Identifying and locating possible lines corresponding to pallet structure in an image

• US 8,995,743 B2
• Filed: 10/16/2012
• Issued: 03/31/2015
• Est. Priority Date: 10/19/2011
• Status: Active Grant

• Current Assignee: Crown Equipment Corporation
• Original Assignee: Crown Equipment Corporation
• Inventors: Holeva, Lee F., Elston, Edwin R., Jensen, Eric L., Seelinger, Michael J.
• Primary Examiner(s): MARIAM, DANIEL G
• Application Number:
  US13/652,516
• Publication Number:
  US 20130101201A1
• Time in Patent Office: 896 Days
• Field of Search: None
• US Class Current: 382/141
• CPC Class Codes: B66F 9/122 longitudinally movable
• CPC Class Codes: B66F 9/24 Electrical devices or systems
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51

Abstract

A computer-implemented method is provided for finding a Ro image providing data corresponding to possible orthogonal distances to possible lines on a pallet in an image. The method comprises: acquiring a grey scale image including one or more pallets; determining, using a computer, a horizontal gradient image by convolving the grey scale image and a first convolution kernel; determining, using the computer, a vertical gradient image by convolving the grey scale image and a second convolution kernel; and determining, using the computer, respective pixel values of a first Ro image providing data corresponding to a possible orthogonal distance from an origin point of the grey scale image to one or more possible lines on one or more possible pallets in the grey scale image.

Claims

1. A computer-implemented method for finding a Ro image providing data corresponding to possible orthogonal distances to possible lines on a pallet in an image comprising:

acquiring a grey scale image including one or more pallets;

determining, using a computer, a horizontal gradient image by convolving the grey scale image and a first convolution kernel;

determining, using the computer, a vertical gradient image by convolving the grey scale image and a second convolution kernel; and

based on the horizontal gradient image and the vertical gradient image, determining, using the computer, respective pixel values of a first Ro image providing data corresponding to a possible orthogonal distance from an origin point of the grey scale image to one or more possible lines on one or more possible pallets in the grey scale image.

2. The method of claim 1, further comprising normalizing the grey scale image and wherein the horizontal gradient image is determined by convolving the normalized grey scale image and said first convolution kernel and the vertical gradient image is determined by convolving the normalized grey scale image and said second convolution kernel.

3. The method of claim 2, wherein determining the horizontal gradient image comprises evaluating the following convolution equation using a first sliding window having a horizontal number of adjacent cells that is equal to a number of elements of the first convolution kernel, wherein the first sliding window is positioned so that each cell corresponds to a respective pixel along a portion of a particular row of the normalized grey scale image, said convolution equation for calculating a value for each pixel of the horizontal gradient image comprising:

g(k)=Σ

_ju(j)*v(k−

j)

wherein;

j=a particular pixel column location in the grey scale image wherein, for the convolution equation, a value of j ranges between a first pixel column location in the portion of the particular row and a last pixel column location in the portion of the particular row;

u(j)=pixel value in the portion of the particular row of the normalized grey-scale image having a j column location;

k=a pixel column location of the normalized grey-scale image over which the first sliding window is centered;

(k−

j)=is an index value for the first convolution kernel that ranges, as j varies, from a lowest index value corresponding to a first element of the first convolution kernel and a highest index value corresponding to a last element of the first convolution kernel; and

v(k−

j)=a value of a particular element of said first convolution kernel at the index value (k−

j).

4. The method of claim 2, wherein determining the vertical gradient image comprises evaluating the following convolution equation using a second sliding window having a vertical number of adjacent cells that is equal to a number of elements of the second convolution kernel, wherein the second sliding window is positioned so that each cell corresponds to a respective pixel along a portion of a particular column of the normalized grey scale image, said convolution equation for calculating a value for each pixel of the vertical gradient image comprising:

g(d)=Σ

_cu(c)*v(d−

c)

wherein;

c=a particular pixel row location in the grey scale image wherein, for the convolution equation, a value of c ranges between a first pixel row location in the portion of the particular column and a last pixel row location in the portion of the particular column;

u(c)=pixel value in the portion of the particular column of the normalized grey-scale image having a c row location;

d=a pixel row location of the normalized grey-scale image over which the second sliding window is centered;

(d−

c)=is an index value for the second convolution kernel that ranges, as c varies, from a lowest index value corresponding to a first element of the second convolution kernel and a highest index value corresponding to a last element of the second convolution kernel; and

v(d−

c)=a value of a particular element of said second convolution kernel at the index value (d−

c).

5. The method of claim 1, wherein determining the respective pixel values of the first Ro image comprises using gradient pixel locations and pixel values from the horizontal and vertical gradient images.

6. The method of claim 5, wherein determining the respective pixel values of the first Ro image comprises evaluating the following equation:

7. The method of claim 1, further comprising, based on the horizontal gradient image and the vertical gradient image, determining, using the computer, respective pixel values for a second Ro image providing data corresponding to a possible orthogonal distance from the origin point in the grey scale image to one or more possible lines on one or more possible pallets in the grey scale image.

8. The method of claim 7, wherein determining the respective pixel values for the second Ro image comprises using gradient pixel locations and pixel values from the horizontal and vertical gradient images.

9. The method of claim 8, wherein determining the respective pixel values for the second Ro image comprises evaluating the following equation:

10. The method of claim 1, wherein the first convolution kernel is the same as the second convolution kernel.

20. The system of claim 10, wherein the first convolution kernel is the same as the second convolution kernel.

11. A system for finding a Ro image providing data corresponding to possible orthogonal distances to possible lines on a pallet in an image comprising:

an imaging camera configured to acquire a grey scale image including one or more pallets;

a computer configured to determine a horizontal gradient image by convolving the grey scale image and a first convolution kernel;

said computer further configured to determine a vertical gradient image by convolving the grey scale image and a second convolution kernel; and

said computer further configured to determine, based on the horizontal gradient image and the vertical gradient image, respective pixel values for a first Ro image providing data corresponding to a possible orthogonal distance from an origin point of the grey scale image to one or more possible lines on one or more possible pallets in the grey scale image.

12. The system of claim 11, wherein:

said computer is further configured to normalize the grey scale image; and

said computer is further configured to determine the horizontal gradient by convolving the normalized grey scale image and the first convolution kernel and to determine the vertical gradient by convolving the normalized grey scale image and said second convolution kernel.

13. The system of claim 12, wherein said computer is further configured to determine the horizontal gradient image by evaluating the following convolution equation using a first sliding window having a horizontal number of adjacent cells that is equal to a number of elements of the first convolution kernel, wherein the first sliding window is positioned so that each cell corresponds to a respective pixel along a portion of a particular row of the normalized grey scale image, said convolution equation for calculating a value for each pixel of the horizontal gradient image comprising:

g(k)=Σ

_ju(j)*v(k−

j)

wherein;

j=a particular pixel column location in the grey scale image wherein, for the convolution equation, a value of j ranges between a first pixel column location in the portion of the particular row and a last pixel column location in the portion of the particular row;

u(j)=pixel value in the portion of the particular row of the normalized grey-scale image having a j column location;

k=a pixel column location of the normalized grey-scale image over which the first sliding window is centered;

(k−

j)=is an index value for the first convolution kernel that ranges, as j varies, from a lowest index value corresponding to a first element of the first convolution kernel and a highest index value corresponding to a last element of the first convolution kernel; and

v(k−

j)=a value of a particular element of said first convolution kernel at the index value (k−

j).

14. The system of claim 12, wherein said computer is further configured to determine the vertical gradient image by evaluating the following convolution equation using a second sliding window having a vertical number of adjacent cells that is equal to a number of elements of the second convolution kernel, wherein the second sliding window is positioned so that each cell corresponds to a respective pixel along a portion of a particular column of the normalized grey scale image, said convolution equation for calculating a value for each pixel of the vertical gradient image comprising:

g(d)=Σ

_cu(c)*v(d−

c)

wherein;

c=a particular pixel row location in the grey scale image wherein, for the convolution equation, a value of c ranges between a first pixel row location in the portion of the particular column and a last pixel row location in the portion of the particular column;

u(c)=pixel value in the portion of the particular column of the normalized grey-scale image having a c row location;

d=a pixel row location of the normalized grey-scale image over which the second sliding window is centered;

(d−

c)=is an index value for the second convolution kernel that ranges, as c varies, from a lowest index value corresponding to a first element of the second convolution kernel and a highest index value corresponding to a last element of the second convolution kernel; and

v(d−

c)=a value of a particular element of said second convolution kernel at the index value (d−

c).

15. The system of claim 11, wherein to determine the respective pixel values for the first Ro image said computer is further configured to use gradient pixel locations and pixel values from the horizontal and vertical gradient images.

16. The system of claim 15, wherein said computer is further configured to determine the respective pixel values for the first Ro image by evaluating the following equation:

17. The system of claim 11, wherein said computer is further configured to determine, based on the horizontal gradient image and the vertical gradient image, respective pixel values for a second Ro image providing data corresponding to a possible orthogonal distance from an origin point to one or more possible lines on one or more possible pallets in the grey scale image.

18. The system of claim 17, wherein to determine the respective pixel values for the second Ro image said computer is further configured to use gradient pixel locations and pixel values from the horizontal and vertical gradient images.

19. The system of claim 18, wherein said computer is further configured to determine the respective pixel values for the second Ro image by evaluating the following equation:

21. A computer program product for finding a Ro image providing data corresponding to possible orthogonal distances to possible lines on a pallet in an image, 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 acquire a grey scale image including one or more pallets;

computer readable program code configured to determine a horizontal gradient image by convolving the grey scale image and a first convolution kernel;

computer readable program code configured to determine a vertical gradient image by convolving the grey scale image and a second convolution kernel; and

computer readable program code configured to determine, based on the horizontal gradient image and the vertical gradient image, respective pixel values of a first Ro image providing data corresponding to a possible orthogonal distance from an origin point of the grey scale image to one or more possible lines on one or more possible pallets in the grey scale image.

22. The computer program product of claim 21, further comprising:

computer readable program code configured to normalize the grey scale image and wherein the horizontal gradient image is determined by convolving the normalized grey scale image and said first convolution kernel and the vertical gradient image is determined by convolving the normalized grey scale image and said second convolution kernel.

23. The computer program product of claim 22, further comprising:

computer readable program code configured to evaluate the following convolution equation using a first sliding window having a horizontal number of adjacent cells that is equal to a number of elements of the first convolution kernel, wherein the first sliding window is positioned so that each cell corresponds to a respective pixel along a portion of a particular row of the normalized grey scale image, said convolution equation for calculating a value for each pixel of the horizontal gradient image comprising;

g(k)=Σ

_ju(j)*v(k−

j)

wherein;

j=a particular pixel column location in the grey scale image wherein, for the convolution equation, a value of j ranges between a first pixel column location in the portion of the particular row and a last pixel column location in the portion of the particular row;

u(j)=pixel value in the portion of the particular row of the normalized grey-scale image having a j column location;

k=a pixel column location of the normalized grey-scale image over which the first sliding window is centered;

(k−

j)=is an index value for the first convolution kernel that ranges, as j varies, from a lowest index value corresponding to a first element of the first convolution kernel and a highest index value corresponding to a last element of the first convolution kernel; and

v(k−

j)=a value of a particular element of said first convolution kernel at the index value (k−

j).

24. The computer program product of claim 22, further comprising:

computer readable program code configured to evaluate the following convolution equation using a second sliding window having a vertical number of adjacent cells that is equal to a number of elements of the second convolution kernel, wherein the second sliding window is positioned so that each cell corresponds to a respective pixel along a portion of a particular column of the normalized grey scale image, said convolution equation for calculating a value for each pixel of the vertical gradient image comprising;

g(d)=Σ

_cu(c)*v(d−

c)

wherein;

c=a particular pixel row location in the grey scale image wherein, for the convolution equation, a value of c ranges between a first pixel row location in the portion of the particular column and a last pixel row location in the portion of the particular column;

u(c)=pixel value in the portion of the particular column of the normalized grey-scale image having a c row location;

d=a pixel row location of the normalized grey-scale image over which the second sliding window is centered;

(d−

c)=is an index value for the second convolution kernel that ranges, as c varies, from a lowest index value corresponding to a first element of the second convolution kernel and a highest index value corresponding to a last element of the second convolution kernel; and

v(d−

c)=a value of a particular element of said second convolution kernel at the index value (d−

c).

25. The computer program product of claim 21, wherein the computer readable program code configured to determine the respective pixel values of the first Ro image is configured to use gradient pixel locations and pixel values from the horizontal and vertical gradient images.

26. The computer program product of claim 25, further comprising:

computer readable program code configured to evaluate the following equation;

27. The computer program product of claim 21, further comprising:

computer readable program code configured to determine, based on the horizontal gradient image and the vertical gradient image, respective pixel values for a second Ro image providing data corresponding to a possible orthogonal distance from the origin point in the grey scale image to one or more possible lines on one or more possible pallets in the grey scale image.

28. The computer program product of claim 27, wherein the computer readable program code configured to determine the respective pixel values for the second Ro image is configured to use gradient pixel locations and pixel values from the horizontal and vertical gradient images.

29. The computer program product of claim 28, further comprising:

computer readable program code configured to evaluate the following equation;

30. The computer program product of claim 21, wherein the first convolution kernel is the same as the second convolution kernel.