This paper illustrates an approach to semantic video annotation in the specific context of sports videos.
Videos are automatically annotated according to elements of visual content at different layers of semantic significance.
Unlike previous approaches, videos can include several different sports and can also be interleaved with non sport shots.
Each shot is decomposed into its visual and graphic content elements, including foreground and background, objects, text captions, etc.
Several different low-level visual primitives are combined together by domain-specific rules in order to capture semantic content at a higher level of significance.
Results of experiments on typical sports videos are presented and discussed.