A framework for video scene boundary detection

Abstract

Most current video retrieval systems use shot as the basis for information organization and access. In cinematography, scene is the basic story unit that the directors use to convey their ideas. This paper proposes a framework based on the concept of continuity to analyze video contents and extract scene boundaries. Starting from a set of shots, the framework successively applies the concept of visual, position, cameral focal distance, motion, audio and semantic continuity to group shots that exhibit some form of continuity into scenes. The idea is tested using the first three levels of continuity to extract the scenes defined using most common cinematic rules. The method has been found to be effective.