Integrating Semantic Video Understanding and Knowledge Visualization for Large-Scale News Video Exploration

Authors: Hangzai Luo, Jianping Fan, Shin’ichi Satoh, Jing Yang, and William Ribarsky

In this paper, we have developed a novel framework to enable more effective visual analysis and exploration of large-scale news videos via knowledge visualization. A novel interestingness measurement for video news reports is proposed to enable security experts and general audiences to find news stories of interest at first glance and catch the valuable knowledge in large-scale video news databases. Keyframes, keywords and their relations are automatically extracted from news video clips and visually represented according to their interestingness measurement. Our experimental results have shown that

our techniques for intelligent news video analysis have the capacity to enable more effective visualization and exploration of large-scale news videos. Our visualization-based news video analysis and exploration system is very useful for security applications and for general audiences to quickly find the news stories of interest from large-scale news videos extracted from many channels.

UNCC Technical Report # CVC-UNCC-07-01