基于运动信息和结构信息的视频质量评价方法  

Video Quality Assessment Measurement Based on Motion Information and Structural Distortion

作　　者：卢国庆[1] 李均利[1] 陈刚[1] 满家巨[2] 

机构地区：[1]宁波大学信息学院,浙江宁波315211 [2]湖南师范大学,湖南长沙410083

出　　处：《计算机仿真》2010年第6期262-266,共5页Computer Simulation

基　　金：国家自然科学基金资助项目(60672072);浙江省自然科学基金(Y106505);湖南省自然科学基金(No.08JJ3130)

摘　　要：图像和视频客观质量评价方法在各个领域有着广泛的应用,根据上述问题,主要针对图像边缘结构失真和噪音影响图像质量。以往的测量方法不能很好地应用于视频领域。提出一种基于运动信息和结构信息的视频质量评价方法,主要考虑场景结构和运动信息,然后依据HVS特性对不同程度的信息进行加权处理,从而综合采用一种视频质量评价方法。经实验结果证明,新方法在压缩、模糊方面明显好于PSNR,MSSIM和ESSIM评价方法。Objective image and video quality assessment has been widely used in the variety of image and video processing applications. Aimming at the the disadvantage that the video quality assessment based on structural distortion measurement can not apply directly in the video field, this paper proposes a method of video quality assessment, which is based on motion information and structural distortion and takes the structural distortion measurement and mo- tion information into account . Then, the weighted factor base on the HVS is obtained. Experimental results show that the method is better than the methods based on PSNR, MSSIM and ESSIM in compress losing and smooth losing.

关 键 词：视频质量评价 人眼视觉系统 结构失真 运动信息 

分 类 号：TN949.6[电子电信—信号与信息处理]