Method and apparatus for video quality assessment based on content complexity
View Patent ↗To estimate content complexity of a video, energy of prediction residuals is calculated. The prediction residuals are usually smaller when the video is less complex and more predictable. Scales of prediction residuals also depend on encoding configurations, for example, I pictures usually have larger prediction residuals than P and B pictures even when the contents are very similar and thus have similar perceived content complexity. To more closely reflect the content complexity, alignment scaling factors are estimated for different encoding configurations. Based on the energy of prediction residuals and alignment scaling factors, an overall content unpredictability parameter can be estimated to compute a compression distortion factor for the video. The compression distortion factor, combined with slicing and freezing distortion factors, can be used to estimate a video quality metric for the video.
1. A method for assessing video quality of a video included in a bitstream, wherein the method is configured to be executed on a processor, the method comprising:
determining a parameter responsive to a variance of prediction residuals of a block of a picture in the video;
adjusting the determined parameter responsive to encoding configuration of the block, wherein the encoding configuration includes at least one of a picture type and GOP (Group of Picture) structure; and
determining a quality metric, representative of video quality of the video included in the bitstream, in response to the adjusted parameter.
2. The method of claim 1 , wherein a scaling factor used for adjusting the determined parameter in an I picture is smaller than a scaling factor used for adjusting the determined parameter in a P picture.
3. The method of claim 1 , wherein a scaling factor used for adjusting the determined parameter is determined on the basis that the prediction residuals follow a gamma distribution.
4. The method of claim 3 , wherein respective scaling factors are determined for a plurality of encoding configurations, on the basis that a shape parameter of the gamma distribution for the encoding configuration is same as another shape parameter for another encoding configuration.
5. The method of claim 1 , wherein the parameter is determined for each one of a plurality of blocks in the video, and wherein an overall parameter for the video is determined responsive the determined parameters for the plurality of blocks.
6. The method of claim 1 , farther comprising:
performing at least one of monitoring quality of the bitstream, adjusting the bitstream in response to the quality metric, creating a new bitstream based on the quality metric, adjusting parameters of a distribution network used to transmit the bitstream, determining whether to keep the bitstream based on the quality metric, and choosing an error concealment mode at a decoder.
7. The method of claim 1 , wherein the determining the quality metric is further in response to at least one of a resolution and frame rate.
8. An apparatus for assessing video quality of a video included in a bitstream, comprising at least a memory and one or more processors, wherein the one or more processors are configured to:
access prediction residuals for a block of a picture of the video and determine encoding configuration of the block;
determine a parameter responsive to a variance of prediction residuals of the block, and
adjust the determined parameter responsive to the encoding configuration of the block, wherein the encoding configuration includes at least one of a picture type and GOP (Group of Picture) structure; and
determine a quality metric, representative of video quality of the video included in the bitstream, in response to the adjusted parameter.
9. The apparatus of claim 8 , wherein a scaling factor used to adjust the determined parameter in an I picture is smaller than a scaling factor used to adjust the determined parameter in a P picture.
10. The apparatus of claim 8 , wherein the one or more processors are configured to determine a scaling factor for adjusting the determined parameter on the basis that the prediction residuals follow a gamma distribution.
11. The apparatus of claim 10 , wherein respective scaling factors are determined for a plurality of encoding configurations, on the basis that a shape parameter of the gamma distribution for the encoding configuration is same as another shape parameter for another encoding configuration.
12. The apparatus of claim 8 , wherein the parameter is determined for each one of a plurality of blocks in the video, and wherein an overall parameter for the video is determined responsive the determined parameters for the plurality of blocks.
13. The apparatus of claim 8 , wherein the one or more processors are further configured to perform:
at least one of monitoring quality of the bitstream, adjusting the bitstream in response to the quality metric, creating a new bitstream based on the quality metric, adjusting parameters of a distribution network used to transmit the bitstream, determining whether to keep the bitstream based on the quality metric, and choosing an error concealment mode at a decoder.
14. The apparatus of claim 8 , wherein the one or more processors are configured to determine the quality metric further in response to at least one of a resolution and frame rate.
15. A computer readable storage medium having, stored thereon instructions, for assessing video quality of a video included in a bitstream, configured to perform:
determining a parameter responsive to a variance of prediction residuals of a block of a picture in the video;
adjusting the determined parameter responsive to encoding configuration of the block, wherein the encoding configuration includes at least one of a picture type and GOP (Group of Picture) structure; and
determining a quality metric, representative of video quality of the video included in the bitstream, in response to the scaled parameter.
16. The medium of claim 15 , wherein a scaling factor used for adjusting the determined parameter in an I picture is smaller than a scaling factor used for adjusting the determined parameter in a P picture.
17. The medium of claim 15 , wherein a scaling factor used for adjusting the determined parameter is determined on the basis that the prediction residuals follow a gamma distribution.
18. The medium of claim 17 , wherein respective sealing factors are determined for a plurality of encoding configurations, on the basis that a shape parameter of the gamma distribution for the encoding configuration is same as another shape parameter for another encoding configuration.
19. The medium of claim 15 , wherein the determining the quality metric is further in response to at least one of a resolution and frame rate.