SHOT BOUNDARY DETECTION BASED ON CO-OCCURRENCE MATRICES

摘要

The present invention envisages a system and a method for shot boundary detection, particularly for hard cut detection. This invention proposes a three-tier approach for hard cuts. In the first tier there is sought a sliding- window consisting of three consecutive frames, where the third one is the pivotal frame. In the second tier is computed their intermediate differences and the RGB co-occurrence matrices at different pixel distances for the frame-differences are calculated. And finally in the third tier a set of texture features are extracted from these RGB co-occurrence matrices corresponding to the frame differences in order to identify the shot-frames and non-shot frames and K-means clustering are used to classify them.