A New Hybrid Approach to Video Organization for Content-Based Indexing

Video organization is a key step in the content-based indexing of video archives. The objective of video organization is to capture the semantic structure of a video in a form which is meaningful to the user. We present a hybrid approach to video organization which automatically processes video, creating a video table of contents (VTOC), while providing easy-to-use interfaces for verification, correction and augmentation of the automatically extracted video structure. Algorithms are developed to solve the subproblems of shot detection, shot grouping and VTOC generation without making very restrictive assumptions about the structure or content of the video. We use a nonstationary time series model of difference metrics for shot boundary detection, color and edge similarities for shot grouping and observations about the structure of a wide class of videos for the generation of the VTOC. The use of automatic processing in conjunction with input from the user allows us to produce meaningful video organization efficiently.