Video shot segmentation using fusion of SVD and mutual information features

A new method for detecting shot boundaries in video sequences by fusing features obtained by singular value decomposition (SVD) and mutual information (MI) is proposed. The first method relies on performing singular value decomposition on a matrix created from 3D color histograms of single frames. The method can detect cuts and gradual transitions, such as dissolves, fades and wipes. The second method relies on evaluating mutual information between two consecutive frames. It can detect abrupt cuts, fade-ins and fade-outs with very high accuracy. A combination of features derived from these methods and subsequent processing through a clustering procedure results in very efficient detection of abrupt cuts and gradual transitions, as demonstrated by experiments on the TRECVID2004 video test set containing different types of shots with significant object and camera motion inside the shots.