一种监控视频分段的方法  

An Algorithm of Surveillance Video Segmentation

作　　者：高清芬[1] 

机构地区：[1]衡水学院数学与计算机科学系,河北衡水053000

出　　处：《衡水学院学报》2008年第4期24-27,共4页Journal of Hengshui University

摘　　要：本文提出了一种针对监控视频序列的分段算法.即通过计算输入视频帧与可更新背景帧的差异计算帧运动量,来实时更新背景,按当前帧与实时背景帧的差异进行聚类,然后按照每帧图像的类别对该视频序列进行分段,并提供了计算每帧图像时间的算法,从而可以确定各段视频的起止时间,该算法可以为后续的各种视频挖掘算法提供前期的视频数据处理,方便后续的视频数据分析.An algorithm of surveillance video segmentation is proposed. The first step is to put the difference between video frame and updatable background frame into computer to get the motions of the frame and change the background frame in time. Then video mining is segmented according to the difference between the current frame and the background frame, and video sequence is segmented according to the category. In such a way time algorithm for each frames is provided, and the start and end of the video segmentation is determined. This algorithm can provide video data processing for video mining algorithm, which facilitates the following video data analysis.

关 键 词：监控视频 运动量差异 分段 时间 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]