APPARATUS AND METHOD FOR EXTRACTING STORY-BASED SCENE OF VIDEO CONTENTS

摘要

Disclosed is an apparatus and method for extracting a scene based on a story of moving picture content, and a method for extracting a scene based on a story for inputting a video sequence according to an embodiment of the present disclosure includes: (a) based on similarity between adjacent frames of an input video sequence. Detecting one or more scene change frames, dividing the video sequence into a plurality of shots based on the one or more scene change frames, (b) determining key frames and attributes of each of the plurality of shots, (c ) If the similarity between two of the plurality of shots is measured and it is determined that they are similar to each other, generating a merged scene by merging all the shots from any one of the two shots determined to be similar to each other, and (d) determining a key frame and property of each of the merged scenes.