Multimodal Based Highlight Detection in Broadcast Soccer Video

In this paper, we propose an effective fusion scheme of audio and visual modals for highlight detection in broadcast soccer videos. The Adaboost learning is adopted to learn some discriminating audio features for some special audio classification. The logo-based replay shot detection is used for mid-level visual semantic analysis. A finite state machine is utilized to integrate the audio and visual analysis result for further highlight detection. Experiments conducted on several real-world soccer game videos show that the proposed method has an encouraging performance.