Accurate objective quality metric is crucial for various video processing applications. Although the area of image quality assessment has attained maturity in recent years, video quality assessment still has a long way to go before it reaches the levels of success achieved by still image quality metrics. In the paper, we present a new approach to video quality assessment based quatemion singular value decomposition(QSVD),which take the luminance,chrominance ,edge energy and motion energy of each pixel as the four parts of a quatemion, and the entropy as the degree of visual interest of regions to weight each block. We demonstrate the performance of our algorithm by testing it on the Video Quality Expert Group(VQEG)Phase Ⅰ FR-TV dataset,the results show that our method is competitive with state of the art quality assessment methods and has good correlation with perceived video quality.%准确的客观视频质量评价方法对于视频应用发展是至关重要的.近年来,图像质量评价方法已经比较成熟,而视频质量评价方法与图像质量评价方法在性能上的差距仍然较大.本文提出一种基于四元数奇异值分解的客观视频质量评价方法,该方法将像素的亮度、色度、边缘能量和残差能量作为四元数的四个部分,并用熵作为视觉感兴趣系数对块加权.在视频质量专家组(VQEG)阶段1 FR-TV视频测试库上的测试结果表明,该方法与主观评价结果有很好的相关性.
展开▼
