A New Scene Breakpoint Detection Algorithm Using Slice of Video Stream

Automatic scene breakpoint detection is the first step and also an important step for content-based parsing and indexing of video data. Several methods have been introduced to address this problem, e.g. pixel-by-pixel comparisons and histogram comparisons. Each has some advantages, but all of them are slow because they need process the data of entire image frames. Furthermore, none of these methods fully utilize the spatio-temporal attribute of video stream. In this paper, we propose a new scene breakpoint detection algorithm, which is based on the 2-D vertical and horizontal slice images of video stream. In this way, we largely reduce the amount of data to be processed. Experimental results show that our method is effective in detecting abrupt scene breakpoints.