Filter setup learning for binary sensor

1. A method comprising:

receiving first binary pixel values, the first binary pixel values having been obtained by applying light of a first known color through an array of color filters onto an array of binary pixels, individual ones of said color filters being of unknown color;

receiving second binary pixel values, the second binary pixel values having been obtained by applying light of a second known color through said array of color filters onto said array of binary pixels;

receiving information on the colors of said light of said first and second known colors applied through said array of color filters onto said array of binary pixels;

forming an estimate of a color of a color filter associated with each of said binary pixels having binary pixel values indicating activation by said light of at least one of said known colors using said information on the colors of said light of said first and second known colors; and

storing estimates of the colors of said color filters in an image processing system for subsequent use in processing images.

2. The method according to claim 1 , further comprising:

exposing said binary pixels to said light of said first and second known colors through color filters superimposed on said binary pixels, said light having passed through an optical arrangement, and

forming said binary pixel values from the output of said binary pixels.

3. The method according to claim 1 , further comprising:

forming said estimate using likelihood estimation, and

refining said estimate iteratively.

4. The method according to claim 1 , further comprising:

determining neighborhoods of each of said binary pixels, and

using estimated values of binary pixels in said neighborhoods of each of said binary pixels as information in forming said estimate for each of said binary pixels.

5. The method according to claim 4 , further comprising:

forming said estimate by optimizing an energy function having a first component indicative of similarity of said color of said color filter and said color of said light of at least one of said known colors and a second component indicative of at least one difference in values of each of said binary pixels and a neighbor of each of said binary pixels.

6. The method according to claim 1 , wherein adjusting is performed in said image processing system to form initial values of the color filters of said binary pixels or to calibrate the values of the color filters of said binary pixels.

7. An apparatus comprising:

at least one processor, and

a memory including computer program code, the memory and the computer program code configured, with the at least one processor, to cause the apparatus to perform at least the following:

receive first binary pixel values, the first binary pixel values having been obtained by applying light of a first known color through an array of color filters onto an array of binary pixels, individual ones of said color filters being of unknown color;

receive second binary pixel values, the second binary pixel values having been obtained by applying light of a second known color through said array of color filters onto said array of binary pixels;

receive information on the colors of said light of said first and second known colors applied through said array of color filters onto said array of binary pixels;

form an estimate of a color of a color filter associated with each of said binary pixels having binary pixel values indicating activation by said light of at least one of said known color colors using said information on the color of said light; and

store estimates of the colors of said color filters in an image processing system for subsequent use in processing images.

8. The apparatus according to claim 7 , further comprising computer program code configured, with the processor, to cause the apparatus to perform at least the following:

expose said binary pixels to said light of said first and second known colors through color filters superimposed on said binary pixels, said light having passed through an optical arrangement, and

form said binary pixel values from the output of said binary pixels.

9. The apparatus according to claim 7 , further comprising computer program code configured, with the processor, to cause the apparatus to perform at least the following:

form said estimate using likelihood estimation, and

refine said estimate iteratively.

10. The apparatus according to claim 7 , further comprising computer program code configured, with the processor, to cause the apparatus to perform at least the following:

determine neighborhoods of each of said binary pixels, and

use estimated values of binary pixels in said neighborhoods of each of said binary pixels as information in forming said estimate for each of said binary pixels.

11. The apparatus according to claim 10 , further comprising computer program code configured, with the processor, to cause the apparatus to perform at least the following:

form said estimate by optimizing an energy function having a first component indicative of similarity of said color of said color filter and said color of said light of at least one of said known colors and a second component indicative of at least one difference in values of each of said binary pixels and a neighbor of each of said binary pixels.

12. The apparatus according to claim 7 , further comprising computer program code configured, with the processor, to cause the apparatus to perform at least the following:

adjusting said image processing system to form initial values of the color filters of said binary pixels or to calibrate the values of the color filters of said binary pixels.

13. The apparatus according to claim 7 , further comprising:

a color signal unit comprising at least one neural network, and a memory for storing parameters and/or weights of at least one said neural network.

14. The apparatus according to claim 7 , further comprising:

an optical arrangement for forming an image,

an array of binary pixels for detecting said image, and

groups of said binary pixels.

15. The apparatus according to claim 7 , further comprising:

at least one color filter superimposed on an array of binary pixels, said color filter being superimposed on said array of binary pixels in a manner that is at least one of the group of non-aligned, irregular, random, and unknown superimposition.

16. A system comprising:

at least one processor, and

a memory including computer program code, the memory and the computer program code configured, with the at least one processor, to cause the system to perform at least the following:

receive first binary pixel values, the first binary pixel values having been obtained by applying light of a first known color through an array of color filters onto an array of binary pixels, individual ones of said color filters being of unknown color;

receive second binary pixel values, the second binary pixel values having been obtained by applying light of a second known color through an array of color filters onto said array of binary pixels;

receive information on the colors of said light of said first and second known colors applied through said array of color filters onto said array of binary pixels;

form an estimate of a color of a color filter associated with each of said binary pixels having binary pixel values indicating activation by said light of at least one of said known color colors using said information on the colors of said light of said first and second known colors; and

store estimates of the colors of said color filters in an image processing system for subsequent use in processing images.

17. The system according to claim 16 , wherein the system further comprises:

an adjusting unit configured to receive said binary pixel values and said information on the colors of said light of said first and second known colors, and to form an estimate of a color of said color filter associated with each of said binary pixels by using said binary pixel values and said information on the colors of said light of said first and second known colors, and

an image processing unit comprising a binary pixel array with color filters and configured to form images, wherein said image processing unit is configured to receive adjustment information from said adjusting unit for adapting said image processing unit.

18. A computer program product stored on a non-transitory computer readable storage medium and executable in a data processing device, wherein the computer program product comprises:

a computer program code section for receiving first binary pixel values, the first binary pixel values having been obtained by applying light of a first known color through an array of color filters onto an array of binary pixels, individual ones of said color filters being of unknown color, and for receiving second binary pixel values, the second binary pixel values having been obtained by applying light of a second known color through said array of color filters onto said array of binary pixels;

a computer program code section for receiving information on the colors of said light of said first and second known colors applied through said array of color filters onto said array of binary pixels;

a computer program code section for forming an estimate of a color of a color filter associated with each of said binary pixels having binary pixel values indicating activation by said light of at least one of said known colors using said information on the colors of said light of said first and second known colors; and

a computer program code section for storing estimates of the colors of said color filters in an image processing system for subsequent use in processing images.

19. The computer program product according to claim 18 , wherein the computer program product further comprises:

a computer program code section for adjusting said image processing system to form initial values of the color filters of said binary pixels or to calibrate the values of the color filters of said binary pixels.