SMART: A grammar - based semantic video modeling and representation

Multimedia database modeling and representation is significant for efficient storage and retrieval of multimedia. Modeling of semantic video content that enables spatiotemporal queries is one of the challenging tasks. In this paper, we provide a semantic modeling and retrieval system, termed as SMART. We provide a method that helps represent the semantic contents of video such as objects, events, and locations as a grammar based string. This linear string representation enables both the spatial and temporal description of the video. Various types of queries such as event-object-location, event-location, object-location, and event-object are supported by SMART. We show our results on the tennis video database.