AUTOMATIC PARSING OF AMERICAN FOOTBALL VIDEOS BY INTERMODAL COLLABORATION BASED ON TRANSITION RULES (WedPmPO1)

Author(s) : Naoko Nitta (Osaka University, Japan) Noboru Babaguchi (Osaka University, Japan)

Abstract : This paper proposes an automatic American football video parsing method based on transition rules of an American football game. Combining the results of live scene extraction and superimposed text detection based on template matching with image color features enables us to segment the video into play units of a game. Temporally associating the segmented play units with the detected superimposed texts and the closed-caption texts assigns possible semantic content information to the play units. Finallly, selecting only the play units which comform to transition rules of sport games from the play unit sequence with possible semantic content, while discarding or complementing unnecessary or insufficient information for play units, realizes the semantic video parsing.

Menu