欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
新闻视频故事分割是新闻视频分析的重要底层支持技术，本文提出了一种融合音频、视频等多模态特征的新闻视频故事分割方法．首先分析音频特征的静音片段作为音频特征候选点，对视频进行镜头分割，并将镜头分割结果分类为播音员镜头和新闻报道镜头，将所有的镜头分割点和播音员镜头片段提取为视频片段候选点；然后通过对新闻视频编辑规则的研究，对视频、音频特征候选点融合分析来获取新闻视频的故事分割，实验表明该方法在不同新闻视频编辑规则下都具有较好的分割效率．
英文摘要：
News story segmentation is an important underlying technology for information analysis in news video. This paper presents a method for news video story segmentation, which fuse multi-modal features including audio and visual. At first, it selects silence clips as audio features candidate points and selects shot boundaries and anchor shots as visual features candidate points. Then this paper analyzes rules of video news edition and develops a method, which effectively fuses diverse modal candidate points, to get story boundaries. Experimentresults show that this method has high efficiency and adaptability to different kinds of news video.
同期刊论文项目
同项目期刊论文
期刊信息
位置：