陕西科技大学学报（自然科学版）Issue(1)：159-163,5.
一种基于分层 AP 的视频关键帧提取方法研究
Research on video key-frame extraction based on hierarchical affinity propagation clustering
摘要
Abstract
In order to extract key frames from large‐scale different videos more effectively and accurately ,since traditional AP algorithm is inappropriate to the large‐scale pictures cluste‐ring ,a hierarchical AP method for key frame extraction is proposed .First get the color and texture features of all video sequences ,the pictures set is divided into several subsets ,the tra‐ditional AP is used to obtain the exemplars of each subset ;Then the adaptive AP is imple‐mented on the obtained exemplars ,the key frames of video sequences are extracted according to the index of Silhouette for the best clustering result .The experimental result shows that proposed method is efficient in key‐frame extraction and suitable for all types video re‐sources ,has a high fidelity w hile the compression ratio is improved greatly .关键词
视频检索/关键帧/AP/层次划分/聚类Key words
video retrieval/key-frame/AP/hierarchical division/clustering分类
信息技术与安全科学引用本文复制引用
党宏社,白梅..一种基于分层 AP 的视频关键帧提取方法研究[J].陕西科技大学学报（自然科学版）,2016,(1):159-163,5.基金项目
陕西省科技厅科技攻关计划项目 （）
