Intelligent Video Platform APOLLO

The main objective of APOLLO is to research and develop an intelligent video platform for HTTP adaptive streaming which

•shall provide means for the intelligent distribution of video processing tasks (primarily video transcoding) within current and future distributed environments for efficient HTTP adaptive streaming;

•shall support manifold cloud-like environments ranging from large-scale data centers to small-scale computing environments possibly distributed within the delivery network;

•shall integrate artificial intelligence (AI) / machine learning (ML) techniques for the actual distribution;

•shall support media applications specifically in – but not limited to – the context of 5G, IoT, automotive, industry 4.0, as well as health care and education;

•shall provide real-time intelligent metrics and indicators for the automated efficient resource management.

The idea is to design a cloud-based intelligent video platform that also includes algorithms and tools for Quality of Experience (QoE)-efficient resource management. In this way, the client/customers will be able to get resources with required/predefined Quality of Service (QoS)/QoE values/classes. A mod-ern cloud resource management system should manage cloud encoding/transcoding operations from a QoE perspective, built with a future-proof core architecture and natively configured to use artificial intelligent/machine learning (AI/ML) models;

The expected outcome of the APOLLO project is an intelligent video platform for video processing/en-coding that is efficient and cost-effective on current and future computing platforms with the following novel features:

•elastic and scalable platform with an extensible modular architecture for delivering profes-sional-grade video processing/encoding at scale;

•significant resources saving as well as video quality improvements;

•programmable platform with a comprehensive suite of tools and APIs;

•support for various input/output formats including support for latency-critical applications;

•support for various quality of experience metrics.