| Popis: |
Virtual reality (VR) streaming (a.k.a., 360-degree video streaming) has been gaining popularity recently as a new form of multimedia providing the users with immersive viewing experience. However, the high volume of data for the 360-degree video frames creates significant bandwidth challenges. Research efforts have been made to reduce the bandwidth consumption by predicting and selectively streaming the user's viewports. However, the existing viewport prediction approaches require historical user or video data and cannot be applied to live streaming, the most attractive VR streaming scenario. We develop a set of viewport prediction methods targeting live VR streaming by employing various features obtained from the video content, such as motion (i.e., LiveMotion), deep features (i.e., LiveDeep), object semantics (i.e., LiveObj), and action semantics (i.e., LiveROI). Furthermore, we enhance the video content-based prediction by leveraging runtime user feedback and modeling. Our evaluations using an empirical VR head movement dataset demonstrate high prediction accuracy and significant bandwidth savings obtained by the four methods. Besides, they achieve real-time performance with low processing delay, meeting the requirement of live VR streaming. |
