Obstacle proximity detection device, obstacle proximity detection method, and obstacle proximity detection program

Abstract

This obstacle proximity detection device comprises: an acquisition unit that successively acquires three-dimensional point cloud data representing an outdoor structure acquired by using a three-dimensional laser scanner; a specification unit that specifies first point cloud data representing a subject and second point cloud data representing an obstacle from the three-dimensional point cloud data; a setting unit that sets a first detection area that surrounds the first point cloud data, said area being set in advance by a user; a movement unit that, on the basis of a feature point extracted from the first point cloud data, moves the first point cloud data and the first detection area in accordance with movement of the feature point; and an output unit that, if the first detection area and part of a second detection area surrounding the second point cloud data overlap or if the number of data points in the first point cloud data that are present within the second detection area is equal to or greater than a prescribed threshold value, outputs an alert representing the proximity between the subject and the obstacle.

Description

[Technical Field]

[0001] The disclosed technology relates to an obstacle proximity detection device, an obstacle proximity detection method, and an obstacle proximity detection program. [Background technology]

[0002] Patent Document 1 discloses a three-dimensional space specifying device, method, and program for accurately specifying the three-dimensional space in which a detection target exists.

[0003] Furthermore, Patent Document 2 discloses an equipment status detection method, detection device, and program that enable easy and accurate comparison and confirmation of a three-dimensional model and the actual equipment status without requiring the skilled operator. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2018-97588 [Patent Document 2] Japanese Patent Application Publication No. 2018-195240 Summary of the Invention [Problem to be solved by the invention]

[0005] When carrying out construction work to erect a new utility pole, which is an example of an object, the utility pole is often moved during the construction work. In this case, it is undesirable for the moving utility pole to be in close proximity to other obstacles.

[0006] The technology disclosed in Patent Document 1 is a technology that detects facilities around a road by analyzing a point cloud made up of three-dimensional points contained in a three-dimensional space in which the facilities exist. Furthermore, the technology disclosed in Patent Document 2 is a technology that generates 3D model data of the facilities based on point cloud data of the facilities acquired by laser scanning, and calculates the thickness, inclination angle, and deflection of poles and trees, as well as the minimum ground clearance of cables, based on this 3D model data.

[0007] Therefore, even if the techniques disclosed in the above Patent Documents 1 and 2 are used, there is a problem in that it is not possible to detect in real time the proximity of a moving object to other obstacles.

[0008] The disclosed technology has been developed in consideration of the above points, and aims to provide an obstacle proximity detection device, an obstacle proximity detection method, and an obstacle proximity detection program that can detect the proximity of a moving object to other obstacles in real time. [Means for solving the problem]

[0009] A first aspect of the present disclosure is an obstacle proximity detection device comprising: an acquisition unit that sequentially acquires three-dimensional point cloud data representing an outdoor structure acquired by a three-dimensional laser scanner; an identification unit that identifies first point cloud data representing an object and second point cloud data representing an obstacle from the three-dimensional point cloud data; a setting unit that sets a first detection area that is an area pre-set by a user and that is an area surrounding the first point cloud data; a movement unit that moves the first point cloud data and the first detection area in accordance with movement of feature points extracted from the first point cloud data; and an output unit that outputs an alert indicating the proximity of the object and the obstacle when a part of the first detection area overlaps with a part of a second detection area that is an area surrounding the second point cloud data, or when the number of point data of the first point cloud data present in the second detection area becomes equal to or greater than a predetermined threshold.

[0010] A second aspect of the present disclosure is an obstacle proximity detection method, in which a computer executes the following process: sequentially acquiring three-dimensional point cloud data representing an outdoor structure obtained by a three-dimensional laser scanner; identifying first point cloud data representing an object and second point cloud data representing an obstacle from the three-dimensional point cloud data; setting a first detection area that is an area preset by a user and surrounding the first point cloud data; moving the first point cloud data and the first detection area in accordance with movement of feature points extracted from the first point cloud data; and outputting an alert indicating the proximity of the object and the obstacle when a part of the first detection area overlaps with a part of a second detection area that is an area surrounding the second point cloud data, or when the number of point data of the first point cloud data present in the second detection area becomes equal to or greater than a predetermined threshold.

[0011] A third aspect of the present disclosure is an obstacle proximity detection program that causes a computer to execute the following process: sequentially acquire three-dimensional point cloud data representing an outdoor structure obtained by a three-dimensional laser scanner; identify first point cloud data representing an object and second point cloud data representing an obstacle from the three-dimensional point cloud data; set a first detection area that is an area preset by a user and that is an area surrounding the first point cloud data; move the first point cloud data and the first detection area in accordance with movement of feature points extracted from the first point cloud data; and output an alert indicating the proximity of the object and the obstacle when a part of the first detection area overlaps with a part of a second detection area that is an area surrounding the second point cloud data, or when the number of point data of the first point cloud data present in the second detection area becomes equal to or greater than a predetermined threshold. [Effects of the Invention]

[0012] The disclosed technology has the advantage of being able to detect in real time the proximity of a moving object to another obstacle. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a block diagram showing an example of a hardware configuration of an obstacle proximity detection device according to an embodiment; [Figure 2] 1 is a block diagram showing an example of a functional configuration of an obstacle proximity detection device according to an embodiment; [Figure 3] FIG. 2 is a diagram illustrating the relationship between an obstacle proximity detection device and a three-dimensional laser scanner. [Figure 4] 3A and 3B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 5] 4A and 4B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 6] 4A and 4B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 7] 3A and 3B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 8] 4A and 4B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 9] 3A and 3B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 10] 4A and 4B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 11] 4A and 4B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 12] 4A and 4B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 13] 4A and 4B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 14] 4A and 4B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 15] 4A and 4B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 16] 3A and 3B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 17] 4A and 4B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 18] 4A and 4B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 19] 4A and 4B are diagrams for explaining the operation of the obstacle proximity detection device according to the embodiment; [Figure 20] FIG. 1 is a diagram for explaining a conventional technique. [Figure 21] FIG. 1 is a diagram for explaining a conventional technique. DETAILED DESCRIPTION OF THE INVENTION

[0014] An example of an embodiment of the disclosed technology will be described below with reference to the drawings. Note that in each drawing, the same or equivalent components and parts are given the same reference numerals. Also, the dimensional proportions in the drawings are exaggerated for the convenience of explanation and may differ from the actual proportions.

[0015] 20 and 21 are diagrams illustrating the prior art. As shown in FIG. 20, a technology for 3D modeling of outdoor structures using a vehicle-mounted 3D laser scanner (Mobile Mapping System: MMS) is known. FIG. 20 shows scan lines and 3D point cloud data acquired by the MMS. As shown in FIG. 20, the MMS creates scan lines and 3D point cloud data S1 in a space where no 3D point cloud data exists, for example, based on previously acquired scan lines and 3D point cloud data S2. Then, for example, the MMS generates a 3D model by integrating the 3D point cloud data. This allows for accurate generation of a 3D model even if the 3D point cloud data is rough. Therefore, for example, when a 3D laser scanner is mounted on a vehicle and the vehicle is traveling at a high speed, accurate generation of a 3D model of an outdoor structure around the vehicle is possible. For example, as a 3D model of an outdoor structure, a 3D model of a utility pole and a cable, as shown in FIG. 21, is generated.

[0016] When carrying out construction work to erect a new utility pole, which is an example of an object, the utility pole is often moved during the construction work. In this case, it is undesirable for the moved utility pole to be in close proximity to other obstacles.

[0017] However, the technology disclosed in Patent Document 1 requires time to create scan lines and generate 3D models, making it difficult to detect objects in real time.Furthermore, the technology disclosed in Patent Document 2 specifies a detection area in advance, and detects an object and its behavior only when a certain amount of 3D point cloud data has been acquired, making it difficult to accurately detect the proximity and contact of two objects.

[0018] Therefore, in this embodiment, the behavior of an object during construction work is monitored, and proximity or contact between an object being moved during construction work and other obstacles is detected in real time, and a notification is sent to construction workers.

[0019] First, the hardware configuration of an obstacle proximity detection device 10 according to this embodiment will be described with reference to FIG.

[0020] FIG. 1 is a block diagram showing an example of the hardware configuration of an obstacle proximity detection device 10 according to this embodiment.

[0021] 1, the obstacle proximity detection device 10 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a storage 14, an input unit 15, a display unit 16, and a communication interface (I / F) 17. Each component is connected to each other via a bus 18 so as to be able to communicate with each other.

[0022] The CPU 11 is a central processing unit that executes various programs and controls each component. That is, the CPU 11 reads programs from the ROM 12 or the storage 14 and executes the programs using the RAM 13 as a work area. The CPU 11 controls the above components and performs various arithmetic processing in accordance with the programs stored in the ROM 12 or the storage 14. In this embodiment, the ROM 12 or the storage 14 stores an obstacle proximity detection program.

[0023] The ROM 12 stores various programs and various data. The RAM 13 temporarily stores programs or data as a working area. The storage 14 is configured with an HDD (Hard Disk Drive) or SSD (Solid State Drive) and stores various programs including the operating system and various data.

[0024] The input unit 15 includes a pointing device such as a mouse and a keyboard, and is used to input various information to the device itself.

[0025] The display unit 16 is, for example, a liquid crystal display, and displays various information. The display unit 16 may also function as the input unit 15 by adopting a touch panel system.

[0026] The communication interface 17 is an interface for the device itself to communicate with other external devices. For this communication, a wired communication standard such as Ethernet (registered trademark) or FDDI (Fiber Distributed Data Interface) or a wireless communication standard such as 4G, 5G, or Wi-Fi (registered trademark) is used.

[0027] The obstacle proximity detection device 10 according to this embodiment is implemented by a general-purpose computer such as a server computer or a personal computer (PC).

[0028] Next, the functional configuration of the obstacle proximity detection device 10 will be described with reference to FIG.

[0029] FIG. 2 is a block diagram showing an example of the functional configuration of the obstacle proximity detection device 10 according to this embodiment.

[0030] 2, the obstacle proximity detection device 10 includes, as functional components, a data storage unit 100, an acquisition unit 102, an identification unit 104, a setting unit 106, a movement unit 108, and an output unit 110. Each functional component is realized by the CPU 11 reading out an obstacle proximity detection program stored in the ROM 12 or the storage 14, expanding the program in the RAM 13, and executing the program.

[0031] 3 is a diagram showing the relationship between the obstacle proximity detection device 10 and the 3D laser scanner 20. As shown in FIG. 3, with the position of the 3D laser scanner 20 as the reference, the east-west direction is the x-axis, the north-south direction is the y-axis, and altitude is the z-axis. The 3D laser scanner 20 sequentially acquires 3D point cloud data of outdoor structures and outputs the 3D point cloud data to the obstacle proximity detection device 10. The obstacle proximity detection device 10 sequentially acquires the 3D point cloud data acquired by the 3D laser scanner 20 and stores it in its own data storage unit 100.

[0032] The data storage unit 100 sequentially stores three-dimensional point cloud data representing outdoor structures acquired by the three-dimensional laser scanner 20. The data storage unit 100 also stores various data necessary for executing the obstacle proximity detection process.

[0033] Next, the operation of the obstacle proximity detection device 10 according to this embodiment will be described with reference to FIGS.

[0034] 4 is a flowchart showing an example of the processing flow of the obstacle proximity detection program according to this embodiment. The processing of the obstacle proximity detection program is realized by the CPU 11 of the obstacle proximity detection device 10 writing the obstacle proximity detection program stored in the ROM 12 or the storage 14 to the RAM 13 and executing it.

[0035] In this embodiment, an example will be described in which, during construction work to erect a new utility pole, which is an example of an object, a 3D laser scanner 20 sequentially acquires 3D point cloud data of outdoor structures including the new utility pole, and an obstacle proximity detection device 10 detects the proximity of the utility pole to an obstacle.

[0036] First, during construction work to erect a new utility pole, 3D laser scanner 20 sequentially acquires 3D point cloud data of outdoor structures including the new utility pole, and outputs the data to obstacle proximity detection device 10. Then, obstacle proximity detection device 10 sequentially stores the 3D point cloud data in data storage unit 100. When the 3D point cloud data starts to be stored in data storage unit 100, obstacle proximity detection device 10 executes the processing of FIG.

[0037] First, in step S100 of Fig. 4, the CPU 11 executes a utility pole point cloud identification process to identify three-dimensional point cloud data of a new utility pole from the three-dimensional point cloud data stored in the data storage unit 100. The utility pole point cloud identification process is realized by Fig. 5 or Fig. 6.

[0038] In step S102 of FIG. 5, the CPU 11 functions as the acquisition unit 102 to acquire the three-dimensional point cloud data stored in the data storage unit 100.

[0039] In step S104, the CPU 11, functioning as the identification unit 104, deletes 3D point cloud data in an unnecessary range from the 3D point cloud data acquired in step S102. For example, 3D point cloud data that is a certain distance or more from the measurement point where the 3D laser scanner 20 is located is deleted as data in an unnecessary range.

[0040] In step S106, the CPU 11, as the specifying unit 104, acquires an angle a for dividing the three-dimensional point cloud data and the angle θ of the utility pole. Note that the angle θ of the utility pole is input to the obstacle proximity detection device 10 manually, for example, by an operator at the construction site. This angle θ is the angle formed between the z-axis on the xyz coordinates shown in FIG. 3 and the utility pole P. When the object is a utility pole under construction, states such as the utility pole being placed on the ground, the utility pole being gripped and suspended by a heavy machine, and the utility pole standing independently are assumed, and the direction and angle in which the utility pole is facing change depending on the situation. Therefore, it is necessary to acquire the angle θ based on the three-dimensional laser scanner 20 in advance. The process of FIG. 5 is the process when the angle θ is determined by the operator and input to the obstacle proximity detection device 10. It is also possible to calculate the angle θ using known techniques by the user inputting in advance to the obstacle proximity detection device 10 the distances from the three-dimensional laser scanner 20 to the lower and upper parts of the utility pole. Although the angle θ of the utility pole can be acquired as described above, the direction in which the utility pole is tilted cannot be calculated. For this reason, as will be described later, by rotating each of the data obtained by dividing the three-dimensional point cloud data at regular intervals by the angle θ, it is possible to identify the utility pole without calculating the direction in which the utility pole is tilted. When identifying the three-dimensional point cloud data representing the utility pole, a threshold value may be set for the distance from the three-dimensional laser scanner 20 and the size of the extracted point cloud, etc., and the three-dimensional point cloud data representing the utility pole may be identified based on this.

[0041] In step S108, the CPU 11, as the specifying unit 104, divides the three-dimensional point cloud data according to the angle a (0 < a < 360) acquired in step S106.

[0042] [[ID=k7]] FIG. 7 illustrates the division of 3D point cloud data according to angle a. As shown on the left side of FIG. 7, the 3D point cloud data within a predetermined region R is divided according to angle a on the xy plane of the xyz coordinate system. P in FIG. 7 represents 3D point cloud data corresponding to a utility pole under construction. FIG. 7 illustrates a case where angle a=45 degrees. Data i divided for each angle a is an index for identifying data within the predetermined region R, and satisfies 1≦j≦360 / a. For example, data within predetermined region R3 corresponds to data with i=3. In the example shown on the left side of FIG. 7, the 3D point cloud data within predetermined region R is divided into eight regions R1 to R8. In the following process, each of these regions R1 to R8 is rotated by the angle θ of the utility pole so that the 3D point cloud data corresponding to the utility pole is aligned with the z-axis. This allows a determination to be made as to whether the 3D point cloud data represents a utility pole.

[0043] For example, as shown on the right side of Figure 7, the 3D point cloud data within a predetermined region R3 is rotated by an angle θ, starting from the origin of the xyz coordinate system. In this case, the utility pole P will be shaped along the z-axis. In this case, consider the case where the 3D point cloud data of the utility pole P shaped along the z-axis is projected onto the xy plane.

[0044] FIG. 8 is a diagram illustrating the processing of 3D point cloud data according to this embodiment. Note that the black circles in FIG. 8 represent 3D point data. As described above, when the 3D point cloud data of utility pole P shaped along the z axis is projected onto the xy plane, the projection result of the 3D point cloud data onto the xy plane becomes a circle, as shown in A1 of FIG. 8. Therefore, in this embodiment, whether or not the 3D point cloud data represents a utility pole is determined depending on whether or not the projection result onto the xy plane obtained in this manner is a circle.

[0045] Furthermore, in this embodiment, as shown in B1 of Fig. 8, the 3D point cloud data is divided into groups G that intersect with the z-axis, and it is determined whether a circular shape is detected for each group G (hereinafter, simply referred to as "circle detection"). Note that B1 of Fig. 8 also depicts a heavy machine M gripping a utility pole P. Furthermore, for detecting circular shapes and linear shapes, for example, well-known RANSAC processing or the like is used.

[0046] In addition, in this embodiment, as shown in C1 of Figure 8, when determining the three-dimensional point cloud data corresponding to a cable Ca existing between existing utility poles, the three-dimensional point cloud data is projected onto a specified plane, and whether the projection result is a circular shape is used to determine whether the three-dimensional point cloud data is a cable.

[0047] As shown on the right side of Figure 7, when the data of the predetermined region R3 is rotated by an angle θ, a circular shape is detected in the projection result, and the data of the predetermined region R3 is identified as a utility pole point cloud. On the other hand, when the data of the predetermined region R7 is rotated by an angle θ, a circular shape is not detected in the projection result, and the data of the predetermined region R7 is identified as not being a utility pole point cloud. Even in this case, since the data of the predetermined region R7 partially includes a utility pole, for example, the data of the predetermined region R7 located diagonally from the data of the predetermined region R3 may also be identified as a utility pole point cloud. Note that circle detection may be performed on all axes of the 3D point cloud data without using the angle θ of the utility pole.

[0048] Specifically, in step S110 of FIG. 5, the CPU 11, as the specifying unit 104, sets data of one predetermined region (for example, data of the predetermined region R1) of the divided three-dimensional point cloud data.

[0049] In step S112, the CPU 11, functioning as the identification unit 104, rotates the data of the predetermined region set in step S110 by an angle θ. If the data of the predetermined region is three-dimensional point cloud data of a utility pole, the data of the predetermined region after rotation will be oriented along the z-axis. In step S114, the CPU 11, functioning as the identification unit 104, divides the data of the predetermined region rotated in step S112 in regions intersecting with the z-axis direction to generate a plurality of groups.

[0050] In step S116, the CPU 11, functioning as the identification unit 104, projects the three-dimensional point cloud data belonging to each of the groups generated in step S114 onto the xy plane.

[0051] In step S118, the CPU 11, functioning as the identification unit 104, detects a circular shape based on the projection results for each group obtained in step S116.

[0052] In step S120, the CPU 11, functioning as the identification unit 104, determines whether or not there are a predetermined threshold or more groups in which circles have been detected. If there are a predetermined threshold or more groups in which circles have been detected, the process proceeds to step S122. On the other hand, if there are fewer groups in which circles have been detected than the predetermined threshold, the process proceeds to step S124.

[0053] In step S122, the CPU 11, functioning as the specifying unit 104, temporarily stores the data of the predetermined area set in step S110 in the data storage unit 100 as a utility pole candidate point cloud.

[0054] In step S124, the CPU 11, functioning as the identification unit 104, determines whether or not the processes of steps S110 to S122 have been executed for the data of all the predetermined areas divided in step S108. If the processes of steps S110 to S122 have been executed for the data of all the predetermined areas, the process proceeds to step S126. If there is data of a predetermined area for which the processes of steps S110 to S122 have not been executed, the process returns to step S110.

[0055] In step S126, the CPU 11 as the identifying unit 104 identifies the utility pole P by taking the data of the predetermined area in which the number of circular shapes detected is the largest as utility pole point cloud data, which is an example of first point cloud data.

[0056] It should be noted that the utility pole point cloud identification process in step S100 in Fig. 4 is not limited to the process in Fig. 5, and may be realized, for example, by the process in Fig. 6. The process in Fig. 6 identifies utility pole point cloud data without requiring input of the angle θ between the z axis on the xyz coordinate system and the utility pole P.

[0057] Specifically, in step S128, the CPU 11, functioning as the identification unit 104, executes an existing feature point analysis algorithm on the 3D point cloud data to identify a feature point cloud cluster from the 3D point cloud data. A feature point cloud cluster is, for example, a cluster of points of an object in the 3D point cloud data that has characteristics such as high reflection intensity or a unique shape. For example, the feature point cloud cluster can be used to identify a scaffolding bolt or a heavy equipment gripper attached to or near a utility pole. Or, for example, the feature point cloud cluster can be used to identify both ends of a utility pole.

[0058] For this reason, in step S128 of FIG. 6, the CPU 11, functioning as the identification unit 104, generates an axis by connecting the two feature point group clusters identified as both ends of the utility pole.

[0059] Next, in step S130, the CPU 11, functioning as the specifying unit 104, rotates the three-dimensional point cloud data so that the axis generated in step S128 is aligned with the z-axis.

[0060] Then, in step S132, the CPU 11, functioning as the specifying unit 104, divides the rotated three-dimensional point cloud data in areas that intersect with the z-axis direction to generate a plurality of groups.

[0061] Other processes shown in Fig. 6 are the same as those in Fig. 5, and therefore description thereof will be omitted. Note that utility pole point cloud data may be specified using both the processes in Fig. 5 and Fig. 6.

[0062] In this way, utility pole point cloud data, which is an example of first point cloud data, is identified from the 3D point cloud data. Note that utility pole point cloud data may be identified using methods different from those shown in FIGS. 5 and 6. For example, an object made of a highly reflective material or structure may be attached to a utility pole or heavy equipment. Or, an object with a unique shape may be attached to a utility pole or heavy equipment. The axis of the utility pole is then calculated based on the positions of the objects in the 3D point cloud data. More specifically, for example, two highly reflective objects may be attached to the grip of the heavy equipment. Then, for example, the objects may be extracted from the 3D point cloud data, and the axis connecting the two objects may be used as the utility pole axis, and circle detection may be performed to identify the utility pole point cloud data. Utility pole point cloud data may also be identified by performing circle detection on all axes of the 3D point cloud data without using the utility pole angle θ.

[0063] Next, in step S200 of Fig. 4, the CPU 11 executes a wall surface point cloud identification process to identify 3D point cloud data of a wall surface, which is an example of an obstacle, from the 3D point cloud data. The wall surface point cloud identification process is realized by Fig. 9.

[0064] In step S202 of FIG. 9, the CPU 11, functioning as the specifying unit 104, divides the input three-dimensional point cloud data in areas that intersect with the z-axis direction to generate a plurality of groups.

[0065] In step S204, the CPU 11, functioning as the identification unit 104, projects the three-dimensional point cloud data belonging to each of the groups generated in step S202 onto the xy plane.

[0066] In step S206, the CPU 11, functioning as the identification unit 104, detects a linear shape based on the projection results for each group obtained in step S204.

[0067] In step S208, the CPU 11, functioning as the identification unit 104, determines whether or not there are a predetermined threshold or more groups in which a linear shape has been detected. If there are a predetermined threshold or more groups in which a linear shape has been detected, the process proceeds to step S210. On the other hand, if there are fewer groups in which a linear shape has been detected than the predetermined threshold, the process ends.

[0068] In step S210, the CPU 11, functioning as the identification unit 104, stores the input three-dimensional point cloud data in the data storage unit 100 as wall surface point cloud data, which is an example of second point cloud data.

[0069] Next, in step S300 of Fig. 4, the CPU 11 executes a cable point cloud identification process to identify 3D point cloud data of a cable, which is an example of an obstacle, from the 3D point cloud data. The cable point cloud identification process is realized by Fig. 10.

[0070] In step S302 of FIG. 10, the CPU 11 functions as the specifying unit 104 and acquires the angle b for dividing the input three-dimensional point cloud data of the target.

[0071] In step S304, the CPU 11, functioning as the identification unit 104, divides the three-dimensional point cloud data according to the angle b acquired in step S302.

[0072] FIG. 11 is a diagram illustrating the division of 3D point cloud data according to angle b. As shown on the left side of FIG. 11, the 3D point cloud data within a predetermined region R is divided according to angle b on the xy plane of the xyz coordinate system. Ca in FIG. 11 is 3D point cloud data corresponding to an existing cable. Note that FIG. 11 illustrates a case where angle b=45 degrees. In the example shown on the left side of FIG. 11, the 3D point cloud data within the predetermined region R is divided into eight predetermined regions R1 to R8. In the following processing, each of these predetermined regions R1 to R8 is rotated by angle b around the z axis so that the 3D point cloud data corresponding to the cable is aligned with the x axis. This allows a determination to be made as to whether the 3D point cloud data is a cable.

[0073] For example, as shown on the right side of Figure 11, the 3D point cloud data within the predetermined region R3 is rotated around the z-axis by an angle (b*jb / 2). Note that j is an index for identifying the data within the predetermined region R, and satisfies 1≦j≦360 / b. For example, the data within the predetermined region R3 corresponds to data with j=3. Therefore, the 3D point cloud data within the predetermined region R3 is rotated by (45*3-45 / 2)=112.5 degrees, and is aligned with the x-axis.

[0074] Then, the three-dimensional point cloud data within the rotated predetermined region R3 is projected onto the yz plane, and depending on whether the projection results in a circular shape, it is determined whether the three-dimensional point cloud data represents a cable.

[0075] Specifically, in step S306, the CPU 11, functioning as the specifying unit 104, sets data of one predetermined region (for example, data of the predetermined region R1) of the divided three-dimensional point cloud data.

[0076] In step S308, the CPU 11, functioning as the identification unit 104, rotates the data of the predetermined region set in step S306 around the z-axis by an angle (b*jb / 2). If the data of the predetermined region is three-dimensional point cloud data of the cable Ca, the data of the predetermined region after rotation will be oriented along the x-axis.

[0077] In step S310, the CPU 11, functioning as the identification unit 104, divides the data of the predetermined region rotated in step S308 in regions intersecting with the x-axis direction to generate a plurality of groups.

[0078] In step S312, the CPU 11, functioning as the identification unit 104, projects, for each of the groups generated in step S310, the three-dimensional point cloud data belonging to that group onto the yz plane.

[0079] In step S314, the CPU 11, functioning as the identification unit 104, detects a circular shape based on the projection results for each group obtained in step S312.

[0080] In step S316, the CPU 11, functioning as the identification unit 104, determines whether or not the number of groups in which circles have been detected is equal to or greater than a predetermined threshold. If the number of groups in which circles have been detected is equal to or greater than the predetermined threshold, the process proceeds to step S318. On the other hand, if the number of groups in which circles have been detected is less than the predetermined threshold, the process proceeds to step S320.

[0081] In step S318, the CPU 11, functioning as the identification unit 104, temporarily stores the data of the predetermined area set in step S306 in the data storage unit 100 as a cable candidate point group.

[0082] In step S320, CPU 11, functioning as identification unit 104, determines whether the processes of steps S306 to S318 have been executed for all of the data in the predetermined area divided in step S304. If the processes of steps S306 to S318 have been executed for all of the data in the predetermined area, the process proceeds to step S322. If there is data in the predetermined area for which the processes of steps S306 to S318 have not been executed, the process returns to step S306.

[0083] In step S322, the CPU 11, as the identification unit 104, identifies the cable by determining that the data of the predetermined area in which the number of circular shapes was greatest is a cable point cloud, which is an example of second point cloud data. In this way, when identifying cable point cloud data, circles are detected parallel to the ground, and when identifying wall point cloud data, straight lines are detected perpendicular to the ground. Note that, although the above description has been given using an example in which utility pole point cloud data, wall point cloud data, and cable point cloud data are automatically identified, for example, utility pole point cloud data, wall point cloud data, cable point cloud data, etc. may be manually extracted by a user and labeled to identify each piece of data.

[0084] Next, in step S400 of Fig. 4, the CPU 11 executes a utility pole detection area setting process for setting a utility pole detection area, which is an example of a first detection area, for the utility pole point cloud data. The utility pole detection area setting process is realized by Fig. 12 or Fig. 13. In the process of Fig. 12, a utility pole detection area is set by a user such as a worker at a construction site.

[0085] 12, the CPU 11, functioning as the setting unit 106, acquires data of any two points set in advance by the user. The data of these two points is three-dimensional point data included in the utility pole point cloud data. Then, the CPU 11, functioning as the setting unit 106, sets the data of the any two points in the utility pole point cloud data.

[0086] In step S404, the CPU 11, functioning as the setting unit 106, sets the vertices of a quadrangle based on the data of the two points set in step S402.

[0087] In step S406, the CPU 11, functioning as the setting unit 106, sets a utility pole detection area, which is an area surrounding the utility pole point cloud data, based on the vertices of the quadrangle set in step S404.

[0088] A diagram for explaining the setting of a utility pole detection area is shown in Fig. 14. As shown in A2 of Fig. 14, when the circle of the utility pole is viewed from above, if any two points of the utility pole point cloud data are set by the user, the vertices of the utility pole detection area are set, for example, at the positions of the vector from those two points expressed by the following formula:

[0089]

number

[0090] In A2 of Fig. 14, for example, four vertices corresponding to four vectors w1, w2, w3, and w4 of the utility pole detection area are set in a certain direction and position from two endpoints of a circle, and a quadrangle D1 corresponding to those four vertices is set. Then, as shown in A2 of Fig. 14, lines of any length (in the depth direction and forward direction in A2 of Fig. 14) are set from the four vertices of quadrangle D1 so as to be perpendicular to the circle, thereby setting a cube D2 as shown in B2 of Fig. 14 as the utility pole detection area.

[0091] Alternatively, arbitrary vertices may be set at the top and bottom of the utility pole point cloud data based on feature points, and points that are connected along the axis of the cylindrical object represented by the utility pole point cloud data may be connected to form a utility pole detection area.

[0092] By setting the utility pole detection area using the method described above, it becomes possible to automatically track the utility pole point cloud data and the utility pole detection area even if the direction of the circle forming the utility pole point cloud data changes. Note that, although the above description has been given using an example in which the user sets two points of data, the user may also set each detection area (the utility pole detection area, the cable detection area and the wall detection area described below) using a different method.

[0093] Furthermore, as shown in C2 of Fig. 14, a cable detection area can also be set for cable point cloud data representing cable Ca using a method similar to the method described above. C2 of Fig. 14 shows a case where the straight line portion representing an obstacle is cable Ca, but the straight line portion representing an obstacle may also be a wall as seen from above. In this case, as described above, wall surface point cloud data is identified by performing line detection, and a wall surface detection area is set for that wall surface point cloud data. Note that, as described above, when identifying cable point cloud data, circle detection is performed parallel to the ground, but cable point cloud data may also be identified by performing line detection in the same way as when identifying wall surface point cloud data.

[0094] On the other hand, in the process of FIG. 13, a utility pole detection area is automatically set. Specifically, in the process of FIG. 13, a feature point group is extracted from the utility pole point cloud data, a predetermined height and a predetermined width are set for the feature points included in the feature point group, and the area is set as the utility pole detection area. Feature points extracted from such 3D point cloud data (e.g., scaffolding bolts, suspension ropes, heavy equipment grips, or the outer edge of utility poles) are rarely in blind spots even during construction work, making tracking in the tracking process described below relatively easy. Furthermore, when this method is adopted, it may be sufficient to track only the feature points, thereby reducing calculation time. In this case, it is considered necessary to acquire 3D point cloud data of the outer shapes of all utility poles in order to perfectly track the utility pole point cloud data during construction.

[0095] In step S408 of FIG. 13, the CPU 11, functioning as the setting unit 106, extracts feature point group data, which is a plurality of feature points, from the utility pole point group data.

[0096] In step S410, the CPU 11, as the setting unit 106, selects two feature points (for example, feature points representing the outer edge of the utility pole) from the feature point group data extracted in step S408, and sets the vertices of a rectangle from the two feature points.

[0097] In step S412, the CPU 11, functioning as the setting unit 106, sets a utility pole detection area, which is an area surrounding the utility pole point cloud data, based on the vertices of the quadrangle set in step S410.

[0098] Next, in step S500 of Fig. 4, the CPU 11 executes a wall surface detection area setting process to set a wall surface detection area, which is an example of the second detection area, for the wall surface point cloud data, which is the second point cloud data. The wall surface detection area setting process is realized by Fig. 15.

[0099] 15, the CPU 11, functioning as the setting unit 106, selects any two points of data from the wall surface point cloud data. Note that the selection of these two points of data may be performed by the user.

[0100] In step S504, the CPU 11, functioning as the setting unit 106, sets the vertices of a quadrangle based on the data of the two points set in step S502.

[0101] In step S506, the CPU 11, functioning as the setting unit 106, sets a wall detection area, which is an area surrounding the wall point cloud data, based on the vertices of the quadrangle set in step S504.

[0102] Next, in step S600 of Fig. 4, the CPU 11 executes a cable detection area setting process to set a cable detection area, which is an example of the second detection area, for the cable point cloud data, which is the second point cloud data. The cable detection area setting process is realized by Fig. 16.

[0103] 16, the CPU 11, functioning as the setting unit 106, selects any two points of data from the cable point cloud data. Note that the selection of these two points of data may be performed by the user.

[0104] In step S604, the CPU 11, functioning as the setting unit 106, sets the vertices of a quadrangle based on the data of the two points set in step S602.

[0105] In step S606, the CPU 11, functioning as the setting unit 106, sets a cable detection area, which is an area surrounding the cable point cloud data, based on the vertices of the quadrangle set in step S604.

[0106] The wall surface detection area setting process in FIG. 15 and the cable detection process in FIG. 16 may be performed in the same manner as the utility pole detection area setting process in FIG. 12 or FIG.

[0107] Next, in step S700 of Fig. 4, the CPU 11 executes a tracking process to track utility pole point cloud data and output an alert when a predetermined condition is satisfied. The tracking process is realized by Fig. 17 or 18.

[0108] A diagram for explaining the alert output process is shown in Fig. 19. For example, as shown in Fig. 19, when utility pole detection area D2 moves and utility pole detection area D2 overlaps with cable detection area D3, an alert indicating the proximity of a utility pole and a cable is output.

[0109] In step S702 of FIG. 17, the CPU 11, functioning as the moving unit 108, extracts a plurality of feature points from the utility pole point cloud data.

[0110] In step S704, the CPU 11, functioning as the movement unit 108, moves the utility pole point cloud data in accordance with the movement of the plurality of feature points extracted in step S702, thereby realizing tracking of the utility pole point cloud data.

[0111] In step S706, the CPU 11, functioning as the movement unit 108, resets the utility pole detection area in accordance with the utility pole point cloud data moved in step S704. As a result, the utility pole detection area also moves in accordance with the movement of the utility pole point cloud data.

[0112] In step S708, the CPU 11, as the output unit 110, determines whether the utility pole detection area and the obstacle area (representing at least one of the cable detection area and the wall detection area) overlap. If the utility pole detection area and the obstacle area overlap, the process proceeds to step S710. If the utility pole detection area and the obstacle area do not overlap, the process returns to step S704.

[0113] In step S708, the CPU 11 may function as the output unit 110 to proceed to step S710 if the size of the volume of the overlapping utility pole detection area and obstacle detection area exceeds a threshold value.

[0114] In step S710, the CPU 11 outputs an alert indicating the proximity of a utility pole to a wall or a cable as the output unit 110. The alert output from the output unit 110 is output in a form that can be recognized by the user (for example, sound or display) by a sound output device (not shown) or a display device (not shown).

[0115] The alert output process may be realized by the process of FIG.

[0116] In step S712 of Fig. 18, the CPU 11, as the output unit 110, determines whether the number of 3D point cloud data of utility pole point cloud data that has infiltrated into the cable detection area or wall surface detection area is equal to or greater than a threshold. If the number of 3D point cloud data of utility pole point cloud data that has infiltrated into the cable detection area or wall surface detection area is equal to or greater than the threshold, the process proceeds to step S710. If the number of 3D point cloud data of utility pole point cloud data that has infiltrated into the cable detection area or wall surface detection area is less than the threshold, the process returns to step S704. In this case, it is not necessary to set a utility pole detection area. This is because it is known which point cloud data within the 3D point cloud data is utility pole point cloud data by tracking the utility pole point cloud data.

[0117] When workers at the construction site see the alert, they can, for example, stop heavy machinery moving a utility pole.

[0118] In the alert output process of Figures 17 and 18, feature points (for example, scaffolding bolts, suspension ropes, or heavy equipment grips) are extracted from the utility pole point cloud data, and the utility pole point cloud data is tracked by tracking these feature points. Scaffolding bolts are cylindrical objects with several straight lines emerging from them. Furthermore, suspension ropes and heavy equipment grips are cylindrical objects with a shape where the diameter of the object is larger in some places. Therefore, by extracting these parts as feature points, it becomes possible to track the utility pole point cloud data. Furthermore, by maintaining the positional relationship between these feature points and the initially set endpoints and vertices, the utility pole detection area can also be moved at the same time. Specifically, by identifying the position of the circle included in the utility pole point cloud data while tracking the feature points, it becomes possible to maintain the initially defined positional relationship. When redefining a vertex, the vector w n is automatically corrected according to the position of the circle. As a method for tracking feature points, known methods for calculating feature amounts, such as SHOT, PCL, or Spinimage, can be used.

[0119] In this embodiment, objects other than utility poles (for example, cables or wall surfaces) are considered stationary objects and are not tracked. For objects other than utility poles (for example, cables or wall surfaces), the initially set obstacle detection area is used. In this way, by focusing on the feature values ​​during construction work and performing tracking, it is possible to reset the detection area with high accuracy. Furthermore, in the alert output process of FIG. 18, since the utility pole detection area is not fixed, it can also be set for moving objects, allowing for highly flexible sensing.

[0120] As described above, the obstacle proximity detection device sequentially acquires 3D point cloud data representing outdoor structures acquired by a 3D laser scanner. The obstacle proximity detection device then identifies, from the 3D point cloud data, first point cloud data representing a utility pole under construction, which is an example of an object, and second point cloud data representing a cable or wall, which is an example of an obstacle. The obstacle proximity detection device sets a first detection area, which is an area preset by a user and surrounding the first point cloud data. The obstacle proximity detection device moves the first point cloud data and the first detection area in accordance with the movement of feature points extracted from the first point cloud data. The obstacle proximity detection device outputs an alert indicating the proximity of the utility pole under construction to the cable or wall when a portion of the first detection area overlaps with a portion of the second detection area, which is the area surrounding the second point cloud data, or when the number of point data points of the first point cloud data present in the second detection area exceeds a predetermined threshold. This allows the proximity of a moving object to other obstacles to be detected in real time. Specifically, the conventional technology disclosed in Patent Document 1 lacks real-time capabilities, while the technology disclosed in Patent Document 2 has the drawback of requiring the acquisition of a sufficient number of 3D point data sets to detect an object within a predefined detection area. Specifically, the technology disclosed in Patent Document 2 requires a predefined detection area and detects an object only when a certain amount of 3D point cloud data has been acquired. In contrast, the obstacle proximity detection device of this embodiment enables highly accurate real-time sensing by identifying utility pole point cloud data and then moving the utility pole detection area. Furthermore, by tracking utility poles while they are being constructed, it becomes possible to accurately reconfigure the utility pole detection area. Furthermore, since it is possible to set a detection area for moving objects such as utility poles under construction, it enables highly flexible sensing. Furthermore, because predefined 3D point cloud data is tracked, it is possible to determine, for example, whether utility pole point cloud data has entered a cable detection area or a wall detection area.

[0121] In the above embodiment, the obstacle proximity detection process executed by the CPU 11 after reading the obstacle proximity detection program may be executed by various processors other than the CPU 11. Examples of such processors include dedicated electrical circuits, such as programmable logic devices (PLDs) (such as field-programmable gate arrays (FPGAs)) whose circuit configuration can be changed after manufacture, and application-specific integrated circuits (ASICs) that are processors having circuit configurations specifically designed to execute specific processes. The obstacle proximity detection process may be executed by one of these various processors, or by a combination of two or more processors of the same or different types (e.g., multiple FPGAs, or a combination of a CPU and an FPGA). The hardware structure of these various processors is, more specifically, an electrical circuit that combines circuit elements such as semiconductor devices.

[0122] In the above embodiment, the obstacle proximity detection program is described as being pre-stored (also referred to as "installed") in the ROM 12 or the storage 14, but the present invention is not limited to this. The obstacle proximity detection program may be provided in a form stored in a non-transitory storage medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), or a USB (Universal Serial Bus) memory. The obstacle proximity detection program may also be downloaded from an external device via a network.

[0123] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0124] The following additional notes are provided regarding the above-described embodiments.

[0125] (Additional note 1) Memory and at least one processor coupled to said memory; Including, The processor: Sequentially acquire 3D point cloud data representing outdoor structures acquired by a 3D laser scanner; Identifying first point cloud data representing an object and second point cloud data representing an obstacle from the three-dimensional point cloud data; setting a first detection area, which is an area preset by a user and is an area surrounding the first point cloud data; based on feature points extracted from the first point cloud data, moving the first point cloud data and the first detection area in accordance with movement of the feature points; outputting an alert indicating the proximity of the object and the obstacle when a part of the first detection area overlaps with a part of a second detection area that is a surrounding area of ​​the second point cloud data, or when the number of point data of the first point cloud data present in the second detection area becomes equal to or greater than a predetermined threshold; An obstacle proximity detection device configured as follows.

[0126] (Additional note 2) A non-transitory storage medium storing a program executable by a computer to perform an obstacle proximity detection process, The obstacle proximity detection process includes: Sequentially acquire 3D point cloud data representing outdoor structures acquired by a 3D laser scanner; Identifying first point cloud data representing an object and second point cloud data representing an obstacle from the three-dimensional point cloud data; setting a first detection area, which is an area preset by a user and is an area surrounding the first point cloud data; based on feature points extracted from the first point cloud data, moving the first point cloud data and the first detection area in accordance with movement of the feature points; outputting an alert indicating the proximity of the object and the obstacle when a part of the first detection area overlaps with a part of a second detection area that is a surrounding area of ​​the second point cloud data, or when the number of point data of the first point cloud data present in the second detection area becomes equal to or greater than a predetermined threshold; Non-transitory storage medium. [Explanation of symbols]

[0127] 10. Obstacle proximity detection device 20 3D laser scanner 100 Data storage unit 102 Acquisition Department 104 Specific part 106 Setting section 108 Mobile Unit 110 Output section

Claims

1. an acquisition unit that sequentially acquires three-dimensional point cloud data representing an outdoor structure acquired by a three-dimensional laser scanner; an identification unit that identifies first point cloud data representing an object and second point cloud data representing an obstacle from the three-dimensional point cloud data; a setting unit that sets a first detection area, which is an area set in advance by a user and is an area surrounding the first point cloud data; a moving unit that moves the first point cloud data and the first detection area in accordance with movement of feature points extracted from the first point cloud data; an output unit that outputs an alert indicating the proximity of the object and the obstacle when a part of the first detection area overlaps with a part of a second detection area that is a surrounding area of ​​the second point cloud data, or when the number of point data of the first point cloud data present in the second detection area becomes equal to or greater than a predetermined threshold; Equipped with When identifying the first point cloud data, the identification unit rotates data of a predetermined region included in the three-dimensional point cloud data by a predetermined angle with respect to an xy plane, projects the rotated data of the predetermined region onto the xy plane, and, if the data of the predetermined region projected onto the xy plane is circular, identifies the data of the predetermined region as the first point cloud data. Obstacle proximity detection device.

2. an acquisition unit that sequentially acquires three-dimensional point cloud data representing an outdoor structure acquired by a three-dimensional laser scanner; an identification unit that identifies first point cloud data representing an object and second point cloud data representing an obstacle from the three-dimensional point cloud data; a setting unit that sets a first detection area, which is an area set in advance by a user and is an area surrounding the first point cloud data; a moving unit that moves the first point cloud data and the first detection area in accordance with movement of feature points extracted from the first point cloud data; an output unit that outputs an alert indicating the proximity of the object and the obstacle when a part of the first detection area overlaps with a part of a second detection area that is a surrounding area of ​​the second point cloud data, or when the number of point data of the first point cloud data present in the second detection area becomes equal to or greater than a predetermined threshold; Equipped with The object is a utility pole under construction, The obstacle is a cable existing between existing utility poles, When identifying the second point cloud data representing the cable, the identification unit rotates data of a predetermined region included in the three-dimensional point cloud data by a predetermined angle around the z-axis, projects the rotated data of the predetermined region onto a yz-plane, and, if the data of the predetermined region projected onto the yz-plane is circular, identifies the data of the predetermined region as the second point cloud data representing the cable. Obstacle proximity detection device.

3. an acquisition unit that sequentially acquires three-dimensional point cloud data representing an outdoor structure acquired by a three-dimensional laser scanner; an identification unit that identifies first point cloud data representing an object and second point cloud data representing an obstacle from the three-dimensional point cloud data; a setting unit that sets a first detection area, which is an area set in advance by a user and is an area surrounding the first point cloud data; a moving unit that moves the first point cloud data and the first detection area in accordance with movement of feature points extracted from the first point cloud data; an output unit that outputs an alert indicating the proximity of the object and the obstacle when a part of the first detection area overlaps with a part of a second detection area that is a surrounding area of ​​the second point cloud data, or when the number of point data of the first point cloud data present in the second detection area becomes equal to or greater than a predetermined threshold; Equipped with The object is a utility pole under construction, the obstacle is a wall surface, When identifying the second point cloud data representing the wall surface, the identification unit projects data of a predetermined region included in the three-dimensional point cloud data onto an xy plane, and, if the data of the predetermined region projected onto the xy plane has a linear shape, identifies the data of the predetermined region as the second point cloud data representing the wall surface. Obstacle proximity detection device.

4. The object is a utility pole under construction, The obstacle is a cable or a wall existing between existing utility poles. The obstacle proximity detection device according to claim 1 .

5. Sequentially acquiring three-dimensional point cloud data representing outdoor structures acquired by a three-dimensional laser scanner; Identifying first point cloud data representing an object and second point cloud data representing an obstacle from the three-dimensional point cloud data; setting a first detection area, which is an area preset by a user and is an area surrounding the first point cloud data; based on feature points extracted from the first point cloud data, moving the first point cloud data and the first detection area in accordance with movement of the feature points; outputting an alert indicating the proximity of the object and the obstacle when a part of the first detection area overlaps with a part of a second detection area that is a surrounding area of ​​the second point cloud data, or when the number of point data of the first point cloud data present in the second detection area becomes equal to or greater than a predetermined threshold; An obstacle proximity detection method in which processing is executed by a computer, When identifying the first point cloud data, data of a predetermined region included in the three-dimensional point cloud data is rotated by a predetermined angle with respect to an xy plane, the rotated data of the predetermined region is projected onto the xy plane, and if the data of the predetermined region projected onto the xy plane is circular, the data of the predetermined region is identified as the first point cloud data. A method for detecting the proximity of an obstacle, in which processing is performed by a computer.

6. Sequentially acquiring three-dimensional point cloud data representing outdoor structures acquired by a three-dimensional laser scanner; Identifying first point cloud data representing an object and second point cloud data representing an obstacle from the three-dimensional point cloud data; setting a first detection area, which is an area preset by a user and is an area surrounding the first point cloud data; based on feature points extracted from the first point cloud data, moving the first point cloud data and the first detection area in accordance with movement of the feature points; outputting an alert indicating the proximity of the object and the obstacle when a part of the first detection area overlaps with a part of a second detection area that is a surrounding area of ​​the second point cloud data, or when the number of point data of the first point cloud data present in the second detection area becomes equal to or greater than a predetermined threshold; An obstacle proximity detection method in which processing is executed by a computer, The object is a utility pole under construction, The obstacle is a cable existing between existing utility poles, When identifying the second point cloud data representing the cable, data of a predetermined region included in the three-dimensional point cloud data is rotated by a predetermined angle around the z-axis, and the rotated data of the predetermined region is projected onto a yz-plane; and if the data of the predetermined region projected onto the yz-plane is circular, the data of the predetermined region is identified as the second point cloud data representing the cable. A method for detecting the proximity of an obstacle, in which processing is performed by a computer.

7. Sequentially acquiring three-dimensional point cloud data representing outdoor structures acquired by a three-dimensional laser scanner; Identifying first point cloud data representing an object and second point cloud data representing an obstacle from the three-dimensional point cloud data; setting a first detection area, which is an area preset by a user and is an area surrounding the first point cloud data; based on feature points extracted from the first point cloud data, moving the first point cloud data and the first detection area in accordance with movement of the feature points; outputting an alert indicating the proximity of the object and the obstacle when a part of the first detection area overlaps with a part of a second detection area that is a surrounding area of ​​the second point cloud data, or when the number of point data of the first point cloud data present in the second detection area becomes equal to or greater than a predetermined threshold; An obstacle proximity detection method in which processing is executed by a computer, The object is a utility pole under construction, the obstacle is a wall surface, When identifying the second point cloud data representing the wall surface, data of a predetermined area included in the three-dimensional point cloud data is projected onto an xy plane, and if the data of the predetermined area projected onto the xy plane has a linear shape, the data of the predetermined area is identified as the second point cloud data representing the wall surface. A method for detecting the proximity of an obstacle, in which processing is performed by a computer.

8. Sequentially acquiring three-dimensional point cloud data representing outdoor structures acquired by a three-dimensional laser scanner; Identifying first point cloud data representing an object and second point cloud data representing an obstacle from the three-dimensional point cloud data; setting a first detection area, which is an area preset by a user and is an area surrounding the first point cloud data; based on feature points extracted from the first point cloud data, moving the first point cloud data and the first detection area in accordance with movement of the feature points; outputting an alert indicating the proximity of the object and the obstacle when a part of the first detection area overlaps with a part of a second detection area that is a surrounding area of ​​the second point cloud data, or when the number of point data of the first point cloud data present in the second detection area becomes equal to or greater than a predetermined threshold; An obstacle proximity detection program for causing a computer to execute processing, When identifying the first point cloud data, data of a predetermined region included in the three-dimensional point cloud data is rotated by a predetermined angle with respect to an xy plane, the rotated data of the predetermined region is projected onto the xy plane, and if the data of the predetermined region projected onto the xy plane is circular, the data of the predetermined region is identified as the first point cloud data. An obstacle proximity detection program that causes a computer to execute processing.

9. Sequentially acquiring three-dimensional point cloud data representing outdoor structures acquired by a three-dimensional laser scanner; Identifying first point cloud data representing an object and second point cloud data representing an obstacle from the three-dimensional point cloud data; setting a first detection area, which is an area preset by a user and is an area surrounding the first point cloud data; based on feature points extracted from the first point cloud data, moving the first point cloud data and the first detection area in accordance with movement of the feature points; outputting an alert indicating the proximity of the object and the obstacle when a part of the first detection area overlaps with a part of a second detection area that is a surrounding area of ​​the second point cloud data, or when the number of point data of the first point cloud data present in the second detection area becomes equal to or greater than a predetermined threshold; An obstacle proximity detection program for causing a computer to execute processing, The object is a utility pole under construction, The obstacle is a cable existing between existing utility poles, When identifying the second point cloud data representing the cable, data of a predetermined region included in the three-dimensional point cloud data is rotated by a predetermined angle around the z-axis, and the rotated data of the predetermined region is projected onto a yz-plane; and if the data of the predetermined region projected onto the yz-plane is circular, the data of the predetermined region is identified as the second point cloud data representing the cable. A method for detecting the proximity of an obstacle, in which processing is performed by a computer.

10. Sequentially acquiring three-dimensional point cloud data representing outdoor structures acquired by a three-dimensional laser scanner; Identifying first point cloud data representing an object and second point cloud data representing an obstacle from the three-dimensional point cloud data; setting a first detection area, which is an area preset by a user and is an area surrounding the first point cloud data; based on feature points extracted from the first point cloud data, moving the first point cloud data and the first detection area in accordance with movement of the feature points; outputting an alert indicating the proximity of the object and the obstacle when a part of the first detection area overlaps with a part of a second detection area that is a surrounding area of ​​the second point cloud data, or when the number of point data of the first point cloud data present in the second detection area becomes equal to or greater than a predetermined threshold; An obstacle proximity detection program for causing a computer to execute processing, The object is a utility pole under construction, the obstacle is a wall surface, When identifying the second point cloud data representing the wall surface, data of a predetermined area included in the three-dimensional point cloud data is projected onto an xy plane, and if the data of the predetermined area projected onto the xy plane has a linear shape, the data of the predetermined area is identified as the second point cloud data representing the wall surface. A method for detecting the proximity of an obstacle, in which processing is performed by a computer.

Images