Morphological Automatic Triangle Orientation Detection

• US 20160328626A1
• Filed: 05/05/2016
• Published: 11/10/2016
• Est. Priority Date: 05/07/2015
• Status: Active Grant

• Current Assignee: US Department of The Air Force (U.S. Department Of Defense)
• Original Assignee: US Department of The Air Force (U.S. Department Of Defense)
• Inventors: Pinkus, Alan R, Dommett, David W, Task, Harry Lee
• Granted Patent: US 9,679,216 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• CPC Class Codes: G06V 10/242 by image rotation, e.g. by 90 degrees
• CPC Class Codes: G06V 10/267 by performing operations on regions, e.g. growing, shrinking or watersheds
• CPC Class Codes: G06V 10/467 Encoded features or binary features, e.g. local binary patterns [LBP]
• CPC Class Codes: H04N 17/002 for television cameras

Abstract

A system and method are provided for assessing a resolution of an optical sensor. An image is obtained from the optical sensor. A target area is selected from the image. The selected area is subjected to a thresholding process to generate a binary image. Pixels at a center of the binary image are tagged. The remaining pixels of the binary image are looped through, where pixels that are not already tagged, are touching a tagged pixel, and are of the same color of previously tagged pixels are tagged. A plurality of distances associated with each corner of the binary image is calculated from the corner to the nearest tagged pixel in a row or column of pixels. At least two shortest distances of the calculated plurality of distances are selected to determine an orientation of an object defined by the tagged pixels in the generated binary image.

Claims

1. A method of assessing a resolution of an optical sensor, the method comprising:

obtaining an image from the optical sensor;

selecting a target area from the obtained image;

thresholding the selected area to generate a binary image;

tagging pixels at a center of the generated binary image;

looping through remaining pixels of the generated binary image, tagging pixels that are not already tagged, touching a tagged pixel, and are of the same color of previously tagged pixels;

calculating a plurality of distances associated with each corner of the generated binary image from the corner to the nearest tagged pixel in a row or column of pixels;

selecting at least two shortest distances of the calculated plurality of distances; and

determining an orientation of an object defined by the tagged pixels in the generated binary image from the selected distances.

2. The method of claim 1, further comprising:

comparing the determined orientation to a known orientation; and

assessing a quality of the optical sensor.

3. The method of claim 1, further comprising:

eliminating noise pixels in the binary image near the object after thresholding.

4. The method of claim 1, further comprising:

removing pixels of the same color as the tagged pixels that are not tagged before calculating the plurality of distances.

5. A system comprising:

an optical sensor;

a memory;

a processor; and

program code resident in the memory and configured to assess a resolution of the optical sensor, the program code further configured, when executed by the processor, to obtain an image from the optical sensor, select a target area from the obtained image;

threshold the selected area to generate a binary image;

tag pixels at a center of the generated binary image;

loop through remaining pixels of the generated binary image, tagging pixels that are not already tagged, touching a tagged pixel, and are of the same color of previously tagged pixels;

calculate a plurality of distances associated with each corner of the generated binary image from the corner to the nearest tagged pixel in a row or column of pixels;

select at least two shortest distances of the calculated plurality of distances; and

determine an orientation of an object defined by the tagged pixels in the generated binary image from the selected distances.

6. The system of claim 5, wherein the program code is further configured to:

compare the determined orientation to a known orientation; and

assess a quality of the optical sensor.

7. The system of claim 5, wherein the program code is further configured to eliminate noise pixels in the binary image near the object after thresholding.

8. The system of claim 5, wherein the program code is further configured to remove pixels of the same color as the tagged pixels that are not tagged before calculating the plurality of distances.

9. The system of claim 5, wherein the optical sensor is selected from a group consisting of visible sensors, near infrared sensors, short-wave infrared sensors, thermal sensors, and combinations thereof.

10. The system of claim 5, wherein the optical sensor is a synthetic sensor providing algorithmically combined information from multiple sensors.

11. A program product comprising:

a non-transitory computer recordable type medium; and

program code resident on the computer recordable type medium and configured to assess a resolution of the optical sensor, the program code further configured, when executed on a hardware implemented processor, to obtain an image from the optical sensor, select a target area from the obtained image;

threshold the selected area to generate a binary image;

tag pixels at a center of the generated binary image;

loop through remaining pixels of the generated binary image, tagging pixels that are not already tagged, touching a tagged pixel, and are of the same color of previously tagged pixels;

calculate a plurality of distances associated with each corner of the generated binary image from the corner to the nearest tagged pixel in a row or column of pixels;

select at least two shortest distances of the calculated plurality of distances; and

determine an orientation of an object defined by the tagged pixels in the generated binary image from the selected distances.

12. The program product of claim 11, wherein the program code is further configured to:

compare the determined orientation to a known orientation; and

assess a quality of the optical sensor.

13. The program product of claim 11, wherein the program code is further configured to eliminate noise pixels in the binary image near the object after thresholding.

14. The program product of claim 11, wherein the program code is further configured to remove pixels of the same color as the tagged pixels that are not tagged before calculating the plurality of distances.