Temporal Quality Assessment for Mobile Videos An (Jack) Chan, Amit - - PowerPoint PPT Presentation
Temporal Quality Assessment for Mobile Videos An (Jack) Chan, Amit Pande, Eilwoo Baik, Prasant Mohapatra Department of Computer Science, University of California, Davis Videos are Everywhere Ciscos Virtual Network Index In 2011, video
An (Jack) Chan, Amit Pande, Eilwoo Baik, Prasant Mohapatra Department of Computer Science, University of California, Davis
Evaluated by computer programs To approximate subjective measurement, MOS
Low computational power requirement Video codec independent Network impairment estimation No original (reference) videos Correlated to subjective scores
storage-news.com greenwala.com sciencedirect.com
Measure temporal information at low cost
Reduced-reference video quality metric Estimates subjective video quality Estimates network impairments
Blocking and blurring Image quality measurement Pixel-by-pixel comparison (e.g. PSNR, SSIM)
Jerkiness and freezing Optical flows More pervasive in wireless mobile networks
sciencedirect.com
Partially evaluated [Vidal2006][Yang2007]
Focus on the effect from network packet loss No high correlation to subjective scores
Modeling human visual system
Evaluate both spatial and temporal quality High complexity Require original copies
Motion
Codec-dependent
Difference between two neighboring frames
Temporal versions of SSIM, ESS
TSSIM, TESS and TVSNR
Length from 10 to 60 seconds Resolution from 352X288 to 1920X1080 Motion degree from slow to very fast
Developed an Android app Engaged 17 volunteers Collected 50 video clips (3 motion groups) Measured Mean Opinion Score (MOS) Calculate TVM and TVI
adroid.com
Strong linear correlation Pearson correlation coefficient
Slow motion Moderate motion Fast motion
Set up an 802.11n single-hop testbed Streaming videos (3 motion groups) Introduce packet loss and delay Calculate TVM and TVI Collect 183 video samples
Causes blocking, blurring and freezing TVM in received video is inconsistent with that in the
Freezing leads to infinite TVM
Causes blocking, blurring and freezing TVM in received video is inconsistent with that in the
Freezing leads to infinite TVM
Strong linear correlation Evaluated with 45 videos Pearson correlation coefficient
Slow motion Moderate motion Fast motion
Results in freezing Infinite TVM values TVM of the received video is like a delayed version of
Evaluated by randomly chosen videos The average accuracy rate ~ 95% delay happens
TVM to measure the temporal information at low cost Derive TVI as a quality and network condition predictor TVI is highly correlated with MOS (0.925) TVI is highly correlated with packet loss rate (0.94) Predict end-to-end delay with 95% accuracy
[Vidal2006] R. Pastrana-Vidal and J. Gicquel. Automatic quality
[Yang2007] K.-C. Yang, C. Guest, K. El-Maleh, and P. Das. Perceptual
[Sesha2010] K. Seshadrinathan and A. C. Bovik. Motion tuned spatio-
[Moorthy2010] A. K. Moorthy and A. C. Bovik. Efficient video quality
Questions and Answers