Modeling Dynamic Objects in Video Databases: A Logic Based Approach

摘要

In this work we propose a state-based approach to model video data so that the semantics of the video is specified by the properties (static and dynamic) of the objects present in the video. The object dynamics is captured by the states and state transitions. The video database is then segmented and indexed based on these information. Finally, examples have been given to show how state-based queries can be used to retrieve information from the video database.