一种快速有效的海量视频拷贝检测方法

An Efficient Fast Copy Detection Method for Large-scale Video

随着网络上视频拷贝的不断增多,快速有效的视频拷贝检测方法变得越来越重要.针对大规模的视频数据库,提出一种快速有效的视频拷贝检测方法.该方法首先利用视频帧内的频域空间信息与帧间的序列时间信息,将每个视频表示为基于离散余弦变换的时空特征并建立鲁棒的压缩二值SimHash签名;然后对视频数据库中的每个视频的SimHash签名进行置换并排序得到多张签名表;最后通过在多张签名表中高效地查找与查询视频的SimHash签名的汉明距离小于给定阈值的签名,并将其对应的视频作为拷贝视频从而完成视频拷贝检测.针对包含10335个视频,大小为272.48GB的实际数据集的实验表明该方法十分有效.

With the web video copy increased, fast and effective video copy detection method becomes more and more important. Considering large-scale video database, we propose an efficient fast copy detection method. This method first extracts spatiotemporal feature based on discrete cosine transform by considering frequency domain spatial information in frame and time information between frames, and then constructs a robust compact signature based on SimHash for every video. Secondly, get signature tables by permuta- tion and sorting the signatures. Finally, achieves video copy detection by using efficient hamming distance retrieval in signature ta- bles. The experiment on the dataset which contains 10335 video and size is 272.48 GB show the effectiveness of the proposed method for large-scale video copy detecting.