AI in Media Production

Helps Members move towards the understanding, adoption and use of Artificial Intelligence.

More than ever, metadata is indispensable for all production to distribution processes. As we move to service-based production, broadcasters need to consider the widespread adoption of automatic information extraction tools, incl. in the cloud, as new processes in agile workflows. These tools can be used to produce more information (including structured metadata) that is needed by modern production systems, at a lower cost. The EBU AME project is working on the identification of usage scenarios, i.e. how do EBU members use AME. Features to be extracted as part of AME tools capabilities are being registered as a set of AME cards to faciliate service registration and discoverability. Artificial intelligence techniques such as machine learning and deep learning or neuronal networks are behind most AME tools.

AME_ow_logo1-1.jpg

The topic of Automatic Metadata Extraction is part of the EBU's Strategic Programme on Production.

Main activities:

  • Helps Members move towards the adoption of automatic information extraction tools.
  • Identifies and evaluates tools investigating how they can help with e.g. archive management applications, multi-purpose / multi-channel productions and news production. A set of tools features is being published as AME cards (https://github.com/ebu/ame-cards).
  • A link to EBU members' use cases has been provided on the welcome page of the AME project.
  • Collects test material and ground truth material.
  • Develops recommendations such as the MPEG-7 AVDP guidelines.
  • The project group contributes to the AMWA-EBU FIMS project, which has published an AME service intetrface in its version 1.3 (https://github.com/fims-tv/fims).

Related topics