Video quality measurement considering multiple artifacts
View Patent ↗A particular implementation determines objective distortion levels (d,) respectively for a plurality of artifact types. The objective distortion levels are aligned to ensure that the same distortion level of different types of artifacts corresponds to the same perceived distortion level. The aligned distortion levels (d,′) are sorted to obtain sorted distortion levels (d,″). The sorted distortion levels are then pooled together into an overall distortion level or an overall quality metric. The sorted distortion levels may be pooled using a weighted sum, wherein the weight is larger when the sorted distortion level is greater.
1. A method, comprising:
accessing picture data including a plurality of artifact types;
adjusting a corresponding objective distortion level of each respective one of the plurality of artifact types to obtain aligned distortion levels for the plurality of artifact types, wherein each of the aligned distortion levels corresponds to a respective one of the plurality of artifact types, and wherein if an aligned distortion level for one of the plurality of artifact types is same as another aligned distortion level for another one of the plurality of the artifact types, then perceived distortion levels corresponding to the two different artifact types are substantially same;
sorting the aligned distortion levels regardless of their corresponding artifact types to provide sorted aligned distortion levels; and
determining an overall distortion level in response to a weighted sum of the sorted aligned distortion levels,
wherein a greater sorted aligned distortion level has a greater impact on the overall distortion level,
wherein a first weighting factor, applied to a first sorted aligned distortion level for obtaining the weighted sum, is greater than a second weighting factor, applied to a second sorted aligned distortion level for obtaining the weighted sum, if the first sorted aligned distortion level is greater than the second sorted aligned distortion level, and
wherein the application of the first weighting factor to the first sorted aligned distortion level increases the value of the first sorted aligned distortion level.
2. The method of claim 1 , wherein the overall distortion level is determined in response to a subset of the sorted aligned distortion levels.
3. The method of claim 1 , further comprising:
determining a quality metric in response to the overall distortion level.
4. The method of claim 1 , further comprising:
determining respective objective distortion levels for the plurality of artifact types.
5. The method of claim 4 , wherein the respective objective distortion levels for the plurality of artifact types are determined at a bitstream level.
6. The method of claim 1 , wherein the aligning the objective distortion levels is performed as a polynomial function.
7. The method of claim 1 , wherein the plurality of artifact types include at least one of compression artifacts, channel artifacts, freezing artifacts, blockiness, ringing, and blurriness.
8. An apparatus, comprising at least a memory and one or more processors, the one more processors being configured to:
adjust objective distortion levels to obtain aligned distortion levels for a plurality of artifact types, wherein if an aligned distortion level for one of the plurality of artifact types is same as another aligned distortion level for another one of the plurality of the artifact types, then perceived distortion levels corresponding to the two different artifact types are substantially same,
sort the aligned distortion levels regardless of their corresponding artifact types to provide sorted aligned distortion levels, and
determine an overall distortion level in response to a weighted sum of the sorted aligned distortion levels,
wherein a greater sorted aligned distortion level has a greater impact on the overall distortion level,
wherein a first weighting factor, applied to a first sorted aligned distortion level for obtaining the weighted sum, is greater than a second weighting factor, applied to a second sorted aligned distortion level for obtaining the weighted sum, if the first sorted aligned distortion level is greater than the second sorted aligned distortion level, and
wherein the application of the first weighting factor to the first sorted aligned distortion level increases the value of the first sorted aligned distortion level.
9. The apparatus of claim 8 , wherein the one or more processors are configured to determine the overall distortion level in response to a subset of the sorted aligned distortion levels.
10. The apparatus of claim 8 , wherein the one or more processors are further configured to determine a quality metric in response to the overall distortion level.
11. The apparatus of claim 8 , wherein the one or more processors are further configured to determine respective objective distortion levels for the plurality of artifact types.
12. The apparatus of claim 8 , wherein the one or more processors are configured to determine respective objective distortion levels for the plurality of artifact types at a bitstream level.
13. The apparatus of claim 8 , wherein the plurality of artifact types include at least one of compression artifacts, channel artifacts, freezing artifacts, blockiness, ringing, and blurriness.
14. A non-transitory processor readable medium having stored thereupon instructions for causing one or more processors to collectively perform:
accessing picture data including a plurality of artifact types;
adjusting objective distortion levels to obtain aligned distortion levels for the plurality of artifact types, wherein if an aligned distortion level for one of the plurality of artifact types is same as another aligned distortion level for another one of the plurality of the artifact types, then perceived distortion levels corresponding to the two different artifact types are substantially same;
sorting the aligned distortion levels regardless of their corresponding artifact types to provide sorted aligned distortion levels; and
determining an overall distortion level in response to a weighted sum of the sorted aligned distortion levels,
wherein a greater sorted aligned distortion level has a greater impact on the overall distortion level,
wherein a first weighting factor, applied to a first sorted aligned distortion level for obtaining the weighted sum, is greater than a second weighting factor, applied to a second sorted aligned distortion level for obtaining the weighted sum, if the first sorted aligned distortion level is greater than the second sorted aligned distortion level, and
wherein the application of the first weighting factor to the first sorted aligned distortion level increases the value of the first sorted aligned distortion level.
15. The method of claim 1 , wherein the subset corresponds to the strongest artifact only.
16. The apparatus of claim 8 , wherein the subset corresponds to the strongest artifact only.