In the 20-year history of video compression for broadcast TV services, there has been a major codec standard created every decade. This began with the release of MPEG-2 in 1995, then came AVC in 2005, and recently HEVC in 2015. Each codec took many years to develop, with teams of engineers making consistent but slow improvements. Then after each standard issue, it would take more time to reach its full potential as more advances are made.
With the introduction of this new and disruptive technology, Artificial Intelligence (AI) is driving the next frontier of video compression enhancements with the promise of faster advancements. AI is being used to improve several key areas including consistent higher video quality (VQ) at any bit rate, higher density using less computing resources, and improving the quality of experiences (QoE). This can be accomplished with AI through Dynamic Encoding Style (DES), Dynamic Resolution Encoding (DRE), and Dynamic Frame rate Encoding (DFE).
This paper will present three examples of AI applied to video encoding to optimize broadcast and OTT content delivery through these methods and explore the operational and end-user benefits enabled by AI and machine learning. Additionally, it will provide measurement for the applications that are presented and address the possible future evolutions of AI for video compression.
Technical Depth of Presentation
Intermediate technical depth. Highlights technologies and explains the main concepts.
What Attendees will Benefit Most from this Presentation
Technical decision makers and executives
Take-Aways from this Presentation
This presentation is aimed at technical decision makers and executives in broadcast looking for the next evolution in video compression and what benefits it can bring to them and their end users.