Systems, methods, and apparatus for real-time encoding
View Patent ↗Presented herein are systems, methods, and apparatus for real-time high definition television encoding. In one embodiment, there is a method for encoding video data. The method comprises estimating amounts of data for encoding a plurality of pictures in parallel; generating a plurality of target rates corresponding to the plurality of pictures based on the estimated amounts of data for encoding the plurality of pictures; and lossy compressing the plurality of pictures based on the target rates corresponding to the plurality of pictures.
1. A method for encoding video data, said method comprising:
estimating amounts of data for encoding a plurality of pictures in parallel;
generating a plurality of target rates corresponding to the plurality of pictures based on the estimated amounts of data for encoding the plurality of pictures, wherein at least one of the plurality of pictures is data dependent on another one of the plurality of pictures; and
lossy compressing the plurality of pictures based on the target rates corresponding to the plurality of pictures.
2. The method of claim 1 , wherein estimating amounts of data for encoding the plurality of pictures comprises:
searching at least one original reference picture for candidate blocks that are similar to blocks in the plurality of pictures;
selecting the candidate blocks based on comparison between the candidate blocks and the blocks in the plurality of pictures; and
estimating the amount of data for encoding the plurality of pictures based on the comparisons.
3. The method of claim 2 , wherein the original reference picture is scaled down.
4. The method of claim 2 , further comprising:
searching vicinities of areas in at least one reconstructed reference picture, said areas corresponding to the candidate blocks, for reference blocks that are similar to smaller blocks in the plurality of pictures.
5. The method of claim 1 , wherein lossy compressing the plurality of pictures further comprises quantizing with at least one quantization parameter, wherein the at least one quantization parameter is a function of the target rate associated with the picture.
6. A system for encoding video data, said system comprising:
a plurality of encoders for estimating amounts of data for encoding a corresponding plurality of pictures in parallel;
a master for generating a plurality of target rates corresponding to the plurality of pictures based on the estimated amounts of data for encoding the plurality of pictures, wherein at least one of the plurality of pictures is data dependent on another one of the plurality of pictures; and
wherein each of the plurality of encoders comprises a lossy compressor for lossy compressing the picture corresponding to the encoder, based on the target rate corresponding to the picture.
7. The system of claim 6 , further comprising:
a hardware accelerator for searching at least one original reference picture for candidate blocks that are similar to blocks in the plurality of pictures and comparing the candidate blocks to the blocks in the plurality of pictures; and
wherein each of the plurality of encoders estimates the number of bits for encoding the corresponding picture, based on the comparisons between the blocks from the corresponding picture and the candidate blocks that are similar to the blocks in the corresponding picture.
8. The system of claim 7 , wherein the at least one original reference picture is scaled down.
9. The system of claim 7 , wherein each of the plurality of encoders further comprises:
a motion estimator for searching vicinities of areas in at least one reconstructed picture, said areas corresponding to the candidate blocks that are similar to the blocks in the picture corresponding to the encoder, for reference blocks that are similar to the blocks in the picture corresponding to the encoder.
10. The system of claim 6 , wherein each of the plurality of encoders further comprise:
a quantizer for quantizing with at least one quantization parameter, wherein the at least one quantization parameter is a function of the target rate for the picture that corresponds to the encoder.
11. The system of claim 6 , wherein the master provides the corresponding plurality of pictures to the plurality of encoders.
12. A system for encoding video data, said system comprising:
a plurality of encoders for encoding a corresponding plurality of pictures;
a master for distributing the corresponding plurality of pictures to the plurality of encoders; and
a hardware accelerator for searching at least one original reference picture for candidate blocks that are similar to blocks in each of the plurality of pictures in parallel and comparing the candidate blocks to the blocks in the each of the plurality of pictures in parallel.
13. The system of claim 12 , wherein the at least one original reference picture is scaled down.
14. The system of claim 12 , wherein each of the plurality of encoders further comprises:
a motion estimator for searching vicinities of areas in at least one reconstructed picture, said areas corresponding to the candidate blocks that are similar to the blocks in the picture corresponding to the encoder, for reference blocks that are similar to the blocks in the picture corresponding to the encoder.
15. The system of claim 12 , wherein the reference picture is one of the plurality of pictures.
16. The system of claim 12 , wherein the original reference picture is unquantized.