Granted Patent B2

US 8,638,329 · App. 12/634,379 · Granted Jan 28, 2014

Abstract

Claims (44)

1. A computerized method for auto-stereoscopic interpolation, the method comprising:

executing a computer program encoded on a non-transitory computer-readable medium to perform the steps of:

receiving, by an input unit of a computer, a first two dimensional image and a second two dimensional image, each two dimensional image comprising a pixel size;

generating, by a preprocessing unit of the computer, a reduced pixel image for each of the first and second two dimensional images, wherein each reduced pixel image comprises a reduced pixel size that is less than the pixel size;

calculating, by the preprocessing unit, boundary information for each of the first and second two dimensional images;

calculating, by a depth map unit of the computer, a depth map for the first and second reduced pixel images, wherein the depth map comprises data indicative of three dimensional information for one or more objects in the first and second reduced pixel images; and

calculating, by the depth map unit of the computer, a depth map for the first and second two dimensional images based on the boundary information for each of the first and second two dimensional images and the depth map of the first and second reduced pixel images.

2. The method of claim 1 , further comprising generating a third two dimensional image based on the depth map for the first and second two dimensional images, wherein the third two dimensional image comprises a vantage point that is between a first vantage point of the first two dimensional image and a second vantage point of the second two dimensional image.

3. The method of claim 1 , wherein calculating the depth map for the first and second reduced pixel images comprises generating the data based on a difference in pixel locations for each of the objects in the reduced pixel images.

4. The method of claim 3 , further comprising:

comparing two corresponding pixels, wherein a first pixel of the two corresponding pixels is located within the first reduced pixel image and a second pixel of the two corresponding pixels is located within the second reduced pixel image;

calculating a distance value indicative of how far apart the first pixel is from the second pixel; and

assigning data indicative of depth information for the two corresponding pixels in the depth map to indicate the object is away from a viewer for a three dimensional view that includes the object.

5. The method of claim 3 , further comprising:

comparing two corresponding pixels, wherein a first pixel of the two corresponding pixels is located within the first reduced pixel image and a second pixel of the two corresponding pixels is located within the second reduced pixel image;

calculating a cross value indicative of how far crossed the first pixel is from the second pixel; and

assigning data indicative of depth information for the two corresponding pixels in the depth map to indicate the object is close to a viewer for a three dimensional view that includes the object.

6. The method of claim 1 , wherein the pixel size is calculated as the product of a length of pixels and a width of pixels of each corresponding two dimensional image.

7. The method of claim 1 , wherein calculating a depth map for the first and second two dimensional images comprises:

calculating the depth map of each boundary pixel for the boundary information based on the first and second two dimensional images; and

determining depth information of the depth map for remaining pixels with data near corresponding boundary pixels of the first and second reduced pixel images.

8. The method of claim 1 , wherein calculating the boundary information comprises:

generating a plurality of color segmented frames based on the two dimensional image, wherein each color segmented frame comprises one or more objects; and

for each pixel of the first and second reduced pixel images, setting a boundary point indicator for the pixel based on the color segmented frames, wherein the boundary point indicator comprises data indicative of whether or not the pixel is a boundary point.

9. The method of claim 8 , comprising verifying each of the plurality of color segmented frames comprises one or more cohesive objects, each cohesive object comprising identifiable boundary lines.

10. The method of claim 8 , wherein calculating the depth map comprises identifying a hidden pixel of the first reduced pixel image by identifying a visible pixel within the first reduced pixel image, wherein the visible pixel does not have a corresponding pixel within the second reduced pixel image.

11. The method of claim 10 , further comprising generating a third two dimensional image based on the depth map for the first and second two dimensional images, wherein the third two dimensional image comprises a vantage point that is between a first vantage point of the first two dimensional image and a second vantage point of the second two dimensional image, and wherein the third two dimensional image comprises an area coming into view or an area going out of view based on the identified hidden pixel.

12. A system for auto-stereoscopic interpolation, the system comprising:

a non-transitory computer-readable medium encoded with a computer program comprising:

an input unit configured to cause a processor to receive a first two dimensional image and a second two dimensional image, each two dimensional image comprising a pixel size;

a preprocessing unit in communication with the input unit configured to cause the processor to:

generate a reduced pixel image for each of the first and second two dimensional images, wherein each reduced pixel image comprises a reduced pixel size that is less than the pixel size; and

calculate boundary information for each of the first and second two dimensional images; and

a depth map unit in communication with the preprocessing unit configured to cause the processor to:

calculate a depth map for the first and second reduced pixel images, wherein the depth map comprises data indicative of three dimensional information for one or more objects in the first and second reduced pixel images; and

calculate a depth map for the first and second two dimensional images based on the boundary information for each of the first and second two dimensional images and the depth map of the first and second reduced pixel images.

13. The system of claim 12 , further comprising a color segmentation unit in communication with the preprocessing unit configured to cause the processor to generate a plurality of color segmented frames based on the two dimensional image, wherein each color segmented frame comprises one or more objects.

14. The system of claim 12 , further comprising a conversion unit configured to generate a third two dimensional image based on the depth map, wherein the third two dimensional image comprises a vantage point that is between a first vantage point of the first two dimensional image and a second vantage point of the second two dimensional image.

15. A computer program product, tangibly embodied in a non-transitory computer readable storage medium, the computer program product including instructions being operable to cause a data processing apparatus to:

receive a first two dimensional image and a second two dimensional image, each two dimensional image comprising a pixel size;

generate a reduced pixel image for each of the first and second two dimensional images, wherein each reduced pixel image comprises a reduced pixel size that is less than the pixel size;

calculate boundary information for each of the first and second two dimensional images;

calculate a depth map for the first and second reduced pixel images, wherein the depth map comprises data indicative of three dimensional information for one or more objects in the first and second reduced pixel images; and

calculate a depth map for the first and second two dimensional images based on the boundary information for each of the first and second two dimensional images and the depth map of the first and second reduced pixel images.

Assignments (42)