A content-based broadcasted sports video retrieval system using multiple modalities: SportBR

In this paper, an advanced content-based broadcasted sports video retrieval system, SportBR, is proposed. Its main features include event-based sports video browsing and keyword-based sports video retrieval. The paper first defines the framework of our system, and then introduces a novel approach that integrates multimodal analysis, such as visual streams analysis, speech recognition, speech signal processing and text extraction to realize event-based video clips selection. The experimental results for sports video of world cup football games indicate that multimodal analysis is effective. The system is proved to be helpful and effective for understanding the sports video content.