FBRA360: A Fuzzy-Based Bitrate Adaptation Scheme for 360° Video Streaming

Abstract

Bitrate adaptation is a classic research problem in video streaming. In a tile-based 360° video streaming system, the problem becomes even more complicated because the system needs to conduct viewport prediction (VP) except for traditional bitrate selection (BS). Existing methods usually treat VP and BS separately, which is sub-optimal and thus limits performance improvement. Inspired by our observation of the bidirectional dependency between VP and BS, we propose FBRA360, a fuzzy-based low-complexity joint optimization scheme, to tackle this problem. A fuzzy logic controller has been devised to control simultaneously: (1) the weighted combination of VP from individual users' historical trajectory and multi-user attention distribution, and (2) the expected buffer occupancy after each download. Experimental results show that FBRA360 improves the VP accuracy by 16.2% and the video quality by 7.5%, compared with the state-of-the-art algorithms.