A dynamic key frame extraction based on a multi-feature descriptor
首发时间:2012-01-06
Abstract:Key frame extraction is one of the basic procedures in video retrieval. Key frame extraction aims at finding a small collection of image frame sequences extracted from a video sequence in order to reduce the amount of data that must be examined. Efficient key frame extraction techniques will facilitate the video browsing systems, which have wide applications in real world. In this paper, we proposed an innovative approach to the selection of key frames of a video sequence. First, two descriptors of color and edge features are used to describe visual content, and are integrated as a muti-feature descriptor, then we analyze the differences between two consecutive frames of a video sequence. Finally, key frames are extracted by the dynamic threshold algorithm. Experimental results show that the proposed algorithm can dynamically and rapidly select a variable number of key frames within each sequence and can achieve high compression ratio and high fidelity.
keywords: video retrieval color and edge features dynamic threshold algorithm
点击查看论文中文信息
基于多特征的动态关键帧提取
摘要:关键帧提取是视频检索中一个基本的环节。进行关键帧提取的主要目的是从一个视频序列中提取出一部分能够图像帧序列,来降低对视频处理时所需要的数据量。有效的关键帧提取方法使得视频检索系统更加方便,也在真实世界中获得了广泛的应用。本文提出了一个新颖的动态提取关键帧的算法。首先,选用两个算子来描述图片内容,并结合起来作为一种多特征度量方式,然后在视频序列中的相邻两帧之间计算帧间差,最后,使用动态阈值算法提取关键帧。实验结果表明所提出的算法能够早视频序列内动态、快速地提取一系列的关键帧,并且取得了较高的压缩率和保真度。
基金:
论文图表:
引用
No.****
同行评议
共计0人参与
勘误表
基于多特征的动态关键帧提取
评论
全部评论0/1000