Using boundary maps to refine imagery
View Patent ↗A boundary map and a first image are received. The boundary map is used to determine that brightness values for a set of pixels included in the first image should be regularized. The first set of pixels include, at a first pixel position, a first pixel having a first set of brightness values. The first set of pixels further includes, at a second pixel position, a second set of brightness values. An output image is generated by storing, at both a first and second pixel position in the output image, a set of regularized values.
1. A system, comprising:
a processor configured to:
receive: (1) a first image and (2) a boundary map constructed prior to receipt of the first image;
determine, at least in part by using the boundary map, that a plurality of different brightness values of a first set of pixels included in the first image should be regularized to at least one common shared value for the first set of pixels, wherein the first set of pixels includes, at a first pixel position in the first image, a first pixel having a first set of brightness values, and wherein the first set of pixels includes, at a second pixel position in the first image that is different from the first pixel position, a second set of brightness values, and wherein at least one value included in the first set of brightness values is different from a corresponding value included in the second set of brightness values; and
generate an output image, wherein generating the output image includes storing, at the first pixel position in the output image, a set of regularized values including the at least one common shared value, and storing, at the second pixel position in the output image, the set of regularized values including the at least one common shared value; and
a memory coupled to the processor and configured to provide the processor with instructions.
2. The system of claim 1 wherein the first image has a first amount of noise and wherein the output image has an amount of noise that is less than the first amount of noise.
3. The system of claim 1 wherein the processor is further configured to determine the common shared value at least in part by determining a mean brightness value for the first set of pixels.
4. The system of claim 1 wherein the processor is further configured to determine the common shared value at least in part by determining a median brightness value for the first set of pixels.
5. The system of claim 1 wherein the processor is further configured to determine the common shared value at least in part by determining a mean brightness value for a set of logarithms of the first set of pixels.
6. The system of claim 1 wherein the first image comprises multi-spectral data and wherein the set of regularized values stored at the first pixel includes a plurality of regularized values corresponding to each spectrum.
7. The system of claim 1 wherein the boundary map comprises a plurality of fields and wherein each field included in the plurality of fields has a unique identifier.
8. A method, comprising:
receiving: (1) a first image and (2) a boundary map constructed prior to receipt of the first image;
determining, at least in part by using the boundary map, that a plurality of different brightness values of a first set of pixels included in the first image should be regularized to at least one common shared value for the first set of pixels, wherein the first set of pixels includes, at a first pixel position in the first image, a first pixel having a first set of brightness values, and wherein the first set of pixels includes, at a second pixel position in the first image that is different from the first pixel position, a second set of brightness values, and wherein at least one value included in the first set of brightness values is different from a corresponding value included in the second set of brightness values; and
generating an output image, wherein generating the output image includes storing, at the first pixel position in the output image, a set of regularized values including the at least one common shared value, and storing, at the second pixel position in the output image, the set of regularized values including the at least one common shared value.
9. The method of claim 8 wherein the first image has a first amount of noise and wherein the output image has an amount of noise that is less than the first amount of noise.
10. The method of claim 8 further comprising determining the common shared value at least in part by determining a mean brightness value for the first set of pixels.
11. The method of claim 8 further comprising determining the common shared value at least in part by determining a median brightness value for the first set of pixels.
12. The method of claim 8 wherein determining the common shared value includes determining a mean brightness value for a set of logarithms of the first set of pixels.
13. The method of claim 8 wherein the first image comprises multi-spectral data and wherein the set of regularized values stored at the first pixel includes a plurality of regularized values corresponding to each spectrum.
14. The method of claim 8 wherein the boundary map comprises a plurality of fields and wherein each field included in the plurality of fields has a unique identifier.
15. A computer program product embodied in a tangible, non-transitory, computer readable storage medium and comprising instructions for:
receiving: (1) a first image and (2) a boundary map constructed prior to receipt of the first image;
determining, at least in part by using the boundary map, that a plurality of different brightness values of a first set of pixels included in the first image should be regularized to at least one common shared value for the first set of pixels, wherein the first set of pixels includes, at a first pixel position in the first image, a first pixel having a first set of brightness values, and wherein the first set of pixels includes, at a second pixel position in the first image that is different from the first pixel position, a second set of brightness values, and wherein at least one value included in the first set of brightness values is different from a corresponding value included in the second set of brightness values; and
generating an output image, wherein generating the output image includes storing, at the first pixel position in the output image, a set of regularized values including the at least one common shared value, and storing, at the second pixel position in the output image, the set of regularized values including the at least one common shared value.
16. The computer program product of claim 15 wherein the first image has a first amount of noise and wherein the output image has an amount of noise that is less than the first amount of noise.
17. The computer program product of claim 15 further comprising instructions for determining the common shared value at least in part by determining a mean brightness value for the first set of pixels.
18. The computer program product of claim 15 further comprising instructions for determining the common shared value at least in part by determining a median brightness value for the first set of pixels.
19. The computer program product of claim 15 wherein determining the common shared value includes determining a mean brightness value for a set of logarithms of the first set of pixels.
20. The computer program product of claim 15 wherein the first image comprises multi-spectral data and wherein the set of regularized values stored at the first pixel includes a plurality of regularized values corresponding to each spectrum.
21. The computer program product of claim 15 wherein the boundary map comprises a plurality of fields and wherein each field included in the plurality of fields has a unique identifier.