Effective shot boundary classification using video spatial-temporal information

We propose in this paper a new video shot boundary classification (SBC) method. First we present a method to extract features, which exploits the spatial-temporal information of video frames in a sliding window centered at the detected shot boundary. Then feature projection and classification methods such as principal component analysis (PCA) and linear discriminant analysis (LDA) combined with k-nearest neighbor classification, and hierarchical discriminant regression (HDR) are proposed to classify different types of shot boundaries. Experimental results have shown the effectiveness of the proposed SBC method.