一种新型的视频码流识别算法

随着流媒体技术的兴起,越来越多的人选择从网上获得视频点播、网络电视、远程会议、远程教育等服务.但同时网络上充斥着一些淫秽、非法等有害视频,对社会造成很大危害.现有的基于视频内容的离线检测方法需要解码数据包,且匹配算法复杂度高,不适于数据量庞大的流媒体服务器或网关做实时检测.为此,提出一种基于媒体业务流特征的视频匹配算法,对流媒体服务器的码流进行实时检测和过滤.采用被广泛应用的MP4码流作为测试对象,分析了算法中各个参数对于判定结果的影响.实验结果表明,所提算法简单易行,无论是在拒真率还是取伪率方面都取得较为满意的结果.

A New Video Identification Algorithm for Video Stream

Since the emergence of technology of streaming multi-media,it becomes prevalent to obtain services like VOD,live streaming,remote meeting and education from retwork.But some illegal and obscene videos are also available in network which will harm the society.Current methods for identifying the content of video need decode the frame and have high complexity,which is not suitable for real-time detection in places of mass data like gateway and multi-media server.In this paper,a video identification method based on traffic characteristic is presented to detect the media stream from media server in real-time.The prevalent MP4 format media stream is examined using the proposed algorithm and the influence of different parameters in the algorithm on the result is analyzed.The experimental result shows that the method is easy to implement and has a relative satisfactory result in both false positive and false negative in video identification.