Amazon updates its video segment detection software


Amazon today announced new features for its Rekognition Video Segment Detection API which uses machine learning to enable VOD providers to automatically detect precise end-of-frame credits, black frame segments, plane changes and color bars. The update now includes support for four new types of segments: opening credits, content segments, slates, and studio logos. It also improves the accuracy of the detection of credits and shots and new filters to control the detection of black images.

Introduced a year ago, Rekognition Video Segment Detection gives VOD providers the ability to automate media analysis tasks, especially the detection of black frames, end credits, shot changes, and color bars, using fully managed, ML-based APIs. Amazon claims that Rekognition’s video segment detection capability can help reduce review time from hours to minutes, reduce manual operations costs up to 5 times, and prepare archived content for VOD in a short delay.

For new features, Rekognition automatically detects the opening and closing frames of movie or TV show credits and identifies the start and end of “slates,” which are sections that appear at the start of videos, and include text metadata about episode, studio, video format, audio channels. This makes it easier for operators to use metadata for analysis or to remove slates when preparing for streaming services.

The update also allows operators to now be able to identify and review the logos of production studios that appear at the start of on-demand content as well as identify the start and end of content segments. to review for execution and customize content in different languages ​​for international markets. .

More information is available on the Amazon blog.


Comments are closed.