Your browser is out-of-date!

Update your browser to view this website correctly. Update my browser now


Amazon adds new media analysis features to Rekognition Video

Allow users to execute workflows such as content preparation and ad insertion, and add ‘binge-markers’ to content at scale in the Cloud

Amazon has added new features to its machine-learning powered video analysis service Video Rekognition which enable users to automate detection of black frames, end credits, shot changes, and colour bars.

According to Amazon, the features enable users to execute workflows such as content preparation, ad insertion, and add ‘binge-markers’ to content at scale in the Cloud.

Users will also be able to automate the detection of empty black frames with no audio to demarcate ad insertion slots or end of a scene. The service can also identify exact frames in VoD content to prompt ‘Next Episode’ messages to viewers.

Amazon Rekognition Video can also detect shot changes, when a scene cuts from one camera to another. Using this information, editors can create promotional videos using selected shots, generate high-quality preview thumbnails by choosing key frames in shots, and insert ads without disrupting viewer experience.

Another feature helps users detect sections of video that display SMPTE colour bars, to remove them from VoD content, or to detect issues such as loss of broadcast signals in a recording, when colour bars may be shown continuously as the default signal.

The company said the new APIs can easily analyse large volumes of videos stored in Amazon S3 and give users SMPTE timecodes and timestamps for each detection – without requiring any machine learning experience.