Identifying and selecting objects that may correspond to pallets in an image scene

• US 9,025,886 B2
• Filed: 10/16/2012
• Issued: 05/05/2015
• 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., Seelinger, Michael J., Yoder, John-David S.
• Primary Examiner(s): MARIAM, DANIEL G
• Application Number:
  US13/652,630
• Publication Number:
  US 20130101229A1
• Time in Patent Office: 931 Days
• Field of Search: None
• US Class Current: 382/202
• 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 method is provided for identifying one or more scored candidate objects that may correspond to one or more actual pallets in a gray scale image. The method may comprise: identifying, by a computer, a first plurality of scored candidate objects in the gray scale image; storing, by the computer, a list of the first plurality of scored candidate objects, wherein the list includes a respective record for each of the first plurality of scored candidate objects; determining, by the computer, a subset of the first plurality of scored candidate objects to eliminate from the list based on a comparison amongst the respective records of the first plurality of scored candidate objects; and removing, by the computer, the subset of the first plurality of scored candidate objects from the list to create an updated list for a second plurality of scored candidate objects, wherein the updated list includes a respective record for each of the second plurality of scored candidate objects.

Claims

1. A method for identifying one or more scored candidate objects that may correspond to one or more actual pallets in a gray scale image, comprising:

identifying, by a computer, a first plurality of scored candidate objects in the gray scale image;

storing, by the computer, a list of the first plurality of scored candidate objects, wherein the list includes a respective record for each of the first plurality of scored candidate objects;

determining, by the computer, a subset of the first plurality of scored candidate objects to eliminate from the list based on a comparison amongst the respective records of the first plurality of scored candidate objects; and

removing, by the computer, the subset of the first plurality of scored candidate objects from the list to create an updated list for a second plurality of scored candidate objects, wherein the updated list includes a respective record for each of the second plurality of scored candidate objects.

2. The method of claim 1, wherein the respective record for each of the first plurality of scored candidate objects includes a respective composite object score that represents a likelihood that the scored candidate object corresponds to an actual pallet structure in the gray scale image.

3. The method of claim 2, further comprising:

calculating the respective composite object score for each of the first plurality of scored candidate objects by;

generating a first confidence score Score_{LowerLeftCorner} for a lower left corner associated with that scored candidate object;

generating a second confidence score Score_{LowerRightCorner} for a lower right corner associated with that scored candidate object;

generating a third confidence score Score_{BaseboardLine} for a bottom pallet board line associated with that scored candidate object;

generating a fourth confidence score Score_hole for a center stringer associated with that scored candidate object; and

calculating the respective composite object score based on the first, second, third and fourth confidence scores.

4. The method of claim 2, wherein the subset of the first plurality of scored candidate objects includes those scored candidate objects of the first plurality of candidate objects having a respective composite object score below a predetermined value.

5. The method of claim 4, wherein the respective record for each of the first plurality of scored candidate objects includes a respective location of the scored candidate object within the gray scale image.

6. The method of claim 5, wherein determining, by the computer, the subset of the first plurality of scored candidate objects to eliminate from the list, further comprises:

for each particular scored candidate object in the list;

identifying all other of the first plurality of scored candidate objects that are nearby the respective location of the particular scored candidate object;

determining if any of the identified other of the first plurality of scored candidate objects has a respective composite object score greater than the respective composite object score of the particular scored candidate object; and

adding the particular scored candidate object to the subset, if any of the identified other of the first plurality of candidate objects has a respective composite object score greater than the respective composite object score of the particular candidate object.

7. The method of claim 2, wherein the respective record for each of the first plurality of scored candidate objects includes a respective location of the scored candidate object within the gray scale image.

8. The method of claim 7, wherein determining, by the computer, the subset of the first plurality of scored candidate objects to eliminate from the list, comprises:

for each particular scored candidate object in the list;

identifying all other of the first plurality of scored candidate objects that are nearby the respective location of the particular scored candidate object;

determining if any of the identified other of the first plurality of scored candidate objects has a respective composite object score greater than the respective composite object score of the particular scored candidate object; and

adding the particular scored candidate object to the subset, if any of the identified other of the first plurality of scored candidate objects has a respective composite object score greater than the respective composite object score of the particular scored candidate object.

9. The method of claim 7, wherein the respective record for each of the first plurality of scored candidate objects includes respective attributes of a center stringer associated with that scored candidate object.

10. The method of claim 9, wherein the respective attributes include:

a respective x-coordinate value, x_LLC, of a respective lower left corner;

a respective x-coordinate value, x_LRC, of a respective lower right corner; and

a respective orthogonal distance value, ρ

_BPBL, of an orthogonal distance from an origin to a line drawn through the respective lower left corner at a respective, predetermined angle φ

_BPBL; and

wherein the respective, predetermined angle φ

_BPBL is associated with a respective bottom pallet board line of the scored candidate object and is measured relative to a horizontal line.

11. The method of claim 10, wherein the respective location of that scored candidate object has an x-coordinate estimated to be equal to

12. The method of claim 11, wherein determining, by the computer, the subset of the first plurality of scored candidate objects to eliminate from the list, comprises:

for each particular scored candidate object in the list;

identifying all other of the first plurality of scored candidate objects that are nearby the respective location of the particular scored candidate object;

determining if any of the identified nearby scored candidate objects has a respective composite object score greater than the respective composite object score of the particular scored candidate object; and

adding the particular scored candidate object to the subset, if any of the identified nearby scored candidate objects has a respective composite object score greater than the respective composite object score of the particular scored candidate object.

13. The method of claim 12, wherein two of the first plurality of scored candidate objects are identified as nearby one another if their respective locations are within a predetermined number of pixels of one another.

14. The method of claim 13, wherein the predetermined number of pixels is about 50.

15. A system for identifying one or more scored candidate objects that may correspond to one or more actual pallets in a gray scale image, comprising:

a computer configured to execute instructions stored in an accessible memory;

the computer when executing instructions stored in the accessible memory identifies a first plurality of scored candidate objects in the gray scale image;

a storage device coupled with the processor and configured to store a list of the first plurality of scored candidate objects, wherein the list includes a respective record for each of the first plurality of scored candidate objects;

the computer when executing instructions stored in the accessible memory;

determines a subset of the first plurality of scored candidate objects to eliminate from the list based on a comparison amongst the respective records of the first plurality of scored candidate objects; and

removes the subset of the first plurality of scored candidate objects from the list to create an updated list for a second plurality of scored candidate objects, wherein the updated list includes a respective record for each of the second plurality of scored candidate objects.

16. The system of claim 15, wherein the respective record for each of the first plurality of scored candidate objects includes a respective composite object score that represents a likelihood that the scored candidate object corresponds to an actual pallet structure in the gray scale image.

17. The system of claim 16, wherein the computer when executing instructions stored in the accessible memory:

calculates the respective composite object score for each of the first plurality of scored candidate objects by;

generating a first confidence score Score_{LowerLeftCorner} for a lower left corner associated with that scored candidate object;

generating a second confidence score Score_{LowerRightCorner} for a lower right corner associated with that scored candidate object;

generating a third confidence score Score_{BaseboardLine} for a bottom pallet board line associated with that scored candidate object;

generating a fourth confidence score Score_hole for a center stringer associated with that scored candidate object; and

calculating the respective composite object score based on the first, second, third and fourth confidence scores.

18. The system of claim 16, wherein the subset of the first plurality of scored candidate objects includes those scored candidate objects of the first plurality of candidate objects having a respective composite object score below a predetermined value.

19. The system of claim 18, wherein the respective record for each of the first plurality of scored candidate objects includes a respective location of the scored candidate object within the gray scale image.

20. The system of claim 19, wherein the computer when executing instructions stored in the accessible memory:

for each particular scored candidate object in the list;

identifies all other of the first plurality of scored candidate objects that are nearby the respective location of the particular scored candidate object;

determines if any of the identified other of the first plurality of scored candidate objects has a respective composite object score greater than the respective composite object score of the particular scored candidate object; and

adds the particular scored candidate object to the subset, if any of the identified other of the first plurality of candidate objects has a respective composite object score greater than the respective composite object score of the particular candidate object.

21. The system of claim 16, wherein the respective record for each of the first plurality of scored candidate objects includes a respective location of the scored candidate object within the gray scale image.

22. The system of claim 21, wherein the computer when executing instructions stored in the accessible memory:

for each particular scored candidate object in the list;

identifies all other of the first plurality of scored candidate objects that are nearby the respective location of the particular scored candidate object;

determines if any of the identified other of the first plurality of scored candidate objects has a respective composite object score greater than the respective composite object score of the particular scored candidate object; and

adds the particular scored candidate object to the subset, if any of the identified other of the first plurality of candidate objects has a respective composite object score greater than the respective composite object score of the particular candidate object.

23. The system of claim 21, wherein the respective record for each of the first plurality of scored candidate objects includes respective attributes of a center stringer associated with that scored candidate object.

24. The system of claim 23, wherein the respective attributes include:

a respective x-coordinate value, x_LLC, of a respective lower left corner;

a respective x-coordinate value, x_LRC, of a respective lower right corner; and

a respective orthogonal distance value, ρ

_BPBL, of an orthogonal distance from an origin to a line drawn through the respective lower left corner at a respective, predetermined angle φ

_BPBL; and

wherein the respective, predetermined angle φ

_BPBL is associated with a respective bottom pallet board line of the scored candidate object and is measured relative to a horizontal line.

25. The system of claim 24, wherein the respective location of that scored candidate object has an x-coordinate estimated to be equal to

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

for each particular scored candidate object in the list;

identifies all other of the first plurality of scored candidate objects that are nearby the respective location of the particular scored candidate object;

determines if any of the identified other of the first plurality of scored candidate objects has a respective composite object score greater than the respective composite object score of the particular scored candidate object; and

adds the particular scored candidate object to the subset, if any of the identified other of the first plurality of candidate objects has a respective composite object score greater than the respective composite object score of the particular candidate object.

27. The system of claim 26, wherein two of the first plurality of scored candidate objects are identified as nearby one another if their respective locations are within a predetermined number of pixels of one another.

28. The system of claim 27, wherein the predetermined number of pixels is about 50.

29. A computer program product for identifying one or more scored candidate objects that may correspond to one or more actual pallets in a gray scale 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 identify, a first plurality of scored candidate objects in the gray scale image;

computer readable program code configured to maintain a list of the first plurality of scored candidate objects, wherein the list includes a respective record for each of the first plurality of scored candidate objects;

computer readable program code configured to determine a subset of the first plurality of scored candidate objects to eliminate from the list based on a comparison amongst the respective records of the first plurality of scored candidate objects; and

computer readable program code configured to remove the subset of the first plurality of scored candidate objects from the list to create an updated list for a second plurality of scored candidate objects, wherein the updated list includes a respective record for each of the second plurality of scored candidate objects.

30. The computer program product of claim 29, wherein the respective record for each of the first plurality of scored candidate objects includes a respective composite object score that represents a likelihood that the scored candidate object corresponds to an actual pallet structure in the gray scale image.

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

computer readable program code configured to calculate the respective composite object score for each of the first plurality of scored candidate objects by;

generating a first confidence score Score_{LowerLeftCorner} for a lower left corner associated with that scored candidate object;

generating a second confidence score Score_{LowerRightCorner} for a lower right corner associated with that scored candidate object;

generating a third confidence score Score_{BaseboardLine} for a bottom pallet board line associated with that scored candidate object;

generating a fourth confidence score Score_hole for a center stringer associated with that scored candidate object; and

calculating the respective composite object score based on the first, second, third and fourth confidence scores.

32. The computer program product of claim 30, wherein the subset of the first plurality of scored candidate objects includes those scored candidate objects of the first plurality of candidate objects having a respective composite object score below a predetermined value.

33. The computer program product of claim 32, wherein the respective record for each of the first plurality of scored candidate objects includes a respective location of the scored candidate object within the gray scale image.

34. The computer program product of claim 33, further comprising computer readable program code configured to:

for each particular scored candidate object in the list;

identify all other of the first plurality of scored candidate objects that are nearby the respective location of the particular scored candidate object;

determine if any of the identified other of the first plurality of scored candidate objects has a respective composite object score greater than the respective composite object score of the particular scored candidate object; and

add the particular scored candidate object to the subset, if any of the identified other of the first plurality of candidate objects has a respective composite object score greater than the respective composite object score of the particular candidate object.

35. The computer program product of claim 30, wherein the respective record for each of the first plurality of scored candidate objects includes a respective location of the scored candidate object within the gray scale image.

36. The computer program product of claim 35, further comprising computer readable program code configured to:

for each particular scored candidate object in the list;

identify all other of the first plurality of scored candidate objects that are nearby the respective location of the particular scored candidate object;

determine if any of the identified other of the first plurality of scored candidate objects has a respective composite object score greater than the respective composite object score of the particular scored candidate object; and

add the particular scored candidate object to the subset, if any of the identified other of the first plurality of candidate objects has a respective composite object score greater than the respective composite object score of the particular candidate object.

37. The computer program product of claim 35, wherein the respective record for each of the first plurality of scored candidate objects includes respective attributes of a center stringer associated with that scored candidate object.

38. The computer program product of claim 37, wherein the respective attributes include:

a respective x-coordinate value, x_LLC, of a respective lower left corner;

a respective x-coordinate value, x_LRC, of a respective lower right corner; and

a respective orthogonal distance value, ρ

_BPBL, of an orthogonal distance from an origin to a line drawn through the respective lower left corner at a respective, predetermined angle φ

_BPBL; and

wherein the respective, predetermined angle φ

_BPBL is associated with a respective bottom pallet board line of the scored candidate object and is measured relative to a horizontal line.

39. The computer program product of claim 38, wherein the respective location of that scored candidate object has an x-coordinate estimated to be equal to

40. The computer program product of claim 39, further comprising computer readable program code configured to:

for each particular scored candidate object in the list;

identify all other of the first plurality of scored candidate objects that are nearby the respective location of the particular scored candidate object;

determine if any of the identified other of the first plurality of scored candidate objects has a respective composite object score greater than the respective composite object score of the particular scored candidate object; and

add the particular scored candidate object to the subset, if any of the identified other of the first plurality of candidate objects has a respective composite object score greater than the respective composite object score of the particular candidate object.

41. The computer program product of claim 40, wherein two of the first plurality of scored candidate objects are identified as nearby one another if their respective locations are within a predetermined number of pixels of one another.

42. The computer program product of claim 41, wherein the predetermined number of pixels is about 50.