Video encoding complexity measure system
Classifying video for encoding optimization may include computing a content complexity score of a video, the content complexity score indicating a measure of how detailed the video is in terms of spatial and temporal information, categorizing the video into one of a plurality of buckets according to the content complexity score, each bucket representing a category of video content having a different range of content complexity scores and being associated with a ladder specific to the range, and encoding the video according to the ladder of the one of the plurality of buckets into which the video is categorized.
1. A method for classifying video for encoding optimization, comprising:
computing a content complexity score of a video, the content complexity score indicating a measure of how detailed the video is in terms of spatial and temporal information, wherein the complexity score is a function of a human perceptual quality of experience score, such that a higher complexity score relates to a lower perceptual quality of experience and a lower complexity score relates to a higher perceptual quality of experience;
adjusting the content complexity score to account for any difference between a target bit rate and the actual bitrate,
categorizing the video into one of a plurality of buckets according to the content complexity score as adjusted, each bucket representing a category of video content having a different range of content complexity scores and being associated with a ladder specific to the range; and
encoding the video according to the ladder of the one of the plurality of buckets into which the video is categorized.
2. The method of claim 1 , further comprising performing a pixel-based method to summarize a relationship of compression rate and quality (BD rate) using SSIMPLUS.
3. The method of claim 1 , further comprising generating a BD rate curve based on a resolution of the video.
4. The method of claim 1 , further comprising generating a BD rate curve based on codecs and encoder configurations.
5. The method of claim 1 , further comprising generating a BD rate curve based on a frame rates of the video.
6. The method of claim 1 , further comprising generating a BD rate curve based on a viewing device configured to display the video.
7. The method of claim 1 , further comprising generating a BD rate curve based on a dynamic range of the video.
8. A system for classifying video for encoding optimization, comprising:
a processor programmed to
identify an actual bitrate of a video encoded at a target bitrate;
generating a BD rate curve based on a dynamic range of the video;
compute a content complexity score of the video, the content complexity score indicating a measure of how detailed the video is in terms of spatial and temporal information;
categorize the video into one of a plurality of buckets according to the content complexity score, each bucket representing a category of video content having a different range of content complexity scores based on the BD rate curve and being associated with a ladder specific to the range; and
encode the video according to the ladder of the one of the plurality of buckets into which the video is categorized.
9. The system of claim 8 , wherein the processor is further programmed to compute the complexity score as an inverse of a human perceptual quality of experience score, such that a higher complexity score relates to a lower perceptual quality of experience and a lower complexity score relates to a higher perceptual quality of experience.
10. The system of claim 8 , wherein the processor is further programmed to adjust the content complexity score to account for any difference between the target bitrate and the complexity target bitrate, wherein the categorizing of the video into one of a plurality of buckets is in accordance with the content complexity score as adjusted.
11. The system of claim 8 , wherein the processor is further programmed to perform a pixel-based method to summarize a relationship of compression rate and quality (BD rate) using SSIMPLUS.
12. A non-transitory computer readable medium comprising instructions for classifying video for encoding optimization, that, when executed by a processor of a computing device, cause the computing device to perform operations including to:
identify an actual bitrate of a video encoded at a target bitrate;
generate a BD rate curve based on at least one of a resolution of the video, generate a BD rate curve based on codecs and encoder configurations, generate a BD rate curve based on a frame rates of the video, generate a BD rate curve based on a viewing device configured to display the video or generate a BD rate curve based on a dynamic range of the video;
compute a content complexity score of the video, the content complexity score indicating a measure of how detailed the video is in terms of spatial and temporal information;
categorize the video into one of a plurality of buckets according to the content complexity score, each bucket representing a category of video content having a different range of content complexity scores and based on the BD rate curve and being associated with a ladder specific to the range; and
encode the video according to the ladder of the one of the plurality of buckets into which the video is categorized.
13. The medium of claim 12 , further comprising instructions that, when executed by the processor of the computing device, cause the computing device to compute the complexity score as an inverse of a human perceptual quality of experience score, such that a higher complexity score relates to a lower perceptual quality of experience and a lower complexity score relates to a higher perceptual quality of experience.
14. The medium of claim 12 , further comprising instructions that, when executed by the processor of the computing device, cause the computing device to adjust the content complexity score to account for any difference between the target bitrate and the actual bitrate, wherein the categorizing of the video into one of a plurality of buckets is in accordance with the content complexity score as adjusted.
15. The medium of claim 12 , further comprising instructions that, when executed by the processor of the computing device, cause the computing device to perform a pixel-based method to summarize a relationship of compression rate and quality (BD rate) using SSIMPLUS.
16. The medium of claim 12 , wherein the plurality of buckets include a first bucket having a first range and a second bucket having a second range different from the first range and further comprising instructions that, when executed by the processor of the computing device, cause the computing device to categorize the video into one of the first range or the second range according to the content complexity score.