Comparing the Streaming of FGS Encoded Video at Different Aggregation Levels: Frame, GoP, and Scene

Fine granularity scalability (FGS), a new coding technique that has<br>recently been added to the MPEG-4 video coding standard, allows for<br>the flexible scaling of each individual video frame at very fine<br>granularity. This flexibility makes FGS video very well suited for<br>rate-distortion optimized streaming mechanisms, which minimize the<br>distortion (i.e. maximize the quality) of the streamed video by transmitting<br>the optimal number of bits for each individual frame. The per-frame<br>optimization of the transmission schedule, however, puts a significant<br>computational burden on video servers and intermediate streaming<br>gateways. In this paper we investigate the rate-distortion optimized<br>streaming at different video frame aggregation levels. We find that<br>compared to the optimization for each individual video frame, optimization<br>at the level of video scenes reduces the computational effort dramatically,<br>while reducing the video quality only very slightly.