Integrated framework for shot boundary detection with multilevel features similarity

This paper describes an integrated framework for the detection of shot boundaries with multilevel features. Three kinds of features are extracted: low-level features of frame-to-frame difference, temporal-level features and high-level features with video-context sensitivity. Major advantages of the proposed framework are its accuracy and robustness. The information from shot transitions tagging also has great help to the content-based video processing. The experimental results demonstrate the new method improves the detection performance of hard cuts and gradual transitions well in terms of precision and recall values.