Content-based scene segmentation scheme for efficient multimedia information retrieval

While current approaches for segmenting or classifying audiovisual data are mostly focused on visual information, audio information can also play an important role in the content parsing for many applications. In this paper, we address the problem of parsing audiovisual data for content-based multimedia information retrieval, and propose a novel scheme for determining video scenes by analysing both audio and video data. In this scheme, audio segments are automatically classified into six categories based on acoustic features. To show its effectiveness, we have implemented a prototype system and performed several preliminary experiments. We report some of the results.