Currently, a fixed set of bitrate-resolution pairs termed a “bitrate ladder” is used in live streaming applications. Similarly, two-pass variable bitrate (VBR) encoding schemes are not used in live streaming applications to avoid the additional latency added by the first-pass. Bitrate ladder optimization is necessary to (i) decrease storage or delivery costs or/and (ii) increase Quality of Experience. Using two-pass VBR encoding improves compression efficiency, owing to better encoding decisions in the second-pass encoding using the first-pass analysis. In this light, this paper introduces a perceptually-aware constrained Variable Bitrate (cVBR) encoding Scheme (Live VBR) for HTTP adaptive streaming applications, which includes a joint optimization of the perceptual redundancy between the representations of the bitrate ladder, maximizing the perceptual quality (in terms of VMAF) and optimized constant rate factor (CRF). Discrete Cosine Transform (DCT)-energy-based low-complexity spatial and temporal features for every video segment, namely, brightness, spatial texture information, and temporal activity, are extracted to predict a perceptually-aware bitrate ladder for encoding. Experimental results show that, on average, Live VBR yields bitrate savings of 7.21% and 13.03% to maintain the same peak PSNR and VMAF, respectively, compared to the reference HTTP Live Streaming (HLS) bitrate ladder Constant Bitrate (CBR) encoding using x264 AVC encoder without any noticeable additional latency in streaming. Additionally, Live VBR results in a 52.59% cumulative decrease in storage space for various representations, and a 28.78% cumulative decrease in energy consumption, considering a perceptual difference of 6 VMAF points.
Vignesh V. Menon | Christian Doppler Laboratory ATHENA, Alpen-Adria-Universität | Klagenfurt, Austria Prajit T. Rajendran | CEA, List, F-91120 Palaiseau, Université Paris-Saclay | France Christian Feldmann | Bitmovin | Klagenfurt, Austria Martin Smole | Bitmovin | Klagenfurt, Austria Mohammad Ghanbari | Christian Doppler Laboratory ATHENA, Alpen-Adria-Universität and School of Computer Science and Electronic Engineering | Klagenfurt, Austria and University of Essex, United Kingdom Christian Timmerer | Christian Doppler Laboratory ATHENA, Alpen-Adria-Universität | Klagenfurt, Austria
When building a Telco-CDN infrastructure, Internet Service Providers (ISP) first consider the peak throughput and then provision the infrastructure as a function of peak capacity. New network design practices indicate that instead, operators would benefit from dimensioning the infrastructure to cover the traffic demand for a fraction of time, and develop strategies to manage the peaks, which happen when the demand exceeds the capacity of the infrastructure. A peak offloading strategy is particularly effective in online video delivery where demand peaks, often driven by sports events, are transient and significantly higher than average traffic. This paper provides a tour of CDN management, described by a new approach to design Telco-CDN with greater fluidity, mixing appropriate technologies to provide the right elasticity at the right time.
Ultra-low latency over-the-top (OTT) video streaming is becoming increasingly important in gaming, metaverse, and gambling applications, enabling social interaction and monetization in live events such as sports and concerts. Moreover, all those applications are conceptually converging. These applications require real-time, interactive experiences that are highly responsive and immersive, and ultra-low latency OTT streaming is essential for delivering this type of experience. Tremendous innovation resources have been invested to build robust OTT delivery systems with ultra-low latency capabilities. Necessary optimizations affect most steps from encoding to packaging and even last mile delivery. In this paper, we explain a setup that leverages the ultra-low latency technology using the Live Media Ingest Protocol and Just-In-Time packaging. We also explore how such setup can be used to enable amazing technologies that have direct impact on the performance of the Content Delivery Network (CDN) and the users’ quality of experience (QOE) to achieve the seamless and immersive experience they require.