It can now identify four new segments

End credits

Amazon Rekognition video segment detection has added support for four new segments, opening and end credits, slates, studio logos, and content.

Launched last year, Rekognition uses machine learning to automatically detect frame accurate end credits, black frame segments, shot changes, and color bars in video files.

This allows media supply chain teams ot streamline content preparation and quality control tasks for VOD applications, such as adding markers like ‘Next Episode’ and ‘Skip Intro’, detecting pre-inserted ad break markers indicated by silent black frames, and removing unwanted sections such as slates and color bars.

For the four new segments that it can now detect, opening and end credits aims to streamline generation of ’binge markers’, and slates - which contain text metadata about the episode, studio, video format, audio channels, and more - aims to assist removing or reading them more easily.

Meanwhile, detection of studio logos allows users to identify studios, and content means that operators can identify program or related elements such as recaps and post-credits scenes.

Further information and how to use the application with the likes of BlackMagic Davinci Resolve or Adobe Premiere Pro can be found here.

Topics