Identifying and evaluating potential center stringers of a pallet in an image scene

1. A method for evaluating a possible center stringer of a pallet comprising:

providing a first Ro image comprising pixels that may generally correspond to an orthogonal distance from an origin point to one or more possible vertical left lines in a corresponding gray scale image;

providing a second Ro image comprising pixels that may generally correspond to an orthogonal distance from an origin point to one or more possible vertical right lines in the corresponding gray scale image;

identifying, using a computer, a possible lower left corner location of a center stringer in the corresponding gray scale image;

determining, using the computer, an upper left corner location based on the possible lower left corner location;

identifying, using the computer, a possible lower right corner location of the center stringer in the corresponding gray scale image; and

determining, using the computer, an upper right corner location based on the possible lower right corner location.

2. The method of claim 1 , wherein the upper left corner location is horizontally aligned with the possible lower left corner location and located a predetermined number of pixels above the possible lower left corner location.

3. The method of claim 2 , wherein the upper right corner location is horizontally aligned with the possible lower right corner location and located the predetermined number of pixels above the possible lower right corner location.

4. The method of claim 1 , further comprising:

calculating a left vertical stringer line extending between the possible lower left corner location and the upper left corner location.

5. The method of claim 4 , wherein calculating a left vertical stringer line further comprises calculating:

φ

1

=

tan

-

1

⁡

(

P

LowerLeft

⁡

(

y

)

-

P

UpperLeft

⁡

(

y

)

P

LowerLeft

⁡

(

x

)

-

P

UpperLeft

⁡

(

x

)

)

ρ

1

⁢

desired

=

-

P

LowerLeft

⁡

(

x

)

⁢

sin

⁢

⁢

φ

1

+

P

LowerLeft

⁡

(

y

)

⁢

cos

⁢

⁢

φ

1

wherein:

φ 1 =is an angle between a horizontal line and the left vertical stringer line;

P LowerLeft (y)=a Y coordinate value for the possible lower left corner location;

P UpperLeft (y)=a Y coordinate value for the upper left corner location;

P LowerLeft (x)=an X coordinate value for the possible lower left corner location;

P UpperLeft (x)=an X coordinate value for the upper left corner location;

ρ 1desired =an orthogonal distance from an origin point on the corresponding gray scale image to a vertical line passing through the possible lower left corner location and the upper left corner location.

6. The method of claim 5 , further comprising:

identifying a plurality of contiguous pixel locations adjacent the possible lower left corner location and extending vertically upwards, the plurality of pixel locations comprising h left pixels.

7. The method of claim 6 , wherein:

h left =min( P LowerLeft ( y )− P UpperLeft ( y ),10).

8. The method of claim 7 , further comprising:

calculating a score value, Score left , that represents a likelihood that the plurality of contiguous pixel locations correspond to an actual stringer left edge in the corresponding gray scale image, wherein:

Score

left

=

A

1

h

left

where A 1 is an accumulator value that is incremented each time the following inequality is true:

|ρ( x i ,y i )−ρ 1desired |≦TOL 4*ρ 1desired

wherein:

i=an index value referring to x and y coordinates of one particular pixel location of the plurality of contiguous pixel locations, the index value ranging from 1 to h left ;

ρ(x i , y i )=a value of an i th pixel in the first Ro image at the one particular pixel location of the plurality of contiguous pixel locations;

TOL4=an empirically determined value equal to 0.5.

9. The method of claim 1 , further comprising:

calculating a right vertical stringer line extending between the possible lower right corner location and the upper right corner location.

10. The method of claim 9 , wherein calculating a right vertical stringer line further comprises calculating:

φ

2

=

tan

-

1

⁡

(

P

LowerRight

⁡

(

y

)

-

P

UpperRight

⁡

(

y

)

P

LowerRight

⁡

(

x

)

-

P

UpperRight

⁡

(

x

)

)

ρ

2

⁢

desired

=

-

P

LowerRight

⁡

(

x

)

⁢

sin

⁢

⁢

φ

2

+

P

LowerRight

⁡

(

y

)

⁢

cos

⁢

⁢

φ

2

wherein:

φ 2 =is an angle between a horizontal line and the right vertical stringer line;

P LowerRight (y)=a Y coordinate value for the possible lower right corner location;

P UpperRight (y)=a Y coordinate value for the upper right corner location;

P LowerRight (x)=an X coordinate value for the possible lower right corner location;

P UpperRight (x)=an X coordinate value for the upper right corner location;

ρ 2desired =an orthogonal distance from an origin point on the corresponding gray scale image to a vertical line passing through the possible lower right corner location and the upper right corner location.

11. The method of claim 10 , further comprising:

identifying a plurality of contiguous pixel locations adjacent the possible lower right corner and extending vertically upwards, the plurality of pixel locations comprising h right pixels.

12. The method of claim 11 , wherein:

h right =min( P LowerRight ( y )− P UpperRight ( y ),10).

13. The method of claim 12 , further comprising:

calculating a score value, Score right , that represents a likelihood that the plurality of contiguous pixel locations correspond to an actual stringer right edge in the corresponding gray scale image, wherein:

Score

right

=

A

2

h

right

where A 2 is an accumulator value that is incremented each time the following inequality is true:

|ρ( x j ,y j )−ρ 2desired |≦TOL 4*ρ 2desired

wherein:

j=an index value referring to x and y coordinates of one particular pixel location of the plurality of contiguous pixel locations, the index value ranging from 1 to h right ;

ρ(x j , y j )=a value of j th pixel in the second Ro image at the one particular pixel location of the plurality of contiguous pixel locations;

TOL4=an empirically determined value equal to 0.5.

14. A system for evaluating a possible center stringer of a pallet comprising:

a memory storage device;

a computer configured to execute instructions stored in the memory storage device;

a first Ro image comprising pixels that may generally correspond to an orthogonal distance from an origin point to one or more possible vertical left lines in a corresponding gray scale image;

a second Ro image comprising pixels that may generally correspond to an orthogonal distance from an origin point to one or more possible vertical right lines in the corresponding gray scale image;

the computer when executing instructions stored in the memory storage device:

identifies a possible lower left corner location of a center stringer in the corresponding gray scale image;

determines an upper left corner location based on the possible lower left corner location;

identifies a possible lower right corner location of the center stringer in the corresponding gray scale image; and

determines an upper right corner location based on the possible lower right corner location.

15. The system of claim 14 , wherein the upper left corner location is horizontally aligned with the possible lower left corner location and located a predetermined number of pixels above the possible lower left corner location.

16. The system of claim 15 , wherein the upper right corner location is horizontally aligned with the possible lower right corner location and located the predetermined number of pixels above the possible lower right corner location.

17. The system of claim 14 , wherein the computer when executing instructions stored in the memory storage device:

calculates a left vertical stringer line extending between the possible lower left corner location and the upper left corner location.

18. The system of claim 17 , wherein the computer when calculating the left vertical stringer line, calculates:

φ

1

=

tan

-

1

⁡

(

P

LowerLeft

⁡

(

y

)

-

P

UpperLeft

⁡

(

y

)

P

LowerLeft

⁡

(

x

)

-

P

UpperLeft

⁡

(

x

)

)

ρ

1

⁢

desired

=

-

P

LowerLeft

⁡

(

x

)

⁢

sin

⁢

⁢

φ

1

+

P

LowerLeft

⁡

(

y

)

⁢

cos

⁢

⁢

φ

1

ρ 1desired =−P LowerLeft ( x )sin φ 1 +P LowerLeft ( y )cos φ 1

wherein:

φ 1 =is an angle between a horizontal line and the left vertical stringer line;

P LowerLeft (y)=a Y coordinate value for the possible lower left corner location;

P UpperLeft (y)=a Y coordinate value for the upper left corner location;

P LowerLeft (x) an X coordinate value for the possible lower left corner location;

P UpperLeft (x) an X coordinate value for the upper left corner location;

ρ 1desired =an orthogonal distance from an origin point on the corresponding gray scale image to a vertical line passing through the possible lower left corner location and the upper left corner location.

19. The system of claim 18 , wherein the computer when executing instructions stored in the memory storage device:

identifies a plurality of contiguous pixel locations adjacent the possible lower left corner location and extending vertically upwards, the plurality of pixel locations comprising h left pixels.

20. The system of claim 19 , wherein:

h left =min( P LowerLeft ( y )− P UpperLeft ( y ),10).

21. The system of claim 20 , wherein the computer when executing instructions stored in the memory storage device:

calculates a score value, Score left , that represents a likelihood that the plurality of contiguous pixel locations correspond to an actual stringer left edge in the corresponding gray scale image, wherein:

Score

left

=

A

1

h

left

where A 1 is an accumulator value that is incremented each time the following inequality is true:

|ρ( x i ,y i )−ρ 1desired |≦TOL 4*ρ 1desired

wherein:

i=an index value referring to x and y coordinates of one particular pixel location of the plurality of contiguous pixel locations, the index value ranging from 1 to h left ;

ρ(x i , y i )=a value of an i th pixel in the first Ro image at the one particular pixel location of the plurality of contiguous pixel locations;

TOL4=an empirically determined value equal to 0.5.

22. The system of claim 14 , wherein the computer when executing instructions stored in the memory storage device:

calculates a right vertical stringer line extending between the possible lower right corner location and the upper right corner location.

23. The system of claim 22 , wherein the computer when calculating the right vertical stringer line, calculates:

φ

2

=

tan

-

1

⁡

(

P

LowerRight

⁡

(

y

)

-

P

UpperRight

⁡

(

y

)

P

LowerRight

⁡

(

x

)

-

P

UpperRight

⁡

(

x

)

)

ρ

2

⁢

desired

=

-

P

LowerRight

⁡

(

x

)

⁢

sin

⁢

⁢

φ

2

+

P

LowerRight

⁡

(

y

)

⁢

cos

⁢

⁢

φ

2

wherein:

φ 2 =is an angle between a horizontal line and the right vertical stringer line;

P LowerRight (y)=a Y coordinate value for the possible lower right corner location;

P UpperRight (y)=a Y coordinate value for the upper right corner location;

P LowerRight (x)=an X coordinate value for the possible lower right corner location;

P UpperRight (x)=an X coordinate value for the upper right corner location;

ρ 1desired =an orthogonal distance from an origin point on the corresponding gray scale image to a vertical line passing through the possible lower right corner location and the upper right corner location.

24. The system of claim 23 , wherein the computer when executing instructions stored in the memory storage device:

identifies a plurality of contiguous pixel locations adjacent the possible lower right corner and extending vertically upwards, the plurality of pixel locations comprising h right pixels.

25. The system of claim 24 , wherein:

h right =min( P LowerRight ( y )− P UpperRight ( y ),10).

26. The system of claim 25 , wherein the computer when executing instructions stored in the memory storage device:

calculates a score value, Score right , that represents a likelihood that the plurality of contiguous pixel locations correspond to an actual stringer right edge in the corresponding gray scale image, wherein:

Score

right

=

A

2

h

right

where A 2 is an accumulator value that is incremented each time the following inequality is true:

|ρ( x j ,y j )−ρ 2desired |≦TOL 4*ρ 2desired

wherein:

j=an index value referring to x and y coordinates of one particular pixel location of the plurality of contiguous pixel locations, the index value ranging from 1 to h right ;

ρ(x j , y j )=a value of j th pixel in the second Ro image at the one particular pixel location of the plurality of contiguous pixel locations;

TOL4=an empirically determined value equal to 0.5.

27. A computer program product for evaluating a possible center stringer of a pallet, comprising:

a non-transitory computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising:

computer readable program code configured to analyze a first Ro image comprising pixels that may generally correspond to an orthogonal distance from an origin point to one or more possible vertical left lines in a corresponding gray scale image;

computer readable program code configured to analyze a second Ro image comprising pixels that may generally correspond to an orthogonal distance from an origin point to one or more possible vertical right lines in the corresponding gray scale image;

computer readable program code configured to identify a possible lower left corner location of a center stringer in the corresponding gray scale image;

computer readable program code configured to determine an upper left corner location based on the possible lower left corner location;

computer readable program code configured to identify a possible lower right corner location of the center stringer in the corresponding gray scale image; and

computer readable program code configured to determine an upper right corner location based on the possible lower right corner location.

28. The computer program product of claim 27 , wherein the upper left corner location is horizontally aligned with the possible lower left corner location and located a predetermined number of pixels above the possible lower left corner location.

29. The computer program product of claim 28 , wherein the upper right corner location is horizontally aligned with the possible lower right corner location and located the predetermined number of pixels above the possible lower right corner location.

30. The computer program product of claim 27 , further comprising:

computer readable program code configured to calculate a left vertical stringer line extending between the possible lower left corner location and the upper left corner location.

31. The computer program product of claim 30 , wherein the computer readable program code configured to calculate a left vertical stringer line is further configured to calculate:

φ

1

=

tan

-

1

⁡

(

P

LowerLeft

⁡

(

y

)

-

P

UpperLeft

⁡

(

y

)

P

LowerLeft

⁡

(

x

)

-

P

UpperLeft

⁡

(

x

)

)

ρ

1

⁢

desired

=

-

P

LowerLeft

⁡

(

x

)

⁢

sin

⁢

⁢

φ

1

+

P

LowerLeft

⁡

(

y

)

⁢

cos

⁢

⁢

φ

1

wherein:

φ 1 =is an angle between a horizontal line and the left vertical stringer line;

P LowerLeft (y)=a Y coordinate value for the possible lower left corner location;

P UpperLeft (y)=a Y coordinate value for the upper left corner location;

P LowerLeft (X)=an X coordinate value for the possible lower left corner location;

P UpperLeft (x)=an X coordinate value for the upper left corner location;

ρ 1desired =an orthogonal distance from an origin point on the corresponding gray scale image to a vertical line passing through the possible lower left corner location and the upper left corner location.

32. The computer program product of claim 31 , further comprising:

computer readable program code configured to identify a plurality of contiguous pixel locations adjacent the possible lower left corner location and extending vertically upwards, the plurality of pixel locations comprising h left pixels.

33. The computer program product of claim 23 , wherein:

h left =min( P LowerLeft ( y )− P UpperLeft ( y ),10).

34. The computer program product of claim 33 , further comprising:

computer readable program code configured to calculate a score value, Score left , that represents a likelihood that the plurality of contiguous pixel locations correspond to an actual stringer left edge in the corresponding gray scale image, wherein:

Score

left

=

A

1

h

left

where A 1 is an accumulator value that is incremented each time the following inequality is true:

|ρ( x i ,y i )−ρ 1desired |≦TOL 4*ρ 1desired

wherein:

i=an index value referring to x and y coordinates of one particular pixel location of the plurality of contiguous pixel locations, the index value ranging from 1 to h left ;

ρ(x i , y i )=a value of an i th pixel in the first Ro image at the one particular pixel location of the plurality of contiguous pixel locations;

TOL4=an empirically determined value equal to 0.5.

35. The computer program product of claim 27 , further comprising:

computer readable program code configured to calculate a right vertical stringer line extending between the possible lower right corner location and the upper right corner location.

36. The computer program product of claim 35 , wherein the computer readable program code configured to calculate a right vertical stringer line is further configured to calculate:

φ

2

=

tan

-

1

⁡

(

P

LowerRight

⁡

(

y

)

-

P

UpperRight

⁡

(

y

)

P

LowerRight

⁡

(

x

)

-

P

UpperRight

⁡

(

x

)

)

ρ

2

⁢

desired

=

-

P

LowerRight

⁡

(

x

)

⁢

sin

⁢

⁢

φ

2

+

P

LowerRight

⁡

(

y

)

⁢

cos

⁢

⁢

φ

2

wherein:

φ 2 =is an angle between a horizontal line and the right vertical stringer line;

P LowerRight (y)=a Y coordinate value for the possible lower right corner location;

P UpperRight (y)=a Y coordinate value for the upper right corner location;

P LowerRight (x)=an X coordinate value for the possible lower right corner location;

P UpperRight (x)=an X coordinate value for the upper right corner location;

ρ 2desired =an orthogonal distance from an origin point on the corresponding gray scale image to a vertical line passing through the possible lower right corner location and the upper right corner location.

37. The computer program product of claim 36 , further comprising:

computer readable program code configured to identify a plurality of contiguous pixel locations adjacent the possible lower right corner and extending vertically upwards, the plurality of pixel locations comprising h right pixels.

38. The computer program product of claim 37 , wherein:

h right =min( P LowerRight ( y )− P UpperRight ( y ),10).

39. The computer program product of claim 38 , further comprising:

computer readable program code configured to calculate a score value, Score right , that represents a likelihood that the plurality of contiguous pixel locations correspond to an actual stringer right edge in the corresponding gray scale image, wherein:

Score

right

=

A

2

h

right

where A 2 is an accumulator value that is incremented each time the following inequality is true:

|ρ( x j ,y j )−ρ 2desired |≦TOL 4*ρ 2desired

wherein:

j=an index value referring to x and y coordinates of one particular pixel location of the plurality of contiguous pixel locations, the index value ranging from 1 to h right ;

ρ(x j , y j )=a value of j th pixel in the second Ro image at the one particular pixel location of the plurality of contiguous pixel locations;

TOL4=an empirically determined value equal to 0.5.