Computing higher resolution images from multiple lower resolution images

• US 20090324118A1
• Filed: 06/30/2008
• Published: 12/31/2009
• Est. Priority Date: 06/30/2008
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Pisarevsky, Vadim, Maslov, Oleg, Rodyushkin, Konstantin
• Granted Patent: US 8,326,069 B2
• Time in Patent Office: Days
• US Class Current: 382/254
• CPC Class Codes: G06T 3/4053 based on super-resolution, i.e. the output image resolution being higher than the sensor resolution

Abstract

Super-resolution images may be produced by dividing a higher resolution image into a set of non-overlapping rectangular tiles of substantially the same size. Then, each pixel in each lower resolution image is mapped to the higher resolution image and it is determined which tiles are mapped to which lower resolution image pixels. A continuous buffer may be allocated for each tile and the relevant lower resolution pixels may be stored, together with optical flow vectors, in that continuous buffer. Then, the determination of gradients may use the information now stored in the buffer to facilitate symmetric multiprocessing using multi-core processors.

Claims

1. A method comprising:

forming a super-resolution image by mapping lower resolution pixels to a particular area of a higher resolution image; and

collecting the associated data for said pixels within a buffer.

2. The method of claim 1 including collecting the associated data in a buffer that is continuous.

3. The method of claim 1 including dividing the higher resolution image into a set of non-overlapping rectangular tiles of substantially the same size.

4. The method of claim 3 including, for each pixel in each lower resolution image, finding its mapping to the higher resolution image.

5. The method of claim 4 including finding the tile within the higher resolution image that the pixels in the lower resolution image are mapped into.

6. The method of claim 5 including counting the number of lower resolution pixels mapped to each tile.

7. The method of claim 6 including, for each tile, allocating a continuous buffer of a size equal to the counted number of lower resolution pixels mapped into that tile.

8. The method of claim 7 including calculating a tile within the higher resolution image that a lower resolution pixel is mapped into and placing the value of the lower resolution pixels, together with its optical flow vector, within a continuous buffer for the tile.

9. The method of claim 8 including using the reorganized data to calculate a gradient for each tile.

10. The method of claim 9 including retrieving a low resolution pixel value and optical flow vector from the tile'"'"'s continuous buffer, using the optical flow vector to calculate a direct projection of the higher resolution image into the lower resolution pixel, and updating the tile'"'"'s gradient with the inverse projected delta.

11. The method of claim 9 including combining the gradients calculated for each tile into one combined gradient.

12. The method of claim 10 including calculating a gradient for each of a plurality of tiles in parallel on a multicore processor.

13. The method of claim 12 including updating values in a tile'"'"'s continuous buffer with an inverse projected delta that is equal to a robust function derivative of the difference between a direct projected pixel and a lower resolution pixel.

14. An apparatus comprising:

a multi-core processor to form a super-resolution image by mapping lower resolution pixels to a particular area of the higher resolution image; and

a buffer coupled to said processor to collect the associated data for said pixels.

15. The apparatus of claim 14 wherein said buffer is continuous.

16. The apparatus of claim 14, said processor to divide the higher resolution image into a set of non-overlapping rectangular tiles of substantially the same size.

17. The apparatus of claim 16, said processor to find the mapping for each pixel in each lower resolution image to the higher resolution image.

18. The apparatus of claim 17, said processor to find the tiles within the higher resolution image that the pixels in the lower resolution image are mapped into.

19. The apparatus of claim 18, said processor to allocate a continuous buffer for each tile.

20. The apparatus of claim 19, said processor to place the values of the lower resolution pixels, together with optical flow vectors, within a continuous buffer for each tile.

21. The apparatus of claim 20, said processor to use the reorganized data to calculate a gradient for each tile.

22. The apparatus of claim 21, said processor to combine the gradients calculated for each tile into one combined gradient.

23. The apparatus of claim 22, said apparatus to calculate a difference between a derivative of a robust function and a direct projection function.

24. The apparatus of claim 23, said processor to update each gradient with an inverse projected delta.