Abstract
Because of the large amount of rich visual video information, conventional video search techniques such as fast-forward/rewind are no longer sufficient. Users want to be able to browse and be selective in what they see as when accessing textual information. We propose a hierarchical meta data model to represent video information. This model consists of two separate hierarchies of meta data. The first hierarchy is a directed acyclic graph which compares the relationship between video segments at the semantic level. The second hierarchy is an object composition graph that holds objects representing meaningful content appearing in the video. We have developed a video meta data authoring and browsing system that uses video segmentation results and generates the aforementioned hierarchical meta data output in XML. The meta data output uses some terminologies from the current MPEG-7 draft.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call