摘要 |
PROBLEM TO BE SOLVED: To provide a method and a system for efficiently dividing and classifying video. SOLUTION: This method for dividing, classifying and summarizing video on the basis of singular value decomposition represents the frame of an input video sequence with a vector composed of a connection histogram showing color space distribution in a video frame and maps the fame into a sophisticated feature space by singular value decomposition. Measurement reference for measuring information quantity included in each video shot of the input video sequence is used, and residual frames are made to be a cluster with the contents value of the most static video shot as a threshold. In the video dividing method, calculates the similarity between frames in the input video sequence in calculated on the basis of a distance between frames in the sophisticated feature space and video in devided on the basis of the value of similarity. Finally, in segment classification, a mean video attribute in each segment is used. |