Gradual transition detection based on fuzzy logic using visual attention model

Abstract

Shot boundary detection (SBD) is the process of automatically detecting the boundaries between shots in video. It is a problem which has attracted much attention since video became available in digital form as it is an essential pre-processing step to almost all video analysis, indexing, summarization, search, and other content based operations. The existing SBD algorithms are sensitive to video object motion and there are no reliable solutions to detect gradual transitions (GT). GT is difficult to detect because of the following reasons. First, GT include various special editing effects, including dissolve, wipe, Fade Out/In. Each effect results in a distinct temporal pattern over the continuity signal curve. Secondly, GT exhibit varying temporal duration and also the temporal patterns of GT are similar to those caused by object/camera movement, since both of them are essentially processes of gradual visual content variation. The proposed approach uses Fuzzy rule based system to detect the Gradual Transitions based on the features derived from visual attention model which detects the gradual transition better than the existing approaches.