A Semi-Automatic Soccer Video Annotation System based on Ontology Paradigm

Currently, the video annotation process becomes a very necessary task to overcome the problem of finding the adequate information on a huge database. To achieve this, it will be necessary to translate low level analysis results to a semantic meaning related to the video sequence, generally known as problem of semantic gap. Many researchers have worked on this issue in the aim to find new solutions, where the ontology paradigm is represented as one of them. In this paper, we consider this problem by developing a soccer ontology, that is used in our OSAS annotation system (Ontology Soccer Annotation System). This one is based on a set of Semantic Web Rule Language (SWRL) rules that bridges the semantic gap problem. Our idea show new directions and perspectives for future developments.