Method and System for Detecting Audio and Video Scene Changes

In this invention we introduce a method and system for segmenting both a video
sequence and an accompanying audio sequence into respective video and
audio scenes. To allow for ready integration of the audio and video scene
segmentation information the concept of an audio shot is introduced
corresponding to readily identifiable video shots. By synchronising the audio
stream with the video stream on the basis of corresponding audio shots and
video shots the integration of respective determined audio and video semantic
scene information (a scene comprising one or more shots) becomes relatively
straightforward, thus giving richer semantic understanding of the content. Moreover the fusion of audio and visual analysis results through heuristic rules also provides further advantages. The industrial applicability of the invention is in the field of automating the time­ consuming and laborious process of organising and indexing increasingly large video databases such that they can be easily browsed and searched using natural query structures that are close to human concepts.