A Study of Video Scenes Clustering Based on Shot Key Frames

0IntroductionRgecreonwtlinyg ,itnhcer aeapspienagrlayn.ceI nan tdh eus per oofce mssuilntig m oefdi aal lh akviend bsee onfmedia ,that of video dataisthe most challengingtask,for vid-eo dataincludes other kinds of media data.Itis difficult to an-alyze, browse and retrieve video data stream due to theirlengths and non-structure characteristics .Inthe past ,the study of video datafocus onthe shots de-tection and videoretrieve based onshot .Butin most video da-ta,the content granularity of shot …

A study of video scenes clustering based on shot key frames

In digital video analysis, browse, retrieval and query, shot is incapable of meeting needs. Scene is a cluster of a series of shots, which partially meets above demands. In this paper, an algorithm of video scenes clustering based on shot key frame sets is proposed. We use X^2 histogram match and twin histogram comparison for shot detection. A method is presented for key frame set extraction based on distance of non adjacent frames, further more, the minimum distance of key frame sets as distance of shots is computed, eventually scenes are clustered according to the distance of shots. Experiments of this algorithm show satisfactory performance in cor rectness and computing speed.