Motion tuned spatio-temporal quality assessment of natural videos
IEEE Transactions on Image Processing
Study of subjective and objective quality assessment of video
IEEE Transactions on Image Processing
Image quality assessment: from error visibility to structural similarity
IEEE Transactions on Image Processing
VSNR: A Wavelet-Based Visual Signal-to-Noise Ratio for Natural Images
IEEE Transactions on Image Processing
Fuzzy logic and temporal information applied to video quality assessment
Journal of Mobile Multimedia
Hi-index | 0.00 |
This paper presents a low complexity algorithm for video quality assessment, called ViMSSIM, which extends the image quality metric MS-SSIM to take into account visual perception of spatial and temporal quality of the video. First, we use a modified exponential moving average model to pool the MS-SSIM indices of all frames and create the spatial quality index. Next, we apply MS-SSIM to the frame-different images of the distorted video and the reference video. Here each pair i of frame differences is formed by taking the difference between frame i+1 of the original video and its previous frame i, and the difference between frame i+1 of the distorted video and frame i of the original video. Averaging the MS-SSIM indices of these frame-different images leads to the temporal quality index. The final quality index is the average of the computed spatial and temporal index. Testing on the LIVE video database consisting of 150 videos demonstrates that ViMSSIM performs well in predicting video quality. In addition, the proposed algorithm has significantly lower complexity compared to current state-of-the-art benchmark video quality metrics.