Abstract

Abstract—In this paper we present a method of abrupt cut detection with a novel logic of frames ’ comparison. Actual frame is compared with its motion estimated prediction instead of comparison with successive frame. Four different similarity metrics were employed to estimate the resemblance of compared frames. Obtained results were evaluated by standard used measures of test accuracy and compared with existing approach. Based on the results, we claim the proposed method is more effective and Pearson correlation coefficient obtained the best results among chosen similarity metrics. Keywords—Abrupt cut, mutual information, shot cut detection, Pearson correlation coefficient. P I.

Citations