可变树长混合小波和子树自量化分形视频编码

对可变树长混合小波和子树自量化分形视频编码方案进行了探讨。通过金字塔小波分解，每一视频序列帧被分解为多频率子带，将它们按一定方式组织成小波子树结构来表示视频序列的运动特性。对这些小波子树进行运动检测，分成运动树和非运动树两类。非运动树的编码直接、简单；运动树则采用可变树长混合小波和子树自量化方法来进行编码。实验结果表明在低比特率情况下，所述的方案在PSNR和主观质量两方面均可获得较好的性能。

A new wavelet video compression scheme using adaptive fractal coding is presented in this paper.Through pyramidal wavelet transform, each video frame is decomposed into multiresolution subbans and then organized into a set of wavelet subtrees to represent motion activities. After multiresolution motion detection, these wavelet subtrees are classified into motion and non-motion subtrees. The coding of non-motion subtrees is straightforward and simple, while the motion subtrees are adaptively separated and then encoded using vallable tree size fractal coding. Experimental results show that the proposed scheme provides a superior performance in terms of PSNR as well as the subjective quality at low bit-rates.