Automatic extraction of useful shot sections for a video editing support system based on video grammar

Abstract

Video editing is used to produce a final version with a specific duration by finding and selecting appropriate shots from the raw video material and connecting them. Video editing process is generally conducted according to the special rules called "video grammar" in order to produce excellent and intelligible videos for broadcasting. However, this editing consumes a lot of human editor's working time. To solve this problem, an efficient and new video editing technique or system is required. The goal of this study is to develop an intelligent support system for video editing based on video grammar. This paper proposas a method of using camerawork density, camerawork instability, and cut point parameters to automatically segment the raw video materials into useful sections and useless sections. The method is based on video grammar as a part of the video editing support system.