基于速度场的手持重拍摄视频检测算法  

Analysis of Hand-Held Recaptured Video Detection Algorithm Exploiting Velocity Field

作　　者：蒋卓彦 孙锬锋[1] 蒋兴浩[1] 

机构地区：[1]上海交通大学,上海

出　　处：《计算机科学与应用》2016年第12期761-771,共11页Computer Science and Application

基　　金：国家自然科学基金项目.

摘　　要：视频重拍摄检测是检测视频侵权的重要方法之一,可用于被动检测视频的版权。本文针对手持重拍摄视频,结合了手持拍摄视频的特点,对视频帧间进行速度场计算,根据连续两个速度场的方向判定速度场的变化程度,提取多个变化程度以得到一组速度场变化程度值,选取该组值的平均值与方差作为二维手持抖动特征,并使用支持向量机(support vector machine, SVM)进行重拍摄检测实验。对比实验证明该算法具有更高的准确率。Video recaptured detection is one of the important methods of detecting video infringement. It is a passive detection method and can be used for video copyright. In this paper, combining with the hand-held video characteristics and the velocity field algorithm, we calculate the velocity field between frames, according to the moving trend to judge whether velocity field changes or not. We extract a set of velocity change values and select the average and variance value as a two-dimen- sional characteristic, and finally we use support vector machine (SVM) for experiments. The experiment result shows that this algorithm has a higher accuracy.

关 键 词：被动检测 手持重拍摄 速度场 速度场变化程度 SVM 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]