Abstract
According to the key technique of semantic-based video retrieval, the paper presents directly extracting I-frames in the compressed domain, and using the DC coefficient of I frame to establish the model of information system. Then the reduction of I Frame by the theory of attribute reduction based on RS, to produce A key frame that reflects the main content of the lens. Finally, the key frames ‘s DC coefficient has constructed the mathematical modeling, and has classified the shot according to the differences of frames. So the polymerization of I frames of similar lens, we could obtain the scenario summary.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have