POSE ESTIMATION

• US 20090202174A1
• Filed: 02/06/2009
• Published: 08/13/2009
• Est. Priority Date: 02/07/2008
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: SHIBA, HISASHI
• Granted Patent: US 8,401,295 B2
• Time in Patent Office: Days
• US Class Current: 382/282
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06V 10/48 by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation

Abstract

In a pose estimation for estimating the pose of an object of pose estimation with respect to a reference surface that serves as a reference for estimating a pose, a data processing device: extracts pose parameters from a binarized image; identifies a combination of pose parameters for which the number of cross surfaces of parameter surfaces that accord with surface parameter formulas, which are numerical formulas for expressing a reference surface, is a maximum; finds a slope weighting for each of cross pixels, which are pixels on each candidate surface and which are pixels within a prescribed range, that is identified based on the angles of the tangent plane at the cross pixel and based on planes formed by each of the axes of parameter space; and identifies the significant candidate surface for which a number, which is the sum of slope weightings, is a maximum, as the actual surface that is the reference surface that actually exists in the image.

Claims

1-60. -60. (canceled)

61. A data processing device comprising:

a binarization unit for dividing an image received as input into a candidate region that is a candidate for a reference surface that serves as a reference for estimating pose and a background region that is a region other than the candidate region;

a surface parameter formula expression unit for extracting pose parameters that indicate pose of an object of pose estimation with respect to a reference surface that appears in said image that was received as input and, based on a combination of values obtained by implementing a transform by a prescribed function upon, of the pose parameters that were extracted, parameters that indicate the direction in which the object of pose estimation is directed and pose parameters other than the parameters that indicate direction, finding surface parameter formulas that are numerical formulas that express said reference surface;

a parameter computation unit for, based on pose parameters that were extracted by said surface parameter formula expression unit, computing the combination of pose parameters that make up said surface parameter formulas that express all surfaces that pass through each pixel contained in the candidate region that was divided by said binarization unit;

a parameter surface drawing unit for, based on the combination of pose parameters computed by said parameter computation unit, drawing parameter surfaces in accordance with said surface parameter formulas on parameter space, which is space that includes each of the parameters belonging to said pose parameters as the axes of base vectors;

an intersection detection unit for finding cross point coordinates, which are the coordinates of intersections through which pass a plurality of said parameter surfaces that were drawn by said parameter surface drawing unit, and a cross surface number, which is the number of parameter surfaces that pass through the cross point coordinates;

a significant candidate extraction unit for, when the cross surface number at each cross point that was found by said intersection detection unit is compared with cross surface numbers at other cross point coordinates in prescribed neighboring regions that take as a reference the cross point coordinate corresponding to the cross surface number and is thus determined to be a maximum, identifying the combination of pose parameters that make up the parameter surface that corresponds to the determined cross surface number as a significant candidate that is an optimum combination of pose parameters for expressing said reference surface;

a significant candidate surface drawing unit for, based on a significant candidate identified by said significant candidate extraction unit and a combination of pose parameters that were computed by said parameter computation unit for which distance to said significant candidate in parameter space in prescribed neighboring regions that take the significant candidate as a reference is no greater than a prescribed value, drawing significant candidate surfaces on said image;

a cross determination unit for, regarding each significant candidate surface that was drawn by said significant candidate surface drawing unit, identifying pixels that are located on, of said candidate region, the significant candidate surface, and pixels that are located within a prescribed range from the significant candidate surface as cross pixels and finding coordinates of the cross pixels and tangent planes at said cross pixels;

a weighting computation unit for, based on angles that are formed by tangent planes in cross pixels that were found by said cross determination unit and planes that are formed by the axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified by said cross determination unit;

a number measurement unit for computing for each of said significant candidate surfaces a number that is the value obtained by adding up the slope weightings of cross pixels that were found by said weighting computation unit and that were contained in each of the significant candidates; and

an actual surface determination unit for, when the number computed by said number measurement unit is compared with a number belonging to other significant candidate surfaces in neighboring regions that take as a reference the significant candidate surface that has this number and that thus is determined to be a maximum, identifying the significant candidate surface having said determined number as an actual surface that is a reference surface that actually exists in said image.

62. The data processing device according to claim 61, wherein, of said pose parameters, pose parameters that indicate direction are angles.

63. The data processing device according to claim 62, wherein:

said prescribed function for implementing a transform upon said angles is a trigonometric function; and

said surface parameter formula expression unit finds said surface parameter formulas based on values obtained by implementing a transform by said trigonometric function upon said angles and pose parameters other than said angles.

64. The data processing device according to claim 61, wherein said significant candidate extraction unit compares the cross surface number at each cross point found by said intersection detection unit and a first threshold value and identifies said significant candidates from among a combination of said pose parameters that corresponds to cross surface numbers determined to be greater than the first threshold value.

65. The data processing device according to claim 64, wherein said significant candidate extraction unit, when extracting said significant candidates, alters a significant candidate surface bit for a combination of pose parameters that was extracted as the significant candidate to a prescribed value that identifies said significant candidates as a significant candidate surface.

66. The data processing device according to claim 61, wherein said weighting computation unit:

at each point in a significant candidate surface that was drawn by said significant candidate surface drawing unit, finds angles formed by the tangent plane at that point and surfaces formed by the axes of each base vector included in said parameter space; and

determines, of said angles that were found, the angle for which the absolute value is a minimum as the minimum angle, and, by computing the absolute value of the reciprocal of the cosine for the determined minimum angle, finds a slope weighting of a pixel at which said significant candidate surfaces cross.

67. The data processing device according to claim 61, wherein said actual surface determination unit compares the numbers computed by said number measurement unit and a second threshold value, and identifies said actual surface from among significant candidate surfaces having a number that is determined to be greater than the second threshold value.

68. The data processing device according to claim 67, wherein said actual surface determination unit, when identifying said actual surface, alters an actual surface bit for said pose parameter combination, that forms a significant candidate surface identified as the actual surface, to a prescribed value that identifies said significant candidate surface as an actual surface.

69. The data processing device according to claim 61, further comprising a smoothing unit for implementing a process to smooth said image received as input, wherein said binarization unit, based on an image that has undergone smoothing by said smoothing unit, generates a binarized image.

70. The data processing device according to claim 61, further comprising a dilation/erosion unit for subjecting a candidate region of a binarized image generated by said binarization unit to a prescribed number of dilation processes for dilating the candidate region or erosion processes for eroding the candidate region.

71. The data processing device according to claim 70, further comprising:

an image size conversion unit for changing the image size by reducing or enlarging the size of any image; and

a parameter micro-adjustment unit for causing the alternate and repeated execution of changes of image sizes of differing magnifications by said image size conversion unit and identification of a new actual surface by said actual surface determination unit until a prescribed number is reached or until a prescribed accuracy is obtained;

wherein said image size conversion unit;

before said actual surface determination unit identifies an actual surface, generates a reduced image by reducing at a prescribed reduction ratio said image received as input; and

after said actual surface determination unit identifies an actual surface, generates a new image by changing said reduced image that was generated to a size that is smaller than said image received as input, and moreover, larger than the reduced image.

72. The data processing device according to claim 61, further comprising:

a parameter space coarse-graining unit for increasing the discretization width of said parameter space to a predetermined width to coarsen the parameter space and find an actual surface, and after once finding an actual surface, changing discretization to make the parameter space finer; and

a parameter micro-adjustment unit for repeatedly executing derivation of new actual surfaces in the parameter space of different discretization widths in neighboring regions of an actual surface that has been found in parameter space that has undergone said discretization until reaching a prescribed number of processes or until the discretization width reaches a prescribed value.

73. The data processing device according to claim 61, further comprising:

a positional relation estimation unit for, when a plurality of actual surfaces appear in said image that is received as input, estimating both the positional relation between each of said actual surfaces and identifying the actual surfaces by placing said actual surfaces in correspondence with physical entities; and

a pose significance unit for carrying out a significance process, which is a process of, based on the positional relation of said plurality of surfaces estimated by said positional relation estimation unit, placing said pose parameters in correspondence with said actual surfaces to determine the pose of an object of pose estimation with respect to the actual surfaces.

79. The data processing device according to claim 61, further comprising:

a pixel value-weighted parameter surface drawing unit for, based on a pixel value weighting found by multiplication of a combination of pose parameters that was computed by said parameter computation unit and a value computed based on pixel values of an image before binarization by said binarization unit, drawing on said parameter space parameter surfaces that accord with said surface parameter formulas;

a pixel value-weighted significant candidate extraction unit for, when at said cross point coordinates, the sum of the number of cross surfaces at which said parameter surfaces intersect each other and pixel value weightings is greater than a prescribed value, and moreover, when the number of cross surfaces are a maximum in neighboring regions that take the cross point coordinates as a reference, identifying the combination of parameters at the cross point coordinates as a significant candidate of a combination of parameters that form a reference surface that is the object of detection; and

a pixel value-weighted weighting computation unit for, based on angles formed by tangent planes at cross pixels that were found by said cross determination unit and surfaces that were formed by axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified by said cross determination unit, and, by multiplying these slope weightings that were found and values that were computed based on pixel values of an image before binarization by said binarization unit, finding pixel value-weighted slope weightings.

127. The record medium according to claim 64, further comprising:

an image size conversion procedure for changing image size by reducing or enlarging the size of any image; and

a parameter micro-adjustment procedure for alternately and repeatedly executing changes of image size of differing magnifications by said image size conversion procedure and for identifying new actual surfaces by said actual surface determination procedure until reaching a prescribed number of times is reached or until a prescribed accuracy is obtained;

wherein, in said image size conversion procedure;

before an actual surface is identified in said actual surface determination procedure, a reduced image is generated by reducing at a prescribed reduction ratio said image received as input; and

after an actual surface is identified in said actual surface determination procedure, a new image is generated by changing said reduced image that was generated to a size that is smaller than said image received as input, and moreover, that is larger than the reduced image.

74. A data processing device for, based on an image received as input, estimating pose of an object of pose estimation with respect to a reference surface that serves as a reference for estimating pose, said data processing device comprising:

a binarization unit for dividing said image into a candidate region that is a candidate for said reference surface and a background region that is a region other than the candidate region;

a surface parameter formula expression unit for extracting pose parameters that indicate the pose of an object of pose estimation with respect to a reference surface that appears in said image that was received as input and, based on the combination of a value obtained by implementing a transform by a prescribed function upon, of the pose parameters that were extracted, parameters that indicate a direction in which the object of the pose estimation is directed and pose parameters other than the parameters that indicate direction, finding surface parameter formulas that are numerical formulas that express said reference surface;

an all-candidate surface drawing unit for, based on the combination of all pose parameters in parameter space, which is space having, as the axes of base vectors, each of the parameters included in said pose parameters, drawing candidate surfaces that accord with said surface parameter formulas on said image in said parameter space;

a cross determination unit for, as regards each candidate surface that was drawn by said all-candidate surface drawing unit, identifying pixels that are located on, of said candidate region, the candidate surface, and pixels that are located within a prescribed range from the candidate surface as cross pixels and finding coordinates of the cross pixels and tangent planes at said cross pixels;

a weighting computation unit for, based on angles that are formed by tangent planes at the cross pixels that were found by said cross determination unit and planes that are formed by the axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified by said cross determination unit;

a number measurement unit for computing for each of said candidate surfaces a number that is the value obtained by adding up the slope weightings of cross pixels that were found by said weighting computation unit and that were contained in each of the candidate surfaces; and

an actual surface determination unit for, based on the number computed by said number measurement unit, identifying from among candidate surfaces drawn by said all-candidate surface drawing unit an actual surface that is a reference surface that actually exists in said image.

75. The data processing device according to claim 74, further comprising a smoothing unit for implementing a process to smooth said image received as input, wherein said binarization unit, based on an image that has undergone smoothing by said smoothing unit, generates a binarized image.

76. The data processing device according to claim 74, further comprising a dilation/erosion unit for subjecting a candidate region of a binarized image generated by said binarization unit to a prescribed number of dilation processes for dilating the candidate region or erosion processes for eroding the candidate region.

77. The data processing device according to claim 76, further comprising:

an image size conversion unit for changing the image size by reducing or enlarging the size of any image; and

a parameter micro-adjustment unit for causing the alternate and repeated execution of changes of image sizes of differing magnifications by said image size conversion unit and identification of a new actual surface by said actual surface determination unit until a prescribed number is reached or until a prescribed accuracy is obtained;

wherein said image size conversion unit;

before said actual surface determination unit identifies an actual surface, generates a reduced image by reducing at a prescribed reduction ratio said image received as input; and

after said actual surface determination unit identifies an actual surface, generates a new image by changing said reduced image that was generated to a size that is smaller than said image received as input, and moreover, larger than the reduced image.

78. The data processing device according to claim 74, further comprising:

a parameter space coarse-graining unit for increasing the discretization width of said parameter space to a predetermined width to coarsen the parameter space and find an actual surface, and after once finding an actual surface, changing discretization to make the parameter space finer; and

a parameter micro-adjustment unit for repeatedly executing derivation of new actual surfaces in the parameter space of different discretization widths in neighboring regions of an actual surface that has been found in parameter space that has undergone said discretization until reaching a prescribed number of processes or until the discretization width reaches a prescribed value.

80. The data processing device according to claim 74, further comprising a pixel value-weighted weighting computation unit for finding pixel value-weighted slope weightings by multiplying said slope weightings and values computed based on pixel value of an image before binarization by said binarization unit.

81. The data processing device according to claim 74, further comprising:

a positional relation estimation unit for, when a plurality of actual surfaces appear in said image that is received as input, estimating both the positional relation between each of said actual surfaces and identifying the actual surfaces by placing said actual surfaces in correspondence with physical entities; and

a pose significance unit for carrying out a significance process, which is a process of, based on the positional relation of said plurality of surfaces estimated by said positional relation estimation unit, placing said pose parameters in correspondence with said actual surfaces to determine the pose of an object of pose estimation with respect to the actual surfaces.

82. A pose estimation system provided with a first data processing device, a second processing device and a data process switching device, said first data processing device comprising:

a binarization unit for dividing an image received as input into a candidate region that is a candidate for a reference surface that serves as a reference for estimating pose and a background region that is a region other than the candidate region;

a surface parameter formula expression unit for extracting pose parameters that indicate pose of an object of pose estimation with respect to a reference surface that appears in said image that was received as input and, based on a combination of values obtained by implementing a transform by a prescribed function upon, of the pose parameters that were extracted, parameters that indicate the direction in which the object of pose estimation is directed and pose parameters other than the parameters that indicate direction, finding surface parameter formulas that are numerical formulas that express said reference surface;

a parameter computation unit for, based on pose parameters that were extracted by said surface parameter formula expression unit, computing the combination of pose parameters that make up said surface parameter formulas that express all surfaces that pass through each pixel contained in the candidate region that was divided by said binarization unit;

a parameter surface drawing unit for, based on the combination of pose parameters computed by said parameter computation unit, drawing parameter surfaces in accordance with said surface parameter formulas on parameter space, which is space that includes each of the parameters belonging to said pose parameters as the axes of base vectors;

an intersection detection unit for finding cross point coordinates, which are the coordinates of intersections through which pass a plurality of said parameter surfaces that were drawn by said parameter surface drawing unit, and a cross surface number, which is the number of parameter surfaces that pass through the cross point coordinates;

a significant candidate extraction unit for, when the cross surface number at each cross point that was found by said intersection detection unit is compared with cross surface numbers at other cross point coordinates in prescribed neighboring regions that take as a reference the cross point coordinate corresponding to the cross surface number and is thus determined to be a maximum, identifying the combination of pose parameters that make up the parameter surface that corresponds to the determined cross surface number as a significant candidate that is an optimum combination of pose parameters for expressing said reference surface;

a significant candidate surface drawing unit for, based on a significant candidate identified by said significant candidate extraction unit and a combination of pose parameters that were computed by said parameter computation unit for which distance to said significant candidate in parameter space in prescribed neighboring regions that take the significant candidate as a reference is no greater than a prescribed value, drawing significant candidate surfaces on said image;

a cross determination unit for, regarding each significant candidate surface that was drawn by said significant candidate surface drawing unit, identifying pixels that are located on, of said candidate region, the significant candidate surface, and pixels that are located within a prescribed range from the significant candidate surface as cross pixels and finding coordinates of the cross pixels and tangent planes at said cross pixels;

a weighting computation unit for, based on angles that are formed by tangent planes in cross pixels that were found by said cross determination unit and planes that are formed by the axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified by said cross determination unit;

a number measurement unit for computing for each of said significant candidate surfaces a number that is the value obtained by adding up the slope weightings of cross pixels that were found by said weighting computation unit and that were contained in each of the significant candidates; and

an actual surface determination unit for, when the number computed by said number measurement unit is compared with a number belonging to other significant candidate surfaces in neighboring regions that take as a reference the significant candidate surface that has this number and that thus is determined to be a maximum, identifying the significant candidate surface having said determined number as an actual surface that is a reference surface that actually exists in said image;

said second data processing device for, based on an image received as input, estimating pose of an object of pose estimation with respect to a reference surface that serves as a reference for estimating pose, said second data processing device comprising;

a binarization unit for dividing said image into a candidate region that is a candidate for said reference surface and a background region that is a region other than the candidate region;

a surface parameter formula expression unit for extracting pose parameters that indicate the pose of an object of pose estimation with respect to a reference surface that appears in said image that was received as input and, based on the combination of a value obtained by implementing a transform by a prescribed function upon, of the pose parameters that were extracted, parameters that indicate a direction in which the object of the pose estimation is directed and pose parameters other than the parameters that indicate direction, finding surface parameter formulas that are numerical formulas that express said reference surface;

an all-candidate surface drawing unit for, based on the combination of all pose parameters in parameter space, which is space having, as the axes of base vectors, each of the parameters included in said pose parameters, drawing candidate surfaces that accord with said surface parameter formulas on said image in said parameter space;

a cross determination unit for, as regards each candidate surface that was drawn by said all-candidate surface drawing unit, identifying pixels that are located on, of said candidate region, the candidate surface, and pixels that are located within a prescribed range from the candidate surface as cross pixels and finding coordinates of the cross pixels and tangent planes at said cross pixels;

a weighting computation unit for, based on angles that are formed by tangent planes at the cross pixels that were found by said cross determination unit and planes that are formed by the axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified by said cross determination unit;

a number measurement unit for computing for each of said candidate surfaces a number that is the value obtained by adding up the slope weightings of cross pixels that were found by said weighting computation unit and that were contained in each of the candidate surfaces; and

an actual surface determination unit for, based on the number computed by said number measurement unit, identifying from among candidate surfaces drawn by said all-candidate surface drawing unit an actual surface that is a reference surface that actually exists in said image;

said data process switching device for, based on the results of comparing a parameter space calculation amount, which is a calculation amount indicating the volume of arithmetic processing by the first data processing device to realize identification of an actual surface that is said reference surface, and an image space calculation amount, which is a calculation amount indicating the volume of arithmetic processing by the second data processing device to realize identification of an actual surface, selecting the first data processing device or the second data processing device and causing the selected data processing device to identify said actual surface.

83. The pose estimation system according to claim 82, wherein said data processing switching device comprises:

a binarization unit for dividing said image into a candidate region that is a candidate for said reference surface and a background region that is a region other than the candidate region;

a surface parameter formula expression unit for extracting pose parameters that indicate the pose of an object of pose estimation with respect to a reference surface that appears in said image that was received as input and, based on a combination of values obtained by implementing a transform by a prescribed function upon, of the pose parameters that were extracted, parameters that indicate direction in which the object of pose estimation is directed and pose parameters other than the parameters that indicate direction, finding surface parameter formulas that are numerical formulas that express said reference surface;

a parameter computation calculation amount estimation unit for estimating a parameter computation calculation amount, which is an amount that indicates the volume of arithmetic processing for said first data processing device to compute the combinations of pose parameters that make up said surface parameter formulas that express all reference surfaces that pass through each pixel contained in a candidate region divided by said binarization unit;

a parameter surface drawing calculation amount estimation unit for estimating a parameter surface drawing calculation amount for said first data processing device to draw parameter surfaces that accord with said surface parameter formulas;

an intersection detection calculation amount estimation unit for estimating an intersection detection calculation amount for said first data processing device to find said cross point coordinates and said cross surface numbers;

a significant candidate extraction calculation amount estimation unit for estimating a significant candidate extraction calculation amount for said first data processing device to identify said significant candidates;

a significant candidate surface drawing calculation amount estimation unit for estimating a significant candidate surface drawing calculation amount for said first data processing device to draw said significant candidate surfaces;

a cross determination calculation amount estimation unit for estimating a cross determination calculation amount for said first data processing device to identify said cross pixels and for said first data processing device to find the coordinates of the cross pixels and tangent planes at said cross pixels;

a weighting computation calculation amount estimation unit for estimating a weighting computation calculation amount for said first data processing device to find said slope weightings;

a number measurement calculation amount estimation unit for estimating a number measurement calculation amount for said first data processing device to compute said numbers for each said significant candidate surface;

an actual surface determination calculation amount estimation unit for estimating an actual surface determination calculation amount for said first data processing device to identify said actual surfaces from among said significant candidate surfaces;

an all-candidate surface drawing calculation amount estimation unit for estimating an all-candidate surface drawing calculation amount for said second data processing device to draw candidate surfaces that accord with said surface parameter formulas;

an all-cross determination calculation amount estimation unit for estimating an all-cross determination calculation amount for said second data processing device to identify said cross pixels and for said second data processing device to find coordinates of the cross pixels and tangent planes at said cross pixels;

an all-weighting computation calculation amount estimation unit for estimating an all-weighting computation calculation amount for said second data processing device to find said slope weightings;

an all-number measurement calculation amount estimation unit for estimating an all-number measurement calculation amount for said second data processing device to compute said numbers;

an all-actual surface determination calculation amount estimation unit for estimating an all-actual surface determination calculation amount for said second data processing device to identify said actual surfaces from among said candidate surfaces; and

a method selection unit for;

finding said parameter space calculation amount by adding up said parameter computation calculation amount, said parameter surface drawing calculation amount, said intersection detection calculation amount, said significant candidate extraction calculation amount, said significant candidate surface drawing calculation amount, said cross determination calculation amount, said weighting computation calculation amount, said number measurement calculation amount, and said actual surface determination calculation amount;

finding said image space calculation amount by adding up said all-candidate surface drawing calculation amount, said all-cross determination calculation amount, said all weighting computation calculation amount, said all-number measurement calculation amount, and said all-actual surface determination calculation amount; and

when, as a result of comparing said parameter space calculation amount that was found and said image space calculation amount that was found, said parameter space calculation amount is determined to be less than said image space calculation amount, selecting said first data processing device to identify said actual surface, and when said parameter space calculation amount is determined to be greater than said image space calculation amount, selecting said second data processing device to identify said actual surface.

84. The pose estimation system according to claim 83, wherein,

the first data processing device, further comprising:

a pixel value-weighted parameter surface drawing unit for, based on a pixel value weighting found by multiplication of a combination of pose parameters that was computed by said parameter computation unit and a value computed based on pixel values of an image before binarization by said binarization unit, drawing on said parameter space parameter surfaces that accord with said surface parameter formulas;

a pixel value-weighted significant candidate extraction unit for, when at said cross point coordinates, the sum of the number of cross surfaces at which said parameter surfaces intersect each other and pixel value weightings is greater than a prescribed value, and moreover, when the number of cross surfaces are a maximum in neighboring regions that take the cross point coordinates as a reference, identifying the combination of parameters at the cross point coordinates as a significant candidate of a combination of parameters that form a reference surface that is the object of detection; and

a pixel value-weighted weighting computation unit for, based on angles formed by tangent planes at cross pixels that were found by said cross determination unit and surfaces that were formed by axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified by said cross determination unit, and, by multiplying these slope weightings that were found and values that were computed based on pixel values of an image before binarization by said binarization unit, finding pixel value-weighted slope weightings;

said data processing switching device comprises;

a pixel value-weighted parameter surface drawing unit for, when drawing parameter surfaces on said parameter space, finding pixel value weightings based on pixel values of an image before binarization by said binarization unit;

a pixel value-weighted significant candidate extraction unit for, when at said intersections, the sum of the number of cross surfaces at which said parameter surfaces intersect each other and pixel value weightings is greater than a prescribed value, and moreover, when the number of cross surfaces is a maximum in neighboring regions that take the cross point coordinates as a reference, identifying the combination of parameters at the cross point coordinates as a significant candidate of a combination of parameters that form a reference surface that is the object of detection;

a pixel value-weighted weighting computation unit for further multiplying said slope weightings by values that are computed based on pixel values of a three-dimensional image before binarization and then taking the result as new slope weightings;

a pixel value-weighted parameter surface drawing calculation amount estimation unit for estimating the calculation amount necessary for execution by said weighted parameter surface drawing unit;

a pixel value-weighted significant candidate extraction calculation amount estimation unit for estimating the calculation amount necessary for execution by said pixel value-weighted significant candidate extraction unit; and

a pixel value-weighted weighting computation calculation amount estimation unit for estimating the calculation amount necessary for execution by said pixel value-weighted weighting computation unit.

85. The pose estimation system according to claim 84, comprising a communication device for, when said actual surface determination unit determines an actual surface, transmitting to the outside pose parameters that make up the actual surface that has been determined.

86. A pose estimation method for, based on an image that is received as input, estimating the pose of an object of pose estimation with respect to a reference surface that serves as a reference for estimating the pose, said pose estimation method comprising:

a binarization process for dividing said image into a candidate region that is a candidate for said reference surface and a background region that is a region other than the candidate region;

a surface parameter formula expression process for extracting pose parameters that indicate the pose of an object of pose estimation with respect to a reference surface that appears in said image that is received as input and, based on the combination of values obtained by applying a transform by a prescribed function upon, of pose parameters that have been extracted, parameters that indicate direction in which an object of pose estimation is directed and pose parameters other than the parameters that indicate direction, finding surface parameter formulas that are numerical formulas that express said reference surface;

a parameter computation process for, based on pose parameters that were extracted in said surface parameter formula expression process, computing a combination of pose parameters that make up said surface parameter formulas that express all surfaces that pass through each pixel contained in a candidate region that was divided in said binarization process;

a parameter surface drawing process for, based on the combination of pose parameters computed in said parameter computation process, drawing parameter surfaces that accord with said surface parameter formulas on parameter space, which is space that includes each of the parameters belonging to said pose parameters as the axes of base vectors;

an intersection detection process for finding cross point coordinates, which are the coordinates of intersections through which pass a plurality of said parameter surfaces that were drawn in said parameter surface drawing process, and cross surface numbers, which are the numbers of parameter surfaces that pass through the cross point coordinates;

a significant candidate extraction process for, when the cross surface number at each cross point that was found in said intersection detection process is compared with the cross surface numbers at other cross point coordinates in prescribed neighboring regions that take the cross point coordinates corresponding to the cross surface number as a reference and is thus determined to be a maximum, identifying the combinations of pose parameters that make up the parameter surface that corresponds to the determined cross surface number as significant candidates, which are optimum combinations of pose parameters for expressing said reference surface;

a significant candidate surface drawing process for, based on a significant candidate identified in said significant candidate extraction process and a combination of pose parameters that were computed in said parameter computation process, for which a distance to said significant candidate in said parameter space in prescribed neighboring regions that take the significant candidate as a reference is no greater than a prescribed value, drawing a significant candidate surfaces on said image;

a cross determination process for, regarding each significant candidate surface that was drawn in said significant candidate surface drawing process, identifying pixels that are located on, of said candidate region, the significant candidate surface, and pixels that are located within a prescribed range from the significant candidate surface as cross pixels and finding coordinates of the cross pixels and tangent planes at said cross pixels;

a weighting computation process for, based on angles that are formed by tangent planes at the cross pixels that were found in said cross determination process and planes that are formed by the axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified in said cross determination process;

a number measurement process for computing for each of said significant candidate surfaces a number that is the value obtained by adding up the slope weightings of cross pixels that were found in said weighting computation process and that were contained in each of the significant candidates; and

an actual surface determination process for, when the number computed in said number measurement process is compared with a number belonging to other significant candidate surfaces in neighboring regions that take as a reference the significant candidate surface that has this number and thus is determined to be a maximum, identifying the significant candidate surface having the determined number as an actual surface that is a reference surface that actually exists in said image.

87. The pose estimation method according to claim 86, wherein, of said pose parameters, pose parameters that indicate direction are angles.

88. The pose estimation method according to claim 87, wherein:

said prescribed function for implementing a transform upon said angles is a trigonometric function; and

in said surface parameter formula expression process, said surface parameter formulas are found based on values obtained by implementing a transform by said trigonometric function upon said angles and pose parameters other than said angles.

89. The pose estimation method according to claim 86, wherein, in said significant candidate extraction process, the cross surface number at each cross point found by said intersection detection process and a first threshold value are compared to identify said significant candidates from among combinations of said pose parameters that correspond to cross surface numbers determined to be greater than the first threshold value.

90. The pose estimation method according to claim 89, wherein, in said significant candidate extraction process, when said significant candidates are extracted, a significant candidate surface bit for a combination of pose parameters that was extracted as the significant candidate is changed to a prescribed value that identifies said significant candidates as a significant candidate surface.

91. The pose estimation method according to claim 86, wherein, in said weighting computation process:

at each point in a significant candidate surface that was drawn in said significant candidate surface drawing process, angles formed by the tangent plane at that point and surfaces formed by the axes of each base vector included in said parameter space are found; and

of said angles that were found, the angle for which the absolute value is a minimum is determined as the minimum angle, and a slope weighting of a pixel through which said significant candidate surfaces cross is found by computing the absolute value of the reciprocal of the cosine that corresponds to the determined minimum angle.

92. The pose estimation method according to claim 86, wherein, in said actual surface determination process, the numbers computed in said number measurement process are compared with a second threshold value, and said actual surface is identified from among significant candidate surfaces having numbers that are determined to be greater than the second threshold value.

93. The pose estimation method according to claim 92, wherein, in said actual surface determination process, when identifying said actual surface, an actual surface bit for said pose parameter combination that forms a significant candidate surface identified as the actual surface is changed to a prescribed value that identifies said significant candidate surface as an actual surface.

94. The pose estimation method according to claim 86, further comprising a smoothing process for implementing a process to smooth said image received as input, wherein, in said binarization process, a binarized image is generated based on an image that has undergone smoothing in said smoothing process.

95. The pose estimation method according to claim 86, further comprising a dilation/erosion process for subjecting a candidate region of a binarized image generated in said binarization process to a prescribed number of dilation processes for dilating the candidate region or erosion processes for eroding the candidate region.

96. The pose estimation method according to claim 86, further comprising:

an image size conversion process for changing image size by reducing or enlarging the size of any image; and

a parameter micro-adjustment process for causing alternate and repeated execution of change of image sizes of differing magnifications by said image size conversion process and identification of a new actual surface by said actual surface determination process until reaching a prescribed number of times is reached or until a prescribed accuracy is obtained;

wherein, in said image size conversion process;

before an actual surface is identified in said actual surface determination process, a reduced image is generated by reducing at a prescribed reduction ratio said image received as input; and

after an actual surface is identified in said actual surface determination process, a new image is generated by changing said reduced image that was generated to a size that is smaller than said image received as input, and moreover, that is larger than the reduced image.

97. The pose estimation method according to claim 86, further comprising:

a parameter space coarse-graining process for increasing the discretization width of said parameter space to a predetermined width to coarsen the parameter space and find an actual surface, and after an actual surface has once been found, changing discretization to make parameter space finer; and

a parameter micro-adjustment process for repeatedly executing derivation of new actual surfaces in parameter space of different discretization widths in neighboring regions of an actual surface that has once been found in parameter space that has undergone said discretization until reaching a prescribed number of processes is reached or until discretization width reaches a prescribed value.

98. The pose estimation method according to claim 86, further comprising:

a positional relation estimation process for, when a plurality of actual surfaces appear in said image that is received as input, estimating both the positional relation between each of said actual surfaces and identifying the actual surfaces by placing said actual surfaces in correspondence with physical entities; and

a pose significance process for carrying out a significance process, which is a process for, based on the positional relation of said plurality of surfaces estimated in said positional relation estimation process, placing said pose parameters in correspondence with said actual surfaces to determine the pose of an object of pose estimation with respect to the actual surfaces.

104. The pose estimation method according to claim 86, further comprising:

a pixel value-weighted parameter surface drawing process for, based on a pixel value weighting found by multiplication of a combination of pose parameters computed in said parameter computation process and a value that was computed based on pixel values of an image before binarization in said binarization process, drawing on said parameter space parameter surfaces that accord with said surface parameter formulas;

a pixel value-weighted significant candidate extraction process for, when at said cross point coordinates, the sum of the number of cross surfaces at which said parameter surfaces intersect each other and pixel value weightings is greater than a prescribed value, and moreover, when the number of cross surfaces is a maximum in neighboring regions that take the cross point coordinates as a reference, identifying the combination of parameters at the cross point coordinates as a significant candidate of a combination of parameters that form a reference surface that is the object of detection; and

a pixel value-weighted weighting computation process for, based on angles formed by tangent planes at cross pixels that were found in said cross determination process and surfaces formed by axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified in said cross determination process, and, by multiplying these slope weightings that were found and values computed based on pixel values of an image before binarization in said binarization process, finding pixel value-weighted slope weightings.

99. A pose estimation method for, based on an image that is received as input, estimating the pose of an object of pose estimation with respect to a reference surface that serves as the reference for estimating pose, said pose estimation method comprising:

a binarization process for dividing said image into a candidate region that is a candidate for said reference surface and a background region that is a region other than the candidate region;

a surface parameter formula expression process for extracting pose parameters that indicate the pose of an object of pose estimation with respect to a reference surface that appears in said image received as input and, based on the combination of values obtained by implementing a transform by a prescribed function upon, of the pose parameters that were extracted, parameters that indicate a direction in which the object of pose estimation is directed and pose parameters other than the parameters that indicate direction, finding surface parameter formulas that are numerical formulas that express said reference surface;

an all-candidate surface drawing process for, based on the combination of all pose parameters in parameter space, which is space having, as the axes of base vectors, each of the parameters belonging to said pose parameters, drawing candidate surfaces that accord with said surface parameter formulas on the image in said parameter space;

a cross determination process for, as regards each candidate surface that was drawn in said all-candidate surface drawing process, identifying pixels that are located on, of said candidate region, the candidate surface, and pixels that are located within a prescribed range from the candidate surface as cross pixels and finding coordinates of the cross pixels and tangent planes at said cross pixels;

a weighting computation process for, based on angles that are formed by tangent planes at cross pixels that were found in said cross determination process and planes that are formed by the axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified in said cross determination process;

a number measurement process for computing for each of said candidate surfaces a number that is a value obtained by adding up the slope weightings of cross pixels that were found in said weighting computation process and that were contained in each of the candidate surfaces; and

an actual surface determination process for, based on the numbers computed in said number measurement process, identifying an actual surface that is a reference surface that actually exists in said image from among candidate surfaces drawn in said all-candidate surface drawing process.

100. The pose estimation method according to claim 99, further comprising a smoothing process for implementing a process to smooth said image received as input, wherein, in said binarization process, a binarized image is generated based on an image that has undergone smoothing in said smoothing process.

101. The pose estimation method according to claim 99, further comprising a dilation/erosion process for subjecting a candidate region of a binarized image generated in said binarization process to a prescribed number of dilation processes for dilating the candidate region or erosion processes for eroding the candidate region.

102. The pose estimation method according to claim 99, further comprising:

an image size conversion process for changing image size by reducing or enlarging the size of any image; and

a parameter micro-adjustment process for causing alternate and repeated execution of change of image sizes of differing magnifications by said image size conversion process and identification of a new actual surface by said actual surface determination process until reaching a prescribed number of times is reached or until a prescribed accuracy is obtained;

wherein, in said image size conversion process;

before an actual surface is identified in said actual surface determination process, a reduced image is generated by reducing at a prescribed reduction ratio said image received as input; and

after an actual surface is identified in said actual surface determination process, a new image is generated by changing said reduced image that was generated to a size that is smaller than said image received as input, and moreover, that is larger than the reduced image.

103. The pose estimation method according to claim 99, further comprising:

a parameter space coarse-graining process for increasing the discretization width of said parameter space to a predetermined width to coarsen the parameter space and find an actual surface, and after an actual surface has once been found, changing discretization to make parameter space finer; and

a parameter micro-adjustment process for repeatedly executing derivation of new actual surfaces in parameter space of different discretization widths in neighboring regions of an actual surface that has once been found in parameter space that has undergone said discretization until reaching a prescribed number of processes is reached or until discretization width reaches a prescribed value.

105. The pose estimation method according to claim 99, further comprising a pixel value-weighted weighting computation process for finding pixel value-weighted slope weightings by multiplying said slope weightings and values that are computed based on pixel values of an image before binarization in said binarization process.

106. The pose estimation method according to claim 99, further comprising:

a positional relation estimation process for, when a plurality of actual surfaces appear in said image that is received as input, estimating both the positional relation between each of said actual surfaces and identifying the actual surfaces by placing said actual surfaces in correspondence with physical entities; and

a pose significance process for carrying out a significance process, which is a process for, based on the positional relation of said plurality of surfaces estimated in said positional relation estimation process, placing said pose parameters in correspondence with said actual surfaces to determine the pose of an object of pose estimation with respect to the actual surfaces.

107. A pose estimation method including a data processing switching process for, based on the results of comparing a parameter space calculation amount, which is a calculation amount indicating the volume of arithmetic processing carried out by using a first pose estimation method to identify an actual surface that is said reference surface, and an image space calculation amount, which is a calculation amount indicating the volume of arithmetic processing carried out by using a second pose estimation method to identify an actual surface, selecting one of the pose estimation methods, among the first pose estimation method and the second pose estimation methods and using the selected pose estimation method to identify said actual surface:

the first pose estimation method for, based on an image that is received as input, estimating the pose of an object of pose estimation with respect to a reference surface that serves as a reference for estimating the pose, said pose estimation method comprising;

a binarization process for dividing said image into a candidate region that is a candidate for said reference surface and a background region that is a region other than the candidate region;

a surface parameter formula expression process for extracting pose parameters that indicate the pose of an object of pose estimation with respect to a reference surface that appears in said image that is received as input and, based on the combination of values obtained by applying a transform by a prescribed function upon, of pose parameters that have been extracted, parameters that indicate direction in which an object of pose estimation is directed and pose parameters other than the parameters that indicate direction, finding surface parameter formulas that are numerical formulas that express said reference surface;

a parameter computation process for, based on pose parameters that were extracted in said surface parameter formula expression process, computing a combination of pose parameters that make up said surface parameter formulas that express all surfaces that pass through each pixel contained in a candidate region that was divided in said binarization process;

a parameter surface drawing process for, based on the combination of pose parameters computed in said parameter computation process, drawing parameter surfaces that accord with said surface parameter formulas on parameter space, which is space that includes each of the parameters belonging to said pose parameters as the axes of base vectors;

an intersection detection process for finding cross point coordinates, which are the coordinates of intersections through which pass a plurality of said parameter surfaces that were drawn in said parameter surface drawing process, and cross surface numbers, which are the numbers of parameter surfaces that pass through the cross point coordinates;

a significant candidate extraction process for, when the cross surface number at each cross point that was found in said intersection detection process is compared with the cross surface numbers at other cross point coordinates in prescribed neighboring regions that take the cross point coordinates corresponding to the cross surface number as a reference and is thus determined to be a maximum, identifying the combinations of pose parameters that make up the parameter surface that corresponds to the determined cross surface number as significant candidates, which are optimum combinations of pose parameters for expressing said reference surface;

a significant candidate surface drawing process for, based on a significant candidate identified in said significant candidate extraction process and a combination of pose parameters that were computed in said parameter computation process, for which a distance to said significant candidate in said parameter space in prescribed neighboring regions that take the significant candidate as a reference is no greater than a prescribed value, drawing a significant candidate surfaces on said image;

a cross determination process for, regarding each significant candidate surface that was drawn in said significant candidate surface drawing process, identifying pixels that are located on, of said candidate region, the significant candidate surface, and pixels that are located within a prescribed range from the significant candidate surface as cross pixels and finding coordinates of the cross pixels and tangent planes at said cross pixels;

a weighting computation process for, based on angles that are formed by tangent planes at the cross pixels that were found in said cross determination process and planes that are formed by the axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified in said cross determination process;

a number measurement process for computing for each of said significant candidate surfaces a number that is the value obtained by adding up the slope weightings of cross pixels that were found in said weighting computation process and that were contained in each of the significant candidates; and

an actual surface determination process for, when the number computed in said number measurement process is compared with a number belonging to other significant candidate surfaces in neighboring regions that take as a reference the significant candidate surface that has this number and thus is determined to be a maximum, identifying the significant candidate surface having the determined number as an actual surface that is a reference surface that actually exists in said image;

the second pose estimation method for, based on an image that is received as input, estimating the pose of an object of pose estimation with respect to a reference surface that serves as the reference for estimating pose, said pose estimation method comprising;

a binarization process for dividing said image into a candidate region that is a candidate for said reference surface and a background region that is a region other than the candidate region;

a surface parameter formula expression process for extracting pose parameters that indicate the pose of an object of pose estimation with respect to a reference surface that appears in said image received as input and, based on the combination of values obtained by implementing a transform by a prescribed function upon, of the pose parameters that were extracted, parameters that indicate a direction in which the object of pose estimation is directed and pose parameters other than the parameters that indicate direction, finding surface parameter formulas that are numerical formulas that express said reference surface;

an all-candidate surface drawing process for, based on the combination of all pose parameters in parameter space, which is space having, as the axes of base vectors, each of the parameters belonging to said pose parameters, drawing candidate surfaces that accord with said surface parameter formulas on the image in said parameter space;

a cross determination process for, as regards each candidate surface that was drawn in said all-candidate surface drawing process, identifying pixels that are located on, of said candidate region, the candidate surface, and pixels that are located within a prescribed range from the candidate surface as cross pixels and finding coordinates of the cross pixels and tangent planes at said cross pixels;

a weighting computation process for, based on angles that are formed by tangent planes at cross pixels that were found in said cross determination process and planes that are formed by the axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified in said cross determination process;

a number measurement process for computing for each of said candidate surfaces a number that is a value obtained by adding up the slope weightings of cross pixels that were found in said weighting computation process and that were contained in each of the candidate surfaces; and

an actual surface determination process for, based on the numbers computed in said number measurement process, identifying an actual surface that is a reference surface that actually exists in said image from among candidate surfaces drawn in said all-candidate surface drawing process.

108. The pose estimation method according to claim 107, wherein said data processing switching process comprises:

a binarization process for dividing said image into a candidate region that is a candidate for said reference surface and a background region that is a region other than the candidate region;

a surface parameter formula expression process for extracting pose parameters that indicate the pose of an object of pose estimation with respect to a reference surface that appears in said image that was received as input and, based on a combination of values obtained by implementing a transform by a prescribed function upon, of the pose parameters that were extracted, parameters that indicate direction in which the object of pose estimation is directed and pose parameters other than the parameters that indicate direction, finding surface parameter formulas that are numerical formulas that express said reference surface;

a parameter computation calculation amount estimation process for estimating a parameter computation calculation amount, which is an amount that indicates the volume of arithmetic processing for using said first pose estimation method to compute the combinations of pose parameters that make up said surface parameter formulas that express all reference surfaces that pass through each pixel contained in a candidate region that was divided in said binarization process;

a parameter surface drawing calculation amount estimation process for estimating a parameter surface drawing calculation amount for using said first pose estimation method to draw parameter surfaces that accord with said surface parameter formulas;

an intersection detection calculation amount estimation process for estimating an intersection detection calculation amount for using said first pose estimation method to find said cross point coordinates and said cross surface numbers;

a significant candidate extraction calculation amount estimation process for estimating a significant candidate extraction calculation amount for using said first pose estimation method to identify said significant candidates;

a significant candidate surface drawing calculation amount estimation process for estimating a significant candidate surface drawing calculation amount for using said first pose estimation method to draw said significant candidate surfaces;

a cross determination calculation amount estimation process for estimating a cross determination calculation amount for using said first pose estimation method to identify said cross pixels and for using said first pose estimation method to find the coordinates of the cross pixels and tangent planes at said cross pixels;

a weighting computation calculation amount estimation process for estimating a weighting computation calculation amount for using said first pose estimation method to find said slope weightings;

a number measurement calculation amount estimation process for estimating a number measurement calculation amount for using said first pose estimation method to compute said numbers for each said significant candidate surface;

an actual surface determination calculation amount estimation process for estimating an actual surface determination calculation amount for using said first pose estimation method to identify said actual surfaces from among said significant candidate surfaces;

an all-candidate surface drawing calculation amount estimation process for estimating an all-candidate surface drawing calculation amount for using said second pose estimation method to draw candidate surfaces that accord with said surface parameter formulas;

an all-cross determination calculation amount estimation process for estimating an all-cross determination calculation amount for using said second pose estimation method to identify said cross pixels and for using said first pose estimation method to find coordinates of the cross pixels and tangent planes at said cross pixels;

an all-weighting computation calculation amount estimation process for estimating an all-weighting computation calculation amount for using said second pose estimation method to find said slope weightings;

an all-number measurement calculation amount estimation process for estimating an all-number measurement calculation amount for using said second pose estimation method to compute said numbers;

an all-actual surface determination calculation amount estimation process for estimating an all-actual surface determination calculation amount for using said second pose estimation method to identify said actual surfaces from among said candidate surfaces; and

said method selection process for;

finding said parameter space calculation amount by adding up said parameter computation calculation amount, said parameter surface drawing calculation amount, said intersection detection calculation amount, said significant candidate extraction calculation amount, said significant candidate surface drawing calculation amount, said cross determination calculation amount, said weighting computation calculation amount, said number measurement calculation amount, and said actual surface determination calculation amount;

finding said image space calculation amount by adding up said all-candidate surface drawing calculation amount, said all-cross determination calculation amount, said all weighting computation calculation amount, said all-number measurement calculation amount, and said all-actual surface determination calculation amount; and

when, as a result of comparing said parameter space calculation amount that was found and said image space calculation amount that was found, said parameter space calculation amount is determined to be less than said image space calculation amount, selecting said first pose estimation method to identify said actual surface, and when said parameter space calculation amount is determined to be greater than said image space calculation amount, selecting said second pose estimation method to identify said actual surface.

109. The pose estimation method according to claim 108, wherein, the first pose estimation method, further comprising:

a pixel value-weighted parameter surface drawing process for, based on a pixel value weighting found by multiplication of a combination of pose parameters computed in said parameter computation process and a value that was computed based on pixel values of an image before binarization in said binarization process, drawing on said parameter space parameter surfaces that accord with said surface parameter formulas;

a pixel value-weighted significant candidate extraction process for, when at said cross point coordinates, the sum of the number of cross surfaces at which said parameter surfaces intersect each other and pixel value weightings is greater than a prescribed value, and moreover, when the number of cross surfaces is a maximum in neighboring regions that take the cross point coordinates as a reference, identifying the combination of parameters at the cross point coordinates as a significant candidate of a combination of parameters that form a reference surface that is the object of detection; and

a pixel value-weighted weighting computation process for, based on angles formed by tangent planes at cross pixels that were found in said cross determination process and surfaces formed by axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified in said cross determination process, and, by multiplying these slope weightings that were found and values computed based on pixel values of an image before binarization in said binarization process, finding pixel value-weighted slope weightings;

said data processing switching process comprises;

a pixel value-weighted parameter surface drawing process for, when drawing parameter surfaces on said parameter space, finding pixel value weightings based on pixel values of an image before binarization in said binarization process;

a pixel value-weighted significant candidate extraction process for, when at said intersections, the sum of the number of cross surfaces at which parameter surfaces intersect each other and pixel value weightings is greater than a prescribed value, and moreover, when the number of cross surfaces is a maximum in neighboring regions that take the cross point coordinates as a reference, identifying the combination of parameters at the cross point coordinates as a significant candidate of a combination of parameters that form a reference surface that is the object of detection;

a pixel value-weighted weighting computation process for further multiplying said slope weightings by values that are computed based on pixel values of a three-dimensional image before binarization and then taking the result as new slope weightings;

a pixel value-weighted parameter surface drawing calculation amount estimation process for estimating the calculation amount necessary for execution of said weighted parameter surface drawing process;

a pixel value-weighted significant candidate extraction calculation amount estimation process for estimating the calculation amount necessary for execution of said pixel value-weighted significant candidate extraction process; and

a pixel value-weighted weighting computation calculation amount estimation process for estimating the calculation amount necessary for execution of said pixel value-weighted weighting computation process.

110. The pose estimation method according to claim 107, comprising a communication process for, when an actual surface is determined in said actual surface determination process, transmitting to the outside pose parameters that make up the actual surface that was determined.

111. A record medium having recorded there on a computer-readable program for causing a computer to execute:

a binarization procedure for dividing an image that is received as input into a candidate region that is a candidate for a reference surface that is the reference for estimating pose and a background region that is a region other than the candidate region;

a surface parameter formula expression procedure for extracting pose parameters that indicate the pose of an object of pose estimation with respect to a reference surface that appears in said image received as input and, based on a combination of values obtained by implementing a transform by a prescribed function upon, of the pose parameters that were extracted, parameters that indicate the direction in which the object of pose estimation is directed and pose parameters other than the parameters that indicate direction, finding a surface parameter formulas that are numerical formulas that express the reference surface;

a parameter computation procedure for, based on pose parameters that were extracted in said surface parameter formula expression procedure, computing a combination of pose parameters that make up said surface parameter formulas that express all surfaces that pass through each pixel contained in the candidate region that was divided in said binarization procedure;

a parameter surface drawing procedure for, based on the combination of pose parameters computed in said parameter computation procedure, drawing parameter surfaces that accord with said surface parameter formulas on parameter space, which is space that includes each of the parameters belonging to said pose parameters as the axes of base vectors;

an intersection detection procedure for finding cross point coordinates, which are the coordinates of intersections through which a plurality of said parameter surfaces that were drawn in said parameter surface drawing procedure pass, and cross surface numbers, which are the numbers of parameter surfaces that pass through the cross point coordinates;

a significant candidate extraction procedure for, when the cross surface number at each cross point that was found in said intersection detection procedure is compared with the cross surface numbers at other cross point coordinates in prescribed neighboring regions that take the cross point coordinates corresponding to the cross surface number as a reference and is thus determined to be a maximum, identifying the combination of pose parameters that make up the parameter surface that corresponds to the determined cross surface number as a significant candidate, which is the optimum combination of pose parameters for expressing said reference surface;

a significant candidate surface drawing procedure for, based on a significant candidate identified in said significant candidate extraction procedure and the combination of pose parameters that were computed in said parameter computation procedure for which distance to the significant candidate in said parameter space in prescribed neighboring regions that take the significant candidate as a reference is no greater than a prescribed value, drawing significant candidate surfaces on said image;

a cross determination procedure for, regarding each significant candidate surface that was drawn in said significant candidate surface drawing procedure, identifying pixels that are located on, of said candidate region, the significant candidate surface, and pixels that are located within a prescribed range from the significant candidate surface as cross pixels and finding coordinates of the cross pixels and tangent planes at the cross pixels;

a weighting computation procedure for, based on angles that are formed by tangent planes at the cross pixels that were found in said cross determination procedure and planes that are formed by the axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified in said cross determination procedure;

a number measurement procedure for computing for each of said significant candidate surfaces a number that is the value obtained by adding up the slope weightings of cross pixels that were found in said weighting computation procedure and that were contained in each of the significant candidates; and

an actual surface determination procedure for, when the number computed in said number measurement procedure is compared with numbers belonging to other significant candidate surfaces in neighboring regions that take as a reference the significant candidate surface that has this number and thus is determined to be a maximum, identifying the significant candidate surface having the determined number as an actual surface that is a reference surface that actually exists in said image.

112. The record medium according to claim 111, wherein, of said pose parameters, pose parameters that indicate direction are angles.

113. The record medium according to claim 112, wherein:

said prescribed function for implementing a transform upon said angles is a trigonometric function; and

in said surface parameter formula expression procedure, said surface parameter formulas are found based on values obtained by implementing a transform by said trigonometric function upon said angles and pose parameters other than said angles.

114. The record medium according to claim 111, wherein, in said significant candidate extraction procedure, the cross surface number at each cross point found in said intersection detection procedure and a first threshold value are compared, and said significant candidates are identified from among combinations of said pose parameters that correspond to cross surface numbers determined to be greater than the first threshold value.

115. The record medium according to claim 114, wherein, upon extraction of said significant candidates in said significant candidate extraction procedure, a significant candidate surface bit for a combination of pose parameters that were extracted as the significant candidate is changed to a prescribed value that identifies said significant candidates as a significant candidate surface.

116. The record medium according to claim 111, wherein, in said weighting computation procedure:

at each point on a significant candidate surface that was drawn in said significant candidate surface drawing procedure, angles formed by the tangent plane at that point and surfaces formed by the axes of each base vector included in said parameter space are found; and

of said angles that were found, the angle for which the absolute value is a minimum is determined as the minimum angle, and a slope weighting of a pixel through which said significant candidate surfaces cross is found by computing the absolute value of the reciprocal of the cosine that corresponds to the determined minimum angle.

117. The record medium according to claim 111, wherein, in said actual surface determination procedure, the numbers computed in said number measurement procedure are compared with a second threshold value, and said actual surface is identified from among significant candidate surfaces having numbers that are determined to be greater than the second threshold value.

118. The record medium according to claim 117, wherein, in said actual surface determination procedure, upon identifying said actual surface, an actual surface bit for said combination of pose parameters that forms a significant candidate surface identified as the actual surface is changed to a prescribed value that identifies said significant candidate surface as an actual surface.

119. The record medium according to claim 111, further comprising a smoothing procedure for implementing a process for smoothing said image received as input, wherein, in said binarization procedure, a binarized image is generated based on an image that has undergone smoothing in said smoothing procedure.

120. The record medium according to claim 111, further comprising a dilation/erosion procedure for subjecting a candidate region of a binarized image generated in said binarization procedure to a prescribed number of dilation procedures for dilating the candidate region or to erosion procedures for eroding the candidate region.

121. The record medium according to claim 111, further comprising:

an image size conversion procedure for changing image size by reducing or enlarging the size of any image; and

a parameter micro-adjustment procedure for alternately and repeatedly executing changes of image size of differing magnifications by said image size conversion procedure and for identifying new actual surfaces by said actual surface determination procedure until reaching a prescribed number of times is reached or until a prescribed accuracy is obtained;

wherein, in said image size conversion procedure;

before an actual surface is identified in said actual surface determination procedure, a reduced image is generated by reducing at a prescribed reduction ratio said image received as input; and

after an actual surface is identified in said actual surface determination procedure, a new image is generated by changing said reduced image that was generated to a size that is smaller than said image received as input, and moreover, that is larger than the reduced image.

122. The record medium according to claim 111, further comprising:

a parameter space coarse-graining procedure for increasing the discretization width of said parameter space to a predetermined width to coarsen parameter space and find an actual surface, and after an actual surface has once been found, changing discretization to make the parameter space finer; and

a parameter micro-adjustment procedure for repeatedly executing derivation of new actual surfaces in the parameter space of different discretization widths in neighboring regions of an actual surface that has once been found in parameter space that has undergone said discretization until reaching a prescribed number of processes is reached or until the discretization width reaches a prescribed value.

123. The record medium according to claim 111, further comprising:

a positional relation estimation procedure for, when a plurality of actual surfaces appear in said image that is received as input, estimating both the positional relation between each of said actual surfaces and identifying the actual surfaces by placing said actual surfaces in correspondence with physical entities; and

a pose significance procedure for carrying out a significance process, which is a process of, based on the positional relation of said plurality of surfaces estimated in said positional relation estimation procedure, placing said pose parameters in correspondence with said actual surfaces to determine the pose of an object of pose estimation with respect to the actual surfaces.

129. The record medium according to claim 111, further comprising:

a pixel value-weighted parameter surface drawing procedure for, based on a pixel value weighting found by multiplication of a combination of pose parameters computed in said parameter computation procedure and values that are computed based on pixel values of an image before binarization in said binarization procedure, drawing a surface on said parameter space parameter surfaces that accord with said surface parameter formulas;

a pixel value-weighted significant candidate extraction procedure for, when at said cross point coordinates, the sum of the number of cross surfaces at which said parameter surfaces intersect each other and pixel value weightings is greater than a prescribed value, and moreover, when the number of cross surfaces is a maximum in neighboring regions that take the cross point coordinates as a reference, identifying the combination of parameters at the cross point coordinates as a significant candidate of a combination of parameters that form a reference surface that is the object of detection; and

a pixel value-weighted weighting computation procedure for, based on angles formed by tangent planes at cross pixels that were found in said cross determination procedure and surfaces formed by axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified in said cross determination procedure, and, by multiplying these slope weightings that were found and values computed based on pixel values of an image before binarization in said binarization procedure, finding pixel value-weighted slope weightings.

124. A record medium having recorded there on a computer-readable program for causing a computer to execute:

a binarization procedure for dividing an image received as input into a candidate region that is a candidate for a reference surface that is a reference for estimating pose and a background region that is a region other than the candidate region;

a surface parameter formula expression procedure for extracting pose parameters that indicate the pose of an object of pose estimation with respect to a reference surface that appears in said image received as input and, based on a combination of values obtained by implementing a transform by a prescribed function upon, of pose parameters that were extracted, parameters that indicate the direction in which an object of pose estimation is directed and pose parameters other than parameter that indicate direction, finding surface parameter formulas that are numerical formulas that express said reference surface;

an all-candidate surface drawing procedure for, based on a combination of all pose parameters in parameter space, which is space having, as axes of base vectors, each of the parameters belonging to said pose parameters, drawing candidate surfaces that accord with said surface parameter formulas on said image in said parameter space;

a cross determination procedure for, as regards each candidate surface that was drawn in said all-candidate surface drawing procedure, identifying pixels that are located on, of said candidate region, the candidate surface, and pixels that are located within a prescribed range from the candidate surface as cross pixels and finding coordinates of the cross pixels and tangent planes at said cross pixels;

a weighting computation procedure for, based on angles that are formed by tangent planes at cross pixels that were found in said cross determination procedure and planes that are formed by the axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified in said cross determination procedure;

a number measurement procedure for computing for each of said candidate surfaces a number that is a value obtained by adding up the slope weightings of cross pixels that were found in said weighting computation procedure and that were contained in each of the candidate surfaces; and

an actual surface determination procedure for, based on the numbers computed in said number measurement procedure, identifying from among candidate surfaces drawn in said all-candidate surface drawing procedure an actual surface that is a reference surface that actually exists in said image.

125. The record medium according to claim 124, further comprising a smoothing procedure for implementing a process for smoothing said image received as input, wherein, in said binarization procedure, a binarized image is generated based on an image that has undergone smoothing in said smoothing procedure.

126. The record medium according to claim 124, further comprising a dilation/erosion procedure for subjecting a candidate region of a binarized image generated in said binarization procedure to a prescribed number of dilation procedures for dilating the candidate region or to erosion procedures for eroding the candidate region.

128. The record medium according to claim 124, further comprising:

a parameter space coarse-graining procedure for increasing the discretization width of said parameter space to a predetermined width to coarsen parameter space and find an actual surface, and after an actual surface has once been found, changing discretization to make the parameter space finer; and

a parameter micro-adjustment procedure for repeatedly executing derivation of new actual surfaces in the parameter space of different discretization widths in neighboring regions of an actual surface that has once been found in parameter space that has undergone said discretization until reaching a prescribed number of processes is reached or until the discretization width reaches a prescribed value.

130. The record medium according to claim 124, further comprising a pixel value-weighted weighting computation procedure for finding pixel value-weighted slope weightings by multiplying said slope weightings and values computed based on pixel values of an image before binarization in said binarization procedure.

131. The record medium according to claim 124, further comprising:

a positional relation estimation procedure for, when a plurality of actual surfaces appear in said image that is received as input, estimating both the positional relation between each of said actual surfaces and identifying the actual surfaces by placing said actual surfaces in correspondence with physical entities; and

a pose significance procedure for carrying out a significance process, which is a process of, based on the positional relation of said plurality of surfaces estimated in said positional relation estimation procedure, placing said pose parameters in correspondence with said actual surfaces to determine the pose of an object of pose estimation with respect to the actual surfaces.

132. A record medium having recorded there on a computer-readable program for causing a computer to execute a data processing switching procedure for, based on the results of comparing a parameter space calculation amount, which is a calculation amount indicating the volume of arithmetic processing carried out by executing a first program to identify an actual surface that is said reference surface, and an image space calculation amount, which is a calculation amount indicating the volume of arithmetic processing carried out by executing a second program to identify an actual surface, selecting one of the programs, among the first program and the second program and executing the selected program to identify said actual surface:

the first program for causing a computer to execute;

a binarization procedure for dividing an image that is received as input into a candidate region that is a candidate for a reference surface that is the reference for estimating pose and a background region that is a region other than the candidate region;

a surface parameter formula expression procedure for extracting pose parameters that indicate the pose of an object of pose estimation with respect to a reference surface that appears in said image received as input and, based on a combination of values obtained by implementing a transform by a prescribed function upon, of the pose parameters that were extracted, parameters that indicate the direction in which the object of pose estimation is directed and pose parameters other than the parameters that indicate direction, finding a surface parameter formulas that are numerical formulas that express the reference surface;

a parameter computation procedure for, based on pose parameters that were extracted in said surface parameter formula expression procedure, computing a combination of pose parameters that make up said surface parameter formulas that express all surfaces that pass through each pixel contained in the candidate region that was divided in said binarization procedure;

a parameter surface drawing procedure for, based on the combination of pose parameters computed in said parameter computation procedure, drawing parameter surfaces that accord with said surface parameter formulas on parameter space, which is space that includes each of the parameters belonging to said pose parameters as the axes of base vectors;

an intersection detection procedure for finding cross point coordinates, which are the coordinates of intersections through which a plurality of said parameter surfaces that were drawn in said parameter surface drawing procedure pass, and cross surface numbers, which are the numbers of parameter surfaces that pass through the cross point coordinates;

a significant candidate extraction procedure for, when the cross surface number at each cross point that was found in said intersection detection procedure is compared with the cross surface numbers at other cross point coordinates in prescribed neighboring regions that take the cross point coordinates corresponding to the cross surface number as a reference and is thus determined to be a maximum, identifying the combination of pose parameters that make up the parameter surface that corresponds to the determined cross surface number as a significant candidate, which is the optimum combination of pose parameters for expressing said reference surface;

a significant candidate surface drawing procedure for, based on a significant candidate identified in said significant candidate extraction procedure and the combination of pose parameters that were computed in said parameter computation procedure for which distance to the significant candidate in said parameter space in prescribed neighboring regions that take the significant candidate as a reference is no greater than a prescribed value, drawing significant candidate surfaces on said image;

a cross determination procedure for, regarding each significant candidate surface that was drawn in said significant candidate surface drawing procedure, identifying pixels that are located on, of said candidate region, the significant candidate surface, and pixels that are located within a prescribed range from the significant candidate surface as cross pixels and finding coordinates of the cross pixels and tangent planes at the cross pixels;

a weighting computation procedure for, based on angles that are formed by tangent planes at the cross pixels that were found in said cross determination procedure and planes that are formed by the axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified in said cross determination procedure;

a number measurement procedure for computing for each of said significant candidate surfaces a number that is the value obtained by adding up the slope weightings of cross pixels that were found in said weighting computation procedure and that were contained in each of the significant candidates; and

an actual surface determination procedure for, when the number computed in said number measurement procedure is compared with numbers belonging to other significant candidate surfaces in neighboring regions that take as a reference the significant candidate surface that has this number and thus is determined to be a maximum, identifying the significant candidate surface having the determined number as an actual surface that is a reference surface that actually exists in said image;

the second program for causing a computer to execute;

a binarization procedure for dividing an image received as input into a candidate region that is a candidate for a reference surface that is a reference for estimating pose and a background region that is a region other than the candidate region;

a surface parameter formula expression procedure for extracting pose parameters that indicate the pose of an object of pose estimation with respect to a reference surface that appears in said image received as input and, based on a combination of values obtained by implementing a transform by a prescribed function upon, of pose parameters that were extracted, parameters that indicate the direction in which an object of pose estimation is directed and pose parameters other than parameter that indicate direction, finding surface parameter formulas that are numerical formulas that express said reference surface;

an all-candidate surface drawing procedure for, based on a combination of all pose parameters in parameter space, which is space having, as axes of base vectors, each of the parameters belonging to said pose parameters, drawing candidate surfaces that accord with said surface parameter formulas on said image in said parameter space;

a cross determination procedure for, as regards each candidate surface that was drawn in said all-candidate surface drawing procedure, identifying pixels that are located on, of said candidate region, the candidate surface, and pixels that are located within a prescribed range from the candidate surface as cross pixels and finding coordinates of the cross pixels and tangent planes at said cross pixels;

a weighting computation procedure for, based on angles that are formed by tangent planes at cross pixels that were found in said cross determination procedure and planes that are formed by the axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified in said cross determination procedure;

a number measurement procedure for computing for each of said candidate surfaces a number that is a value obtained by adding up the slope weightings of cross pixels that were found in said weighting computation procedure and that were contained in each of the candidate surfaces; and

an actual surface determination procedure for, based on the numbers computed in said number measurement procedure, identifying from among candidate surfaces drawn in said all-candidate surface drawing procedure an actual surface that is a reference surface that actually exists in said image.

133. The record medium according to claim 132, wherein said data processing switching procedure comprises:

a binarization procedure for dividing said image into a candidate region that is a candidate for said reference surface and a background region that is a region other than the candidate region;

a surface parameter formula expression procedure for extracting pose parameters that indicate the pose of an object of pose estimation with respect to a reference surface that appears in said image that was received as input and, based on a combination of values obtained by implementing a transform by a prescribed function upon, of the pose parameters that were extracted, parameters that indicate the direction in which the object of pose estimation is directed and pose parameters other than the parameters that indicate the direction, finding surface parameter formulas that are numerical formulas that express said reference surface;

a parameter computation calculation amount estimation procedure for estimating a parameter computation calculation amount, which is an amount that indicates the volume of arithmetic processing for executing the first program to compute the combinations of pose parameters that make up said surface parameter formulas that express all reference surfaces that pass through each pixel contained in the candidate region that was divided by said binarization unit;

a parameter surface drawing calculation amount estimation procedure for estimating a parameter surface drawing calculation amount for executing the first program to draw parameter surfaces that accord with said surface parameter formulas;

an intersection detection calculation amount estimation procedure for estimating an intersection detection calculation amount for executing the first program to find said cross point coordinates and said cross surface numbers;

a significant candidate extraction calculation amount estimation procedure for estimating a significant candidate extraction calculation amount for executing the first program to identify said significant candidates;

a significant candidate surface drawing calculation amount estimation procedure for estimating a significant candidate surface drawing calculation amount for executing the first program to draw said significant candidate surfaces;

a cross determination calculation amount estimation procedure for estimating a cross determination calculation amount for executing the first program to identify said cross pixels and for executing the first program to find the coordinates of the cross pixels and tangent planes at said cross pixels;

a weighting computation calculation amount estimation procedure for estimating a weighting computation calculation amount for executing the first program to find said slope weightings;

a number measurement calculation amount estimation procedure for estimating a number measurement calculation amount for executing the first program to compute said number for each said significant candidate surface;

an actual surface determination calculation amount estimation procedure for estimating an actual surface determination calculation amount for executing the first program to identify said actual surfaces from among said significant candidate surfaces;

an all-candidate surface drawing calculation amount estimation procedure for estimating an all-candidate surface drawing calculation amount for executing the second program to draw candidate surfaces that accord with said surface parameter formulas;

an all-cross determination calculation amount estimation procedure for estimating an all-cross determination calculation amount for executing the second program to identify said cross pixels and for executing the second program to find coordinates of the cross pixels and tangent planes at said cross pixels;

an all-weighting computation calculation amount estimation procedure for estimating an all-weighting computation calculation amount for executing the second program to find said slope weightings;

an all-number measurement calculation amount estimation procedure for estimating an all-number measurement calculation amount for executing the second program to compute said numbers;

an all-actual surface determination calculation amount estimation procedure for estimating an all-actual surface determination calculation amount for executing the second program to identify said actual surfaces from among said candidate surfaces; and

a method selection procedure for;

finding said parameter space calculation amount by adding up said parameter computation calculation amount, said parameter surface drawing calculation amount, said intersection detection calculation amount, said significant candidate extraction calculation amount, said significant candidate surface drawing calculation amount, said cross determination calculation amount, said weighting computation calculation amount, said number measurement calculation amount, and said actual surface determination calculation amount;

finding said image space calculation amount by adding up said all-candidate surface drawing calculation amount, said all-cross determination calculation amount, said all weighting computation calculation amount, said all-number measurement calculation amount, and said all-actual surface determination calculation amount; and

when, as a result of comparing said parameter space calculation amount that was found and said image space calculation amount that was found, said parameter space calculation amount is determined to be less than said image space calculation amount, selecting said first program to identify said actual surface, and when said parameter space calculation amount is determined to be greater than said image space calculation amount, selecting said second program to identify said actual surface.

134. The record medium according to claim 133, wherein,

the first program, further comprising:

a pixel value-weighted parameter surface drawing procedure for, based on a pixel value weighting found by multiplication of a combination of pose parameters computed in said parameter computation procedure and values that are computed based on pixel values of an image before binarization in said binarization procedure, drawing a surface on said parameter space parameter surfaces that accord with said surface parameter formulas;

a pixel value-weighted significant candidate extraction procedure for, when at said cross point coordinates, the sum of the number of cross surfaces at which said parameter surfaces intersect each other and pixel value weightings is greater than a prescribed value, and moreover, when the number of cross surfaces is a maximum in neighboring regions that take the cross point coordinates as a reference, identifying the combination of parameters at the cross point coordinates as a significant candidate of a combination of parameters that form a reference surface that is the object of detection; and

a pixel value-weighted weighting computation procedure for, based on angles formed by tangent planes at cross pixels that were found in said cross determination procedure and surfaces formed by axes of each base vector included in said parameter space, finding a slope weighting for each cross pixel that was identified in said cross determination procedure, and, by multiplying these slope weightings that were found and values computed based on pixel values of an image before binarization in said binarization procedure, finding pixel value-weighted slope weightings;

said data processing switching procedure further comprises;

a pixel value-weighted parameter surface drawing procedure for, when drawing parameter surfaces on said parameter space, finding pixel value weightings based on pixel values of an image before binarization in said binarization procedure;

a pixel value-weighted significant candidate extraction procedure for, when at said intersections, the sum of the number of cross surfaces at which parameter surfaces intersect each other and pixel value weightings is greater than a prescribed value, and moreover, when the number of cross surfaces is a maximum in neighboring regions that take the cross point coordinates as a reference, identifying the combination of parameters at the cross point coordinates as a significant candidate of a combination of parameters that form a reference surface that is the object of detection;

a pixel value-weighted weighting computation procedure for further multiplying said slope weightings by values that are computed based on pixel values of a three-dimensional image before binarization and then taking the result as new slope weightings;

a pixel value-weighted parameter surface drawing calculation amount estimation procedure for estimating the calculation amount necessary for execution of said weighted parameter surface drawing procedure;

a pixel value-weighted significant candidate extraction calculation amount estimation procedure for estimating the calculation amount necessary for execution of said pixel value-weighted significant candidate extraction procedure; and

a pixel value-weighted weighting computation calculation amount estimation procedure for estimating the calculation amount necessary for execution of said pixel value-weighted weighting computation procedure.

135. The record medium according to claim 132, further comprising a communication procedure for, when an actual surface is determined in said actual surface determination procedure, transmitting to the outside pose parameters that make up the actual surface that was determined.