VIDEO EDITING DEVICE, VIDEO EDITING METHOD, AND VIDEO EDITING PROGRAM

摘要

PROBLEM TO BE SOLVED: To automatically generate edited video while taking into consideration context of video to be generated. SOLUTION: Video is divided into video sections (S202), the likelihood of each semantic content is given from the video feature of each video section and a likelihood model of a semantic content category dictionary (S204). The semantic likelihood is used to cluster the video sections (S205). A semantic change degree of the video is calculated from a connecting relationship as the video is calculated about a representative video section selected from each cluster (S206), a representative video section group to be used for edited video is selected from the semantic change degree of the entire candidate representative video sections (S207), and the edited video is generated (S209). COPYRIGHT: (C)2011,JPO&INPIT