Video Quality Assessment Based on Measuring Perceptual Noise from Spatial and Temporal Perspectives

被引:38
作者
Zhao, Yin [1 ,2 ]
Yu, Lu [1 ,2 ]
Chen, Zhenzhong [3 ]
Zhu, Ce [3 ]
机构
[1] Zhejiang Univ, Inst Informat & Commun Engn, Hangzhou 310027, Zhejiang, Peoples R China
[2] Zhejiang Prov Key Lab Informat Network Technol, Hangzhou 310027, Zhejiang, Peoples R China
[3] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore 639798, Singapore
关键词
Human visual system; just noticeable difference; perceptual quality index; temporal noise; video quality assessment; ATTENTION; DURATION; MODEL; MAGNIFICATION; INFORMATION; SENSITIVITY; VISION;
D O I
10.1109/TCSVT.2011.2157189
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Video quality assessment (VQA) exploits important properties of the sophisticated human visual system (HVS). In this paper, we study a series of fundamental HVS characteristics for subjective video quality assessment, and incorporate them into a systematic framework to simulate subjective evaluation on impaired videos. Based on this framework, we develop a novel full-reference metric, namely, perceptual quality index (PQI). Specifically, the proposed PQI metric comprises four major modules: 1) visual performance equation for the foveal and extra-foveal vision based on the cortical magnification theory; 2) perceptible noise detection using a spatial-temporal just noticeable difference model, and its quantification in both spatial and temporal channels, considering the varying error sensitivity due to the contrast and motion masking effects; 3) instantaneous error summation with inhibition of weak local distortions, and quality degradation accumulation over time that models the visual persistence and recency effect; and 4) fusion of the spatial and temporal noise intensities into a perceptual quality index. Compared with some state-of-the-art VQA models, the PQI metric, which exploits multiple visual properties, measures video quality more accurately and reliably on two VQA databases.
引用
收藏
页码:1890 / 1902
页数:13
相关论文
共 67 条
[1]   MEASUREMENT OF SCENE-DEPENDENT QUALITY VARIATIONS IN DIGITALLY CODED TELEVISION PICTURES [J].
ALDRIDGE, R ;
DAVIDOFF, J ;
GHANBARI, M ;
HANDS, D ;
PEARSON, D .
IEE PROCEEDINGS-VISION IMAGE AND SIGNAL PROCESSING, 1995, 142 (03) :149-154
[2]   A production system theory of serial memory [J].
Anderson, JR ;
Matessa, M .
PSYCHOLOGICAL REVIEW, 1997, 104 (04) :728-748
[3]  
[Anonymous], 2000, Final report from the video quality experts group on the validation of objective models of video quality assessment
[4]   Temporal Trajectory Aware Video Quality Measure [J].
Barkowsky, Marcus ;
Bialkowski, Jens ;
Eskofier, Bjoern ;
Bitto, Roland ;
Kaup, Andre .
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2009, 3 (02) :266-279
[5]   VISUAL PERSISTENCE - EFFECTS OF FLASH LUMINANCE, DURATION AND ENERGY [J].
BOWEN, RW ;
POLA, J ;
MATIN, L .
VISION RESEARCH, 1974, 14 (04) :295-303
[6]  
Breitmeyer Bruno G, 2008, Adv Cogn Psychol, V3, P9, DOI 10.2478/v10053-008-0010-7
[7]   AN ANALYTICAL DERIVATION OF VISUAL NONLINEARITY [J].
BUCHSBAUM, G .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 1980, 27 (05) :237-242
[8]   VISUAL SIGNAL-DETECTION .2. SIGNAL-LOCATION IDENTIFICATION [J].
BURGESS, AE ;
GHANDEHARIAN, H .
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1984, 1 (08) :906-910
[9]   VSNR: A wavelet-based visual signal-to-noise ratio for natural images [J].
Chandler, Damon M. ;
Hemami, Sheila S. .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2007, 16 (09) :2284-2298
[10]   Perceptually-Friendly H.264/AVC Video Coding Based on Foveated Just-Noticeable-Distortion Model [J].
Chen, Zhenzhong ;
Guillemot, Christine .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2010, 20 (06) :806-819