Semantic Annotation of Sports Videos

ion when we annotate content. This therefore requires us to investigate and model video semantics. Because of the type and volume of data, general-purpose approaches are likely to fail since semantics inherently depend on a specific application context. Many researchers have addressed semantic modeling of content in multimedia databases. Researchers have also reported on concrete video retrieval applications by high-level semantics in specific contexts such as movies, news, and commercials.2,3 Due to their enormous commercial appeal, sports videos represent an important application domain. However, most research efforts so far have been devoted to characterizing single, specific sports. (For example, Miyamori and Iisaku4 proposed a method for annotating videos according to human behavior; Ariki and Sygiyama5 proposed a method for classifying TV sports news videos using discrete cosine transform [DCT] features; and Zhou et al.6 classified nine basketball events using color features, edg...

• Type: Journal
• Year: 2002
• Where: IEEEMM
• Authors: Jürgen Assfalg, Marco Bertini, Carlo Colombo, Alberto Del Bimbo
• Keywords: IEEEMM 2002, Semantic, Sports, Sports Videos