一种基于支持向量机的镜头边界检测算法  

An Algorithm of Video Shot Boundary Detection Based on SVM

作　　者：常虹[1] 张明[1] 

机构地区：[1]上海海事大学信息工程学院,上海201306

出　　处：《现代计算机（中旬刊）》2016年第7期73-77,共5页Modern Computer

摘　　要：以往镜头边界检测对阈值的依赖性很大,提出一种基于支持向量机的镜头边界检测算法来避免对镜头检测阈值的依赖。该算法利用SVM对视频数据进行分析和处理,把从视频像素帧中提取的特征数据作为支持向量机的输入数据,从而把镜头边界检测问题转化成分类问题。有效地将镜头边界检测跟机器学习的方法结合起来,实验表明这种方法对镜头边界检测的切变检测有很好的检测效果。Proposes an improved shot boundary detection algorithm based on Support Vector Machine, which is not dependent on the threshold. The algorithm makes use of SVM to analyze and process the video data, the feature extracted from the video frame is used as the input data of SVM, thus, the shot boundary detection problem is transformed into a classification problem. The shot boundary detection and machine learning effective combination, experimental results show that this method has a good effect on the mutation detection of shot boundary detection.

关 键 词：视频检索 镜头边界检测 支持向量机 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]