Sciweavers

Share
ICASSP
2010
IEEE

Temporal motion smoothness measurement for reduced-reference video quality assessment

9 years 2 months ago
Temporal motion smoothness measurement for reduced-reference video quality assessment
Reduced-reference (RR) video quality measures aim to predict the perceptual quality of distorted video signals using only partial information about the reference video. Existing RR video quality assessment models are mostly designed and/or trained for specific applications such as lossy compression, where the detectable distortion types are often fixed and limited. Here we propose a novel approach that measures temporal motion smoothness of a video sequence by examining the temporal variations of local phase structures in the complex wavelet transform domain. We show that the proposed measure can detect a wide range of well-known practical distortions, including noise contamination, blurring, line or frame jittering, and frame dropping. In addition, the proposed algorithm does not require a costly motion estimation process and has a low RR data rate, making it much easier to be adopted in real-world visual communication applications.
Kai Zeng, Zhou Wang
Added 06 Dec 2010
Updated 06 Dec 2010
Type Conference
Year 2010
Where ICASSP
Authors Kai Zeng, Zhou Wang
Comments (0)
books