Semantic Segmentation and Event Detection in Sports Video using Rule Based Approach

The paper addresses two main problems of sports video processing: semantic segmentation and event detection. The theme is domain specific approach which exploits the typical characteristics of cricket video to design the most effective approach for the semantic segmentation and event detection which supports, efficient and effective retrieval of video scenes. Cricket video has been selected as the primary application, because they attract viewer worldwide and the complexity of the game is high. This paper proposes a novel hybrid multilayered approach for semantic segmentation of cricket video and major cricket events detection. The approach uses low level features and high level semantics with the rule based approach. The top layer uses the DLER tool to extract and recognize the super imposed text and the bottom layer applies the game rules to detect the boundaries of the video segments and major cricket events. The proposed model has been implemented, tested and the results are promising. Future work has been discussed at the end.