Pilot Prototype Analysis: Ongoing Framework for Semantic Extraction Retrieval in Tennis Sports Video

Producing large amounts of digital media data every day requires fast transmission, efficient storage, flexible manipulation, and reuse of visual content. Since humans tend to use high-level semantic concepts when querying and browsing multimedia databases, there is an increasing need for semantic video indexing and analysis. For this purpose, we proposed a unified framework for semantic extraction retrieval with motion vector analysis and color tracking model in sports video and also focus on clustering by aggregating shots or key-frames with similar low-level features, the proposed scheme employs supervised learning to perform a top-down video shot classification. This paper also focuses on the integration of multimodal features for sport video structure analysis. In this paper stochastic modeling and hidden Markov models (HMMs) that can be efficiently applied to merge audio and visual cues. Currently our approach is validated in the particular domain of tennis videos. For initial analysis we undergone a pilot prototype study with existing works and added up proposed methods, based on results achieved we further need to enhanced the framework. We are now in the stage of analyzing and formulating the problem solution for implementation in Matlab.