Door and Window Detection in an AR Environment

1 . A method performed by a processor for locating ceiling and floor within a 3D mesh, the method comprising:

locating, within a memory associated with the processor, a 3D mesh representing a surface of a room, the 3D mesh having z values;

finding a minimum z value of the 3D mesh;

finding a maximum z value of the 3D mesh;

making a histogram of the z values;

determining the histogram with most area in an up direction;

determining the histogram with most area in a down direction;

setting the histogram with most area in an up direction as a ceiling; and

setting the histogram with most area in a down direction as a floor.

2 . The method of claim 1 , wherein the up direction is oriented with respect to gravity.

3 . The method of claim 1 , further comprising finding a hole.

4 . The method of claim 3 , wherein finding a hole further comprises determining a virtual picture bottom and a virtual picture top.

5 . The method of claim 4 , further comprising locating a 2D segment correlated with the 3D mesh.

6 . The method of claim 5 , further comprising using the virtual picture bottom and the virtual picture top, taking a virtual 2D picture of the 3D mesh along the 2D segment.

7 . The method of claim 6 , further comprising finding the hole within the virtual 2D picture.

8 . The method of claim 7 , wherein when the hole does not intersect the vertical picture bottom or when the hole is not at least as wide as a predetermined door width, then classifying the hole as a window.

9 . The method of claim 8 , wherein taking a virtual 2D picture of the 3D mesh along the 2D segment comprises taking a virtual picture with a y axis running from the virtual picture bottom to the virtual picture top.

10 . A system for locating features within a 3D mesh, the system comprising:

a processor in communication with a memory storing a 3D mesh, the processor being configured to:

locate, within the memory, a 3D mesh representing a surface of a room, the 3D mesh having z values;

find a minimum z value of the 3D mesh;

find a maximum z value of the 3D mesh;

use the minimum z value and the maximum z value to make a histogram of the z values;

determine the histogram with most area in an up direction;

determine the histogram with most area in a down direction;

set the histogram with most area in an up direction as a ceiling; and

set the histogram with most area in a down direction as a floor.

11 . The system of claim 10 , wherein the down direction is oriented with respect to gravity.

12 . The system of claim 10 , the processor being further configured to find a hole.

13 . The system of claim 12 , the processor being further configured to determine a virtual picture bottom and a virtual picture top.

14 . The system of claim 13 , the processor being further configured to locate a 2D segment correlated with the 3D mesh.

15 . The system of claim 14 , the processor being further configured to:

use the virtual picture bottom and the virtual picture top, taking a virtual 2D picture of the 3D mesh along the 2D segment; and

find the hole within the virtual 2D picture.

16 . The system of claim 15 , wherein taking a virtual 2D picture of the 3D mesh along the 2D segment comprises taking a virtual picture with a y axis running from the virtual picture bottom to the virtual picture top.

17 . A non-transitory machine-readable storage medium encoded with instructions for execution by a processor for locating features within a 3D mesh, the non-transitory machine-readable storage medium comprising:

instructions for locating, within a memory associated with the processor, a 3D mesh representing a surface of a room, the 3D mesh having z values;

instructions for finding a minimum z value of the 3D mesh;

finding a maximum z value of the 3D mesh;

instructions for making a histogram of the z values;

instructions for determining the histogram with highest z values in a positive direction;

instructions for setting a histogram with most area in an up direction as a ceiling; and

instructions for setting a histogram with most area in a down direction as a floor.

18 . The non-transitory machine-readable storage medium of claim 17 , further comprising finding a hole.

19 . The non-transitory machine-readable storage medium of claim 18 , wherein finding a hole further comprises determining a virtual picture bottom and a virtual picture top.

20 . The non-transitory machine-readable storage medium of claim 18 , further comprising:

locating a 2D segment correlated with the 3D mesh; and

using a virtual picture bottom and a virtual picture top, taking a virtual 2D picture of the 3D mesh along the 2D segment.