Semantic event detection in sports through motion understanding

In this paper we investigate the retrieval of semantic events that occur in broadcast sports footage. We do so by considering the spatio-temporal behaviour of an object in the footage as being the embodiment of a particular semantic event. Broadcast snooker footage is used as an example of the sports footage for the purpose of this research. The system parses the sports video using the geometry of the content in view and classifies the footage as a particular view type. A colour based particle filter is then employed to robustly track the snooker balls, in the appropriate view, to evoke the semantics of the event. Over the duration of a player shot, the position of the white ball on the snooker table is used to model the high level semantic structure occurring in the footage. Upon collision of the white ball with another coloured ball, a separate track is instantiated allowing for the detection of pots and fouls, providing additional clues to the event in progress.