提出一种基于方向经验模式分解(directional empirical mode decomposition,DEMD)的视频分割方法,并结合独立分量分析(independent component analysis)技术实现视频水印的嵌入.基于DEMD的视频分割方法除去视频帧中反映图像内光照分布与能量的最低频率固有模态函数(intrinsic mode function,IMF)分量,并选择一种简单有效的运动补偿方法,解决了传统基于直方图方法对光照突变、镜头内物体运动和镜头运动及拉伸的敏感问题,减少了镜头边界识别的误检率,在保证召回率不受影响的前提下提高了视频分割的精确度.使用这种视频分割方法与ICA结合,对分割出的每个视频段进行ICA分析得到一系列独立分量帧,以这些独立分量帧为载体,采用一种改进的基于小波域量化的图像水印技术嵌入水印,实现对视频加入水印的过程.实验结果表明,这种视频水印方法对各种水印攻击均有较好的鲁棒性,同基于传统直方图方法的视频水印方法相比较,对丢帧和持续时间不变减少帧数等攻击具有更好的鲁棒性.
In this paper, a video segmentation method based on directional empirical mode decomposition(DEMD) is proposed, which is combined with independent component analysis(ICA) to embed watermark into videos. In the video segmentation method based on DEMD, the intrinsic mode function(IMF) with the lowest frequency is discarded and a simple and effective motion compensation method is adopted. As a result, the video segmentation method is no longer sensitive to abrupt change of luminance, object motion in shots, motion and zoom in/out of cameras, so that the precision of detecting shot boundaries is improved. Using ICA to analyze videos segmented by the method mentioned above, a series of independent component frames are obtained, and then an improved wavelet-domain quantization-based image watermark algorithm is applied to embed watermarks into these frames to realize the embedding of video watermarks. Experimental results show that video watermarking method in this paper is robust enough against several kinds of watermark attacks. It is more robust against attacks such as frames discarding and decreasing in the same time than traditional video segmentation methods based on histogram.