Video summarization using R-sequences

In this paper, we propose a new method of temporal summarization of digital video. First, we address the problem of extracting a fixed number of repre sentative frames to summarize a given digital video. To solve it, we have d evised an algorithm called content-based adaptive clustering (CBAC). In our algorithm; shot boundary detection is not needed. Video frames are treated as points in the multi-dimensional feature space corresponding to a low-le vel feature such as color, motion, shape and texture. The changes of their distances are compared globally for extraction of representative frames. Se cond, we address how to use the representative frames to comprise represent ative sequences (R-Sequence) which can be used for temporal summarization o f video. A video player based on our devised algorithm is developed which h as functions of content-based browsing and content-based video summary. Exp eriments are also shown in the paper. (C) 2000 Academic Press.