Live-Ticker Supported Sports-Video Annotation Enabling Tactic Analysis
Résumé
Automatic semantic annotation of videos remains an open
research problem. In the domain of soccer matches, live tickers are freely
available on the Internet. These tickers can be used as sources of information
about the events of a soccer match: as they are written by humans,
they contain semantic information. This work presents a prototype that
processes live ticker texts and transforms them into machine-readable annotations.
The prototype produces semantic annotated actions as RDFgraphs.
The resulting annotation may be used for other purposes, such
as tactical analysis of the match, semantic multimedia query processing
or assistance to other video annotation tools.