Bandwidth-Efficient Methods to Enhance Adaptive Video Streaming Applications
COM2 Level 4
Executive Classroom, COM2-04-02
Abstract:
Video streaming has seen a renaissance in recent years and the adoption of related technologies is growing tremendously. The area is considered a multi-billion dollar industry nowadays in part because user expectations are moving towards ultra-high quality content, immersion and interactivity while watching videos.
In this proposal, we address two problems that relate to the efficient use of bandwidth in video streaming systems in order to adapt to the varying network conditions: bandwidth estimation for mobile clients and bandwidth saving for 360 degree video streaming systems.
In the first part, we introduce GeoStream, a video streaming system that relies on the use of geostatistics to analyze spatio-temporal bandwidth. Data measured by users streaming videos while commuting is collected in order to predict future bandwidth in unknown locations. Our approach investigates and leverages the relationship between the separation distance between sample bandwidth points, the time they were captured, and the semivariance, expressed by a variogram plot, to finally predict the future bandwidth at unknown locations.
In the second part, we focus on 360 degree video streaming, where we use Scalable High-efficiency Video Coding (SHVC) to stream a panoramic view base layer along with employing a tiling technique for the enhancement layers.