Methods and systems for providing selective disparity refinement

1. A method for processing an image, the method comprising:

executing, using at least one processor, operations comprising:

detecting at least one object of interest in an image that has an original disparity value within a disparity value threshold range, wherein the disparity value threshold range is based on a first disparity value of a selected point of interest in the image;

assigning a second disparity value to the detected at least one object of interest, wherein the second disparity value is based on at least one of the first disparity value or minimum and maximum disparity values in the disparity value threshold range; and

applying at least one effect to the image based on the second disparity value assigned to the detected at least one object of interest, to thereby modify the image for subsequent display.

2. The method of claim 1 , wherein the operations further comprise:

performing a redistribution of an original disparity value of each of at least one further object in the image having a disparity value outside the disparity value threshold range, based on at least one mapping function.

3. The method of claim 2 , wherein the mapping function is based on at least one of the original disparity value of the at least one further object, the disparity value of the point of interest, the assigned disparity value, and the minimum disparity value in the disparity value threshold range, wherein the original disparity value of the further object is less than the minimum disparity value in the disparity value threshold range.

4. The method of claim 2 , wherein the mapping function is based on at least one of the original disparity value of the at least one further object, the first disparity value of the point of interest, the assigned disparity value, the maximum disparity value in the disparity value threshold range, and maximum disparity value of the image, wherein the original disparity value of the at least one further object is higher than the maximum disparity value in the disparity value threshold range.

5. The method of claim 1 , wherein the at least one object of interest is detected by an object detection unit based on thermal response of the at least one object of interest, wherein a type of the detected object of interest is based on a type of the selected point of interest.

6. The method of claim 1 , further comprising obtaining the original disparity value of the at least one object of interest, and the first disparity value of the selected point of interest, from left and right images captured by a stereo camera.

7. The method of claim 1 , wherein,

the at least one effect is a bokeh effect; and

the bokeh effect is applied to pixels of the image outside regions of the first object of interest and the at least one second object of interest.

8. The method of claim 1 , wherein the operations further comprise outputting image data representing the modified image to a display; and further comprising displaying, by the display, the modified image.

9. An electronic device for processing an image, the electronic device comprising:

memory; and

at least one processor executing instructions read from the memory to perform operations comprising:

detecting at least one object of interest in an image that has an original disparity value within a disparity value threshold range, wherein the disparity value threshold range is based on a first disparity value of a selected point of interest in the image;

assigning a second disparity value to the detected at least one object of interest, wherein the second disparity value is based on at least one of the first disparity value or minimum and maximum disparity values in the disparity value threshold range; and

applying at least one effect to the image based on the second disparity value assigned to the detected at least one object of interest, to thereby modify the image for subsequent display.

10. The electronic device of claim 9 , wherein the operations further comprise: performing a redistribution of an original disparity value of each of at least one further object in the image having a disparity value outside the disparity value threshold range, based on at least one mapping function.

11. The electronic device of claim 10 , wherein the at least one mapping function comprises first and second mapping functions, the first mapping function is based on at least one of an original disparity value of the at least one further object, the disparity value of the point of interest, the assigned disparity value, and the minimum disparity value in the disparity value threshold range, wherein the original disparity value of the further object is less than the minimum disparity value in the disparity value threshold range, wherein the second mapping function is based on at least one of the original disparity value of the further object, the disparity value of the point of interest, the assigned disparity value, the maximum disparity value in the disparity value threshold range, and maximum disparity value of the image, wherein disparity value of the further object is higher than the maximum disparity value in the disparity value threshold range.

12. The electronic device of claim 9 , wherein the at least one object of interest is detected by an object detection unit based on thermal response of the at least one object of interest, wherein a type of the detected object of interest is based on a type of the selected point of interest.

13. The electronic device of claim 9 , wherein the at least one processor comprises an object detection circuit configured to detect objects based on at least one of thermal imaging or pattern analysis, an object processing circuit configured to determine disparity values of objects in the image; and a disparity assigning circuit configured to assign the second disparity value to the at least one object of interest.

14. The electronic device of claim 9 , further comprising a stereo camera configured to capture left and right images, wherein,

the image is obtained based on at least one of the left and right images; and

the original disparity value of the at least one object of interest, and the first disparity value of the selected point of interest, are obtained from the left and right images.

15. A non-transitory computer-readable recording medium storing instructions that, when executed by at least one processor, implement a method for processing an image, the method comprising:

receiving a selection for a point of interest coinciding with a first object of interest in the image, the point of interest having a first disparity value;

defining a disparity value threshold range encompassing the first disparity value;

detecting at least one second object of interest in the image that has a disparity value within the disparity value threshold range;

assigning a same modified disparity value to each of the first object of interest and the at least one second object of interest, the modified disparity value being different from each of the first and second disparity values; and

applying at least one effect to the image based on the modified disparity value assigned to the detected at least one object of interest, to thereby modify the image for subsequent display.

16. The non-transitory computer-readable recording medium of claim 15 , wherein,

the at least one effect is a bokeh effect; and

the bokeh effect is applied to pixels of the image outside regions of the first object of interest and the at least one second object of interest.

17. The non-transitory computer-readable recording medium of claim 16 , wherein the method further comprises:

identifying further objects of interest in the image having original disparity values outside the disparity value threshold range;

assigning redistributed disparity values to the further objects of interest that are based on the first disparity value of the point of interest and the disparity value of the at least one second object of interest; and

applying the bokeh effect to the further objects of interest.

18. The non-transitory computer-readable recording medium of claim 17 , wherein the bokeh effect is applied to each of the further objects of interest in a manner dependent upon the redistributed disparity values thereof.

19. The non-transitory computer-readable recording medium of claim 17 , wherein the at least one second object of interest comprises a plurality of second objects of interest, and wherein the method further comprises:

defining a refined disparity value threshold range of (D poi −t 1 to D poi +t 2 ), where D poi is the first disparity value of the first object of interest, D poi −t 1 and D poi +t 2 are disparity values of the second objects of interest with minimum and maximum disparity values respectively within the disparity value threshold range; and

the modified disparity value is defined by:

M=D poi +floor( t 2 −t 1 /2),

where floor (x) is a function that rounds the elements of x to the nearest integer or to the nearest integer less than or equal to x.

20. The non-transitory computer-readable recording medium of claim 19 , wherein the redistributed disparity values assigned to the further objects of interest are obtained by:

for the further objects of interest having disparity values less than D poi −t 1 , a first mapping function for assigning a redistributed disparity value ‘Y’ to each said further object of interest with an original disparity value ‘X’, within the range (0 to (D poi −t 1 −1)) is obtained by:

Y=X /( D poi −t 1 −1)*( M− 1)

and

for the further objects of interest having original disparity values more than D poi +t 2 , a second mapping function for assigning a redistributed disparity value ‘Y’ to each said further object of interest having an original disparity value ‘X’ is:

Y={X −( D poi +t 2 +1)}/{(2 n −1)−( D poi +t 2 +1)}*{(2 n −1)−( M− 1)}+( M+ 1),

where disparity values of pixels in the image are represented by n bits.