Research on Sports Video Analysis Based on Rules

Motivated by principles of natural language processing, we talk about rule-based methods for sports video analysis and propose a video parsing system by using grammar. Firstly, we segments video into elementary shots. Then through event detection, shots are annotated with semantic labels to form a token sequence. Finally, the sequence is parsed and validated with grammar to construct a table of content for the video. Different from other systems in the literature, our system is not only able to annotate semantic events, but also able to recognize hierarchical game structures of sports videos. Thus, it satisfies user’s requirements better .