Eliminating bandwidth estimation from adaptive video streaming in wireless networks |
| |
| Affiliation: | 1. Next Generation R&D Group, Samsung Electronics, Suwon, Gyeonggi-do, Republic of Korea;2. Digital Technology & Biometry Division, National Forensic Service, Wonju, Gangwon-do, South Korea;3. Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea;1. School of Electronic Engineering, Xidian University, China;2. School of Computer Engineering, Nanyang Technological University, Singapore;3. School of Information Technology, Jiangxi University of Finance and Economics, Nanchang, China;4. School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, China;1. School of Automation Science and Electrical Engineering Beihang University, Beijing, China;2. Computer Science and Digital Technologies Department, Northumbria University, Newcastle, UK;3. Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China;4. School of Computer & Software, Nanjing University of Information Science & Technology, China;1. University of Southern California, Los Angeles, CA, USA;2. National Taiwan University, Taipei, Taiwan;1. Nanyang Normal University, Nanyang, Henan 473061, China;2. Center for Internet of Things, Institute of Microelectronics of Chinese Academy of Sciences, Beijing 100029, China;3. Hebei University of Technology, Tianjin 300401, China |
| |
| Abstract: | Dynamic Adaptive Streaming over HTTP (DASH) is the state-of-the-art technology for video streaming and has been widely deployed in both wired and wireless environments. However, mobile DASH users often suffer from video quality oscillation and even video freeze in wireless environments, which results in poor user experience. This is mainly because most quality adaptation algorithms in DASH rely highly on bandwidth estimation to adjust the video quality while wireless network bandwidth is unstable in nature and changes frequently according to wireless channel contention and condition. To provide stable performance, even during severe bandwidth fluctuation, this paper proposes the Wireless Quality Adaptation (WQUAD) algorithm, which eliminates bandwidth estimation from quality adaptation. Thanks to the Scalable Video Codec (SVC), the proposed scheme always prioritizes to lower layers over higher ones as long as the play-out buffer is not completely filled by the lower layers. As a result, the client always fills the buffer with the base layers first and then the upper enhancement layers sequentially. This horizontal adaptation is straightforward and does not require any bandwidth estimation. Through NS-2 simulations, we show that WQUAD achieves (i) stable performance, keeping the video quality level with respect to the long-term network bandwidth, (ii) effective video freeze prevention, and (iii) high video quality on average. |
| |
| Keywords: | Dynamic adaptive streaming over HTTP Scalable video codec Wireless quality adaptation algorithm Video freeze |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
