Point cloud data processing apparatus, point cloud data processing method, and program
A point cloud data processing apparatus 11 includes a processor configured to acquire first form information that indicates a feature of a form of a first object, specify an object region of a second object that is identified from an image and that corresponds to the first form information, select second-object point cloud data, in point cloud data, that corresponds to the object region, on the basis of the object region, acquire second form information that indicates a feature of a form of the second object, on the basis of the second-object point cloud data, and compare the first form information with the second form information and perform determination as to whether the second object is the first object.
1 . A point cloud data processing apparatus comprising:
a memory configured to store an image of a first object that is a detection target and that is a photographic subject and point cloud data that includes a large number of points on a surface of the first object and that represents at least three-dimensional information, in association with positions of pixels that constitute the image and pieces of point data that constitute the point cloud data; and
a processor,
the processor being configured to
acquire first form information that indicates a feature of a form of the first object,
specify an object region of a second object that is identified from the image and that corresponds to the first form information,
select, on the basis of positions of pixels of the object region, second-object point cloud data corresponding to the object region that is stored in association with the positions of the pixels of the object region in the point cloud data stored in the memory,
acquire second form information that indicates a feature of a form of the second object, on the basis of the second-object point cloud data, and
compare the first form information with the second form information and perform determination as to whether the second object is the first object,
wherein the first form information includes, of information about a type of the form of the first object, information about the surface of the first object, and information about a size of the first object, at least the information about the type of the form of the first object,
the first object that is the detection target has a cylindrical form, a rectangular parallelepiped form, or a spherical form, and
the processor is configured to calculate a maximum curvature and a minimum curvature that are principal curvatures of the second object on the basis of the second-object point cloud data and acquire the second form information from the calculated maximum curvature and minimum curvature, or input the second-object point cloud data to a detector subjected to machine learning and acquire the second form information from a result output from the detector.
2 . The point cloud data processing apparatus according to claim 1 , wherein the processor is configured to assign an attribute to the second-object point cloud data on the basis of a result of the determination.
3 . The point cloud data processing apparatus according to claim 1 , wherein the processor is configured to cause a display unit to display a result of the determination.
4 . The point cloud data processing apparatus according to claim 2 , wherein the processor is configured to cause a display unit to display a result of the determination.
5 . The point cloud data processing apparatus according to claim 1 , wherein the form of the first object is a cylindrical form.
6 . The point cloud data processing apparatus according to claim 2 , wherein the form of the first object is a cylindrical form.
7 . The point cloud data processing apparatus according to claim 3 , wherein the form of the first object is a cylindrical form.
8 . The point cloud data processing apparatus according to claim 5 , wherein the processor is configured to acquire the second form information on the basis of the second-object point cloud data by at least one of a Hough transformation process, a RANSAC algorithm, or a detector subjected to machine learning.
9 . The point cloud data processing apparatus according to claim 1 , wherein the first object is piping.
10 . The point cloud data processing apparatus according to claim 2 , wherein the first object is piping.
11 . The point cloud data processing apparatus according to claim 3 , wherein the first object is piping.
12 . The point cloud data processing apparatus according to claim 5 , wherein the first object is piping.
13 . The point cloud data processing apparatus according to claim 8 , wherein the first object is piping.
14 . A point cloud data processing method using a point cloud data processing apparatus comprising: a memory configured to store an image of a first object that is a detection target and that is a photographic subject and point cloud data that includes a large number of points on a surface of the first object and that represents at least three-dimensional information, in association with positions of pixels that constitute the image and pieces of point data that constitute the point cloud data; and a processor,
the processor being configured to perform
a step of acquiring first form information that indicates a feature of a form of the first object,
a step of specifying an object region of a second object that is identified from the image and that corresponds to the first form information,
a step of selecting second-object point cloud data, in the point cloud data, that corresponds to the object region, on the basis of the object region,
a step of selecting, on the basis of positions of pixels of the object region, second-object point cloud data corresponding to the object region that is stored in association with the positions of the pixels of the object region in the point cloud data stored in the memory,
a step of acquiring second form information that indicates a feature of a form of the second object, on the basis of the second-object point cloud data, and
a step of comparing the first form information with the second form information and performing determination as to whether the second object is the first object,
wherein the first form information includes, of information about a type of the form of the first object, information about the surface of the first object, and information about a size of the first object, at least the information about the type of the form of the first object,
the first object that is the detection target has a cylindrical form, a rectangular parallelepiped form, or a spherical form, and
the processor is configured to further perform a step of calculating a maximum curvature and a minimum curvature that are principal curvatures of the second object on the basis of the second-object point cloud data and acquiring the second form information from the calculated maximum curvature and minimum curvature, or inputting the second-object point cloud data to a detector subjected to machine learning and acquiring the second form information from a result output from the detector.
15 . A non-transitory computer recording medium storing a program for causing a point cloud data processing apparatus to perform a point cloud data processing method, the point cloud data processing apparatus comprising: a memory configured to store an image of a first object that is a detection target and that is a photographic subject and point cloud data that includes a large number of points on a surface of the first object and that represents at least three-dimensional information, in association with positions of pixels that constitute the image and pieces of point data that constitute the point cloud data; and a processor,
the program causing the processor to perform
a step of acquiring first form information that indicates a feature of a form of the first object,
a step of specifying an object region of a second object that is identified from the image and that corresponds to the first form information,
a step of selecting, on the basis of positions of pixels of the object region, second-object point cloud data corresponding to the object region that is stored in association with the positions of the pixels of the object region in the point cloud data stored in the memory,
a step of acquiring second form information that indicates a feature of a form of the second object, on the basis of the second-object point cloud data, and
a step of comparing the first form information with the second form information and performing determination as to whether the second object is the first object,
wherein the first form information includes, of information about a type of the form of the first object, information about the surface of the first object, and information about a size of the first object, at least the information about the type of the form of the first object,
the first object that is the detection target has a cylindrical form, a rectangular parallelepiped form, or a spherical form, and
the program causes the processor to further perform a step of calculating a maximum curvature and a minimum curvature that are principal curvatures of the second object on the basis of the second-object point cloud data and acquiring the second form information from the calculated maximum curvature and minimum curvature, or inputting the second-object point cloud data to a detector subjected to machine learning and acquiring the second form information from a result output from the detector.
16 . The point cloud data processing apparatus according to claim 1 , wherein
the first form information includes at least information about a type of the form of the first object.