A method and device for measuring point cloud geometric dimensions based on calipers

Abstract

The present application provides a method and device for measuring the geometric dimensions of a point cloud based on a caliper. The method includes: obtaining a point cloud to be measured, a virtual caliper, and a measurement direction; constructing a search geometry based on the virtual caliper and the measurement direction; segmenting the point cloud to be measured based on the search geometry to obtain a candidate point cloud; extracting point cloud measurement points along the measurement direction from the candidate point cloud based on the virtual caliper; calculating the distance between the point cloud measurement points, and using the distance as the dimension of the point cloud to be measured along the measurement direction. Before extracting the point cloud measurement points, the present application segments the point cloud to be measured by constructing a search geometry to obtain a candidate point cloud, thereby greatly reducing the amount of data and improving computational efficiency. In addition, it can achieve rapid and high-precision measurement of the geometric dimensions of workpieces of different directions and shapes in a variety of application scenarios, thereby improving the accuracy of the point cloud geometric dimension measurement results.

Description

Technical Field

[0001] The present application relates to the technical field of point cloud dimension measurement, and in particular to a method and device for measuring point cloud geometric dimensions based on a caliper. Background Art

[0002] In industrial measurement, collecting surface points on an object or workpiece to form a 3D point cloud and then performing non-contact measurement of the object's dimensions is a common method. Point cloud geometric dimensional measurement typically involves measuring dimensions such as length, width, inner and outer diameters, or height of the collected point cloud model. By comparing these dimensional measurements with standard dimensions, quality control can be achieved during the workpiece production process.

[0003] Currently, point cloud dimension measurement methods primarily rely on designing a series of rules to extract feature points from the point cloud and then measuring the distance between them. Alternatively, surface fitting is performed on the point cloud to obtain an analytical expression, and then measuring the distance between the feature points. However, these methods are computationally complex and cannot meet the diverse requirements for workpiece dimension measurement in real-world industrial settings. Summary of the Invention

[0004] This application provides a caliper-based point cloud geometric dimension measurement method and device to solve the problem that the existing point cloud dimension measurement method has a relatively complex calculation process and cannot meet the diverse needs of workpiece dimension measurement in actual industrial sites.

[0005] In a first aspect, the present application provides a caliper-based point cloud geometric dimension measurement method, comprising: obtaining a point cloud to be measured, a virtual caliper, and a measurement direction; constructing a search geometry based on the virtual caliper and the measurement direction; segmenting the point cloud to be measured according to the search geometry to obtain a candidate point cloud; extracting point cloud measurement points along the measurement direction from the candidate point cloud according to the virtual caliper; calculating the distance between the point cloud measurement points, and using the distance as the dimension of the point cloud to be measured along the measurement direction.

[0006] In combination with the first aspect, in a possible implementation, the shape of the virtual caliper is a sphere, and the search geometry is a search cylinder; then the method of constructing the search geometry based on the virtual caliper and the measurement direction includes: obtaining the search depth and the center and radius of the virtual caliper; constructing a cylinder based on the center, the radius, the search depth and the measurement direction, and using the cylinder as the search cylinder.

[0007] In combination with the first aspect, in a possible implementation, the method of constructing a cylinder based on the center of the sphere, the radius of the sphere, the search depth and the measurement direction includes: using the measurement direction as the axis direction of the search cylinder, the center of the sphere is on the axis of the cylinder, the radius of the sphere is used as the bottom radius of the cylinder, and the search depth is used as the height of the cylinder.

[0008] In combination with the first aspect, in a possible implementation, the shape of the virtual caliper is a cylinder, and the search geometry is a search cuboid; the method of constructing a search geometry based on the virtual caliper and the measurement direction includes: obtaining the search depth and the axis direction, axis center point, bottom radius and height of the virtual caliper; constructing a cuboid based on the search depth, the axis direction, the axis center point, the bottom radius, the height and the measurement direction, and using the cuboid as the search cuboid.

[0009] In conjunction with the first aspect, in one possible implementation, the method of constructing a cuboid based on the search depth, the axis direction, the axis center point, the bottom radius, the height, and the measurement direction includes: using the axis direction as the height direction of the search cuboid, twice the bottom radius as the width of the search cuboid, the search depth as the length of the search cuboid, and the height as the height of the search cuboid; the expression for the width direction of the search cuboid is:

[0010] D l =D h ×D c ;

[0011] Among them, D l is the width direction, D h is the height direction, D c is the measurement direction;

[0012] The expression for the length direction of the search cuboid is:

[0013] D w =D h ×D l ;

[0014] Among them, D w is the length direction, D h is the height direction, D l is the width direction;

[0015] The corrected measurement direction of the search cuboid is the length direction, and the corrected measurement direction expression is:

[0016] D′c =D w ;

[0017] Among them, D′ c is the corrected measurement direction, D w is the length direction;

[0018] The expression for searching the center point of the cuboid is:

[0019]

[0020] Among them, P c is the center point of the search cuboid, P0 is the center point of the axis, w is the length of the search cuboid, D′ c is the corrected measurement direction.

[0021] In combination with the first aspect, in a possible implementation method, the method of segmenting the point cloud to be measured according to the search geometry to obtain a candidate point cloud includes: obtaining the coordinates of each point in the point cloud to be measured; judging whether it is inside the search geometry based on the coordinates of each point; obtaining all points inside the search geometry to form a point cloud set, and using the point cloud set as the candidate point cloud.

[0022] In combination with the first aspect, in a possible implementation, the method of extracting point cloud measurement points along the measurement direction from the candidate point cloud based on the virtual caliper includes: calculating the distance from each point in the candidate point cloud to the virtual caliper along the measurement direction; and taking the point corresponding to the minimum distance value as the point cloud measurement point.

[0023] In combination with the first aspect, in a possible implementation, the method of extracting point cloud measurement points along the measurement direction from the candidate point cloud based on the virtual caliper includes: fitting the candidate point cloud into a geometric surface by a least squares fitting method or a random sampling consistent fitting method; constructing a straight line along the measurement direction based on the center of the sphere; obtaining the intersection of the straight line and the geometric surface; and using the intersection point closest to the virtual caliper as the point cloud measurement point.

[0024] In combination with the first aspect, in a possible implementation, the method of extracting point cloud measurement points along the measurement direction from the candidate point cloud based on the virtual caliper includes: calculating the distance from each point in the candidate point cloud to the virtual caliper along the measurement direction; taking the point corresponding to the minimum distance value as the first measurement point; constructing a constraint plane based on the point cloud to be measured; the virtual caliper starts from the first measurement point and moves on the constraint plane until it has two intersections with the point cloud to be measured, and taking the two intersections as point cloud measurement points.

[0025] In a second aspect, the present application further provides a caliper-based point cloud geometric dimension measuring device, comprising:

[0026] The acquisition module is used to obtain the point cloud to be measured, the virtual caliper and the measurement direction;

[0027] A search geometry building module, configured to build a search geometry according to the virtual caliper and the measurement direction;

[0028] a segmentation module, configured to segment the point cloud to be measured according to the search geometry to obtain a candidate point cloud;

[0029] a measurement point extraction module, configured to extract point cloud measurement points along the measurement direction from the candidate point cloud according to the virtual caliper;

[0030] The distance calculation module is used to calculate the distance between the measurement points of the point cloud and use the distance as the size of the point cloud to be measured along the measurement direction.

[0031] As can be seen from the above technical solutions, the present application provides a method and device for measuring the geometric dimensions of a point cloud based on a caliper, the method comprising: obtaining a point cloud to be measured, a virtual caliper, and a measurement direction; constructing a search geometry based on the virtual caliper and the measurement direction; segmenting the point cloud to be measured based on the search geometry to obtain a candidate point cloud; extracting point cloud measurement points along the measurement direction from the candidate point cloud based on the virtual caliper; calculating the distance between the point cloud measurement points, and using the distance as the dimension of the point cloud to be measured along the measurement direction. Before extracting the point cloud measurement points, the present application segments the point cloud to be measured by constructing a search geometry to obtain a candidate point cloud, thereby greatly reducing the amount of data and improving computational efficiency. In addition, it can achieve rapid and high-precision measurement of the geometric dimensions of workpieces of different directions and shapes in a variety of application scenarios, thereby improving the accuracy of the point cloud geometric dimension measurement results. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0033] Figure 1 A flowchart of a caliper-based point cloud geometric dimension measurement method provided in an embodiment of the present application;

[0034] Figure 2 A schematic diagram of constructing a search cylinder provided in an embodiment of the present application;

[0035] Figure 3 A schematic diagram of constructing a search cuboid provided in an embodiment of the present application;

[0036] Figure 4 A schematic diagram of a search cylinder for segmenting a point cloud to be measured provided in an embodiment of the present application;

[0037] Figure 5 A schematic diagram of searching for a cuboid to segment a point cloud to be measured provided in an embodiment of the present application;

[0038] Figure 6 A schematic diagram of extracting point cloud measurement points based on a spherical virtual caliper provided in an embodiment of the present application;

[0039] Figure 7 A schematic diagram of extracting point cloud measurement points based on a cylindrical virtual caliper provided in an embodiment of the present application;

[0040] Figure 8 A schematic diagram of calculating the distance between point cloud measurement points provided in an embodiment of the present application;

[0041] Figure 9 A schematic structural diagram of a caliper-based point cloud geometric dimension measuring device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] The following embodiments are described in detail, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numerals in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following embodiments are not intended to represent all possible implementations consistent with the present application. They are merely examples of systems and methods consistent with certain aspects of the present application, as detailed in the claims.

[0043] In industrial measurement, collecting surface points on an object or workpiece to form a 3D point cloud and then performing non-contact measurement of the object's dimensions is a common method. Point cloud geometric dimensional measurement typically involves measuring dimensions such as length, width, inner and outer diameters, or height of the collected point cloud model. By comparing these dimensional measurements with standard dimensions, quality control can be achieved during the workpiece production process.

[0044] Currently, point cloud dimension measurement methods primarily rely on designing a series of rules to extract feature points from the point cloud and then measuring the distance between them. Alternatively, surface fitting is performed on the point cloud to obtain an analytical expression, and then measuring the distance between the feature points. However, these methods are computationally complex and cannot meet the diverse requirements for workpiece dimension measurement in real-world industrial settings.

[0045] Based on the above problems in the prior art, this application provides a caliper-based point cloud geometric dimension measurement method and device to solve the problem that the existing point cloud dimension measurement method has a relatively complex calculation process and cannot meet the diverse needs of workpiece dimension measurement in actual industrial sites.

[0046] In a first aspect, the present application provides a method for measuring point cloud geometric dimensions based on a caliper. Figure 1 The flowchart of a method for measuring point cloud geometric dimensions based on a caliper is provided in an embodiment of the present application. Figure 1 As shown, the method includes:

[0047] S101: Obtain the point cloud to be measured, the virtual caliper, and the measurement direction.

[0048] In this embodiment, the point cloud to be measured is three-dimensional point cloud data of the object to be measured. For example, it can be obtained by scanning the surface of the object to be measured using a three-dimensional laser scanner. The point cloud to be measured includes geometric features of the surface of the object to be measured. Therefore, the dimensional information of the object to be measured can be obtained based on the point cloud to be measured.

[0049] The virtual caliper can be determined by the user according to different application scenarios, for example, it can be spherical, cylindrical, etc. The virtual caliper simulates the measurement process of a vernier caliper or a three-dimensional coordinate measuring machine in the real world, thereby achieving the measurement of point cloud geometric dimensions.

[0050] The measurement direction is determined by the size direction that the user needs to measure the point cloud to be measured. It should be noted that the embodiment of the present application mainly measures the length, width, inner and outer diameters, and height of the point cloud to be measured.

[0051] S102: Constructing a search geometry according to the virtual caliper and the measurement direction.

[0052] In this embodiment, a search geometry is constructed based on the virtual caliper and the measurement direction in accordance with different application scenarios. This search geometry is used to segment the point cloud to be measured. The shape of the search geometry varies depending on the shape of the virtual caliper. For example, if the virtual caliper is shaped like a sphere, the search geometry is a search cylinder. If the virtual caliper is shaped like a cylinder, the search geometry is a search cuboid.

[0053] The method of constructing the search geometry is exemplarily described below with reference to the accompanying drawings.

[0054] Figure 2 This is a schematic diagram of constructing a search cylinder provided in an embodiment of the present application. Figure 2 As shown, in a possible implementation, the shape of the virtual caliper is a sphere, and the search geometry is a search cylinder. Then, in step S102, the method of constructing the search geometry according to the virtual caliper and the measurement direction includes:

[0055] S201: Acquire the search depth and the center and radius of the sphere of the virtual caliper.

[0056] S202: Construct a cylinder according to the sphere center, the sphere radius, the search depth, and the measurement direction, and use the cylinder as the search cylinder.

[0057] In one possible implementation, the specific implementation of step S202 includes: using the measurement direction as the axis direction of the search cylinder, the center of the sphere is on the axis of the cylinder, the radius of the sphere is used as the bottom radius of the cylinder, and the search depth is used as the height of the cylinder.

[0058] Specifically, such as Figure 2 As shown, when the shape of the virtual caliper is a sphere, the position of a point on the axis of the search cylinder is defined as the center of the sphere P0, and the direction of the axis of the search cylinder is defined as the measurement direction D c , the height of the search cylinder is defined as the search depth L s The base radius of the search cylinder is defined as the radius of the sphere. The search cylinder can be constructed according to the axis of the search cylinder, the height of the search cylinder and the base radius of the search cylinder.

[0059] Figure 3 This is a schematic diagram of constructing a search cuboid provided in an embodiment of the present application. Figure 3 As shown, in a possible implementation, the shape of the virtual caliper is a cylinder, and the search geometry is a search cuboid. Then, in step S102, the method of constructing the search geometry according to the virtual caliper and the measurement direction includes:

[0060] S301: Acquire the search depth and the axis direction, axis center point, bottom radius and height of the virtual caliper.

[0061] S302: Construct a cuboid according to the search depth, the axis direction, the axis center point, the bottom radius, the height, and the measurement direction, and use the cuboid as the search cuboid.

[0062] In one possible implementation, Figure 3 As shown, the specific implementation of step S302 includes:

[0063] The axis direction is used as the height direction of the search cuboid:

[0064] D h =D cyl ;

[0065] Among them, D h is the height direction, D cyl is the axis direction of the cylinder.

[0066] The width of the search cuboid is twice the base radius:

[0067] l = 2r;

[0068] Wherein, l is the width of the search cuboid, and r is the radius of the bottom surface.

[0069] The search depth is used as the length of the search cuboid:

[0070] w=L s ;

[0071] Wherein, w is the length of the search cuboid, L s is the search depth.

[0072] The height is used as the height of the search cuboid:

[0073] h=h cyl ;

[0074] Wherein, h is the height of the search cuboid, h cyl is the height.

[0075] The expression for the width direction of the search cuboid is:

[0076] D l =D h ×D c ;

[0077] Among them, D l is the width direction, D h is the height direction, D c is the measurement direction;

[0078] The expression for the length direction of the search cuboid is:

[0079] D w =D h ×D l ;

[0080] Among them, D w is the length direction, D h is the height direction, D l is the width direction;

[0081] The corrected measurement direction of the search cuboid is the length direction, and the corrected measurement direction expression is:

[0082] D′ c =D w ;

[0083] Among them, D′ c is the corrected measurement direction, Dw is the length direction;

[0084] The expression for searching the center point of the cuboid is:

[0085]

[0086] Among them, P c is the center point of the search cuboid, P0 is the center point of the axis, w is the length of the search cuboid, D c ' is the corrected measurement direction.

[0087] S103: Segment the point cloud to be measured according to the search geometry to obtain a candidate point cloud.

[0088] In one possible implementation, the method for obtaining a candidate point cloud by segmenting the point cloud to be measured according to the search geometry includes: obtaining the coordinates of each point in the point cloud to be measured; judging whether the point is inside the search geometry according to the coordinates of each point; obtaining all points inside the search geometry to form a point cloud set, and using the point cloud set as the candidate point cloud.

[0089] Figure 4 A schematic diagram of a search cylinder for segmenting a point cloud to be measured provided in an embodiment of the present application. Figure 4 As shown in the example, in one possible implementation, the specific implementation of step S103 includes:

[0090] Point P is a point in the point cloud, P0 is the center of the search cylinder, r is the radius of the bottom of the search cylinder, h is the height of the search cylinder, connect PP0, the projection length of PP0 in the direction of the search cylinder axis is h', the distance from point P to the search cylinder axis When point P satisfies l'<r, h'<h and PP0·D cyl >0, which means that the point P is inside the search cylinder. In this case, the point is retained as a candidate point, and the other points that do not meet the condition are eliminated.

[0091] Figure 5 A schematic diagram of searching for a cuboid to segment a point cloud to be measured provided in an embodiment of the present application. Figure 5 As shown in the example, in one possible implementation, the specific implementation of step S103 includes:

[0092] Point P is a point in the point cloud. Calculate the distances l', w', and h' from point P to the planes containing the length, width, and height of the search cuboid. Let the length, width, and height of the search cuboid be l, w, and h, respectively. If point P satisfies l'<l, w'<w, and h'<h, the point P is inside the search cuboid. In this case, the point is retained as a candidate point, and points that do not meet this condition are discarded.

[0093] S104: extracting point cloud measurement points along the measurement direction from the candidate point cloud according to the virtual caliper.

[0094] In this embodiment, point cloud measurement points are extracted from the candidate point cloud according to the virtual caliper. It can be understood that, in order to obtain the size of the point cloud to be measured, there are usually at least two point cloud measurement points.

[0095] In a possible implementation, the specific method of step S104 includes: calculating the distance from each point in the candidate point cloud to the virtual caliper along the measurement direction; and using the point corresponding to the minimum distance as the point cloud measurement point.

[0096] Figure 6 This is a schematic diagram of extracting point cloud measurement points based on a spherical virtual caliper provided in an embodiment of the present application. Figure 6 As shown in the example, in a possible implementation, when the virtual caliper is a sphere, the specific implementation of step S104 includes:

[0097] Point P is a point in the candidate point cloud. A ray is constructed with point P as the starting point, and the direction D is measured. c is the direction of the ray, and the projection distance s of the line connecting this point and the center of the sphere in the measurement direction is L·D c , the distance from the center of the virtual caliper to the ray Where L is the vector formed by the point and the center of the sphere. Assuming that the straight line distance from the intersection of the ray and the proximal end of the sphere to the center of the sphere and perpendicular to the measurement direction is q, then the distance between the point and the sphere along the measurement direction is Dist = sq, where The measurement direction D c The distance from all candidate point clouds to the surface of the virtual caliper sphere is calculated according to the above method, and the point corresponding to the minimum distance is the point cloud measurement point.

[0098] Figure 7 This is a schematic diagram of extracting point cloud measurement points based on a cylindrical virtual caliper provided in an embodiment of the present application. Figure 7 As shown in the example, in a possible implementation, when the virtual caliper is a cylinder, the specific implementation of step S104 includes:

[0099] When calculating the distance from the candidate point cloud to the cylinder's virtual caliper along the measurement direction, construct a ray along the measurement direction for each point in the candidate point cloud, find the first intersection of the ray with the cylinder's side surface, and then calculate the distance between the two points as the distance between the point and the cylinder's virtual caliper. The equation for the ray formed by the points in the candidate point cloud is:

[0100] P(t)=D c t+E(t≥0);

[0101] Among them, E is the coordinate of the point and t is the parameter.

[0102] like Figure 7 As shown, the equation of the cylindrical surface is:

[0103] (P-P0)·(P-P0)-(A·(P-P0)) 2 =r 2 ;

[0104] Where A is the cylinder axis vector.

[0105] Substituting the ray equation into the cylinder equation, we get:

[0106] (D c t+E-P0)·(D c t+E-P0)-(A·(D c t+E-P0)) 2 -r 2 =0;

[0107] Arranged at 2 +bt+c=0;

[0108] in,

[0109]

[0110] When b 2 When -4ac<0, the ray does not intersect the cylindrical surface; when b 2 When -4ac≥0, the solution is:

[0111]

[0112] Then the parameter of the closest intersection point between the ray and the cylinder is Substituting t2 into the ray equation, we can find the closest point P n , then the distance between this point and the virtual caliper surface of the cylinder is dist=|P n According to this principle, the distance between each point in the candidate point cloud and the surface of the cylinder virtual caliper is calculated, and the point corresponding to the minimum distance is the point cloud measurement point.

[0113] In one possible implementation, when the virtual caliper is a sphere, step S104 may further include: fitting the candidate point cloud to a geometric surface using a least squares fitting method or a random sampling consistent fitting method; constructing a straight line along the measurement direction from the sphere's center; obtaining the intersection of the straight line and the geometric surface; and using the intersection closest to the virtual caliper as the point cloud measurement point. This method, by fitting the candidate point cloud to a geometric surface, allows for more precise location of point cloud measurement points. This method is suitable for scenarios where the collected point cloud contains noise, further reducing the noise in the measured point cloud and improving the accuracy of the point cloud geometric measurement results.

[0114] In one possible implementation, when the virtual caliper is a sphere, step S104 may further include: calculating the distance from each point in the candidate point cloud to the virtual caliper along the measurement direction; selecting the point with the minimum distance as the first measurement point; constructing a constraint plane based on the point cloud to be measured; and moving the virtual caliper along the constraint plane, starting from the first measurement point, until it intersects with the point cloud to be measured, and selecting the two intersections as point cloud measurement points. In this way, by setting the constraint plane based on the actual scenario, the spherical virtual caliper can determine the measurement point where two point clouds intersect. The measurement point at this location is more stable, and the dimensional measurement result is closer to the true value.

[0115] Specifically, when the spherical virtual caliper obtains the first measurement point along the measurement direction, according to the center P0 of the spherical caliper at this time, the measurement direction D c and custom constraint direction D cons , generate a constraint plane, the position of the constraint plane is determined by the center of the sphere P0, and the plane normal vector n is perpendicular to the measurement direction D c and custom constraint direction D cons , that is, n = D c ×D cons The spherical virtual caliper keeps the sphere center on the constraint plane and continues to measure along the direction D c The robot moves until two contact measurement points are formed with the point cloud to be measured and then stops. At this time, a stable state is reached and the two contact measurement points are used as point cloud measurement points.

[0116] S105: Calculate the distance between the measurement points of the point cloud, and use the distance as the size of the point cloud to be measured along the measurement direction.

[0117] Figure 8 This is a schematic diagram of calculating the distance between point cloud measurement points provided in an embodiment of the present application. Figure 8As shown, in this embodiment, taking the spherical virtual caliper as an example, the spherical virtual caliper is used to obtain point cloud measurement points P1 and P2 on both sides of the candidate point cloud. At this time, the size measurement result is the point distance between the point cloud measurement points P1 and P2, that is, P1-P2.

[0118] In a second aspect, the present application also provides a point cloud geometric dimension measuring device based on a caliper, Figure 9 This is a schematic diagram of the structure of a point cloud geometric dimension measuring device based on a caliper provided in an embodiment of the present application. Figure 9 As shown, the device includes:

[0119] The acquisition module is used to obtain the point cloud to be measured, the virtual caliper and the measurement direction.

[0120] The search geometry building module is used to build a search geometry according to the virtual caliper and the measurement direction.

[0121] The segmentation module is used to segment the point cloud to be measured according to the search geometry to obtain a candidate point cloud.

[0122] A measurement point extraction module is used to extract point cloud measurement points along the measurement direction from the candidate point cloud according to the virtual caliper.

[0123] The distance calculation module is used to calculate the distance between the measurement points of the point cloud and use the distance as the size of the point cloud to be measured along the measurement direction.

[0124] As can be seen from the above technical solutions, the present application provides a method and device for measuring the geometric dimensions of a point cloud based on a caliper, the method comprising: obtaining a point cloud to be measured, a virtual caliper, and a measurement direction; constructing a search geometry based on the virtual caliper and the measurement direction; segmenting the point cloud to be measured based on the search geometry to obtain a candidate point cloud; extracting point cloud measurement points along the measurement direction from the candidate point cloud based on the virtual caliper; calculating the distance between the point cloud measurement points, and using the distance as the dimension of the point cloud to be measured along the measurement direction. Before extracting the point cloud measurement points, the present application segments the point cloud to be measured by constructing a search geometry to obtain a candidate point cloud, thereby greatly reducing the amount of data and improving computational efficiency. In addition, it can achieve rapid and high-precision measurement of the geometric dimensions of workpieces of different directions and shapes in a variety of application scenarios, thereby improving the accuracy of the point cloud geometric dimension measurement results.

[0125] It should be understood that in various embodiments of the present application, the size of the serial number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment.

[0126] The various sections of this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, the device and system embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For relevant portions, refer to the descriptions of the method embodiments.

[0127] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the specific embodiments provided above are merely examples of the overall concept of this application and do not constitute a limitation on the scope of protection of this application. For those skilled in the art, any other implementation methods developed based on the present application without creative effort shall fall within the scope of protection of this application.

Claims

1. A point cloud geometric dimension measurement method based on a caliper, characterized in that: include: Obtain the point cloud to be measured, virtual caliper and measurement direction; Constructing a search geometry according to the virtual caliper and the measurement direction, wherein the shape of the search geometry varies according to the shape of the virtual caliper; if the shape of the virtual caliper is a sphere, the search geometry is a search cylinder; if the shape of the virtual caliper is a cylinder, the search geometry is a search cuboid; Segment the point cloud to be measured according to the search geometry to obtain a candidate point cloud; extracting point cloud measurement points along the measurement direction from the candidate point cloud according to the virtual caliper; The distance between the measurement points of the point cloud is calculated, and the distance is used as the size of the point cloud to be measured along the measurement direction.

2. The method according to claim 1, characterized in that The shape of the virtual caliper is a sphere, and the search geometry is a search cylinder; the method of constructing the search geometry according to the virtual caliper and the measurement direction includes: Obtaining the search depth and the center and radius of the sphere of the virtual caliper; A cylinder is constructed according to the sphere center, the sphere radius, the search depth, and the measurement direction, and the cylinder is used as the search cylinder.

3. The method according to claim 2, characterized in that The method for constructing a cylinder according to the sphere center, the sphere radius, the search depth and the measurement direction includes: The measuring direction is used as the axis direction of the search cylinder, the center of the sphere is on the axis of the cylinder, the radius of the sphere is used as the bottom radius of the cylinder, and the search depth is used as the height of the cylinder.

4. The method according to claim 1, wherein The shape of the virtual caliper is a cylinder, and the search geometry is a search cuboid; the method of constructing the search geometry according to the virtual caliper and the measurement direction includes: Obtaining the search depth and the axis direction, axis center point, bottom radius, and height of the virtual caliper; A cuboid is constructed according to the search depth, the axis direction, the axis center point, the bottom radius, the height, and the measurement direction, and the cuboid is used as the search cuboid.

5. The method according to claim 4, characterized in that The method for constructing a cuboid according to the search depth, the axis direction, the axis center point, the bottom radius, the height, and the measurement direction includes: The axis direction is used as the height direction of the search cuboid, twice the bottom radius is used as the width of the search cuboid, the search depth is used as the length of the search cuboid, and the height is used as the height of the search cuboid; The expression for the width direction of the search cuboid is: D l =D h ×D c ; Among them, D l is the width direction, D h is the height direction, D c is the measurement direction; The expression for the length direction of the search cuboid is: D w =D h ×D l ; Among them, D w is the length direction, D h is the height direction, D l is the width direction; The corrected measurement direction of the search cuboid is the length direction, and the corrected measurement direction expression is: D' c =D w ; Among them, D' c is the corrected measurement direction, D w is the length direction; The expression for searching the center point of the cuboid is: Among them, P c is the center point of the search cuboid, P0 is the center point of the axis, w is the length of the search cuboid, D c ' is the corrected measurement direction.

6. The method according to any one of claims 1 to 5, characterized in that The method for obtaining a candidate point cloud by segmenting the point cloud to be measured according to the search geometry includes: Obtaining the coordinates of each point in the point cloud to be measured; Determine whether each point is inside the search geometry according to its coordinates; All points inside the search geometry are acquired to form a point cloud set, and the point cloud set is used as the candidate point cloud.

7. The method according to claim 6, characterized in that The method for extracting point cloud measurement points along the measurement direction from the candidate point cloud according to the virtual caliper includes: Calculating the distance from each point in the candidate point cloud to the virtual caliper along the measurement direction; The point corresponding to the minimum distance value is used as the point cloud measurement point.

8. The method according to claim 2 or 3, characterized in that The method for extracting point cloud measurement points along the measurement direction from the candidate point cloud according to the virtual caliper includes: Fitting the candidate point cloud into a geometric surface by a least squares fitting method or a random sampling consistent fitting method; Constructing a straight line along the measuring direction according to the center of the sphere; Obtaining the intersection point between the straight line and the surface of the geometric body; The intersection point closest to the virtual caliper is used as the point cloud measurement point.

9. The method according to claim 2 or 3, characterized in that The method for extracting point cloud measurement points along the measurement direction from the candidate point cloud according to the virtual caliper includes: Calculating the distance from each point in the candidate point cloud to the virtual caliper along the measurement direction; The point corresponding to the minimum distance is taken as the first measurement point; Constructing a constraint plane according to the point cloud to be measured; The virtual caliper starts from the first measuring point and moves on the constraint plane until it has two intersection points with the point cloud to be measured, and the two intersection points are used as point cloud measurement points.

10. A point cloud geometric dimension measuring device based on a caliper, characterized in that: include: The acquisition module is used to obtain the point cloud to be measured, the virtual caliper and the measurement direction; a search geometry construction module, configured to construct a search geometry according to the virtual caliper and the measurement direction, wherein the shape of the search geometry varies according to the shape of the virtual caliper; if the shape of the virtual caliper is a sphere, the search geometry is a search cylinder; if the shape of the virtual caliper is a cylinder, the search geometry is a search cuboid; a segmentation module, configured to segment the point cloud to be measured according to the search geometry to obtain a candidate point cloud; a measurement point extraction module, configured to extract point cloud measurement points along the measurement direction from the candidate point cloud according to the virtual caliper; The distance calculation module is used to calculate the distance between the measurement points of the point cloud and use the distance as the size of the point cloud to be measured along the measurement direction.

Images