CONTENT-BASED SUMMARIZATION OF FOREIGN LANGUAGE LEARNING VIDEO USING MULTIPLE MPEG-7 VISUAL FEATURES

摘要

The requirement of automatic video summarization is increasing as many broadcasting contents and various user requests and preferences for the bi-directional broadcast environment are spreading. Automatic video summarization is needed for an efficient management and usage of many contents in service provider as well. We proposed a method to generate a content-based summary of foreign language learning videos and to service it using retrieval application. First, shot-boundaries and key frames are generated from a video and then multiple visual features are extracted. Next, the semantic parts (Explanation part, Dialog part, Text-based part) of the foreign language learning video are generated using extracted visual features. Lastly the XML document describing summary information is made based on the hierarchical summary architecture of MPEG-7 MDS (Multimedia Description Scheme) Experimental results show that our proposed algorithm provides reasonable performance for automatic summarization of foreign language learning video. We verified that the proposed method is useful for video summary or highlighting service, shot retrieval service, VOD (video on demand) and so on.