An Efficient and Accurate Shot Boundary Detection Technique Based on Colour Moments

In this paper, a shot boundary detection method based on primitives of colour moments is proposed. The YIQ colour model is used in this paper. Here we compute the colour moments of different order for each frame of the video. The feature vector is formed from the moments and compared between successive frames. The dissimilarity measure higher than a predefined threshold indicates the presence of a shot cut. Experiments have been conducted on the standard TRECVID video database to evaluate the performance of the proposed method.