Sky News brings machine learning to identify Royal Wedding guests

Facial recognition and data analytics tools from Amazon Web Services (AWS) and its technology partners will provide names and information of Royal Wedding attendees
Ahead of the Royal Wedding of Prince Harry and Meghan Markle on May 19, Sky News, a UK-based multimedia news organisation, will be deploying cloud-based machine learning and media services to name guests as they enter the chapel, enriching the video content with facts about the attendees.
Accessible in the Sky News app or via the Sky News’ website, the Royal Wedding: Who’s Who Live functionality employs machine learning to enhance the user experience of a live-streamed news event. The additional information associated with the live video will go beyond subtitles to provide relevant facts about the guests.
To enable and deliver this experience, Sky News will be collaborating with Amazon Web Services (AWS) and two AWS technology partners — GrayMeta and UI Centric. As guests make their way into St George Chapel, Windsor, the live video captured will be sent to cloud-based AWS Elemental Media Services for multi-screen viewing optimisation. An on-demand video asset, including catch-up functionality, will also be generated.
In parallel, Sky will be combining the GrayMeta data analytics platform with the Amazon Rekognition video and image analysis service for identification of guests and tagging with related information.
Furthermore, Sky News will utilise the Amazon CloudFront content delivery network to unify the content for rapid distribution to viewers. UI Centric has designed and developed the application and video player to enhance the experience and user interface accessed by Sky News viewers.
David Gibbs, director of digital news and sports products, explained: “This new functionality allows Royal Wedding viewers greater insights into one of the biggest live events of the year, wherever they are. We’re excited by the software’s potential and ability to give audiences new ways of consuming content.”