An Integrated Scheme for Object-based Video Abstraction

摘要

In this paper, we present a novel scheme for object-based key-frame extraction facilitated by an efficient video object segementation system. Key-frames are the subset of still images which best represent the content of a video dequence in an abstracted manner. Thus, key-frame based video abstraction transforms an entire video clip to a small number of representative images. The cahllenge is that hte extraction of key-frames needs to be automated and context dependent so that they mainain the improtant contents of the video while remove all redundancy.