DATA CLUSTERING PROGRAM, DATA CLUSTERING METHOD AND INFORMATION PROCESSING APPARATUS

Abstract

To extract an accurate feature value of point group data.SOLUTION: An information processing apparatus calculates, for each of plural points included in point group data, an eigenvector by using principal component analysis for point group data that is present within a predetermined distance from a point, calculates a curvature of a multidimensional function having an extreme point that is a point positioned nearest to the eigenvector calculated, executes, on the basis of the curvature for each of the plural points of the point group data, clustering of the plural points, and outputs a result of execution of the clustering.SELECTED DRAWING: Figure 8

Description

[Technical field]

[0001] The present invention relates to a data clustering program, a data clustering method, and an information processing device. [Background technology]

[0002] In many cases in various fields, data to be analyzed is represented as a set of real values, and the data is captured as a point cloud in n-dimensional space. In recent years, features are extracted and classified from such point cloud data. Specifically, a polygon to be associated with the point cloud data is selected, the polygon is fitted to the point cloud data using the least squares method, and a set of singular points is extracted using the minimum distance to the fitted polygon. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-016193 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, with the above techniques, it is difficult to extract the characteristics of each point in the point cloud data. For example, the error fitting technique requires that the shape of the entire point cloud data be known in advance and that it be expressed as a polygon. Furthermore, if an appropriate polygon cannot be expressed, fitting will have to be repeated, which takes time.

[0005] In one aspect, an object of the present invention is to provide a data clustering program, a data clustering method, and an information processing device that are capable of extracting features of each point of point cloud data. [Means for solving the problem]

[0006] In a first proposal, the clustering program causes a computer to execute the following processes: calculate an eigenvector for each of a plurality of points included in the point cloud data by using principal component analysis on the point cloud data that exists within a predetermined distance from the point; calculate the curvature of a multidimensional function that has the point located closest to the calculated eigenvector as an extreme point; perform clustering of the plurality of points based on the curvature for each of the plurality of points of the point cloud data; and output a result of the clustering. Effect of the Invention

[0007] In one aspect, features for each point of the point cloud data can be extracted. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an information processing apparatus according to a first embodiment. [Diagram 2] FIG. 2 is a diagram illustrating the problems caused by TDA. [Diagram 3] FIG. 3 is a functional block diagram of the information processing device according to the first embodiment. [Figure 4] FIG. 4 is a diagram for explaining a method of calculating an eigenvector for each point of the point cloud data. [Diagram 5] FIG. 5 is a diagram illustrating the extraction results of feature amounts of each point cloud data. [Figure 6] FIG. 6 is a flowchart of the process according to the first embodiment. [Figure 7] FIG. 7 is a functional block diagram of the information processing device according to the second embodiment. As illustrated in FIG. [Figure 8] FIG. 8 is a diagram illustrating a clustering result according to the second embodiment. [Figure 9] FIG. 9 is a flowchart of the process according to the second embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of a hardware configuration. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the data clustering program, the data clustering method, and the information processing device disclosed in the present application will be described in detail with reference to the accompanying drawings. Note that the present invention is not limited to these embodiments. In addition, each embodiment can be appropriately combined within a range that does not cause inconsistency. EXAMPLES

[0010] [Overall configuration] 1 is a diagram illustrating an information processing device 10 according to a first embodiment. The information processing device 10 is an example of a computer device that generates and outputs features, such as feature P and feature Q, that accurately represent features of various point cloud data such as point cloud data P and point cloud data Q.

[0011] Here, we will explain TDA, which is used to generate feature quantities of point cloud data. TDA generates feature quantities of point cloud data by performing persistent homology transformation on the point cloud data to generate a persistence diagram that characterizes the transition of m-dimensional holes.

[0012] Here, "homology" is a method of expressing the characteristics of an object by the number of holes in m (m≧0) dimensions. Here, "holes" refer to elements of the homology group, where a 0-dimensional hole is a connected component, a 1-dimensional hole is a hole (tunnel), and a 2-dimensional hole is a cavity. The number of holes in each dimension is called the Betti number. And "persistent homology" is a method for characterizing the transition of m-dimensional holes in an object (here, a set of points (point cloud)), and persistent homology can be used to investigate the characteristics of the arrangement of points. In this method, each point in the object is gradually inflated into a sphere, and the time when each hole appeared (represented by the radius of the sphere at the time of appearance) and the time when it disappeared (represented by the radius of the sphere at the time of disappearance) are identified during the process.

[0013] Next, we will explain the results of generating feature quantities for cylinder-shaped point cloud data P and sphere-shaped point cloud data Q using TDA. Figure 2 is a diagram explaining the problems with TDA.

[0014] 2 shows a persistence diagram representing H0, which is the timing of birth and death of a 0-dimensional hole, H1, which is the timing of birth and death of a 1-dimensional hole, and H2, which is the timing of birth and death of a 2-dimensional hole, by TDA on point cloud data P. Similarly, a persistence diagram representing H0, which is the timing of birth and death of a 0-dimensional hole, H1, which is the timing of birth and death of a 1-dimensional hole, and H2, which is the timing of birth and death of a 2-dimensional hole, by TDA on point cloud data Q, is shown.

[0015] As can be seen by comparing the persistence diagrams in Figure 2, in feature generation (analysis) by TDA, similar features are generated from point cloud data with the same topological shape, making it difficult to distinguish between the point cloud data. In other words, when analyzing point cloud data with unknown shapes, the same features are generated for data with different shapes. For this reason, for example, when generating labeled training data using point cloud data, the same label is assigned to point cloud data that should be assigned different labels, leading to a deterioration in training accuracy.

[0016] It is also possible to select polygons using the features obtained by TDA and fit them to the point cloud data, but if the features used for selection are not accurate, it is not possible to select an appropriate polygon. In the case of Figure 2, the same polygon would be selected for both point cloud data P and point cloud data Q, making accurate fitting impossible.

[0017] Therefore, the information processing device 10 according to the first embodiment calculates an eigenvector for each of a plurality of points included in the point cloud data by using a principal component analysis for the point cloud data that exists within a predetermined distance from the point. The information processing device 10 calculates the curvature of a multidimensional function that has the point located closest to the calculated eigenvector as an extreme point (or stationary point). The information processing device 10 generates a feature amount of the point cloud data based on the curvature for each of the plurality of points of the point cloud data.

[0018] That is, the information processing device 10 calculates a locally determined curvature amount (amount representing the degree of curvature) from the point cloud data, and uses the frequency distribution of the value as a feature amount. As a result, the information processing device 10 becomes able to distinguish between point cloud data that are topologically the same but have different curvature shapes, and can extract accurate feature amounts of the point cloud data.

[0019] [Function configuration] 3 is a functional block diagram showing a functional configuration of the information processing device 10 according to the first embodiment. As shown in FIG. 3, the information processing device 10 includes a communication unit 11, a storage unit 12, and a control unit 20.

[0020] The communication unit 11 is a processing unit that controls communication with other devices, and is realized by, for example, a communication interface, etc. For example, the communication unit 11 receives point cloud data from an administrator terminal or a 3D sensor, etc., and transmits extraction results (analysis results) and the like to the administrator terminal.

[0021] The storage unit 12 is an example of a storage device that stores various data and programs executed by the control unit 20. For example, the storage unit 12 stores a point cloud data DB13 and an extraction result DB14.

[0022] The point cloud data DB13 is a database that stores point cloud data of various objects scanned in a three-dimensional space, for example, using a 3D sensor, a range finder, etc. In the above example, the point cloud data DB13 stores point cloud data P and point cloud data Q. For the purposes of explanation, the point cloud data P has a cylindrical shape and the point cloud data Q has a spherical shape, but these shapes are unknown until they are characterized by the control unit 20.

[0023] The extraction result DB 14 is a database that stores the extraction results by the control unit 20. For example, the extraction result DB 14 stores the feature amount of the point cloud data P and the feature amount of the point cloud data Q.

[0024] The control unit 20 is a processing unit that controls the entire information processing device 10, and is realized by, for example, a processor. The control unit 20 has a vector calculation unit 21, a curvature calculation unit 22, and a feature generation unit 23. Note that the vector calculation unit 21, the curvature calculation unit 22, and the feature generation unit 23 can also be realized as electronic circuits included in the processor or processes executed by the processor.

[0025] The vector calculation unit 21 is a processing unit that calculates an eigenvector for each of a plurality of points included in the point cloud data by using a principal component analysis for the point cloud data that exists within a predetermined distance from each point. For example, the vector calculation unit 21 calculates an eigenvector for each point of the point cloud data P and each point of the point cloud data Q.

[0026] 4 is a diagram for explaining a method of calculating an eigenvector for each point of the point cloud data. First, the vector calculation unit 21 accepts an input from an administrator or the like and calculates an eigenvector for each point of the point cloud data. d For point cloud data X, which is a subset of the points, thresholds ε and δ, which are greater than 0, are set.

[0027] Next, as shown in (a) of Fig. 4, the vector calculation unit 21 selects a point x that is an element of the point cloud data X. Then, as shown in (b) of Fig. 4, the vector calculation unit 21 defines a point cloud B that falls within a sphere of radius ε for the point x as shown in formula (1). Next, as shown in (c) of Fig. 4, the vector calculation unit 21 applies Principal Component Analysis (PCA) to the point cloud B to obtain a space spanned by eigenvectors whose eigenvalues ​​are equal to or greater than a threshold value δ. The vector calculation unit 21 executes the above process for each point in the point cloud data.

[0028]

number

[0029] The curvature calculation unit 22 is a processing unit that calculates the curvature of a multidimensional function that has the points located closest to the calculated eigenvector as extreme points. Specifically, the curvature calculation unit 22 calculates the curvature for each point in the point cloud data P and each point in the point cloud data Q, and outputs the curvature to the feature generation unit 23.

[0030] For example, the curvature calculation unit 22 fits to B by the least squares method a quadratic function having a vertex at a point x in the above space, the vertex having a value in the direction of an eigenvector corresponding to an eigenvalue that is equal to or greater than a predetermined value among the eigenvalues ​​calculated by the vector calculation unit 21.

[0031] That is, the curvature calculation unit 22 calculates a k-dimensional space having coordinates x1, x2, . . . x in which the eigenvalue is equal to or greater than δ. k and set the axis x in the direction of the k+1-th eigenvector. k+1 Next, the curvature calculation unit 22 generates a quadratic function shown in formula (2) by applying the least squares method, and calculates the Hessian shown in formula (3) for the quadratic function. Then, the curvature calculation unit 22 determines the Hessian as the curvature of each point.

[0032]

number

number

[0033] The feature generating unit 23 is a processing unit that generates feature amounts of the point cloud data based on the curvature for each of the multiple points of the point cloud data. Specifically, the feature generating unit 23 calculates the distribution (frequency distribution) of the curvature for each of the multiple points in the point cloud data P and the point cloud data Q as a feature of each point cloud data represented by the multiple points, and stores the calculated feature amount in the extraction result DB 14.

[0034] FIG. 5 is a diagram for explaining the extraction result of the feature amount of each point cloud data. As shown in FIG. 5, the feature generation unit 23 generates a frequency distribution in which the horizontal axis is the value of the curvature and the vertical axis is the degree (the number of points having that curvature). That is, the feature generation unit 23 counts the number of curvatures that each point of the point cloud data has. As a result, the feature generation unit 23 can characterize the point cloud data P as having a shape in which points with a curvature of 0.0 are concentrated and there are relatively few curved surfaces (curves). On the other hand, the feature generation unit 23 can characterize the point cloud data Q as having a shape in which points around a curvature of 1.0 are concentrated and there are many curved surfaces (curves).

[0035] [Processing flow] Fig. 6 is a flowchart showing a process flow according to the embodiment 1. As shown in Fig. 6, the vector calculation unit 21 of the information processing device 10 acquires point cloud data (S101), and selects one point (data) in the point cloud data (S102).

[0036] Next, the vector calculation unit 21 performs a principal component analysis to calculate a space (eigenvector) (S103), and the curvature calculation unit 22 calculates a curvature, which is a curvature-like amount determined locally from the point cloud data (S104).

[0037] If there are unselected points (data) in the point cloud data (S105: Yes), S102 and subsequent steps are repeated for the unselected points. On the other hand, if there are no unselected points (data) in the point cloud data (S105: No), the feature generation unit 23 uses the calculated curvature of each point to generate and output an extraction result of the feature amount of the point cloud data (S106).

[0038] [effect] As described above, the information processing device 10 can calculate the curvature for each point of the point cloud data and generate a feature amount using the curvature. As a result, the information processing device 10 can distinguish between point clouds that are topologically the same but have different curvature shapes by focusing on local differences in curvature. In addition, the information processing device 10 generates a frequency distribution of the curvature of each point, so that the feature amount can be visualized and the user's interpretability can be improved.

[0039] Furthermore, when generating training data for a machine learning model from point cloud data, the information processing device 10 can accurately distinguish between the point cloud data, and can therefore assign accurate labels (teaching information) to each point cloud data. Therefore, the information processing device 10 can improve the training accuracy of the machine learning model. EXAMPLES

[0040] Incidentally, the information processing device 10 can execute clustering of point cloud data by using the feature amount described in the embodiment 1. Therefore, in the embodiment 2, an example will be described in which the clustering of the point cloud data is executed to perform accurate fitting between the point cloud data and a polygon.

[0041] [Function configuration] Fig. 7 is a functional block diagram showing a functional configuration of an information processing device 10 according to Example 2. As shown in Fig. 7, similarly to Example 1, the information processing device 10 includes a communication unit 11, a storage unit 12, and a control unit 20. The difference from the example is that it includes a polygon DB 15 and a clustering execution unit 24, which will be described here.

[0042] The polygon DB 15 is a database that stores a plurality of polygons to be fitted. For example, the polygon DB 15 stores a plurality of polygons having different shapes and a plurality of polygons having similar shapes.

[0043] The clustering execution unit 24 is a processing unit that executes clustering of a plurality of points based on the curvature of each of the plurality of points of the point cloud data, and outputs the result of the clustering execution. Specifically, the clustering execution unit 24 clusters the point cloud data in an n-dimensional space based on geometric features. In this way, for example, when fitting a mesh shape to a point cloud (point cloud data) scanned in a three-dimensional space, it is possible to extract a set of singular points such as corners.

[0044] For example, the clustering execution unit 24 accepts input from an administrator or the like and sets a scale parameter t and a threshold value d. Next, the clustering execution unit 24 performs the clustering on an n-dimensional real number space R n For point cloud data X, which is a subset of x, the curvature c(x) of the point cloud data, which depends on a threshold value, is calculated for each point x (element of X). Here, the clustering execution unit 24 calculates the curvature c(x) by the method of the first embodiment.

[0045] Next, the clustering execution unit 24 determines a(x)=-t if c(x)<-d, a(x)=0 if |c(x)|≦d, and a(x)=t if c(x)>d. The clustering execution unit 24 then adds one dimension to the point cloud data X using the curvature value to create an n+1-dimensional real number space R n+1 Then, the clustering execution unit 24 clusters each point of the point cloud data with one additional dimension into the real number space R n+1 That is, the clustering execution unit 24 embeds each point of the point cloud data, which has been expanded by one dimension, into the real number space R n+1 is mapped to.

[0046]

number

[0047] Thereafter, the clustering execution unit 24 executes clustering by the shortest distance method on the image of the mapping, clusters each point of the point cloud data, and assigns the created cluster to the point cloud before embedding. In other words, the clustering execution unit 24 expresses each point with one additional dimension in the original dimension.

[0048] In this way, the clustering execution unit 24 adds curvature to the number of dimensions of each point of the point cloud data to increase the number of dimensions by one, and then performs clustering in the increased dimension state, thereby enabling accurate clustering of each point of the point cloud data and distinguishing between similar point cloud data.

[0049] 8 is a diagram illustrating a clustering result according to Example 2. The clustering execution unit 24 can cluster the points of the point cloud data, and can classify the points into, for example, cluster A, which is a cluster of points whose curvature is less than a first threshold and has almost no curvature, cluster B, which is a cluster of points whose curvature is equal to or greater than the first threshold and less than a second threshold and has a small curvature, and cluster C, which is a cluster of points whose curvature is equal to or greater than the second threshold and has a large curvature.

[0050] As a result, as shown in FIG. 8, the clustering execution unit 24 can determine that even if the clustering results for the point cloud data P and the clustering results for the point cloud data Q are topologically similar, they are completely different shapes, as can be seen by comparing the clustering results for the point cloud data P and the clustering results for the point cloud data Q.

[0051] Therefore, the clustering execution unit 24 can select and fit a cylindrical polygon to the point cloud data P, and can select and fit a spherical polygon to the point cloud data Q. Therefore, the clustering execution unit 24 can select appropriate polygons from the beginning and perform fitting separately, and can reduce mistakes in polygon selection, thereby achieving a reduction in processing time.

[0052] [Processing flow] Fig. 9 is a flowchart showing a process flow according to Example 2. As shown in Fig. 9, the vector calculation unit 21 of the information processing device 10 acquires point cloud data (S201), and selects one point in the point cloud data (S202).

[0053] Next, the vector calculation unit 21 performs a principal component analysis to calculate a space (eigenvector) (S203), and the curvature calculation unit 22 calculates a curvature, which is a curvature-like amount determined locally from the point cloud data (S204).

[0054] If there are unselected points in the point cloud data (S205: Yes), S202 and subsequent steps are repeated for the unselected points. On the other hand, if there are no unselected points in the point cloud data (S205: No), the clustering execution unit 24 executes clustering of each point using the curvature calculated for each point of the point cloud data (S206).

[0055] Thereafter, the clustering execution unit 24 outputs the clustering result (S207). For example, the clustering execution unit 24 stores the clustering result in the storage unit 12, or transmits the clustering result to a destination specified by an administrator or the like.

[0056] In parallel with this, the clustering execution unit 24 uses the clustering result to select an appropriate polygon from the polygon DB 15 (S208), fits the selected polygon to the point cloud data, and outputs the fitting result (S209). For example, the clustering execution unit 24 stores the fitting result in the storage unit 12, or transmits it to a destination specified by an administrator or the like.

[0057] [effect] As described above, the information processing device 10 calculates a locally determined curvature from the point cloud data, and adds a value dependent on that information as another component to construct point cloud data in a one-dimensional space, and then clusters it. That is, the information processing device 10 can construct a feature from the given point cloud data, and perform clustering by combining it with the coordinate components.

[0058] As a result, the information processing device 10 can extract a set of singular points such as corners when fitting a mesh shape (polygon) to point cloud data scanned in a three-dimensional space, for example. At this time, the information processing device 10 can also separately cluster points having singular points. In this way, the information processing device 10 can extract particularly sharp parts or parts with different dimensions, and can perform clustering that takes into account the geometric characteristics of the point cloud data even for point cloud data whose overall shape is not known in advance, thereby enabling accurate fitting. EXAMPLES

[0059] Although the embodiments of the present invention have been described above, the present invention may be embodied in various different forms other than the above-described embodiments.

[0060] [Numbers, etc.] The numerical examples, matrices, number of dimensions, various variables, etc. used in the above embodiments are merely examples and can be changed as desired. The process flow described in each flowchart can also be changed as appropriate within a range that is consistent. Various clustering methods, such as the K-means method and the mean shift method, can also be used as the clustering method.

[0061] [system] The information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified.

[0062] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure. In other words, all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0063] Furthermore, each processing function performed by each device may be realized, in whole or in part, by a CPU and a program analyzed and executed by the CPU, or may be realized as hardware using wired logic.

[0064] [Hardware] Fig. 10 is a diagram for explaining an example of a hardware configuration. As shown in Fig. 10, the information processing device 10 includes a communication device 10a, a hard disk drive (HDD) 10b, a memory 10c, and a processor 10d. The components shown in Fig. 2 are connected to each other via a bus or the like.

[0065] The communication device 10a is a network interface card or the like, and communicates with other devices. The HDD 10b stores programs and DBs that operate the functions shown in FIG.

[0066] The processor 10d reads out a program that executes the same processes as the respective processing units shown in Fig. 2 from the HDD 10b etc. and loads it in the memory 10c, thereby operating a process that executes each function described in Fig. 2 etc. For example, this process executes a function similar to that of each processing unit possessed by the information processing device 10. Specifically, the processor 10d reads out a program having functions similar to those of the vector calculation unit 21, the curvature calculation unit 22, the feature generation unit 22 etc. from the HDD 10b etc. Then, the processor 10d executes a process that executes the same processes as those of the vector calculation unit 21, the curvature calculation unit 22, the feature generation unit 22 etc.

[0067] In this way, the information processing device 10 operates as an information processing device that executes the extraction method by reading and executing the program. The information processing device 10 can also realize the same functions as the above-mentioned embodiment by reading the above-mentioned program from a recording medium using a medium reading device and executing the read-out program. Note that the program in this other embodiment is not limited to being executed by the information processing device 10. For example, the present invention can be similarly applied to a case where another computer or server executes a program, or a case where these execute a program in cooperation with each other.

[0068] This program can be distributed via a network such as the Internet. This program can also be recorded on a computer-readable recording medium such as a hard disk, a flexible disk (FD), a CD-ROM, a magneto-optical disk (MO), or a digital versatile disk (DVD), and can be executed by being read out from the recording medium by a computer. [Explanation of symbols]

[0069] 10. Information processing device 11 Communications Department 12 Storage section 13 Point Cloud Data DB 14 Extraction result DB 15 Polygon DB 20 Control section 21 Vector calculation section 22 Curvature calculation section 23 Feature Generation Unit 24 Clustering Execution Unit

Claims

1. On the computer, Calculating an eigenvector for each of a plurality of points included in the point cloud data by using principal component analysis on point cloud data that exists within a predetermined distance from the point; Calculating the curvature of a multidimensional function having an extreme point located closest to the calculated eigenvector; performing clustering of the plurality of points based on the curvature for each of the plurality of points of the point cloud data; outputting the results of the clustering; A data clustering program to perform the processing.

2. The process to be performed is Clustering is performed on the plurality of points that have been converted into a higher-dimensional form using the curvature; outputting the result of the clustering as a result of clustering for the plurality of points in a state before being subjected to the high-dimensional processing; 2. The data clustering program according to claim 1.

3. The process to be performed is Selecting an appropriate polygon from among the plurality of polygons based on a result of the clustering; Fitting the selected polygon to the point cloud data; The output process includes: Output the fitting results, 3. The data clustering program according to claim 1, wherein the data clustering program is a program for clustering a plurality of data.

4. The computer Calculating an eigenvector for each of a plurality of points included in the point cloud data by using principal component analysis on point cloud data that exists within a predetermined distance from the point; Calculating the curvature of a multidimensional function having an extreme point located closest to the calculated eigenvector; performing clustering of the plurality of points based on the curvature for each of the plurality of points of the point cloud data; outputting the results of the clustering; A data clustering method for performing processing.

5. a vector calculation unit that calculates an eigenvector for each of a plurality of points included in the point cloud data by using a principal component analysis on the point cloud data that exists within a predetermined distance from the point; a curvature calculation unit that calculates a curvature of a multidimensional function having a point located closest to the calculated eigenvector as an extreme point; a clustering execution unit that executes clustering of the plurality of points based on the curvature for each of the plurality of points of the point cloud data and outputs a result of the clustering; 13. An information processing device comprising:

Images