基于视觉感兴趣区的视频质量评价方法.pdfVIP

35 10 2009 5 Vol.35 No.10 Computer Engineering May 2009 ·· 2009 A TN949.6 1 1 1 1 2 (1. 3152112. 410083) HVS HVS PSNR, MSSIM ESSIM Method of Video Quality Assessment Based on Visual Regions-of-interest 1 1 1 1 2 LU Guo-qing , LI Jun-li , CHEN Gang , ZHANG Ying , MAN Jia-ju (1. College of Information Science and Engineering, Ningbo University, Ningbo 315211; 2. Hunan Normal University, Changsha 410083) AbstractAiming at the the disvantage that the video quality assessment based on structural distortion measurement can not apply directly on the video field and think over HVS, this paper proposes a method of video quality assessment based on visual regions-of-interest. It thinks about HVS, the structural distortion measurement and motion information. Experimental results show that the method is better than the method based on PSNR, MSSIM and ESSIM on the compress losing, smooth losing. Key wordsvideo quality assessment; human visual system; motion information 2µ µ + C 1 x y 1 l(x, y) 2 2 (2) µx + µy + C1 2σ σ + C c(x, y) 2 x y 2 2 (3) σ + σ + C x y 2 σ + C