A new cloud service by IBM aims to help companies extract metadata from raw video footage, the company said today. The new tool uses the artificial intelligence (AI) capabilities from IBM?EU?s Watson platform to analyze video for information such as keywords, main concepts, visual imagery, tone, and emotional context.
“The service highlights IBM’s continued focus on combining artificial intelligence with the IBM Cloud to help media and entertainment companies make sense of unstructured data and make more informed decisions about the content they create, acquire and deliver to viewers,” the company said. Although the new service does not yet have a name, the company said it is planning to launch sometime later this year.
The new platform will use several of Watson’s existing APIs, such as tone analyzer, personality insights, natural language understanding, and visual recognition. In addition, IBM said the platform will include new technology from IBM Research that can analyze data produced by Watson to split videos into discrete scenes based on cues in the content.
As an example, IBM said a sports network could use the service to identify content that is related to basketball and contains positive or exciting scenes based on the language, images, and sentiment included in the video. The platform would allow the network to automate the process of identifying each segment and editing them together, allowing for much faster turnaround.
Advertisers could also use the platform to analyze several years of content from a television show, enabling them to generate and cut together a collection of clips focused on particular themes such as footage of the characters driving in a car or sitting around the kitchen table.
Media and entertainment companies could use the platform to help manage their content libraries. For example, a company might…