More and more video is generated every day. While today m uch of this data is produced and stored in analog form, the tendency is to use the digital form. The digital form allows processing of the video data in order to generate appropriate data abstractions that enable content-based retrieval of video. In the future, video databases will be able to be searched with combined text and visual queries. Additionally, video clips will be retrieved from longer sequences in large databases on the

more »

... of the semantic video content. Ideally, the video will also be automatically annotated as a result of the machine interpretation of the semantic content o f t h e v i d e o . Rowe et al. 32] characterized the types of video queries a user may a s k and identi ed the following three types of metadata indexes that should be associated with the video data in order to satisfy a query: Bibliographic data. This category includes information about the video (e.g., title, abstract, subject, and genre) and the individuals involved in the video (e.g., producer, director, and cast). Structural data. Video and movies can be described by a hierarchy of movie, segment, scene, and shot where each entry in the hierarchy is composed of one or more ent r i e s a t a l o wer level (e.g., a segment is composed of a sequence of scenes and a scene is composed of a sequence of shots 9]). Content data. Users want to retrieve videos based on their content (audio