The US Open is quickly becoming the high-tech star of the tennis world.
In addition to becoming the first sports tournament ever to sell Snapchat Spectacles on location, the New York-based tournament has teamed up with IBM to use Watson to identify exciting highlights and share them on social media.
IBM’s supercomputer combines artificial intelligence (AI) and analytical software and is being used to wade through the “mountains” of video footage produced during the two-week event, analyze it, and curate exciting match moments clips to be shared online.
“At the US Open, there are as many as 18 matches going on at one time,” IBM says in an Aug. 29 press release. “The video streams alone could fill a small data center. And it would take an army of USTA editorial staff to watch and select all of the most meaningful moments from this vast expanse of unstructured data.”
To solve this, Watson has learned to identify the points and shots in a match that are “highlight worthy” through cognitive algorithms. For example, the supercomputer can detect and recognize when a player celebrates with a fist pump through visuals as well as audio like high levels of crowd noise and cheering. It also takes into account vital statistics of the match, including game points, set points, and match points, to determine how critical a moment is to the outcome of the match.
“Once the individual highlights for the match are determined, the system uses meta-data to automatically generate the graphics and facilitate storytelling. These highlights will be shared on the US Open Official platforms like Facebook, Instagram and YouTube. And they will added to a player’s bio page on the app and website,” the press release adds.
IBM says this cognitive highlights functionality is part of its solution called Watson for Media, which includes photo tagging, transcription and translation services, as well as the ability to scan security footage, or observe patterns of behaviour in retail environments.