Methods and apparatuses for corner detection

1. An apparatus configured for head-worn by a user, comprising:

a screen configured to present graphics for the user;

a camera system configured to view an environment in which the user is located; and

a processing unit coupled to the camera system, the processing unit configured to:

obtain an image having a corner, and

detect corner in the image based on a constant k1,

wherein k1=R/(1+R){circumflex over ( )}2, where R is a number different from −1, and wherein a value of k1 is determined by selecting a number for R, and calculating k1 based on the above equation.

2. The apparatus of claim 1 , wherein the processing unit is configured to remove one or more duplicate detected corners in a set of corners detected from the image, the set of corners comprising the corner, before detecting the corner in the image.

3. The apparatus of claim 2 , wherein the processing unit is configured to detect the set of corners in the image based on one or more criteria; and

wherein the one or more criteria comprises a first criterion for excluding one or more objects in the image that is planar and/or that has insufficient texture, a second criterion for excluding one or more objects in the image that has a linear configuration, or both the first criterion and the second criterion.

4. The apparatus of claim 2 , wherein the processing unit is configured to perform spatial binning to select a subset of corners from the set of corners.

5. The apparatus of claim 4 , wherein the processing unit comprises hardware and software;

wherein the hardware of the processing unit is configured to detect the set of corners; and

wherein the software of the processing unit is configured to perform the spatial binning.

6. The apparatus of claim 2 , wherein the processing unit is configured to perform spatial binning by:

dividing the image into a plurality of image portions having a first image portion;

determining a score for each of the corners in the set of corners; and

selecting one or more corners from the corners in the first image portion based on the scores of the corners in the first image portion, and based on a prescribed maximum number of corners for the first image portion.

7. The apparatus of claim 2 , wherein the processing unit is configured to perform non-maxima suppression.

8. The apparatus of claim 7 , wherein the processing unit comprises hardware and software;

wherein the hardware of the processing unit is configured to detect the set of corners; and

wherein the software of the processing unit is configured to perform the non-maxima suppression.

9. The apparatus of claim 1 , wherein the processing unit is configured to detect a set of corners in the image that includes the corner; and

wherein the processing unit is also configured to detect the corner from the set of corners in the image.

10. The apparatus of claim 9 , wherein the processing unit comprises hardware configured to detect the set of corners in the image, and software configured to detect the corner from the set of corners in the image.

11. The apparatus of claim 1 , wherein the processing unit comprises a corner detector configured to operate based on a first criterion; and

wherein the first criterion excludes an object in the image that is planar and/or that has insufficient texture.

12. The apparatus of claim 11 , wherein the corner detector is further configured to operate based on a second criterion; and

wherein the second criterion excludes an object with a linear configuration in the image.

13. The apparatus of claim 1 , wherein the processing unit is configured to detect a second corner in the image based on a second constant k2.

14. The apparatus of claim 13 , wherein the second constant k2 is based on the constant k1.

15. The apparatus of claim 14 , wherein k2=(k1− 1/16)/16, and wherein a value of k2 is determined by obtaining a value for k1, and calculating k2 based on the above equation.

16. The apparatus of claim 1 , wherein the processing unit is configured to perform at least one of non-maxima suppression or spatial binning.

17. The apparatus of claim 16 , wherein the processing unit comprises software configured to perform the at least one of non-maxima suppression or spatial binning.

18. The apparatus of claim 1 , wherein the processing unit is configured to:

determine a position of the corner detected in the image; and

create a map based at least in part on the position of the corner; and

perform localization of the user based on the created map.

19. An apparatus configured for head-worn by a user, comprising:

a screen configured to present graphics for the user;

a camera system configured to view an environment in which the user is located; and

a processing unit coupled to the camera system, the processing unit configured to:

obtain an image having a corner,

determine a position of the corner in the image,

remove one or more duplicate detected corners in a set of corners detected from the image, the set of corners comprising the corner, and

remove a non-duplicate detected corner in the set of corners detected from the image based on corner scores and based on a prescribed maximum number of corners for an image portion that is geometrically smaller than the image.

20. A method performed by a head-worn image display device, comprising:

obtaining an image having a corner;

determining a position of the corner in the image;

removing one or more duplicate detected corners in a set of corners detected from the image, the set of corners comprising the corner; and

removing a non-duplicate detected corner in the set of corners detected from the image based on corner scores and based on a prescribed maximum number of corners for an image portion that is geometrically smaller than the image.