一种基于镜头聚类的视频场景分割方法

A Shot Clustering Based Approach for Scene Segmentation

为了更好地进行视频信息检索和浏览,提出了一种利用视觉和运动特征来进行场景分割的方法,该方法在把镜头聚类到场景中时,不仅考虑同一场景内镜头的视觉特征相似性,而且还考虑了镜头的运动特征的一致性。此外,为避免过度分割,还提出了一种方法用来合并过度分割出的场景。实验结果表明,这种方法是有效的。

In this paper, a scene segmentation method utilizing both visual and motion features is presented. Not only the visual similarity but also the motion consistency of shots within a scene is considered in clustering shots into scenes. In addition, we present a method to merge the over-segmented scenes. Experimental results show the effectiveness of our algorithm.