Apparatus and method for providing three dimensional media content
A system that incorporates teachings of the exemplary embodiments may include, for example, means for generating a disparity map based on a depth map, means for determining accuracy of pixels in the depth map where the determining means identifies the pixels as either accurate or inaccurate based on a confidence map and the disparity map, and means for providing an adjusted depth map where the providing means adjusts inaccurate pixels of the depth map using a cost function associated with the inaccurate pixels. Other embodiments are disclosed.
1. A machine-readable storage device, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:
determining an accuracy of pixels in a depth map by identifying pixels as either accurate or inaccurate based on a confidence map and a disparity map;
adjusting the depth map by adjusting pixels identified as inaccurate pixels in the depth map to generate an adjusted depth map; and
generating media content according to images captured by a camera and the adjusted depth map.
2. The machine-readable storage device of claim 1 , wherein the processor comprises a media processor.
3. The machine-readable storage device of claim 1 , wherein the inaccurate pixels are identified by measuring a disparity variance for a pre-determined region surrounding each pixel of a disparity map generated from the depth map.
4. The machine-readable storage device of claim 1 , wherein the depth map is captured by a range camera.
5. The machine-readable storage device of claim 1 , wherein the inaccurate pixels in the depth map are adjusted according to a graph-cut analysis.
6. The machine-readable storage device of claim 1 , wherein the inaccurate pixels in the depth map are adjusted according to a belief-propagation analysis.
7. The machine-readable storage device of claim 1 , wherein the inaccurate pixels in the depth map are adjusted according to a cost function.
8. The machine-readable storage device of claim 1 , wherein the operations further comprise generating the depth map by measuring parameters associated with infrared light to obtain range data associated with an object in the images captured by the camera.
9. The machine-readable storage device of claim 1 , wherein the operations further comprise providing the media content for presentation at a display device.
10. A method comprising:
receiving, by a processor, images captured by a camera;
determining, by the processor, an accuracy of pixels in a depth map by identifying pixels as either accurate or inaccurate according to a confidence map and a disparity map;
adjusting, by the processor, the depth map by adjusting pixels identified as inaccurate pixels in the depth map to generate an adjusted depth map; and
generating, by the processor, media content according to the images and the adjusted depth map.
11. The method of claim 10 , further comprising presenting the media content at a display device.
12. The method of claim 10 , wherein the determining comprises determining inaccurate pixels by measuring a disparity variance for a pre-determined region surrounding each pixel of the disparity map generated from the depth map.
13. The method of claim 10 , wherein the depth map is captured by a range camera.
14. The method of claim 10 , wherein the inaccurate pixels in the depth map are adjusted according to a graph-cut analysis.
15. The method of claim 10 , wherein the inaccurate pixels in the depth map are adjusted according to a belief-propagation analysis.
16. The method of claim 10 , wherein the inaccurate pixels in the depth map are adjusted according to a cost function.
17. The method of claim 10 , further comprising generating the depth map by measuring parameters associated with infrared light to obtain range data associated with an object in the images captured by the camera.
18. The method of claim 10 , wherein homographic warping approximation is used for calibration of the media content.
19. A device comprising:
a processor; and
a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:
determining an accuracy of pixels in a depth map by identifying pixels as either accurate or inaccurate according to a confidence map and a disparity map; and
adjusting the depth map by adjusting pixels identified as inaccurate pixels in the depth map to generate an adjusted depth map.
20. The device of claim 19 , wherein the operations further comprise:
receiving images captured by a camera; and
generating media content based on the images and the adjusted depth map.