Automatic Generation of Movie Trailers using Ontologies

With the advances in digital audio and video analysis, automatic movie summarization has become an important field of research. Much of the work has been put into movie abstracting for large media databases. Looking at the topic from a different side, the movie industry has long since perfected the art of summarization in their ad-vertising trailers to attract an audience. In this paper we introduce the approach of automatically generating enter-taining Hollywood-like trailers based on a trailer grammar, enhanced by an ontology. The extraction of features from movies using state-of-the-art image and audio processing techniques builds the foundation for the selection of meaningful and usable material, which is re-assembled according to the defined rules. User testing of our automatically produced trailers shows that they are well accepted and in many ways comparable to professionally composed trailers.