Device and method for automatically measuring feature size of irregular object

Abstract

The invention relates to a device and a method for automatically measuring the feature size of an irregular object, and relates to the technical field of size measurement. The device comprises a shape and size measuring device used for carrying out point cloud scanning measurement on an object to be measured and obtaining point cloud data, and further comprises a mechanical arm provided with a vacuum chuck; the conveying belt is arranged below the mechanical arm; and the slide is used for carrying an object to be detected, and the slide is arranged on the conveyor belt to be conveyed. The method comprises the following steps that 1, a mechanical arm adsorbs a slide carrying an object to be measured through a vacuum chuck so as to send the object to be measured to shape and size measurement equipment, point cloud scanning measurement is carried out, and point cloud data are obtained; 2, the feature sizes of the irregular object are defined as X, Y and Z, and X, Y and Z are the sizes of the fragments in the three orthogonal directions; 3, after the irregular point cloud of the to-be-measured object is obtained through scanning, the point cloud needs to be preprocessed, and point cloud noise is removed;

Description

Technical Field

[0001] The present invention relates to the technical field of dimension measurement, and in particular to a device and method for automatically measuring characteristic dimensions of an irregular object. Background Art

[0002] Traditional object size measurement is often done manually, which is inefficient. If there are a large number of objects with completely irregular sizes and shapes, it is impossible to quickly achieve automatic size measurement. At present, point cloud scanning measurement methods based on machine vision are gradually replacing manual measurement in industrial scenarios. In the current irregular object scanning measurement method, the object to be measured needs to be manually placed under the scanning system, and the object to be measured is manually replaced after scanning. After obtaining the three-dimensional point cloud or mesh data of the object to be measured, the original data needs to be imported into a third-party software, and the corresponding surface fitting or intelligent size extraction is manually performed. The process is relatively cumbersome; and for completely irregular objects, such as blasting fragments to be measured, it is often impossible to automatically fit their surfaces or edges, and the characteristic size is difficult to automatically calculate through third-party software.

[0003] In the prior art, Wang Ji Yang of Shenyang University of Technology's "A Three-Dimensional Volume Intelligent Measurement Device for Irregular Objects" proposed a volume intelligent measurement device that can obtain a complete point cloud model through device actuation, and then achieve volume measurement through subsequent segmentation, fitting, and calculation. However, the volume measurement calculation part is not described in detail, and still requires manual fitting and calculation; Wang Tao et al. of Shandong Jierui Digital Technology Co., Ltd.'s "A Size Measurement Method and Measurement Device for Irregular Objects" establishes a corresponding recognition algorithm for the target part through a template part, and measures its position and three-dimensional model. This measurement algorithm is only for the measurement of a single part with a CAD model. Before each measurement, the corresponding recognition algorithm for the part needs to be established. This method can only measure specific irregular objects, but cannot measure random irregular objects, and still has limitations.

[0004] In summary, the current point cloud measurement methods for irregular objects often require manual assistance and cannot achieve automated dimension measurement. Especially in the measurement of large quantities of irregular objects in industry, it is impossible to obtain the characteristic dimensions of the object to be measured by edge surface extraction, fitting, or recognition. If measured manually, the efficiency is low and it cannot adapt to the measurement of large quantities of objects to be measured. Therefore, it is necessary to design an automatic measurement device and method for the characteristic dimensions of irregular objects according to actual conditions to improve measurement efficiency and solve the problem of automated measurement of large quantities of irregular objects. Summary of the invention

[0005] In order to solve the technical problem that the measurement technology existing in the above-mentioned prior art cannot meet the requirements of automatic measurement of point cloud dimensions of irregular objects, the purpose of the present invention is to provide an automatic measurement device and method for characteristic dimensions of irregular objects, which can automatically realize the automatic measurement of characteristic dimensions such as dimensions in three orthogonal directions, cross-sectional area, and volume, solve the problem of characteristic dimension measurement of irregular objects, and replace manual fitting measurement with automatic measurement algorithm, so as to realize the dimension measurement of large quantities of random irregular objects, thereby improving the measurement efficiency in industry.

[0006] To achieve the above-mentioned purpose, the present invention provides an automatic measurement device for characteristic dimensions of irregular objects, including a shape and dimension measurement device for performing point cloud scanning measurement on an object to be measured and obtaining point cloud data, and also including:

[0007] A mechanical arm, wherein a vacuum suction cup is provided on the mechanical arm;

[0008] a conveyor belt disposed below the robot arm; and

[0009] A specimen slide, the specimen slide is used to support the object to be tested, and the specimen slide is placed on the conveyor belt for transportation;

[0010] The robot arm absorbs the specimen slide carrying the object to be measured through the vacuum suction cup to send the object to be measured to the shape and size measuring device.

[0011] Furthermore, the four vacuum suction cups are distributed circumferentially and supported by a bracket, the bracket is connected to the robot arm, and the four vacuum suction cups are simultaneously adsorbed on the edge position of the plane structure of the slide.

[0012] Furthermore, a debris retaining edge is provided between every two adjacent vacuum suction cups along the circumferential distribution direction of the four vacuum suction cups, and the debris retaining edge is only arranged in three consecutive directions between the vacuum suction cups, leaving one direction without the debris retaining edge.

[0013] Furthermore, the vacuum suction cup is connected to the vacuum equipment through a connecting pipe.

[0014] Furthermore, the suction cup material of the vacuum suction cup is made of nitrile rubber.

[0015] A method for automatically measuring characteristic dimensions of an irregular object is implemented by using the device for automatically measuring characteristic dimensions of an irregular object, and the method comprises the following steps:

[0016] Step 1, the robotic arm absorbs the specimen slide carrying the object to be measured through the vacuum suction cup to send the object to be measured to the shape and size measuring device, performs point cloud scanning measurement and obtains point cloud data;

[0017] Step 2: Define the characteristic dimensions of the irregular object, and define the characteristic dimensions as X, Y, and Z, respectively, where X, Y, and Z are the dimensions of the fragment in three orthogonal directions;

[0018] Step 3: After scanning and obtaining the point cloud of the irregular object to be tested, the point cloud needs to be preprocessed first, the point cloud noise is removed, and the point cloud is downsampled to reduce the number of point clouds;

[0019] Step 4: Before calculating the point cloud data, denoise the point cloud by outlier filtering;

[0020] Step 5: De-noising the point cloud by outlier filtering in step 3, using a voxel-based filtering method to divide the point cloud into a number of voxels, and counting the average density of the points in each voxel. Voxels with a density less than a certain threshold are considered as outliers and removed;

[0021] Step 6: based on the voxel division in step 4, down-sampling the point cloud by voxel method is performed for subsequent calculations, and the centroid of all points in the voxel is used as a replacement for the voxel, thereby achieving down-sampling of the original point cloud;

[0022] Step 7: After preprocessing, the point cloud can be used to calculate the feature size of the point cloud through this automatic feature size extraction algorithm.

[0023] Furthermore, the characteristic size calculation process of the point cloud is as follows:

[0024] Process 1: Build a kd tree and query the k neighboring points of each point. After the kd tree is built, the kd tree can be used to perform K neighboring searches to obtain the k points closest to each point cloud point, which is convenient for completing the calculation of the X size.

[0025] Process 2: Roughly calculate the size of X. According to the kd tree established in process 1, calculate the number of k nearest neighbor points in each group {P ij |j=1…k} i , as the representative of the current k points, the calculated data is reduced to 1 / k of the total amount of data N after downsampling. The centroid point set after downsampling is: {p i |i=1…N / k} calculate the Euclidean distance d of all centroids in turn ij After each calculation is completed, the current distance is compared with the temporarily stored distance, and the larger value replaces the smaller value until all calculations are completed, and the maximum distance d between the centroids is obtained. max , the corresponding two centroid points are p1 and p2, and the calculation formula is as follows:

[0026]

[0027] Process 3: Calculate the X size accurately. Use the two centroid points p1 and p2 obtained in process 2 to find two groups of k nearest neighbor points, calculate the Euclidean distance between each original point in turn, and still use the comparison method to get the maximum distance. At this time, the exact feature size X is obtained. The calculation formula is as follows:

[0028] d 1i2j =distance(p 1i ,p 2j ),i1=1…k,i2=1…k

[0029] X=max({d 1i2j |i1=1…k,i2=1…k});

[0030] Process 4: Take the line connecting the two endpoints of the X dimension as the x-axis, take one endpoint of the X dimension as o', and make a perpendicular plane through the o' point to the x-axis to obtain the y'o'z' plane. Project each data point of the obtained fragment scanning result to the y'o'z' plane, calculate its convex hull point, and use the convex hull point to calculate the minimum enclosing rectangle and the farthest point pair to obtain the feature dimension Y. At the same time, obtain the y-axis direction through the two endpoints of the feature dimension Y.

[0031] Process 5: Take a point on the x-axis as the origin o, make the y-axis according to the y-axis direction obtained in process 4, and get the z-axis by cross multiplication of the two axes. Project each data point of the obtained fragment scanning result onto the xoz plane, calculate the length of the line connecting the projection points parallel to the z-axis in turn, and take the maximum value, which is the characteristic size Z;

[0032] Process 6: Calculate other characteristic quantities, including volume calculation:

[0033] The volume of the obtained irregular point cloud is calculated by slicing. The scanned data is cut into n blocks at equal intervals l in a certain direction. The points near the slice are projected onto the slice. Then the points on the slice are simplified. The simplified points are connected by a B-spline curve with control vertices, and the area A enclosed by the curve is calculated. i , the total volume of the object is the product of the sum of the areas of all slices and the distance between the slices. The calculation formula is as follows:

[0034]

[0035] Furthermore, in step 2, X represents the maximum distance between any two points in the fragment, Y represents the maximum distance in a plane perpendicular to the direction of the maximum distance, and Z represents the maximum distance in the third orthogonal direction.

[0036] Furthermore, in the process one: during the construction of the kd tree, the two-dimensional image coordinate points with depth values ​​are arranged in a binary tree manner, the coordinate variances of the row and column dimensions are calculated respectively, and the image coordinate points are vertically divided into left and right point sets based on the median coordinate point with the larger dimensional variance. The left and right subset spaces are recursively divided according to each data point, and the nodes of each division and the parent nodes of each node are recorded at the same time, so as to establish a kd tree that is convenient for point query, until each spatial point is included in the kd tree, and the nodes that no longer have child nodes are recorded as "leaf nodes".

[0037] Furthermore, in the sixth process, the specific steps of volume calculation are as follows:

[0038] a. Select the point cloud involved in volume calculation and store them in order by Z coordinate;

[0039] b. Read the point cloud data corresponding to the slice and store it in array A;

[0040] c. Project the points in array A onto the slice, and connect the simplified points with a B-spline curve through the control vertices to form a closed curve;

[0041] d. Calculate the area of ​​the closed curve. Since the B-spline curve is fitted by multiple small line segments, we can regard the closed curve as a polygon to calculate the area. First calculate the centroid of the polygon, then connect the centroid and each vertex of the polygon to form multiple triangles. The sum of the areas of all triangles is the area of ​​the closed curve.

[0042] e. If array A is not empty, it means that the data in A may fit another curve, and go to step c.

[0043] f. If the data has not been read completely, go to step b; otherwise, end this process. The product of the sum of the areas corresponding to all slices and the distance between the slices is the volume of the object.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] The present invention is based on point cloud scanning measurement, and is combined with an irregular object characteristic dimension automatic measurement device and method, which can realize the rapid automatic measurement of irregular object characteristic dimensions, and is suitable for large-scale irregular object measurement in industrial scenarios. The irregular object characteristic dimension automatic measurement device and method, through a mechanical arm, a stage, a vacuum suction cup and the like to form an automatic measurement device, combined with a point cloud characteristic dimension measurement algorithm, forms an automated irregular object characteristic dimension measurement chain, and can automatically measure the characteristic dimensions of irregular object point clouds of any shape in special scenarios, and obtain geometric quantities such as characteristic dimensions and volume of the point cloud to be measured.

[0046] The present invention discloses an automatic measurement device and method for the characteristic dimensions of irregular objects. A new automatic measurement method is designed. The automatic measurement device and the measurement algorithm of irregular point clouds realize the automatic measurement of the characteristic dimensions of irregular objects of arbitrary shapes. The object to be measured can be automatically transported to the scanning point, and the characteristic dimensions of the irregular object to be measured can be calculated and directly output. Compared with the existing methods, the whole measurement process does not require manual participation in placement and fitting measurement, etc., and multiple dimension data of irregular point clouds can be obtained at one time, saving manpower and time costs; at the same time, compared with other methods, the measurement method is suitable for irregular objects of arbitrary shapes, has a wide range of applications, and is convenient and fast. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 A schematic diagram schematically shows the structure of an automatic measurement device for characteristic dimensions of an irregular object in one embodiment of the present invention;

[0049] Figure 2 A schematic diagram of characteristic dimensions of fragments in three orthogonal directions schematically showing an automatic characteristic dimension measurement method for an irregular object in one embodiment of the present invention;

[0050] Figure 3 A characteristic dimension calculation flow chart schematically showing a method for automatically measuring characteristic dimensions of an irregular object in one embodiment of the present invention;

[0051] Figure 4 The figure schematically shows a schematic diagram of solving convex hull points of a method for automatically measuring characteristic dimensions of an irregular object in one embodiment of the present invention.

[0052] Description of reference numerals:

[0053] 1. Robotic arm; 2. Vacuum suction cup; 3. Conveyor belt; 4. Slide; 5. Bracket; 6. Debris retaining edge. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] See also Figures 1 to 4 As shown; this embodiment discloses an automatic measurement device for characteristic dimensions of irregular objects, including a shape and dimension measurement device for performing point cloud scanning measurement on an object to be measured and obtaining point cloud data, and also includes:

[0056] A mechanical arm 1, wherein a vacuum suction cup 2 is arranged on the mechanical arm 1;

[0057] A conveyor belt 3, which is arranged below the robot arm 1; and

[0058] The specimen slide 4 is used to carry the object to be tested, and the specimen slide 4 is placed on the conveyor belt 3 for transportation;

[0059] The robot arm 1 absorbs the specimen slide 4 carrying the object to be measured through the vacuum suction cup 2 to send the object to be measured to the shape and size measuring device.

[0060] During the measurement process, the irregular object is transferred to the specimen slide 4 by the conveyor belt 3, and the mechanical arm 1 cooperates with the vacuum suction cup 2 to adsorb the specimen slide 4 to realize the transportation of the irregular object to be measured, forming an automatic measurement chain. The mechanical arm 1 adsorbs the specimen slide 4 carrying the object to be measured, and can automatically send the object to be measured to the shape and size measuring equipment, and then measure the characteristic size of the object to be measured by the automatic measurement method of the irregular object size, thereby realizing the automatic measurement of irregular objects. The design of the vacuum suction cup 2 and the specimen slide 4 makes the measurement not limited to the shape of the object, and can measure objects of any shape.

[0061] Furthermore, there are four vacuum suction cups 2 distributed circumferentially and supported by a bracket 5, which is connected to the robot arm 1. The four vacuum suction cups 2 are simultaneously adsorbed on the edge position of the planar structure slide 4 so as to be able to balance and stably adsorb the slide 4.

[0062] Furthermore, a debris retaining edge 6 is provided between every two adjacent vacuum suction cups 2 along the circumferential distribution direction of the four vacuum suction cups 2, and the debris retaining edge 6 is arranged only in three consecutive directions between the vacuum suction cups 2, so that one direction is not provided with a debris retaining edge 6, and the debris retaining edge 6 avoids the risk of the object to be tested falling during the transportation process. One direction is reserved without a debris retaining edge 6, which is convenient for the recovery of the object to be tested.

[0063] Furthermore, the vacuum suction cup 2 is connected to the vacuum equipment through a connecting pipe.

[0064] Furthermore, the suction cup material of the vacuum suction cup 2 is made of nitrile rubber.

[0065] The vacuum suction cup 2 is one of the actuators of the vacuum equipment. The suction cup material is made of nitrile rubber, has a large tearing force, and is widely used in various vacuum holding equipment. Before the system starts to run automatically, the vacuum suction cup 2 is first connected to the vacuum equipment through the connecting pipe, and then it is in contact with the object to be lifted (here is the carrier glass sheet, that is, the carrier sheet 4, on which the fragments are placed), and the vacuum equipment is started to suck, so that negative air pressure is generated in the vacuum suction cup 2, so that the carrier glass sheet is sucked firmly, and the carrier glass sheet can be transported. When the carrier glass sheet is transported to the destination, it is smoothly inflated into the vacuum suction cup 2, so that the negative air pressure in the vacuum suction cup 2 becomes zero air pressure or slightly positive air pressure, and the vacuum suction cup 2 is separated from the carrier glass sheet, thereby completing the task of transporting the object to be tested.

[0066] A method for automatically measuring characteristic dimensions of an irregular object is implemented by using an automatic measuring device for characteristic dimensions of an irregular object. The method comprises the following steps:

[0067] Step 1: The robot arm 1 absorbs the specimen slide 4 carrying the object to be measured through the vacuum suction cup 2 to send the object to be measured to the shape and size measuring device, performs point cloud scanning measurement and obtains point cloud data. This step is achieved by an automatic measurement device for characteristic dimensions of irregular objects;

[0068] Step 2: Define the characteristic size of the irregular object. The choice of characteristic size usually needs to be determined according to the actual application. In most application scenarios, the outer envelope size of the irregular object needs to be obtained to define the size of the object to be measured. The characteristic size is defined as X, Y, and Z, where X, Y, and Z are the sizes of the fragment in three orthogonal directions;

[0069] Step 3: After scanning and obtaining the point cloud of the irregular object to be measured, the point cloud must first be preprocessed to remove the point cloud noise and downsample the point cloud to reduce the number of point clouds, which is convenient for the subsequent calculation of feature dimensions and improves the accuracy of dimension calculation. ;

[0070] Step 4: The 3D point cloud data obtained in actual engineering often contains a certain amount of noise. Therefore, before calculating the point cloud data, the point cloud is denoised by outlier filtering. Outliers refer to points in the point cloud that are significantly different from the surrounding points. These points are usually noise or other irrelevant points, so they need to be removed by filtering.

[0071] Step 5: In step 3, the point cloud is denoised by outlier filtering. The point cloud is divided into several voxels by using a voxel-based filtering method. The average density of the points in each voxel is counted. Voxels with a density less than a certain threshold are regarded as outliers and removed. At the same time, the scanned point cloud is often very dense and has a large number of points, which is not conducive to the calculation of feature size and consumes computing time and resources. Therefore, the point cloud is downsampled by voxel method based on the above voxel division for subsequent calculations;

[0072] Step 6: Based on the voxel division in step 4, the point cloud is downsampled by voxel method for subsequent calculations, and the centroid of all points in the voxel is used as a replacement for the voxel, thereby achieving downsampling of the original point cloud;

[0073] Step 7: After preprocessing, the point cloud can be used to calculate the feature size of the point cloud through this automatic feature size extraction algorithm.

[0074] Furthermore, the characteristic size calculation process of the point cloud is as follows:

[0075] Process 1: Build a kd tree and query the k neighboring points of each point. After the kd tree is built, the kd tree can be used to perform K neighboring searches to obtain the k points closest to each point cloud point, which is convenient for completing the calculation of the X size.

[0076] Process 2: Roughly calculate the size of X. According to the kd tree established in process 1, calculate the number of k nearest neighbor points in each group {P ij |j=1…k} i , as the representative of the current k points, the calculated data is reduced to 1 / k of the total amount of data N after downsampling. The centroid point set after downsampling is: {p i |i=1…N / k} calculate the Euclidean distance d of all centroids in turn ij After each calculation is completed, the current distance is compared with the temporarily stored distance, and the larger value replaces the smaller value until all calculations are completed, and the maximum distance d between the centroids is obtained. max , the corresponding two centroid points are p1 and p2, and the calculation formula is as follows:

[0077]

[0078] Process 3: Calculate the X size. Use the two centroid points p1 and p2 obtained in process 2 to find two groups of k nearest neighbor points. Calculate the Euclidean distance between each original point in turn. Use the comparison method to get the maximum distance. At this time, the exact feature size X is obtained. The calculation formula is as follows:

[0079] d 1i2j =distance(p 1i ,p 2j),i1=1…k,i2=1…k

[0080] X=max({d 1i2j |i1=1…k,i2=1…k});

[0081] Process 4: Take the line connecting the two endpoints of the X dimension as the x-axis, take one endpoint of the X dimension as o', and make a perpendicular plane through the o' point to the x-axis to obtain the y'o'z' plane. Project each data point of the obtained fragment scanning result to the y'o'z' plane, and calculate its convex hull point. The convex hull of a point set refers to a minimum convex polygon that satisfies that the points in the point set are either on the edge of the polygon or inside it. Because the two points with the farthest distance on a two-dimensional plane must be on the convex hull, the convex hull points are used to calculate the minimum enclosing rectangle and the farthest point pair to obtain the feature dimension Y, and at the same time, the y-axis direction is obtained through the two endpoints of the feature dimension Y.

[0082] Process 5: Take a point on the x-axis as the origin o, make the y-axis according to the y-axis direction obtained in process 4, and get the z-axis by cross multiplication of the two axes. Project each data point of the obtained fragment scanning result onto the xoz plane, calculate the length of the line connecting the projection points parallel to the z-axis in turn, and take the maximum value, which is the characteristic size Z;

[0083] Process 6: Calculate other characteristic quantities, including volume calculation:

[0084] The volume of the obtained irregular point cloud is calculated by slicing. The scanned data is cut into n blocks at equal intervals l in a certain direction. The points near the slice are projected onto the slice. Then the points on the slice are simplified. The simplified points are connected by a B-spline curve with control vertices, and the area A enclosed by the curve is calculated. i , the total volume of the object is the product of the sum of the areas of all slices and the distance between the slices. The calculation formula is as follows:

[0085]

[0086] Furthermore, in step 2, X represents the maximum distance between any two points in the fragment, Y represents the maximum distance in the plane perpendicular to the above maximum distance direction, and Z represents the maximum distance in the third orthogonal direction. The three dimensions are shown in the schematic diagram as follows: Figure 2 shown.

[0087] Furthermore, in process one: during the construction of the kd tree, the two-dimensional image coordinate points with depth values ​​are arranged in a binary tree manner, the coordinate variances of the row and column dimensions are calculated respectively, and the image coordinate points are divided vertically into left and right point sets based on the median coordinate point with the larger dimensional variance. The left and right subset spaces are recursively divided according to each data point, and the nodes of each division and the parent nodes of each node are recorded at the same time, so as to establish a kd tree that is convenient for point query, until every spatial point is included in the kd tree, and the nodes that no longer have child nodes are recorded as "leaf nodes".

[0088] Furthermore, in process 6: the specific steps of volume calculation are as follows:

[0089] a. Select the point cloud involved in volume calculation and store them in order by Z coordinate;

[0090] b. Read the point cloud data corresponding to the slice and store it in array A;

[0091] c. Project the points in array A onto the slice, and connect the simplified points with a B-spline curve through the control vertices to form a closed curve;

[0092] d. Calculate the area of ​​the closed curve. Since the B-spline curve is fitted by multiple small line segments, we can regard the closed curve as a polygon to calculate the area. First calculate the centroid of the polygon, then connect the centroid and each vertex of the polygon to form multiple triangles. The sum of the areas of all triangles is the area of ​​the closed curve.

[0093] e. If array A is not empty, it means that the data in A can be fitted into another curve, so go to c.

[0094] f. If the data has not been read, go to b; otherwise, end this process. The product of the sum of the areas corresponding to all slices and the distance between the slices is the volume of the object.

[0095] In summary, the present invention is based on point cloud scanning measurement, and is combined with an irregular object characteristic dimension automatic measurement device and method, which can realize the rapid automatic measurement of irregular object characteristic dimensions, and is suitable for large-scale irregular object measurement in industrial scenarios. The irregular object characteristic dimension automatic measurement device and method, through a mechanical arm, a stage, a vacuum suction cup and the like to form an automatic measurement device, combined with a point cloud characteristic dimension measurement algorithm, forms an automated irregular object characteristic dimension measurement chain, which can automatically measure the characteristic dimensions of irregular object point clouds of any shape in special scenarios, and obtain geometric quantities such as the characteristic dimensions and volume of the point cloud to be measured.

[0096] The present invention discloses an automatic measurement device and method for the characteristic dimensions of irregular objects. A new automatic measurement method is designed. The automatic measurement device and the measurement algorithm of irregular point clouds realize the automatic measurement of the characteristic dimensions of irregular objects of arbitrary shapes. The object to be measured can be automatically transported to the scanning point, and the characteristic dimensions of the irregular object to be measured can be calculated and directly output. Compared with the existing methods, the whole measurement process does not require manual participation in placement and fitting measurement, etc., and multiple dimension data of irregular point clouds can be obtained at one time, saving manpower and time costs; at the same time, compared with other methods, the measurement method is suitable for irregular objects of arbitrary shapes, has a wide range of applications, and is convenient and fast.

[0097] The contents not described in detail in the present invention belong to the common knowledge of those skilled in the art.

[0098] In addition, it should be noted that the present invention can be provided as a method, an apparatus or a computer program product. Therefore, the embodiments of the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0099] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0100] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide the functions specified in the process. Figure 1A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0101] It should also be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0102] Finally, it should be noted that the above is a preferred embodiment of the present invention. It should be pointed out that although the preferred embodiment of the present invention has been described, for those skilled in the art, once the basic creative concept of the present invention is known, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention. Therefore, the attached claims are intended to be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the embodiments of the present invention.

Claims

1. An automatic measurement device for the characteristic dimensions of an irregular object, comprising a shape and dimension measurement device, for performing point cloud scanning measurement on an object to be measured and obtaining point cloud data, characterized in that: Also includes: A mechanical arm (1), wherein a vacuum suction cup (2) is arranged on the mechanical arm (1); a conveyor belt (3), wherein the conveyor belt (3) is arranged below the robot arm (1); and A specimen slide (4), the specimen slide (4) being used to carry an object to be tested, the specimen slide (4) being placed on the conveyor belt (3) for transportation; The mechanical arm (1) absorbs the specimen slide (4) carrying the object to be measured via the vacuum suction cup (2) to deliver the object to be measured to the shape and size measuring device.

2. The device for automatically measuring characteristic dimensions of irregular objects according to claim 1, characterized in that: The four vacuum suction cups (2) are distributed in a circumferential direction and supported by a bracket (5), wherein the bracket (5) is connected to the robot arm (1), and the four vacuum suction cups (2) are simultaneously adsorbed on the edge positions of the plane structure of the specimen slide (4).

3. The device for automatically measuring characteristic dimensions of irregular objects according to claim 2, characterized in that: A debris retaining edge (6) is provided between every two adjacent vacuum suction cups (2) along the circumferential distribution direction of the four vacuum suction cups (2), and the debris retaining edge (6) is only arranged in three consecutive directions between the vacuum suction cups (2), leaving one direction without the debris retaining edge (6).

4. The device for automatically measuring characteristic dimensions of irregular objects according to claim 1, characterized in that: The vacuum suction cup (2) is connected to the vacuum equipment via a connecting pipe.

5. The device for automatically measuring characteristic dimensions of irregular objects according to claim 1, characterized in that: The suction cup material of the vacuum suction cup (2) is made of nitrile rubber.

6. A method for automatically measuring characteristic dimensions of irregular objects, characterized in that: The method is implemented by using an automatic measurement device for characteristic dimensions of an irregular object as described in any one of claims 1 to 5, and comprises the following steps: Step 1, the robotic arm (1) absorbs the specimen slide (4) carrying the object to be measured through the vacuum suction cup (2) to deliver the object to be measured to the shape and size measuring device, performs point cloud scanning measurement and obtains point cloud data; Step 2: Define the characteristic dimensions of the irregular object, and define the characteristic dimensions as X, Y, and Z, respectively, where X, Y, and Z are the dimensions of the fragment in three orthogonal directions; Step 3: After scanning and obtaining the point cloud of the irregular object to be tested, the point cloud needs to be preprocessed first, the point cloud noise is removed, and the point cloud is downsampled to reduce the number of point clouds; Step 4: Before calculating the point cloud data, denoise the point cloud by outlier filtering; Step 5: De-noising the point cloud by outlier filtering in step 3, using a voxel-based filtering method to divide the point cloud into a number of voxels, and counting the average density of the points in each voxel. Voxels with a density less than a certain threshold are considered as outliers and removed; Step 6: based on the voxel division in step 4, down-sampling the point cloud by voxel method is performed for subsequent calculations, and the centroid of all points in the voxel is used as a replacement for the voxel, thereby achieving down-sampling of the original point cloud; Step 7: After preprocessing, the point cloud can be used to calculate the feature size of the point cloud through this automatic feature size extraction algorithm.

7. The method for automatically measuring characteristic dimensions of irregular objects according to claim 6, characterized in that: The characteristic size calculation process of the point cloud is as follows: Process 1: Build a kd tree and query the k neighboring points of each point. After the kd tree is built, the kd tree can be used to perform K neighboring searches to obtain the k points closest to each point cloud point, which is convenient for completing the calculation of the X size. Process 2: Roughly calculate the size of X. According to the kd tree established in process 1, calculate the number of k nearest neighbor points in each group {P ij |j=1…k} i , as the representative of the current k points, the calculated data is reduced to 1 / k of the total amount of data N after downsampling. The centroid point set after downsampling is: {p i |i=1…N / k} calculate the Euclidean distance d of all centroids in turn ij After each calculation is completed, the current distance is compared with the temporarily stored distance, and the larger value replaces the smaller value until all calculations are completed, and the maximum distance d between the centroids is obtained. max , the corresponding two centroid points are p1 and p2, and the calculation formula is as follows: Process 3: Calculate the X size accurately. Use the two centroid points p1 and p2 obtained in process 2 to find two groups of k nearest neighbor points, calculate the Euclidean distance between each original point in turn, and still use the comparison method to get the maximum distance. At this time, the exact feature size X is obtained. The calculation formula is as follows: d 1i2j =distance(p 1i ,p 2j ),i1=1…k,i2=1…k X=max({d 1i2j |i1=1…k,i2=1…k}); Process 4: Take the line connecting the two endpoints of the X dimension as the x-axis, take one endpoint of the X dimension as o', and make a perpendicular plane through the o' point to the x-axis to obtain the y'o'z' plane. Project each data point of the obtained fragment scanning result to the y'o'z' plane, calculate its convex hull point, and use the convex hull point to calculate the minimum enclosing rectangle and the farthest point pair to obtain the feature dimension Y. At the same time, obtain the y-axis direction through the two endpoints of the feature dimension Y. Process 5: Take a point on the x-axis as the origin o, make the y-axis according to the y-axis direction obtained in process 4, and get the z-axis by cross multiplication of the two axes. Project each data point of the obtained fragment scanning result onto the xoz plane, calculate the length of the line connecting the projection points parallel to the z-axis in turn, and take the maximum value, which is the characteristic size Z; Process 6: Calculate other characteristic quantities, including volume calculation: The volume of the obtained irregular point cloud is calculated by slicing. The scanned data is cut into n blocks at equal intervals l in a certain direction. The points near the slice are projected onto the slice. Then the points on the slice are simplified. The simplified points are connected by a B-spline curve with control vertices, and the area A enclosed by the curve is calculated. i , the total volume of the object is the product of the sum of the areas of all slices and the distance between the slices. The calculation formula is as follows:

8. The method for automatically measuring characteristic dimensions of irregular objects according to claim 6, characterized in that: In the step 2, X represents the maximum distance between any two points in the fragment, Y represents the maximum distance in a plane perpendicular to the direction of the maximum distance, and Z represents the maximum distance in the third orthogonal direction.

9. The method for automatically measuring characteristic dimensions of irregular objects according to claim 7, characterized in that: In the process 1: during the construction of the kd tree, the two-dimensional image coordinate points with depth values ​​are arranged in a binary tree manner, the coordinate variances of the row and column dimensions are calculated respectively, and the image coordinate points are divided vertically by the median coordinate point with the larger dimensional variance, and the image coordinate points are divided into two point sets, left and right. The left and right subsets are recursively divided according to each data point, and the nodes of each division and the parent nodes of each node are recorded at the same time, so as to establish a kd tree that is convenient for point query, until each spatial point is included in the kd tree, and the nodes that no longer have child nodes are recorded as "leaf nodes".

10. The method for automatically measuring characteristic dimensions of irregular objects according to claim 7, characterized in that: In the process 6: the specific steps of volume calculation are as follows: a. Select the point cloud involved in volume calculation and store them in order by Z coordinate; b. Read the point cloud data corresponding to the slice and store it in array A; c. Project the points in array A onto the slice, and connect the simplified points with a B-spline curve through control vertices to form a closed curve; d. Calculate the area of ​​the closed curve. Since the B-spline curve is formed by fitting multiple small line segments, we can regard the closed curve as a polygon to calculate the area. First, calculate the centroid of the polygon, then connect the centroid and each vertex of the polygon to form multiple triangles. The sum of the areas of all triangles is the area of ​​the closed curve. e. If array A is not empty, it means that the data in A may fit another curve, and go to step c; f. If the data has not been read completely, go to step b; otherwise, end this process. The product of the sum of the areas corresponding to all slices and the distance between the slices is the volume of the object.

Images