A semi-fragile content authentication algorithm is proposed for low bit-rate H.264/AVC video in VLC domain. Utilizing the intra prediction mode and coded block pattern in VLC domain, the proposed algorithm chooses tho...A semi-fragile content authentication algorithm is proposed for low bit-rate H.264/AVC video in VLC domain. Utilizing the intra prediction mode and coded block pattern in VLC domain, the proposed algorithm chooses those macro-blocks from which the signature is extracted and constructs content signature at macro-block level according to the relationship among the energies of quantized low-frequency coefficients of sub-macroblocks. The signature is embedded by modifying the trailing coefficients. The experimental results show that the proposed algorithm performs well in visual quality impact and keep the bit-rate basically unchanged. In addition, the algorithm can embed signatures into I, P, B slices simultaneously and remarkably enhances the watermark capacity. By verifying the extracted signature, the algorithm can detect and locate video tampering efficiently.展开更多
本文提出了一种基于H.264/AVC压缩域的GOP(Group of Pictures)级视频场景转换检测算法.该算法利用H.264/AVC基本档次码流中的帧内预测模式、运动矢量和宏块编码类型等可用信息,提出了基于子块的色度模式差异、累积运动值和累积帧内宏块...本文提出了一种基于H.264/AVC压缩域的GOP(Group of Pictures)级视频场景转换检测算法.该算法利用H.264/AVC基本档次码流中的帧内预测模式、运动矢量和宏块编码类型等可用信息,提出了基于子块的色度模式差异、累积运动值和累积帧内宏块数等三个判决准则,然后综合利用这三个判决准则,提出了一种GOP级的视频场景转换检测算法.实验结果表明,与现有的一个COP级场景检测算法对比,本文提出的GOP级视频场景转换检测算法可以获得更好的检测性能.展开更多
基金This paper is sponsored by the National Natural Science Foundation of China （No. 60802057, 61071153）, National 863 Plan of China （ 2009AA01Z407 ）, Shanghai Rising-Star Program （10QA1403700）, and Shanghai Educational Development Foundation.
文摘A semi-fragile content authentication algorithm is proposed for low bit-rate H.264/AVC video in VLC domain. Utilizing the intra prediction mode and coded block pattern in VLC domain, the proposed algorithm chooses those macro-blocks from which the signature is extracted and constructs content signature at macro-block level according to the relationship among the energies of quantized low-frequency coefficients of sub-macroblocks. The signature is embedded by modifying the trailing coefficients. The experimental results show that the proposed algorithm performs well in visual quality impact and keep the bit-rate basically unchanged. In addition, the algorithm can embed signatures into I, P, B slices simultaneously and remarkably enhances the watermark capacity. By verifying the extracted signature, the algorithm can detect and locate video tampering efficiently.
文摘本文提出了一种基于H.264/AVC压缩域的GOP(Group of Pictures)级视频场景转换检测算法.该算法利用H.264/AVC基本档次码流中的帧内预测模式、运动矢量和宏块编码类型等可用信息,提出了基于子块的色度模式差异、累积运动值和累积帧内宏块数等三个判决准则,然后综合利用这三个判决准则,提出了一种GOP级的视频场景转换检测算法.实验结果表明,与现有的一个COP级场景检测算法对比,本文提出的GOP级视频场景转换检测算法可以获得更好的检测性能.
