一种高效的基于矢量量化的彩色视频图像压缩编码方法

An efficient VQ-based color video coding method

针对彩色视频图像提出了一种DCT域内基于矢量量化的高效编码方法。为去掉彩色图像各分量间的相关性,首先将图像由RGB空间转换到YUV空间,然后根据人类视觉特征(HVS)对色度信号U、V进行了亚采样和平均化处理;对亮度信号Y则进行分块DCT变换,并根据HVS特征对变化域内的块矢量进行自适应分类,然后根据矢量的类型分别构造码矢和进行全局码书设计。提出的全局码书设计方案可以根据帧间相关性及码字使用频率,对码书的内容自动进行更新和替换,以适应场景内容的变化。实验结果表明:在保证图像重建质量的前提下,本文提出的方法具有较高的压缩效率,比较适合于视频会议以及水下视频观测等应用场合。

This paper presents an efficient vector quantization （VQ） based on color video coding method in discrete cosine transform （DCT） domain. In order to remorse the inherent correlation among. the three components of color image,the image is transformed from the RGB space to the YUV space, and the sub-sampling operations and average computation are per- formed for the chrominance components of U and V based on human visual system （HVS） characteristics. For the luminance Y image, we first partition it into 8×8 blocks which are not overlapped , and then apply DCT to these blocks, to form the transformed vectors. Based on HVS, the transformed vectors are automatically classified and truncated. Finally, for each type of the vectors ,the global codebook is designed accordingly, which can adaptively update and replace the code words of the cookbook with the change of scene according to the inter-frame correlation and the using frequency of code words. The experimental resuIts show that while maintaining the acceptable quality of the reconstructed images,the proposed algorithm can provide high coding efficiency, especially applying to such scenarios as videoconference and video observation of underwater