Video decoder memory bandwidth compression
View Patent ↗A method, system and computer program for decompressing video data, storing the compressed video data in such a way that random access is possible and the data can be mapped efficiently into existing memory systems and interface protocols. The compression is accomplished via lossless compression using an algorithm optimized for video data. Due to the compressed format, data transmission consumes less bandwidth than using uncompressed data and prevents degradation in the decoded video.
1. A method of compressing and decompressing digital video, the method comprising the steps of:
a) dividing a video image into a two dimensional block structure;
b) determining a surface map according to a difference between a mean of data values within the two dimensional block and a mean of data values within a plurality of sub blocks within the two dimensional block;
c) applying a best fit, weight to the surface map to minimize differences;
d) generating a plurality of variable length code (VLC) codes representing a plurality of encoding levels, a weight, a surface map, and a plurality of error terms for each level of mapping; and
e) collecting VLC terms into a linear group of data.
2. The method of claim 1 , wherein the method comprises iteratively processing error terms for additional surface mapping and for the reduction of bit encoding.
3. The method of claim 1 , wherein the method comprises randomly accessing the linear group of data from a buffer.
4. The method of claim 1 , wherein the method comprises fetching a first part of the linear group of data in a read operation and fetching a second part of the linear group of data if it is present.
5. The method of claim 1 , wherein the method comprises indicating whether the linear group of data is compressed.
6. A system for compressing and decompressing digital video, the system comprising:
a processor; and
a memory storing instructions which when executed cause the processor to:
divide a video image into a two dimensional block structure;
determine a surface map according to a difference between a mean of data values within the two dimensional block and a mean of data values within a plurality of sub blocks within the two dimensional block;
apply a best fit weight to the surface map to minimize differences;
generate variable length code (VLC) codes representing a plurality of encoding levels, a weight, a surface map, and a plurality of error terms for each level of mapping; and
collect VLC terms into a linear group of data.
7. The system of claim 6 , wherein the processor is operable to process resulting error terms for additional surface mapping and reduce bit encoding.
8. The system of claim 6 , wherein the processor is operable to randomly access the linear group of data.
9. The system of claim 6 , wherein the processor is operable to fetch a first part of the linear group of data in a read operation and fetch a second part of the linear group of data if it is present.
10. The system of claim 6 , wherein the processor is operable to indicate whether the linear group of data is compressed.
11. A non-transitory computer-executable storage medium comprising program instructions which are computer-executable to implement compressing and decompressing digital video comprising:
program instructions that cause a division of a video image into a two dimensional block structure;
program instructions that cause a determination of a surface map according to a difference between a mean of data values within the two dimensional block and a mean of data values within a plurality of sub blocks within the two dimensional block;
program instructions that cause an application of a best fit weight to the surface map to minimize differences;
program instructions that cause a generation of a plurality of variable length code (VLC) codes representing a plurality of encoding levels, a weight, a surface map, and a plurality of error terms for each level of mapping; and
program instructions that cause a collection of VLC terms into a linear group of data.
12. The non-transitory computer-executable storage medium of claim 11 , wherein the non-transitory computer-executable storage medium comprises program instructions that cause an iteration of processing error terms for additional surface mapping and for the reduction of bit encoding.
13. The non-transitory computer-executable storage medium of claim 11 , wherein the non-transitory computer-executable storage medium comprises program instructions that cause a random access of the linear group of data from a buffer.
14. The non-transitory computer-executable storage medium of claim 11 , wherein the non-transitory computer-executable storage medium comprises program instructions that cause fetching a first part of the linear group of data in a read operation and fetching a second part of the linear group of data if it is present.
15. The non-transitory computer-executable storage medium of claim 11 , wherein the non-transitory computer-executable storage medium comprises program instructions that cause an indicator of whether the linear group of data is compressed.