Content-based representative frame extraction for digital video

被引：15

作者：

Sun, XD ^{[1
]}

Kankanhalli, MS ^{[1
]}

Zhu, YW ^{[1
]}

Wu, JK ^{[1
]}

机构：

[1] RWC Novel Funct ISS Lab, Kent Ridge Digital Lab, Singapore 119597, Singapore

来源：

IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA COMPUTING AND SYSTEMS, PROCEEDINGS | 1998年

关键词：

D O I：

10.1109/MMCS.1998.693638

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, we purpose a content-based adaptive clustering algorithm(CBAC) to extract a fixed predetermined number of representative frames to summarize a given digital video. In our algorithm, shot boundary detection is not needed. The inter-frame changes are compared globally for the extraction of representative frames. Small units of the video are dynamically clustered into two clusters based on the amount of change in content within the unit. One cluster. which has units of low content change, is designated for deletion and the other cluster, which has units of high content change, is for retention. The algorithm adaptively converges to the desired number of frames by deleting some redundant frames from each unit of the deletion cluster during every iteration.

引用

页码：190 / 193

页数：2