Conference paper Open Access
Carter, Juliette; Blasi, Saverio; Mrak, Marta
When using adaptive streaming, the content needs to be segmented so that clients can seamlessly switch to different rates depending on network conditions. On the video server each segment is stored in various bitrate representations, which are in practice provided by very fast encoders. Such encoders rely on parallelisation strategies to limit the encoder complexity. Parallelisation strongly affects the performance of rate-control (RC) algorithms, since different segments and parts of segments are encoded independently from each other. A new approach is proposed in this paper to tackle these issues, based on the optimisation of the initial parameters of a state-of-the-art RC model for inter-predicted frames in an HEVC/H.265 codec. The model makes use of an estimate of the texture complexity of the first frame in the segment to efficiently tune the parameters depending on the target rate. The approach is consistently improving the accuracy of RC schemes as well as the visual quality, with negligible impact on the encoding efficiency.