基于时空切片的新闻主播检测算法

News Anchorperson Detection Algorithm Based on Spatio-Temporal Slice

为实现海量新闻视频的有效索引和检索,提出了一种基于时空切片(spatio-temprol slice,STS)特性的新闻主播检测方法.通过对时空切片的模式分析,聚类和信息融合,实现了新闻主播镜头的自动检测.该方法完全通过对新闻视频结构的分析,利用其共有的特性,对不同的新闻视频实现主播镜头自适应检测.大规模实验证明了该算法准确性高,鲁棒性强且计算复杂度低.

To realize the convenient index and retrieval for vast amount of news videos, a novel anchorperson detection algorithm based on spatio-temporal slice （STS） was presented. Anchorperson shots were detected automatically for browsing news video with STS pattern analysis, clustering and information fusion. The innovation of the algorithm is that it can fulfill the adaptive detection of anchorperson by analyzing the structure of news video without depending on the special models or prior knowledge. The large-scale experimental results demonstrate that the algorithm is accurate, robust and effective.