Method for identifying marking stripes of road lanes

• US 6,212,287 B1
• Filed: 10/17/1997
• Issued: 04/03/2001
• Est. Priority Date: 10/17/1996
• Status: Expired due to Term

• Current Assignee: STMicroelectronics SRL (STMicroelectronics NV)
• Original Assignee: SGS-Thomson Microelectronics, S.R.L. (STMicroelectronics NV)
• Inventors: Olivieri, Massimiliano, Kramer, Alan, Guerrieri, Roberto, Fabbrizio, Vito
• Primary Examiner(s): Au, Amelia
• Assistant Examiner(s): Dastouri, Mehrdad
• Application Number:
  US08/951,956
• Time in Patent Office: 1,264 Days
• Field of Search: 382/104, 382/103, 382/279, 382/281, 382/283, 701/23, 701/28
• US Class Current: 382/104
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means

Abstract

A method, in a system for aiding the guidance of a vehicle, for identifying marking stripes of road lanes. A road image is subjected to a convolution operation with a mask matrix so as to identify discontinuities present in the image. The resulting convolved image is compared with a threshold value and a representation of the marking stripes is determined. The mask matrix is set in such a way as to eliminate at least partially the discontinuities which do not correspond to the marking stripes.

Claims

1. A method, in a system for aiding the guidance of a vehicle, for identifying marking stripes demarcating at least one road lane in a road image represented by a matrix of elements each indicative of the luminosity level of an elementary portion of the image, the method comprising the steps of:

setting a mask matrix;

determining a convolved image matrix via a convolution operation between the matrix of the road image and the mask matrix so as to identify luminosity discontinuities present in the image;

determining a binary image matrix in which each element has a first (0) or a second (1) binary value depending on the result of a comparison of a corresponding element of the convolved image matrix with a threshold value;

determining from the binary image matrix a representation of the marking stripes; and

wherein

said step of setting the mask matrix includes determining a value L indicative of the number of elements of the image matrix corresponding to the width of the marking stripes wherein each row of the mask matrix comprises;

L contiguous elements having a first value;

at least one element having a value of zero being contiguous to and located on both sides of said L contiguous elements; and

a plurality of elements being contiguous to said at least one element having a value of zero and being located at the left and right ends of each row, said plurality of elements being a second value of opposite sign to said first value.

2. The method according to claim 1, wherein the first value of the mask matrix is 1 and the second value of the mask matrix is −

1.

3. The method according to claim 2, wherein each row of the mask matrix comprises at least one element of value 0 contiguous with the L elements.

4. The method according to claim 2, wherein the mask matrix has a substantially zero mean value.

5. The method according to claim 1, wherein the elements of each row of the mask matrix which are equidistant from the ends of the row are equal.

6. The method according to claim 5, wherein the elements of the mask matrix which belong to one and the same column are equal.

7. The method according to claim 5, further comprising the step of modifying at least once during the convolution operation the value L and the contents of the mask matrix.

8. The method according to claim 2, wherein the elements of the mask matrix which belong to one and the same column are equal.

9. The method according to claim 1, wherein the mask matrix has a smaller number of rows than number of columns.

10. The method according to claim 2, further comprising the step of modifying at least once during the convolution operation the value L and the contents of the mask matrix.

11. The method according to claim 1, wherein each row of the mask matrix comprises at least one element of value 0 contiguous with the L elements.

12. The method according to claim 11, wherein the elements of the mask matrix which belong to one and the same column are equal.

13. The method according to claim 11, further comprising the step of modifying at least once during the convolution operation the value L and the contents of the mask matrix.

14. The method according to claim 11, wherein the mask matrix has a substantially zero mean value.

15. The method according to claim 1, wherein the mask matrix has a substantially zero mean value.

16. The method according to claim 15, wherein the elements of the mask matrix which belong to one and the same column are equal.

17. The method according to claim 15, wherein the mask matrix has a smaller number of rows than number of columns.

18. The method according to claim 15, further comprising the step of modifying at least once during the convolution operation the value L and the contents of the mask matrix.

19. The method according to claim 1, wherein the elements of the mask matrix which belong to one and the same column are equal.

20. The method according to claim 19, further comprising the step of modifying at least once during the convolution operation the value L and the contents of the mask matrix.

21. The method according to claim 1, wherein the mask matrix has a smaller number of rows than number of columns.

22. The method according to claim 21, wherein the mask matrix has a number of rows lying between 3 and 8 and a number of columns lying between 20 and 40.

23. The method according to claim 22, further comprising the step of modifying at least once during the convolution operation the value L and the contents of the mask matrix.

24. The method according to claim 21, further comprising the step of modifying at least once during the convolution operation the value L and the contents of the mask matrix.

25. The method according to claim 1, further comprising the step of modifying at least once during the convolution operation the value L and the contents of the mask matrix.

26. The method according to claim 25, wherein the value L is modified twice during the convolution operation.

27. The method according to claim 26, where in the dimensions of the mask matrix are modified in relation with the modification of the value L.

28. The method according to claim 25, wherein the dimensions of the mask matrix are modified in relation with the modification of the value L.

29. The method according to claim 1, wherein the number of said plurality of elements being a second value is substantially equal to L/2.

30. The method according to claim 1, wherein said first value is +1.

31. The method according to claim 1, wherein said first value is −

1.

32. A method, in a system for aiding the guidance of a vehicle, for identifying marking stripes demarcating at least one road lane in a road image represented by a matrix of elements each indicative of the luminosity level of an elementary portion of the image, the method comprising the steps of:

determining a first and a second convolved image matrix via a convolution operation between the matrix of the road image and, respectively, a first and a second mask matrix so as to identify luminosity discontinuities present in the image, the elements of each row of the second mask matrix being equal in reverse order to the elements of a corresponding row of the first mask matrix;

determining a first and a second binary image matrix in which each element has a first (0) or a second (1) binary value depending on the result of a comparison of a corresponding element, respectively, of the first and of the second convolved image matrix with, respectively, a first and a second threshold value;

determining a single binary image matrix via a logic AND operation between the corresponding elements of the first and of the second binary image matrix; and

determining from the single binary image matrix a representation of the marking stripes.

33. The method according to claim 32, wherein the elements of a left half of the first mask matrix have a first value and the elements of a right half of the first mask matrix have a second value of opposite sign to the first value.

34. The method according to claim 33, wherein the first value of the mask matrix is 1 and the second value of the mask matrix is −

1.

35. The method according to claim 34, wherein the first and the second mask matrix have a substantially zero mean value.

36. The method according to claim 34, wherein the first and the second mask matrix have a smaller number of rows than number of columns.

37. The method according to claim 34, wherein the first and the second threshold value are equal.

38. The method according to claim 34, wherein the first mask matrix comprises at least one column of elements of value 0 lying between the left half and the right half.

39. The method according to claim 33, wherein the first mask matrix comprises at least one column of elements of value 0 lying between the left half and the right half.

40. The method according to claim 39, wherein the first and the second mask matrix have a substantially zero mean value.

41. The method according to claim 39, wherein the first and the second threshold value are equal.

42. The method according to claim 39, wherein the first and the second mask matrix have a smaller number of rows than number of columns.

43. The method according to claim 32, wherein the first and the second mask matrix have a substantially zero mean value.

44. The method according to claim 32, wherein the first and the second mask matrix have a smaller number of rows than number of columns.

45. The method according to claim 32, wherein the first and the second threshold value are equal.

46. The method according to claim 32, wherein the first and the second mask matrix have a substantially zero mean value.

47. The method according to claim 46, wherein the first and the second mask matrix have a smaller number of rows than number of columns.

48. The method according to claim 46, wherein the first and the second threshold value are equal.

49. The method according to claim 32, wherein the first and the second mask matrix have a smaller number of rows than number of columns.

50. The method according to claim 49, wherein the first and the second threshold value are equal.

51. The method according to claim 49, wherein the first and the second mask matrix have a number of rows lying between 3 and 8 and a number of columns lying between 20 and 40.

52. The method according to claim 51, wherein the first and the second threshold value are equal.

53. The method according to claim 32, wherein the first and the second threshold value are equal.

54. An apparatus, in a system for aiding the guidance of a vehicle, for identifying marking stripes demarcating at least one road lane in a road image represented by a matrix of elements each indicative of the luminosity level of an elementary portion of the image, the apparatus comprising:

a circuit for setting a mask matrix;

a circuit for determining a convolved image matrix via a convolution operation between the matrix of the road image and the mask matrix so as to identify luminosity discontinuities present in the image;

a circuit for determining a binary image matrix in which each element has a first (0) or a second (1) binary value depending on the result of a circuit comparing a corresponding element of the convolved image matrix with a threshold value;

a circuit for determining from the binary image matrix a representation of the marking stripes; and

a circuit for determining a value L indicative of the number of elements of the image matrix corresponding to the width of the marking stripes, said circuit for setting said mask matrix further;

setting L elements of the mask matrix to a first value;

setting at least one element having a value of zero being contiguous to and located on both sides of said L elements; and

setting a plurality of elements being contiguous to said at least one element having a value of zero and being located at the left and right ends of each row, said plurality of elements being a second value of opposite sign to said first value.

55. The method according to claim 54, wherein the number of said plurality of elements being a second value is substantially equal to L/2.

56. The method according to claim 54, wherein said first value is +1.

57. The method according to claim 54, wherein said first value is −

1.

58. An apparatus, in a system for aiding the guidance of a vehicle, for identifying marking stripes demarcating at least one road lane in a road image represented by a matrix of elements each indicative of the luminosity level of an elementary portion of the image, the apparatus comprising:

a circuit for determining a first and a second convolved image matrix via a convolution operation between the matrix of the road image and, respectively, a first and a second mask matrix so as to identify luminosity discontinuities present in the image, the elements of each row of the second mask matrix being equal in reverse order to the elements of a corresponding row of the first mask matrix;

a circuit for determining a first and a second binary image matrix in which each element has a first (0) or a second (1) binary value depending on the result of a comparison of a corresponding element, respectively, of the first and of the second convolved image matrix with, respectively, a first and a second threshold value;

a circuit for determining a single binary image matrix via a logic AND operation between the corresponding elements of the first and of the second binary image matrix; and

a circuit for determining from the single binary image matrix a representation of the marking stripes.