ABNORMALITY DETECTION DEVICE, CONTROL METHOD, AND PROGRAM

Abstract

This abnormality detection device (2000) acquires reference point cloud data (20) and inspection point cloud data (30), for each of a plurality of locations in a space containing an object (10). The reference point cloud data (20) includes point data representing the three-dimensional position and brightness at the reference point in time, for each of a plurality of locations. The inspection point cloud data (30) includes point data representing the three-dimensional position and brightness at the time of inspection, for each of a plurality of locations. The abnormality detection device (2000) uses the reference point cloud data (20) and the inspection point cloud data (30) to generate difference point cloud data (40) representing a difference in brightness between a reference time point and an inspection time point for each location. The abnormality detection device (2000) detects, from among the plurality of locations, an excluded location to be excluded from an abnormal location detection target. The abnormality detection device (2000) uses the difference point cloud data (40) to detect abnormal locations of the object (10) at the inspection time, from locations excluding excluded locations.

Description

[Technical field]

[0001] The present disclosure relates to a technique for detecting anomalies in an object. [Background technology]

[0002] A technology has been developed to detect abnormalities in facilities, etc., using point cloud data that represents the three-dimensional position and brightness of each of multiple points in a space. For example, Patent Document 1 discloses a technology that classifies a measurement object into clusters for each structure using position information of multiple points on the surface of the measurement object, and identifies abnormalities on the surface of each cluster based on the reflected brightness values ​​of multiple points on the surface of each cluster. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2020 / 203263 Summary of the Invention [Problem to be solved by the invention]

[0004] An object of the present disclosure is to provide a new technology for detecting anomalies in an object located in a space, using point cloud data representing the three-dimensional position and brightness of each of multiple points in the space. [Means for solving the problem]

[0005] The abnormality detection device disclosed herein includes an acquisition unit that acquires reference point cloud data indicating point data representing three-dimensional position and brightness at a reference time for each of a plurality of locations in a space including an object, and inspection point cloud data indicating point data representing three-dimensional position and brightness at the time of inspection for each of the plurality of locations; a difference data generation unit that uses the reference point cloud data and the inspection point cloud data to generate difference point cloud data representing the difference in brightness between the reference time and the inspection time for each of the locations; an exclusion point detection unit that detects moving body locations, which are locations whose positions change over time, among the plurality of locations as exclusion points to be excluded from detection targets for abnormal locations; and an abnormal location detection unit that uses the difference point cloud data to detect abnormal locations of the object at the inspection time from the plurality of locations excluding the exclusion points.

[0006] The control method of the present disclosure is executed by a computer and includes an acquisition step of acquiring reference point cloud data indicating point data representing a three-dimensional position and brightness at a reference time point for each of a plurality of locations in a space including an object, and inspection point cloud data indicating point data representing a three-dimensional position and brightness at an inspection time point for each of the plurality of locations, a difference data generation step of generating difference point cloud data representing a difference in brightness between the reference time point and the inspection time point for each of the locations using the reference point cloud data and the inspection point cloud data, an excluded portion detection step of detecting, from among the plurality of locations, a moving body portion whose position changes over time as an excluded portion to be excluded from detection targets for an abnormal portion, and an abnormal portion detection step of detecting, from among the plurality of locations, an abnormal portion of the object at the inspection time point using the difference point cloud data, the abnormal portion of the object.

[0007] The computer-readable medium of the present disclosure stores a program for causing a computer to execute the control method of the present disclosure. Effect of the Invention

[0008] According to the present disclosure, a new technique is provided for detecting an abnormality in an object located in a space, using point cloud data representing the three-dimensional position and brightness of each of multiple points in the space. [Brief description of the drawings]

[0009] [Figure 1] 2 is a diagram illustrating an example of an outline of the operation of the abnormality detection device of the first embodiment. [Diagram 2] 1 is a block diagram illustrating an example of a functional configuration of an abnormality detection device according to a first embodiment. [Diagram 3] FIG. 2 is a block diagram illustrating a hardware configuration of a computer that realizes the abnormality detection device. [Figure 4] 4 is a flowchart illustrating a flow of processing executed by the abnormality detection device of the first embodiment. [Diagram 5] 1 is a diagram conceptually illustrating a method for generating point cloud data by utilizing electromagnetic waves; [Figure 6] 1A and 1B are diagrams illustrating examples of the influence of the magnitude of the incident angle of an electromagnetic wave on a measurement result. [Figure 7] 1A and 1B are diagrams illustrating examples of the influence of the magnitude of the incident angle of an electromagnetic wave on a measurement result. [Figure 8] 1 is a diagram illustrating a case in which an electromagnetic wave is irradiated onto an edge of an object; [Figure 9] 1 is a diagram illustrating a case in which an electromagnetic wave is irradiated onto an edge of an object; [Figure 10] 13A and 13B conceptually illustrate a process for determining whether point data represents a point on an edge of an object. [Figure 11] 13A and 13B conceptually illustrate a process for determining whether point data represents a point on an edge of an object. [Figure 12] 13A and 13B conceptually illustrate a process for determining whether point data represents a point on an edge of an object. [Figure 13] 10A and 10B are diagrams illustrating an example of a difference in point cloud density between reference point cloud data and inspection point cloud data. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are given the same reference numerals, and duplicated explanations are omitted as necessary for clarity of explanation. Furthermore, unless otherwise specified, predetermined values ​​such as predetermined values ​​and threshold values ​​are stored in advance in a storage device accessible from a device that uses the values. Furthermore, unless otherwise specified, the storage unit is composed of one or more arbitrary number of storage devices.

[0011] Fig. 1 is a diagram illustrating an example of an outline of the operation of the abnormality detection device 2000 according to the embodiment 1. Here, Fig. 1 is a diagram for facilitating understanding of the outline of the abnormality detection device 2000, and the operation of the abnormality detection device 2000 is not limited to that shown in Fig. 1.

[0012] The abnormality detection device 2000 is used to detect an abnormal portion on an object 10. The object 10 is any object that is used with its position fixed, and is, for example, the whole or a part of a facility (structure or building) such as an electric power facility, a steelworks facility, or a chemical plant. However, the object 10 is not necessarily limited to objects classified as real property, and may be objects classified as movable property.

[0013] The abnormality detection device 2000 acquires point cloud data, which is a collection of point data for each of a plurality of points in an object space including the object 10. The point data for each point indicates position data representing the three-dimensional position of the point and brightness data representing the brightness of the point.

[0014] The point cloud data is generated by a measurement device 200. For example, the measurement device 200 generates the point cloud data by measurement using electromagnetic waves such as laser light. The measurement device 200 that uses electromagnetic waves is, for example, a LiDAR (light detection and ranging).

[0015] The point cloud data may be raw data directly representing the results of measurement by the measuring device 200, or may be data obtained by subjecting the raw data to any processing. For example, processing of the raw data may be a process of applying coordinate transformation to each piece of position data so that a specific position in the target space becomes the origin.

[0016] Here, the abnormality detection device 2000 acquires at least two types of point cloud data, namely, reference point cloud data 20 and inspection point cloud data 30, which are generated for an object space at different times. The inspection point cloud data 30 is point cloud data obtained by measurement performed at a time when it is desired to inspect for the presence or absence of an abnormality (hereinafter, inspection time). The reference point cloud data 20 is point cloud data obtained by measurement performed at a time prior to the inspection time, and is used as a reference for abnormality detection. Hereinafter, the time when the measurement for obtaining the reference point cloud data 20 was performed is referred to as the reference time. Note that the state of the object 10 at the reference time does not necessarily have to be completely free of abnormalities.

[0017] The abnormality detection device 2000 generates difference point cloud data 40 using the reference point cloud data 20 and the inspection point cloud data 30. The difference point cloud data 40 indicates difference point data representing the difference in luminance between the inspection time and the reference time for each of multiple points in the target space.

[0018] The abnormality detection device 2000 detects abnormal points of the object 10 from multiple points in the object space using the difference point cloud data 40. In this case, the abnormality detection device 2000 excludes points that satisfy specific conditions from the multiple points in the object space from the abnormality detection targets. Here, the points excluded from the abnormality detection targets are called excluded points. The abnormality detection device 2000 detects abnormal points using the difference point cloud data 40 for the points excluding the excluded points.

[0019] For example, the excluded portion is a portion whose position changes over time in the object space (hereinafter, referred to as a moving object portion). The abnormality detection device 2000 detects the moving object portion using the inspection point cloud data 30, and treats the detected moving object portion as the excluded portion.

[0020] In addition, the excluded portion is, for example, a portion where erroneous determination is likely to occur in determining whether or not the portion is abnormal. As will be described later, examples of the portion where erroneous determination is likely to occur include a portion where the incident angle of the electromagnetic wave emitted from the measuring device 200 is large, and a portion near the edge of an object.

[0021] <Example of action and effect> According to the abnormality detection device 2000 of this embodiment, abnormal points are detected using point cloud data indicating the three-dimensional positions and brightness of each of a plurality of points in a space including the object 10. At this time, abnormal points are detected for points other than the excluded points that satisfy a specific condition. In this way, abnormal points in the object 10 can be detected with higher accuracy.

[0022] For example, the abnormality detection device 2000 treats moving object locations as excluded locations. Here, measurements for obtaining point cloud data are performed on an object space including the object 10. Therefore, the point cloud data may also include point data on objects other than the object 10. Therefore, it is preferable to limit the detection target for abnormal locations to only the object 10 by excluding point data on objects other than the object 10 from the detection target for abnormal locations.

[0023] In this regard, since the object 10 is a facility or the like whose position is fixed, there is a high probability that the moving object part is part of an object other than the object 10 (for example, vegetation, etc.). Therefore, by excluding the moving object part from the target of abnormality detection, it is possible to reduce the probability that an abnormal part will be detected in an object other than the object 10. In other words, it is possible to increase the probability that a part detected as an abnormal part is part of the object 10. Therefore, it is possible to detect an abnormal part in the object 10 with higher accuracy.

[0024] Additionally, for example, the abnormality detection device 2000 treats a portion where erroneous judgment is likely to occur as an excluded portion. In this way, it is possible to reduce the probability that a non-abnormal portion is erroneously detected as an abnormal portion.

[0025] The abnormality detection device 2000 of this embodiment will be described in more detail below.

[0026] <Example of functional configuration> 2 is a block diagram illustrating a functional configuration of an abnormality detection device 2000 according to the first embodiment. The abnormality detection device 2000 includes an acquisition unit 2020, a difference data generation unit 2040, an excluded portion detection unit 2060, and an abnormal portion detection unit 2080. The acquisition unit 2020 acquires the reference point cloud data 20 and the inspection point cloud data 30. The difference data generation unit 2040 generates the difference point cloud data 40 using the reference point cloud data 20 and the inspection point cloud data 30. The excluded portion detection unit 2060 detects the excluded portion using one or both of the reference point cloud data 20 and the inspection point cloud data 30. The abnormal portion detection unit 2080 detects the abnormal portion using data on the portions other than the excluded portion in the difference point cloud data 40.

[0027] <Example of hardware configuration> Each functional component of the anomaly detection device 2000 may be realized by hardware that realizes each functional component (e.g., a hardwired electronic circuit, etc.), or may be realized by a combination of hardware and software (e.g., a combination of an electronic circuit and a program that controls it, etc.). Below, a further explanation will be given of the case where each functional component of the anomaly detection device 2000 is realized by a combination of hardware and software.

[0028] 3 is a block diagram illustrating an example of a hardware configuration of a computer 500 that realizes the anomaly detection device 2000. The computer 500 is any computer. For example, the computer 500 is a stationary computer such as a PC (Personal Computer) or a server machine. In addition, for example, the computer 500 is a portable computer such as a smartphone or a tablet terminal. The computer 500 may be a dedicated computer designed to realize the anomaly detection device 2000, or may be a general-purpose computer.

[0029] For example, by installing a specific application on the computer 500, each function of the anomaly detection device 2000 is realized by the computer 500. The application is configured with a program for realizing each functional component of the anomaly detection device 2000. The method of acquiring the program is arbitrary. For example, the program can be acquired from a storage medium (such as a DVD disk or a USB memory) in which the program is stored. Alternatively, the program can be acquired by downloading the program from a server device that manages the storage device in which the program is stored.

[0030] The computer 500 has a bus 502, a processor 504, a memory 506, a storage device 508, an input / output interface 510, and a network interface 512. The bus 502 is a data transmission path for the processor 504, the memory 506, the storage device 508, the input / output interface 510, and the network interface 512 to transmit and receive data to and from each other. However, the method of connecting the processor 504 and other components to each other is not limited to a bus connection.

[0031] The processor 504 is a processor such as a central processing unit (CPU), a graphics processing unit (GPU), or a field-programmable gate array (FPGA). The memory 506 is a main storage device realized using a random access memory (RAM) or the like. The storage device 508 is an auxiliary storage device realized using a hard disk, a solid state drive (SSD), a memory card, or a read only memory (ROM) or the like.

[0032] The input / output interface 510 is an interface for connecting the computer 500 to an input / output device. For example, the input / output interface 510 is connected to an input device such as a keyboard and an output device such as a display device.

[0033] The network interface 512 is an interface for connecting the computer 500 to a network. This network may be a LAN (Local Area Network) or a WAN (Wide Area Network).

[0034] The storage device 508 stores a program (a program that realizes the above-mentioned application) that realizes each functional component of the abnormality detection device 2000. The processor 504 realizes each functional component of the abnormality detection device 2000 by reading the program into the memory 506 and executing it.

[0035] Anomaly detection device 2000 may be realized by one computer 500, or may be realized by multiple computers 500. In the latter case, the configurations of the computers 500 do not need to be the same, and can be different from each other.

[0036] <Processing flow> 4 is a flowchart illustrating a process flow executed by the abnormality detection device 2000 of the first embodiment. The acquisition unit 2020 acquires the reference point cloud data 20 and the inspection point cloud data 30 (S102). The difference data generation unit 2040 generates the difference point cloud data 40 using the reference point cloud data 20 and the inspection point cloud data 30 (S104). The excluded portion detection unit 2060 detects the excluded portion using one or both of the reference point cloud data 20 and the inspection point cloud data 30 (S106). The abnormal portion detection unit 2080 detects the abnormal portion from the portions other than the excluded portion (S108).

[0037] Here, the flowchart shown in Fig. 4 is merely an example, and the flow of the process executed by the anomaly detection device 2000 is not limited to the flow shown in Fig. 4. For example, the anomaly detection device 2000 may perform a process of detecting an excluded portion (S106) before a process of generating the difference point cloud data 40 (S104). In this case, the difference data generation unit 2040 may generate the difference point cloud data 40 only for the portions other than the excluded portion. Alternatively, for example, the process of generating the difference point cloud data 40 (S104) and the process of detecting the excluded portion (S106) may be performed in parallel with each other.

[0038] <About point cloud data> The measurement device 200 measures three-dimensional positions and luminance using electromagnetic waves such as laser light. Specifically, the measurement device 200 emits electromagnetic waves in a number of different directions, and receives reflected waves of each electromagnetic wave that are reflected by an object. Then, the measurement device 200 generates point data representing the three-dimensional positions and luminance of the points that reflect the electromagnetic waves, based on the relationship between the emitted electromagnetic waves and the reflected waves.

[0039] 5 is a diagram conceptually illustrating a method for generating point cloud data using electromagnetic waves. The dotted arrows represent electromagnetic waves emitted from the measurement device 200. The crosses represent points where the electromagnetic waves are reflected.

[0040] In Fig. 5, the emission direction of an electromagnetic wave is represented by the position of the mass through which the electromagnetic wave passes. Specifically, the emission direction of an electromagnetic wave is expressed as (i,j) by using index i representing the emission direction in the horizontal direction and index j representing the emission direction in the vertical direction.

[0041] In Fig. 5, there are n horizontal directions and m vertical directions for emitting electromagnetic waves. Therefore, the measurement device 200 emits electromagnetic waves in different n*m directions. Therefore, the measurement device 200 can obtain point cloud data having n*m pieces of point data. In other words, the resolution of the measurement device 200 is n*m.

[0042] Hereinafter, point data obtained by electromagnetic waves emitted in a direction (i,j) is expressed as p[i][j]=(a[i][j],b[i][j]). a[i][j] represents the three-dimensional position of the location where the electromagnetic waves emitted in the direction (i,j) are reflected. b[i][j] represents the brightness of the location where the electromagnetic waves emitted in the direction (i,j) are reflected. According to this notation, the point cloud data P can be expressed as P={p[i][j]=(a[i][j],b[i][j])|1<=i<=n,1<=j<=m}. Note that the notation method described here is an example to facilitate the following explanation, and the notation method of point data and point cloud data is not limited to the method described here.

[0043] <Acquisition of point cloud data: S102> The acquisition unit 2020 acquires the reference point cloud data 20 and the inspection point cloud data 30 (S102). There are various methods for the acquisition unit 2020 to acquire these point cloud data. For example, the reference point cloud data 20 and the inspection point cloud data 30 are stored in advance in a storage unit accessible from the abnormality detection device 2000. The acquisition unit 2020 acquires the reference point cloud data 20 and the inspection point cloud data 30 by accessing this storage unit.

[0044] Alternatively, for example, the reference point cloud data 20 and the inspection point cloud data 30 may be input to the anomaly detection device 2000 in response to a user operation. For example, the user connects a portable storage unit (such as a memory card) in which the reference point cloud data 20 and the inspection point cloud data 30 are stored to the anomaly detection device 2000, and inputs the reference point cloud data 20 and the inspection point cloud data 30 from the storage unit to the anomaly detection device 2000.

[0045] Alternatively, for example, the acquisition unit 2020 may acquire the reference point cloud data 20 and the inspection point cloud data 30 by receiving the reference point cloud data 20 and the inspection point cloud data 30 transmitted from another device. For example, the other device is a measuring device 200, a device that processes raw data generated by the measuring device 200 to generate the reference point cloud data 20 and the inspection point cloud data 30, etc.

[0046] The reference point cloud data 20 and the inspection point cloud data 30 may be obtained by the same method or different methods.

[0047] <Generation of difference point cloud data 40: S104> The difference data generating unit 2040 generates the difference point cloud data 40 (S104). Specifically, the difference data generating unit 2040 calculates the difference in luminance between the reference point cloud data 20 and the inspection point cloud data 30 for each of the multiple locations. Here, existing technology can be used to obtain data representing the difference in luminance for each of the multiple measured locations from the two point cloud data.

[0048] For example, as described above, it is assumed that the direction in which the electromagnetic wave is emitted by the measurement device 200 is represented by a pair (i,j) of horizontal index i and vertical index j. In addition, it is assumed that the set of luminance data obtained from the reference point cloud data 20 is represented as B1={b1[i][j]|1<=i<=n,1<=j<=m}, and the set of luminance data obtained from the inspection point cloud data 30 is represented as B2={b2[i][j]|1<=i<=n,1<=j<=m}. In this case, the difference point cloud data 40 can be represented as D={d[i][j]=b2[i][j]-b1[i][j]|1<=i<=n,1<=j<=m}.

[0049] <Exclusion detection: S106> The excluded portion detection unit 2060 detects the excluded portion by using the reference point cloud data 20 (S106). As described above, the excluded portion is, for example, a portion where erroneous determination is likely to occur in determining whether or not it is a moving object portion or an abnormal portion. Alternatively, for example, the excluded portion detection unit 2060 may identify point data from the inspection point cloud data 30 that is highly likely to result in an incorrect measurement result (point data that is highly likely to represent noise), and detect the portion represented by the point data as the excluded portion.

[0050] Here, the exclusion portion detection unit 2060 may treat only one type of portion as an exclusion portion out of multiple types of portions that can be treated as exclusion portions, or may treat two or more types of portions as exclusion portions. Examples of exclusion portions will be specifically described below.

[0051] <<About moving parts>> For example, the excluded portion detection unit 2060 uses the reference point cloud data 20 to detect moving object portions, which are portions whose positions change over time, from within the target space, and treats the moving object portions as excluded portions. As described above, a portion detected as a moving object portion is considered to be part of an object (e.g., vegetation, etc.) other than the target object 10. Thus, by excluding the moving object portion from the target for abnormality determination, it is possible to prevent an abnormal portion from being mistakenly detected in an object other than the target object 10.

[0052] The detection of moving object locations is performed using a plurality of reference point cloud data 20 generated based on the results of measurements performed at different times. The acquisition unit 2020 acquires the plurality of reference point cloud data 20.

[0053] The excluded portion detection unit 2060 calculates the magnitude of difference in three-dimensional position for each of a plurality of portions among a plurality of reference point cloud data 20. Then, the excluded portion detection unit 2060 detects a portion where the magnitude of difference in three-dimensional position is equal to or greater than a threshold as a moving object portion. The magnitude of difference in three-dimensional position can be expressed, for example, by the distance between them.

[0054] For example, as described above, when the measuring device 200 emits electromagnetic waves in multiple directions, the excluded portion detection unit 2060 compares position data obtained by electromagnetic waves emitted in the same direction between multiple reference point cloud data 20. As a more specific example, it is assumed that a set of position data indicated by the first reference point cloud data 20 is expressed as A1={a1[i][j]|1<=i<=n, 1<=j<=m}, and a set of position data indicated by the second reference point cloud data 20 is expressed as A2={a2[i][j]|1<=i<=n, 1<=j<=m}. In this case, the excluded portion detection unit 2060 calculates the distance ||a1[i][j]-a2[i][j]|| between a1[i][j] and a2[i][j] for each portion, i.e., for each direction (i,j).

[0055] The excluded part detection unit 2060 detects the moving object part by using the distance. For example, the moving object part is specified by the direction (i, j) where the distance is equal to or greater than a threshold. For example, when the part detected as the moving object part is expressed by the direction (u, v) (when the distance ||a1[u][v]-a2[u][v]|| is equal to or greater than a threshold), the abnormal part detection unit 2080 excludes d[u][v] from the difference point data included in the difference point cloud data D from the detection target of the abnormal part when detecting the abnormal part.

[0056] Three or more reference point cloud data 20 may be used to detect moving object locations. In this case, for example, the excluded location detection unit 2060 calculates, for each direction (i, j), the magnitude of distribution of position data indicated by each reference point cloud data 20 for that direction. Then, the excluded location detection unit 2060 detects a direction in which the magnitude of distribution is equal to or greater than a threshold as a direction representing a moving object location.

[0057] For example, assume that k pieces of reference point cloud data 20, such as the first reference point cloud data 20, the second reference point cloud data 20, ..., the kth reference point cloud data 20, are obtained. Then, assume that the sets of position data obtained from these are expressed as A1={a1[i][j]|1<=i<=n,1<=j<=m}, A2={a2[i][j]|1<=i<=n,1<=j<=m},..., Ak={ak[i][j]|1<=i<=n,1<=j<=m}. In this case, an index value (e.g., variance) representing the magnitude of distribution of k pieces of three-dimensional positions (a1[i][j], a2[i][j],..., ak[i][j]) for each direction (i,j) is calculated. Then, the excluded part detection unit 2060 detects the direction (i, j) in which the distribution magnitude is equal to or greater than the threshold as the direction representing the moving object part. Note that an existing method can be used as a specific method for calculating the distribution magnitude of multiple three-dimensional data.

[0058] The excluded part detection unit 2060 may treat, in addition to the part detected as the moving object part by the above-mentioned method, other parts that are estimated to be on the same object as the detected part as the excluded part. According to this method, for example, when a tree branch or leaf is detected as the moving object part, the remaining parts such as the trunk of the tree can also be treated as the excluded part.

[0059] For this purpose, the excluded portion detection unit 2060 clusters a plurality of point data included in the reference point cloud data 20 for each piece of point data representing the same object (for each piece of point data representing a position on the same object). Furthermore, the excluded portion detection unit 2060 identifies a cluster including each piece of point data indicating a moving object portion. Then, the excluded portion detection unit 2060 detects a portion represented by each piece of point data included in the identified cluster as an excluded portion. Note that an existing method can be used as a specific method for clustering the point cloud data for each piece of point data representing the same object.

[0060] <<Areas where false positives are likely to occur>> Alternatively, for example, the excluded portion detection unit 2060 detects portions where erroneous determination is likely to occur as excluded portions. In this way, it is possible to reduce the likelihood that a portion that is not an abnormal portion will be erroneously determined to be an abnormal portion.

[0061] Below, we will show several specific examples of parts that are likely to cause erroneous judgment and are treated as excluded parts. Note that only one of the several examples of parts that are likely to cause erroneous judgment described below may be treated as an excluded part, or any two or more types may be treated as excluded parts.

[0062] <<<Areas where the electromagnetic wave incidence angle is large>>> For example, locations where erroneous determinations are likely to occur are locations where the incident angle of the electromagnetic wave emitted from the measurement device 200 is large. The measurement device 200 emits electromagnetic waves in multiple directions. However, when the measurement device 200 performs measurements at different times, even if the electromagnetic waves are treated as being emitted in the same direction (i, j) in the measurement results, a slight error in the emission direction may occur. In locations where the incident angle of the electromagnetic wave is large, there is a high probability that the position on the object where the electromagnetic wave hits will change significantly due to such an error in the emission direction.

[0063] 6 and 7 are diagrams illustrating the effect of the magnitude of the incident angle of the electromagnetic wave on the measurement result. In Fig. 6 and Fig. 7, an electromagnetic wave 50 represents an electromagnetic wave emitted in a direction (u, v) in the measurement for obtaining the reference point cloud data 20. On the other hand, an electromagnetic wave 60 represents an electromagnetic wave emitted in a direction (u, v) in the measurement for obtaining the inspection point cloud data 30. In addition, both the electromagnetic wave 50 and the electromagnetic wave 60 are irradiated onto an object 70.

[0064] In the records of the measuring device 200 (i.e., in the point cloud data), the electromagnetic waves 50 and 60 are treated as being emitted in the same direction. However, in reality, as shown in FIG. 6, there is a slight difference between the emission directions of these electromagnetic waves.

[0065] FIG. 6 illustrates a case where the incident angle of the electromagnetic wave is relatively small. On the other hand, FIG. 7 illustrates a case where the incident angle of the electromagnetic wave is relatively large. In FIG. 6 and FIG. 7, the difference between the direction of the electromagnetic wave 50 and the direction of the electromagnetic wave 60 is the same. However, when FIG. 6 and FIG. 7 are compared, in the case of FIG. 7 where the incident angle of the electromagnetic wave is large, the difference between the position on the object 70 where the electromagnetic wave 50 is irradiated and the position on the object 70 where the electromagnetic wave 60 is irradiated is large compared to the case of FIG. 6 where the incident angle of the electromagnetic wave is small. From this, it can be seen that the difference in the position data becomes large for each measurement at the location where the incident angle of the electromagnetic wave is large.

[0066] Therefore, for example, the excluded portion detection unit 2060 estimates the incident angle of the electromagnetic wave for each of a plurality of portions (emission direction of the electromagnetic wave used for measurement) using the reference point cloud data 20 or the inspection point cloud data 30. Then, the excluded portion detection unit 2060 determines, as excluded portions, the portions where the incident angle of the electromagnetic wave is equal to or greater than a threshold value.

[0067] The incidence angle is estimated, for example, as follows. First, the excluded portion detection unit 2060 calculates, for each point data included in the point cloud data, a normal vector of the object surface at the three-dimensional position indicated by the point data. Then, for each point data, the excluded portion detection unit 2060 calculates the angle formed between the direction of the electromagnetic wave from which the point data was obtained and the direction of the normal vector calculated for the point data as the incidence angle of the electromagnetic wave.

[0068] It should be noted that an existing method can be used to calculate the normal vector for each point data of the point cloud data obtained from the measurement device 200. For example, the excluded portion detection unit 2060 calculates a plane spanned by the three-dimensional position indicated by the point data for which the normal vector is to be calculated and the three-dimensional positions indicated by the multiple point data in the vicinity of the point data. Then, the excluded portion detection unit 2060 calculates a vector perpendicular to this plane as the normal vector.

[0069] <<<Edge>>> Another example of a location where erroneous judgment is likely to occur is the edge of an object. The magnitude of the luminance measured using electromagnetic waves is determined based on the intensity of the reflected light received by the measurement device 200. In this regard, at the edge of an object, a part of the electromagnetic waves is irradiated onto the object, and another part is not irradiated onto the object. Therefore, the magnitude of the measured luminance differs depending on how much of the irradiated electromagnetic waves is irradiated onto the object.

[0070] 8 and 9 are diagrams illustrating a case where an electromagnetic wave is irradiated onto an edge of an object. Electromagnetic wave 50 represents an electromagnetic wave emitted in a direction (u, v) in a measurement for obtaining reference point cloud data 20. Meanwhile, electromagnetic wave 60 represents an electromagnetic wave emitted in a direction (u, v) in a measurement for obtaining inspection point cloud data 30. In Figs. 8 and 9, the portion of object 70 that is irradiated with the electromagnetic wave is represented by a dot pattern.

[0071] In Fig. 8, most of the electromagnetic wave 50 is irradiated onto the object 70. On the other hand, in Fig. 9, only a small portion of the electromagnetic wave 60 is irradiated onto the object 70. Therefore, it is considered that the magnitude of luminance measured by receiving the reflected wave of the electromagnetic wave 50 and the magnitude of luminance measured by receiving the reflected wave of the electromagnetic wave 60 are significantly different from each other. In other words, it is considered that the luminance data indicated by the reference point cloud data 20 for the direction (u, v) and the luminance data indicated by the inspection point cloud data 30 for the direction (u, v) are significantly different from each other.

[0072] In this way, there is a high probability that the measured luminance value will differ significantly at the edge of an object due to an error in the direction of emission of the electromagnetic waves. Therefore, when point data obtained for the edge of an object is used, the difference in luminance between the reference point cloud data 20 and the inspection point cloud data 30 will be large even for points that are not actually abnormal, increasing the probability of false detection of abnormal points.

[0073] Therefore, the excluded portion detection unit 2060 detects portions that represent edges of an object using the reference point cloud data 20 or the inspection point cloud data 30, and treats the portions as excluded portions. Specifically, the excluded portion detection unit 2060 performs the following process on each piece of point data included in the point cloud data to determine whether or not each piece of point data represents an edge of an object.

[0074] 10 to 12 are diagrams conceptually illustrating a process for determining whether point data represents a point (three-dimensional position) on an edge of an object. FIG. 10 is a diagram of an object 70 viewed from the front. FIG. 11 is a diagram of the object 70 viewed from a planar view. A target point 80 represented by a circle is a point, among the points represented by the point cloud data, that is being determined as to whether or not it is a point on the edge of the object 70. A neighboring point 90 represented by a cross is a point, among the points represented by the point cloud data, that is located near the target point 80.

[0075] First, the excluded portion detection unit 2060 identifies a neighboring point 90 from among the points represented by the point cloud data. Specifically, if the three-dimensional position of the target point 80 is b[u][v] and the distance threshold representing the neighborhood is th, the excluded portion detection unit 2060 identifies a point b[i][j] that satisfies ||b[u][v]-b[i][j]||<=th as the neighboring point 90 from among the points represented by the point cloud data.

[0076] Next, the excluded portion detection unit 2060 uses the target point 80 and the neighboring points 90 to identify a plane 100 that is tangent to the object 70 at the target point 80. Furthermore, the excluded portion detection unit 2060 projects each neighboring point 90 onto the plane 100. Fig. 12 is a diagram showing the plane 100 onto which the neighboring points 90 are projected. Each point obtained by projecting the neighboring points 90 onto the plane 100 is depicted as a projected point 110.

[0077] The excluded portion detection unit 2060 judges whether the target point 80 is a point on an edge based on the positional relationship between the target point 80 and the projection point 110. Specifically, the excluded portion detection unit 2060 calculates an opening angle (θ in FIG. 12) using the target point 80 and the projection point 110, and judges whether the opening angle is equal to or greater than a threshold. If the opening angle is equal to or greater than the threshold, the excluded portion detection unit 2060 judges that the target point 80 is on an edge. Therefore, the target point 80 is treated as an excluded portion. For example, if the target point 80 is b[u][v], data for the direction (u, v) of the difference point cloud data 40 is excluded from the target of anomaly detection. On the other hand, if the opening angle is less than the threshold, the excluded portion detection unit 2060 judges that the target point 80 is not on an edge.

[0078] If it is determined that the target point 80 is on an edge, the exclusion portion detection section 2060 may treat each of the neighboring points 90, in addition to the target point 80, as exclusion portions.

[0079] Here, an example of the method of calculating the opening angle described above will be described. First, the excluded portion detection unit 2060 calculates a unit vector from the target point 80 toward the projection point 110 for each projection point 110. Next, the excluded portion detection unit 2060 calculates an average vector of all the calculated unit vectors. Furthermore, the excluded portion detection unit 2060 calculates the magnitude of the rotation angle from the average vector to each unit vector. Note that if the magnitude of the rotation angle from the reference direction to the average vector is greater than the magnitude of the rotation angle from the reference direction (for example, horizontal rightward) to the unit vector, the rotation angle from the average vector to the unit vector will be a negative value.

[0080] The exclusion portion detection unit 2060 extracts the maximum and minimum values ​​from the calculated rotation angles, and calculates a value by subtracting the minimum value from the maximum value.The exclusion portion detection unit 2060 then calculates a value by subtracting the difference between the maximum and minimum rotation angles from 360° as the opening angle.

[0081] <<Noise Removal>> In addition, for example, the excluded portion detection unit 2060 identifies point data that is highly likely to be an incorrect measurement result (point data that is highly likely to represent noise) from the inspection point cloud data 30, and detects the portion represented by the point data as an excluded portion. For example, when the measurement result represented by the point data p[u][v] is not correct, do not have If it is considered that d[u][v] is not detected as an anomaly in the difference point cloud data 40, d[u][v] is excluded from the abnormality detection. Hereinafter, point data that is highly likely to be an incorrect measurement result is called noise point data. Also, the position represented by the noise point data is called a noise point.

[0082] For example, the excluded portion detection unit 2060 identifies noise point data by comparing the density of the point clouds between the reference point cloud data 20 and the inspection point cloud data 30. Fig. 13 is a diagram illustrating an example of a difference in the density of the point clouds between the reference point cloud data 20 and the inspection point cloud data 30. In Fig. 13, a target point 120 is a target to be determined as to whether or not it is a noise point. A neighboring point 130 is a point located near the target point 120.

[0083] Here, the position data indicated by the noise point data represents a position different from the actual position of the measured point. Therefore, when the target point 120 is a noise point, the number of neighboring points 130 is considered to be small. Therefore, when the target point 120 in the inspection point cloud data 30 is a noise point, the density of the point cloud included in the vicinity of the target point 120 is lower than the actual density, and the density is considered to be lower than the density of the point cloud included in the vicinity of the target point 120 in the reference point cloud data 20. On the other hand, when the target point 120 is not a noise point, the density of the point cloud included in the vicinity of the target point 120 in the inspection point cloud data 30 is considered to be approximately the same as the density of the point cloud included in the vicinity of the target point 120 in the reference point cloud data 20.

[0084] Therefore, the excluded portion detection unit 2060 calculates the density of the point cloud located near the point represented by each piece of point data representing the same portion between the reference point cloud data 20 and the inspection point cloud data 30 (e.g., the number of neighboring points 130), and determines whether the difference in density is large. If the difference in density is large, the excluded portion detection unit 2060 determines that the target point 120 is a noise point. On the other hand, if the difference in density is not large, the excluded portion detection unit 2060 determines that the target point 120 is not a noise point.

[0085] The magnitude of the difference in density can be expressed, for example, by a density ratio. For example, the density of the point cloud located near the target point 120 in the reference point cloud data 20 is set to ρ1, and the density of the point cloud located near the target point 120 in the inspection point cloud data 30 is set to ρ2. In this case, the density ratio ρ2 / ρ1 can be used as a value representing the magnitude of the difference in density.

[0086] <Detection of abnormality: S108> The abnormal part detection unit 2080 detects abnormal parts by using data on the point data included in the difference point cloud data 40 other than the excluded parts (S108). For example, as described above, the difference point cloud data 40 is expressed as D={d[i][j]|1<=i<=n, 1<=j<=m}. In this case, the excluded part detection unit 2060 determines whether or not d[i][j] other than the parts detected as the excluded parts is an abnormal part. For example, when the excluded parts are expressed by directions (u,v), the abnormal part detection unit 2060 determines whether or not d[i][j] of the point data included in the difference point cloud data 40 other than the excluded parts is an abnormal part. u ][v] is excluded from anomaly detection.

[0087] Here, an existing method can be used to detect an abnormal part using the brightness difference obtained for a specific part. For example, the abnormal part detection unit 2080 detects a part (u, v) as an abnormal part when the brightness difference d[u][v] for the part (u, v) is equal to or greater than a threshold value.

[0088] <Result output> The abnormality detection device 2000 outputs output information representing the processing result. The output information is information capable of identifying an abnormal location. For example, the output information indicates information representing an abnormal location. Here, the abnormal location may be represented by a pair of indices representing the measurement direction, or may be represented by other methods. In the former case, for example, when the luminance data d[u][v] is equal to or greater than a threshold, the abnormal location is represented by a direction (u,v). On the other hand, in the latter case, the abnormal location in the same case is represented by a three-dimensional position b[u][v] indicated by the inspection point cloud data 30 in the direction (u,v).

[0089] Alternatively, for example, the output information may indicate point cloud data that is obtained by processing the inspection point cloud data 30 so that abnormal points can be distinguished from other points. In this case, for example, the abnormality detection device 2000 generates point cloud data in which position data and color data are associated with each other from the inspection point cloud data 30. Hereinafter, this point cloud data will be referred to as display point cloud data.

[0090] The abnormality detection device 2000 generates point data to be included in the display point cloud data from each point data included in the inspection point cloud data 30. For example, the inspection point cloud data 30 is set as P={p[i][j]=(a[i][j], b[i][j])|1<=i<=n, 1<=j<=m} as described above. In this case, the display point cloud data can be expressed as Q={q[i][j]=(a[i][j], c[i][j])|1<=i<=n, 1<=j<=m}. Here, c[i][i] represents color data for the direction (i,j). The position data indicated by each point data of the display point cloud data is the position data indicated by the corresponding point data of the inspection point cloud data 30.

[0091] Here, a method for generating color data will be described. For example, in the display point cloud data, the color data of a portion other than the abnormal portion indicates the luminance of that portion in grayscale. That is, the color data indicated by the point data of a portion other than the abnormal portion is expressed in gray, which is closer to black the lower the luminance indicated by the inspection point cloud data 30 for that portion, and closer to white the higher the luminance indicated by the inspection point cloud data 30 for that portion.

[0092] On the other hand, in the display point cloud data, the color data of the abnormal portion indicates a specific color other than gray (e.g., red). In this case, the color data of the abnormal portion may be fixed regardless of the luminance of the abnormal portion, or may be set to a color according to the luminance of the abnormal portion. In the latter case, for example, the color data of the abnormal portion indicates a color with a higher luminance as the luminance indicated by the inspection point cloud data 30 for that portion increases. For example, the color data of the abnormal portion is represented only by the red component out of the three primary colors of red, green, and blue. In this case, the color data of the abnormal portion indicates a color with a larger red component as the luminance indicated by the inspection point cloud data 30 for that abnormal portion increases.

[0093] By viewing the display data in which the display point cloud data thus generated is plotted in a virtual three-dimensional space, the user of the abnormality detection device 2000 can easily grasp which part of an object such as the target object 10 existing in the target space is abnormal. Furthermore, if the luminance of the color data is increased as the luminance of the abnormal part increases, the degree of the abnormality can be easily grasped by viewing the display data.

[0094] In the output information, the excluded points may be displayed in a manner that allows them to be distinguished from other data. In this case, for example, in the display point cloud data described above, the color data for the excluded points is represented by a specific color different from the color used for the color data for the abnormal points. For example, the color data for the abnormal points is represented using only the red component, and the color data for the excluded points is represented using only the blue component. In this way, the user of the abnormality detection device 2000 can easily understand the points that have been excluded from the determination of abnormal points.

[0095] The output information may be output in any manner. For example, the output information may be stored in any storage unit. Alternatively, for example, the output information may be transmitted to another device. Alternatively, for example, the output information may be displayed on a display device. Here, when the output information is displayed on a display device, it is preferable to display the display data in which the display point cloud data described above is plotted in a virtual three-dimensional space.

[0096] Although the present invention has been described above with reference to the embodiment, the present invention is not limited to the above embodiment. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0097] In the above example, the program includes a set of instructions (or software code) for making the computer perform one or more functions described in the embodiment when the program is loaded into the computer. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, the computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray (registered trademark) disk or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, the transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagating signals.

[0098] A part or all of the above-described embodiments can be described as, but is not limited to, the following supplementary notes. (Appendix 1) an acquisition unit that acquires reference point cloud data indicating point data representing a three-dimensional position and brightness at a reference time for each of a plurality of locations in a space including an object, and inspection point cloud data indicating point data representing a three-dimensional position and brightness at an inspection time for each of the plurality of locations; a difference data generating unit that generates difference point cloud data representing a difference in luminance between the reference time point and the inspection time point for each of the locations using the reference point cloud data and the inspection point cloud data; an excluded portion detection unit that detects, among the plurality of portions, a moving object portion, which is a portion whose position changes over time, as an excluded portion to be excluded from detection targets for abnormal portions; and an abnormality detection unit that uses the difference point cloud data to detect abnormal points of the object at the time of inspection from among the plurality of points, excluding the excluded points. (Appendix 2) The exclusion portion detection unit clustering the plurality of point data included in the reference point cloud data for each of the point data representing a location on the same object; 2. The anomaly detection device according to claim 1, further comprising: identifying the point data included in the same cluster as the point data representing the moving object location; and detecting the moving object location and the location represented by the identified point data as the excluded locations. (Appendix 3) The abnormality detection device according to claim 1 or 2, wherein the exclusion portion detection unit further detects, as the exclusion portion, from among the plurality of portions, portions that are highly likely to result in an erroneous determination as to whether or not they are abnormal portions. (Appendix 4) the reference point cloud data and the inspection point cloud data are generated using a measurement device that emits electromagnetic waves in each of a plurality of directions, The anomaly detection device described in Appendix 3, wherein the exclusion portion detection unit uses the reference point cloud data or the inspection point cloud data to identify, from among the multiple portions, the portion at which the incident angle of the electromagnetic wave to that portion is equal to or greater than a threshold, and detects the identified portion as the exclusion portion. (Appendix 5) The anomaly detection device described in Appendix 3, wherein the exclusion point detection unit uses the reference point cloud data or the inspection point cloud data to identify the point located on an edge of an object, and detects the identified point as the exclusion point. (Appendix 6) The exclusion portion detection unit For each of the point data included in the reference point cloud data, a first density is calculated that represents the number of the point data indicating a three-dimensional position whose distance from the three-dimensional position represented by the point data is equal to or less than a threshold value; For each of the point data included in the inspection point cloud data, a second density is calculated that represents the number of the point data indicating a three-dimensional position whose distance from the three-dimensional position represented by the point data is equal to or less than a threshold value; 6. The anomaly detection device according to claim 1, further detecting, as the exclusion area, the area where the magnitude of the difference between the first density and the second density is equal to or greater than a threshold value. (Appendix 7) 1. A computer-implemented control method comprising: an acquisition step of acquiring reference point cloud data indicating point data representing a three-dimensional position and brightness at a reference time for each of a plurality of locations in a space including the object, and inspection point cloud data indicating point data representing a three-dimensional position and brightness at an inspection time for each of the plurality of locations; a difference data generating step of generating difference point cloud data representing a difference in luminance between the reference time point and the inspection time point for each of the locations, using the reference point cloud data and the inspection point cloud data; an exclusion portion detection step of detecting, among the plurality of portions, a moving body portion, the position of which changes over time, as an exclusion portion to be excluded from detection targets for abnormal portions; and an abnormality detection step of detecting an abnormality in the object at the time of inspection from among the plurality of locations excluding the excluded locations using the difference point cloud data. (Appendix 8) In the step of detecting an excluded portion, clustering the plurality of point data included in the reference point cloud data for each of the point data representing a location on the same object; The control method of claim 7, further comprising: identifying the point data included in the same cluster as the point data representing the moving object location; and detecting the moving object location and the location represented by the identified point data as the excluded location. (Appendix 9) A control method as described in Appendix 7 or 8, wherein in the excluded portion detection step, among the multiple portions, a portion that is highly likely to result in an erroneous determination as to whether or not it is an abnormal portion is further detected as the excluded portion. (Appendix 10) the reference point cloud data and the inspection point cloud data are generated using a measurement device that emits electromagnetic waves in each of a plurality of directions, A control method as described in Appendix 9, wherein, in the exclusion portion detection step, the reference point cloud data or the inspection point cloud data is used to identify from among the multiple portions a portion at which the incident angle of the electromagnetic wave to that portion is equal to or greater than a threshold, and the identified portion is detected as the exclusion portion. (Appendix 11) 10. The control method of claim 9, wherein in the exclusion portion detection step, the portion located on an edge of an object is identified using the reference point cloud data or the inspection point cloud data, and the identified portion is detected as the exclusion portion. (Appendix 12) In the step of detecting an excluded portion, For each of the point data included in the reference point cloud data, a first density is calculated that represents the number of the point data indicating a three-dimensional position whose distance from the three-dimensional position represented by the point data is equal to or less than a threshold value; For each of the point data included in the inspection point cloud data, a second density is calculated that represents the number of the point data indicating a three-dimensional position whose distance from the three-dimensional position represented by the point data is equal to or less than a threshold value; The control method according to any one of appendices 7 to 11, further detecting, as the excluded portion, the portion where the magnitude of the difference between the first density and the second density is equal to or greater than a threshold value. (Appendix 13) On the computer, an acquisition step of acquiring reference point cloud data indicating point data representing a three-dimensional position and brightness at a reference time for each of a plurality of locations in a space including the object, and inspection point cloud data indicating point data representing a three-dimensional position and brightness at an inspection time for each of the plurality of locations; a difference data generating step of generating difference point cloud data representing a difference in luminance between the reference time point and the inspection time point for each of the locations, using the reference point cloud data and the inspection point cloud data; an exclusion portion detection step of detecting, among the plurality of portions, a moving body portion, the position of which changes over time, as an exclusion portion to be excluded from detection targets for abnormal portions; and an abnormality detection step of detecting abnormalities in the object at the time of inspection from among the plurality of locations, excluding the excluded locations, using the difference point cloud data. (Appendix 14) In the step of detecting an excluded portion, clustering the plurality of point data included in the reference point cloud data for each of the point data representing a location on the same object; The computer-readable medium of claim 13, further comprising: identifying the point data included in the same cluster as the point data representing the moving object location; and detecting the moving object location and the location represented by the identified point data as the excluded location. (Appendix 15) A computer-readable medium according to claim 13 or 14, wherein in the step of detecting excluded locations, among the plurality of locations, locations that are highly likely to result in an erroneous determination as to whether or not they are abnormal are further detected as excluded locations. (Appendix 16) the reference point cloud data and the inspection point cloud data are generated using a measurement device that emits electromagnetic waves in each of a plurality of directions, A computer-readable medium as described in Appendix 15, wherein in the exclusion portion detection step, the reference point cloud data or the inspection point cloud data is used to identify from among the multiple portions a portion at which the incident angle of the electromagnetic wave to that portion is equal to or greater than a threshold, and the identified portion is detected as the exclusion portion. (Appendix 17) 16. The computer-readable medium of claim 15, wherein in the exclusion portion detection step, the reference point cloud data or the inspection point cloud data is used to identify the portion located on an edge of an object, and the identified portion is detected as the exclusion portion. (Appendix 18) In the step of detecting an excluded portion, For each of the point data included in the reference point cloud data, a first density is calculated that represents the number of the point data indicating a three-dimensional position whose distance from the three-dimensional position represented by the point data is equal to or less than a threshold value; For each of the point data included in the inspection point cloud data, a second density is calculated that represents the number of the point data indicating a three-dimensional position whose distance from the three-dimensional position represented by the point data is equal to or less than a threshold value; 18. The computer-readable medium of any one of claims 13 to 17, further detecting the portion where the magnitude of the difference between the first density and the second density is equal to or greater than a threshold as the excluded portion. [Explanation of symbols]

[0099] 10. Object 20 Control point cloud data 30 Inspection point cloud data 40 Difference point cloud data 50 Electromagnetic Waves 60 Electromagnetic Waves 70 Object 80 target points 90 Nearby Points 100 planes 110 Projection point 120 target points 130 Nearby Points 200 Measuring Equipment 500 Computers 502 Bus 504 Processor 506 Memory 508 Storage Devices 510 Input / Output Interface 512 Network Interface 2000 Anomaly Detection Device 2020 Acquisition Department 2040 Differential Data Generation Unit 2060 Exclusion detection section 2080 Abnormality detection section

Claims

1. an acquisition unit that acquires reference point cloud data indicating point data representing a three-dimensional position and brightness at a reference time for each of a plurality of locations in a space including the object, and inspection point cloud data indicating point data representing a three-dimensional position and brightness at an inspection time for each of the plurality of locations; a difference data generating unit that generates difference point cloud data representing a difference in luminance between the reference time point and the inspection time point for each of the locations using the reference point cloud data and the inspection point cloud data; an excluded portion detection unit that detects, among the plurality of portions, a moving object portion, which is a portion whose position changes over time, as an excluded portion to be excluded from detection targets for abnormal portions; an abnormality detection unit that detects an abnormality in the object at the time of inspection from the plurality of the portions excluding the excluded portion by using the difference point cloud data, The exclusion portion detection unit For each of the point data included in the reference point cloud data, a first density is calculated that represents the number of the point data indicating a three-dimensional position whose distance from the three-dimensional position represented by the point data is equal to or less than a threshold value; Calculating a second density representing the number of point data indicating a three-dimensional position whose distance from the three-dimensional position represented by the point data is equal to or less than a threshold value for each of the point data included in the inspection point cloud data; The abnormality detection device further detects, as the excluded portion, the portion where the magnitude of the difference between the first density and the second density is equal to or greater than a threshold.

2. The exclusion part detection unit clustering the plurality of point data included in the reference point cloud data for each of the point data representing a location on the same object; The abnormality detection device according to claim 1 , further comprising: identifying the point data included in the same cluster as the point data representing the moving object location; and detecting the moving object location and the location represented by the identified point data as the excluded location.

3. The abnormality detection device according to claim 1 , wherein the excluded portion detection unit further detects, as the excluded portion, a portion among the plurality of portions that is highly likely to be erroneously determined as being an abnormal portion.

4. the reference point cloud data and the inspection point cloud data are generated using a measurement device that emits electromagnetic waves in each of a plurality of directions, 4. The abnormality detection device according to claim 3, wherein the excluded portion detection unit uses the reference point cloud data or the inspection point cloud data to identify, from among the plurality of portions, a portion where the incident angle of the electromagnetic wave to that portion is equal to or greater than a threshold, and detects the identified portion as a portion where there is a high probability of the erroneous judgment occurring.

5. 4. The anomaly detection device according to claim 3, wherein the exclusion point detection unit uses the reference point cloud data or the inspection point cloud data to identify the points located on an edge of an object, and detects the identified points as points where there is a high probability of the erroneous judgment occurring.

6. 1. A computer-implemented control method comprising: an acquisition step of acquiring reference point cloud data indicating point data representing a three-dimensional position and brightness at a reference time for each of a plurality of locations in a space including the object, and inspection point cloud data indicating point data representing a three-dimensional position and brightness at an inspection time for each of the plurality of locations; a difference data generating step of generating difference point cloud data representing a difference in luminance between the reference time point and the inspection time point for each of the locations, using the reference point cloud data and the inspection point cloud data; an exclusion portion detection step of detecting, among the plurality of portions, a moving body portion, the position of which changes over time, as an exclusion portion to be excluded from detection targets for abnormal portions; an abnormality portion detection step of detecting an abnormal portion of the object at the time of inspection from the portions excluding the excluded portion among the plurality of portions by using the difference point cloud data, In the step of detecting an excluded portion, For each of the point data included in the reference point cloud data, a first density is calculated that represents the number of the point data indicating a three-dimensional position whose distance from the three-dimensional position represented by the point data is equal to or less than a threshold value; Calculating a second density representing the number of point data indicating a three-dimensional position whose distance from the three-dimensional position represented by the point data is equal to or less than a threshold value for each of the point data included in the inspection point cloud data; The control method further detects, as the excluded portion, the portion where the magnitude of the difference between the first density and the second density is equal to or greater than a threshold value.

7. In the step of detecting an excluded portion, clustering the plurality of point data included in the reference point cloud data for each of the point data representing a location on the same object; The control method according to claim 6, further comprising identifying the point data included in the same cluster as the point data representing the moving object location, and detecting the moving object location and the location represented by the identified point data as the excluded location.

8. On the computer, an acquisition step of acquiring reference point cloud data indicating point data representing a three-dimensional position and brightness at a reference time for each of a plurality of locations in a space including the object, and inspection point cloud data indicating point data representing a three-dimensional position and brightness at an inspection time for each of the plurality of locations; a difference data generating step of generating difference point cloud data representing a difference in luminance between the reference time point and the inspection time point for each of the locations, using the reference point cloud data and the inspection point cloud data; an exclusion portion detection step of detecting, among the plurality of portions, a moving body portion, the position of which changes over time, as an exclusion portion to be excluded from detection targets for abnormal portions; an abnormality portion detection step of detecting an abnormal portion of the object at the time of inspection from the portions excluding the excluded portion among the plurality of portions by using the difference point cloud data; In the step of detecting an excluded portion, For each of the point data included in the reference point cloud data, a first density is calculated that represents the number of the point data indicating a three-dimensional position whose distance from the three-dimensional position represented by the point data is equal to or less than a threshold value; Calculating a second density representing the number of point data indicating a three-dimensional position whose distance from the three-dimensional position represented by the point data is equal to or less than a threshold value for each of the point data included in the inspection point cloud data; The program further detects, as the exclusion portion, the portion where the magnitude of the difference between the first density and the second density is equal to or greater than a threshold.

9. In the step of detecting an excluded portion, clustering the plurality of point data included in the reference point cloud data for each of the point data representing a location on the same object; The program according to claim 8 , further comprising: identifying the point data included in the same cluster as the point data representing the moving object location; and detecting the moving object location and the location represented by the identified point data as the excluded location.

Images