Fig 1.
Framework for the proposed VQA method.
Fig 2.
MCTF procedure in a four-frame GoF.
Different levels of MCTF are separated by colors and line styles.
Fig 3.
The original frames and the corresponding results of MCTF of the first GoF in video “Pedestrian Area” form the LIVE database.
(a) 1st GoF in “Pedestrian Area”. (b) Temporal Low-pass component. (c) Temporal High-pass component.
Fig 4.
Training set from randomly selected temporal LPCs
Fig 5.
Parameter determinations in the proposed VQA method.
(a) Tuning Performance of ω1. (b) Tuning Performance of a+ and a-.
Table 1.
Performance indicators of proposed VQA method with different GoF numbers.
Table 2.
PLCC comparison for each module of the proposed VQA method.
Table 3.
Performance on separate types of distortion.
Table 4.
Performance comparison on the LIVE VQA database.
Fig 6.
Scatter plots of proposed VQA metric.
All distortion types in LIVE video databases are listed.