Long transition analysis for digital video sequences

Video indexing is a technique used to extract objects within a video sequen ce and index them so that they can be used for future retrieval. In many vi deo sequences, special effects such as fade and wipe are incorporated, and in some cases, it is desirable to be able to include objects within such ef fects for indexing. In this paper, we introduce an automatic process that d etermines the type of transition and extracts information from it, so that this information can be used in object extraction. Such a process consists of four stages: shot boundary refinement, shot type determination, frame re construction for soft transitions, and shot classification for hard transit ions. In this paper, we will give the implementation, timing, and performan ce analysis for each stage. Long transition analysis bridges the gap betwee n shot boundary detection and object tracking and smoothes the process of a utomatic video indexing for video databases.