Object-based video abstraction for video surveillance systems

ased Video Abstraction for Video Surveillance Systems Changick Kim, Member, IEEE, and Jenq-Neng Hwang, Fellow, IEEE Key frames are the subset of still images which best t the content of a video sequence in an abstracted manner. words, video abstraction transforms an entire video clip to a small number of representative images. In this paper, we present a scheme for object-based video abstraction facilitated by an efficient video-object segmentation (VOS) system. In such a framework, the concept of a "key frame" is replaced by that of a "key video-object plane (VOP)." In order to achieve an online objectbased framework such as object-based video surveillance system, it becomes essential that semantically meaningful video objects are directly accessed from video sequences. Moreover, the extraction of key VOPs needs to be automated and context dependent so that they maintain the important contents of the video while remove all redundancies. Once a VOP is extracted, the...

• Type: Journal
• Year: 2002
• Where: TCSV
• Authors: Changick Kim, Jenq-Neng Hwang
• Keywords: TCSV 2002, Video, Video Abstraction, Video Surveillance