-viewport areas has been regarded as a promising solution.
Existing works have been devoted to the design of 1) viewport prediction (VPP) to predict users' viewport orientation due to head movements, and 2) tile bitrate selection (TBS) to determine tile-based bitrates for viewport and non-viewport areas. In this paper, we propose a system to leverage machine learning to tile-based viewport adaptive streaming for 360 videos. In particular, We apply long short term memory (LSTM) model to VPP, and use part of non-viewport areas to help resist prediction errors. In addition, We use real-world traces to train a TBS agent with reinforcement learning to determine tile bitrates for both viewport and non-viewport areas. The simulation results show that our system outperforms the existing scheme in various QoE metrics. |
キーワード |
(和) |
/ / / / / / / |
(英) |
Tile-based method / viewport adaptive streaming / 360-degree video / reinforcement learning / / / / |
文献情報 |
信学技報, vol. 118, no. 71, CQ2018-26, pp. 49-54, 2018年5月. |
資料番号 |
CQ2018-26 |
発行日 |
2018-05-24 (CQ) |
ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
CQ2018-26 |
|