基于音视频特征和文字信息自动分段新闻故事

News Story Automatic Segmentation Based on Audio-visual Features and Text Information

提出了一种新的基于音视频特征和文字信息自动分段新闻故事的方法。其基本思想是先对新闻视频进行镜头边界检测;其次,通过文字检测算法检测包含有主题字幕文本的帧来获得新闻故事分段的线索;接着用短时能量和短时平均过零率(ZCR)来检测新闻视频中存在的静音片段;最后,综合音视频特征和文字信息实现故事自动分段。在包含135,400帧的实验素材上获得了85.8%的准确率和97.5%的查全率,实验结果证明该方法是十分有效的。

A novel news story automatic segmentation scheme based on audio-visual features and text information is presented. The basic idea is to detect the shot boundaries first for news video, and then frames containing topic caption texts are identified to get news story segmentation cues using text detection algorithm. In the next step, silence clips in news video are detected using short-time energy and short-time average zero-crossing rate parameters. At last, audio-visual features and text information are integrated to realize automatic story segmentation. On test data with 135,400 frames, the accuracy rate 85.8% and the recall rate 97.5% are obtained. The experimental results show the approach is valid and robust.