Nippon Professional Baseball (NPB), the Japanese baseball league, is streamed by DAZN.
Their services help fans to stay connected to their favorite NPB players and teams with live and on-demand coverage of local matchups every day. Related to this broadcast, DAZN Sports Data team launched a new highlights feature for subscribers. They have learned technology from Amazon Web Services (AWS) and other brands. Specifically, this feature is using real-time match data from Stats Perform, Amazon Rekognition Custom Labels machine learning (ML), and video analysis technology.
This service is provided to DAZN subscribers, allowing them to take control over their own highlights experience. They can pull up and select a recorded or in-progress NPB game, load it, and use the scrub bar to navigate to critical highlight markers or to watch important plays.
DAZN worked with its colleagues in Japan to build an application to support this functionality. It first determines which plays the application would define as highlights, using available Stats Perform data. The team then had to sync this data with its live game streams and found machine learning the best way to do so.
Whereas football plays can be mapped to a clock, baseball isn’t timed the same way. The development team needed a way to automatically detect the start of a game. They chose to use the first appearance of the score graphic (including the number of balls, strikes and outs) – which coincides with the start of the first pitch – as the starting marker. With no off-the-shelf tool available to identify this graphic, they set out to build their own model using Amazon Rekognition Custom Labels. Then, they trained the application to detect the initial appearance of this graphic. From there, the team provided the system with a list of all the key moments and times they occur, and it synchronized them with the video based on the time of the game.