BBC R&D’s AI technical paper bags IBC Best Conference Paper Award
The technical paper focuses on how a prototype system, Ed, can be deployed in a production environment to create content with minimal crew
A technical paper produced by a BBC R&D team has been awarded the IBC Best Conference Paper Award.
Entitled AI in production: Video analysis and machine learning for expanded live events coverage, the paper covers a range of skills, including a project known as Ed. Under project lead Mike Evans, Ed is a prototype system that can be used to create near-live content with minimal crew. An example might be a set of three unmanned 4K/Ultra HD (UHD) cameras, from which Ed would produce a number of “properly framed” HD pictures, cutting between them as appropriate.
Evans stressed that Ed allows coverage of more events, and reaches places where operators are unable to reach. He explained: “With conventional production, we cover only about six of the nearly 100 places music is performed at the Glastonbury Festival, for example, or just a tiny fraction of the 50,000 performances in 300 venues at the Edinburgh Fringe.
“But with Ed, we can reach many more of these and do so with production techniques that are much less intrusive for the event itself.”
The paper will be presented at midday on September 16 as part of a new initiative at IBC2018, Tech Talks, which aims to ensure that important technical papers remain an integral part of IBC and its conference by bringing the latest ideas to all delegates.
Dr Paul Entwistle, chair of the IBC Technical Papers Committee, concluded: “The team has developed an artificial intelligence system that understands the rhythms and cadences that make for professional video production. This was validation by research to see how Ed performs compared with a real director, and how the audience perceived the viewing experience.”