Extraction device, extraction method, and extraction program

Abstract

This extraction device comprises: a dividing unit that divides a point group in the height direction and generates height groups; a first calculation unit that, for the divided point group, carries out circle detection in group units by projecting, for each of the height groups, the point group of each height group onto an XY plane containing an x-axis and a y-axis; and a columnar object determination unit that determines whether a circle detected in each of the height groups satisfies a prescribed condition, and that extracts a columnar object which satisfies the prescribed condition.

Description

[Technical Field]

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

[0002] Conventionally, there is a technology that uses the point cloud shape of scan lines to determine whether or not an object is cylindrical and extract it. This technology creates scan lines, determines whether an object is cylindrical based on the shape of the scan lines, and then connects the scan lines to increase the pseudo-point cloud and form a circular model. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] Masaki Waki ​​Takashi Goto Kazunori Katayama, "Novel outside facility management technology for maintenance and inspection work using MMS", International Wire & Cable Symposium, Proceedings of the 66th IWCS Conference. Summary of the Invention [Problem to be solved by the invention]

[0004] However, with a relatively low point cloud density such as LiDAR (Light Detection and Ranging), it is not possible to generate scan lines and detect cylindrical objects. Also, even if you artificially increase the point cloud and form a circular model, the processing time is long, making real-time detection difficult.

[0005] The disclosed technology has been made in consideration of the above points, and aims to provide an extraction device, extraction method, and extraction program that are capable of extracting cylindrical objects even from low-density point clouds. [Means for solving the problem]

[0006] A first aspect of the present disclosure is an extraction device that includes a division unit that divides a point cloud in the height direction and generates height groups; a circle information calculation unit that projects the point cloud of each height group onto an XY plane including the x-axis and y-axis and performs circle detection on a group-by-group basis for the divided point cloud; and a cylindrical object determination unit that determines whether the circle detected for each height group satisfies a predetermined condition and extracts cylindrical objects that satisfy the predetermined condition.

[0007] A second aspect of the present disclosure is an extraction method in which a computer executes the following process: dividing a point cloud in the height direction, generating height groups, projecting the point cloud of each height group onto an XY plane including the x-axis and y-axis for the divided point cloud, detecting circles on a group-by-group basis, determining whether the circle detected for each height group satisfies a predetermined condition, and extracting cylindrical objects that satisfy the predetermined condition.

[0008] A third aspect of the present disclosure is an extraction program that causes a computer to execute the following process: divide a point cloud in the height direction, generate height groups, project the point cloud of each height group onto an XY plane including the x-axis and y-axis for the divided point cloud, perform circle detection on a group-by-group basis, determine whether the circle detected for each height group satisfies specified conditions, and extract cylindrical objects that satisfy the specified conditions. [Effects of the Invention]

[0009] According to the disclosed technology, it is possible to extract cylindrical objects even from a low-density point cloud. [Brief explanation of the drawings]

[0010] [Figure 1]10 shows an example of a process for extracting a cylindrical object according to this embodiment. [Figure 2] FIG. 2 is a block diagram showing a hardware configuration of the extraction device. [Figure 3] 1 is a block diagram showing a configuration of an extraction device according to an embodiment of the present invention; [Figure 4] 10 is a flowchart showing the flow of extraction processing by the extraction device. [Figure 5] FIG. 10 is a diagram showing an example of a cylindrical object extracted in the height direction from the point cloud. DETAILED DESCRIPTION OF THE INVENTION

[0011] An example of an embodiment of the disclosed technology will be described below with reference to the drawings. Note that the same or equivalent components and parts in each drawing 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.

[0012] First, a method according to an embodiment of the present disclosure will be described. Fig. 1 shows an example of the process of extracting a cylindrical object according to this embodiment. The cylindrical object is an example of a utility pole. The process is indicated by A1 to A5. A1, A2, A4, and A5 are cylindrical objects in a three-dimensional space of the x, y, and z axes. A3 is a cross section of the cylindrical object as seen from above.

[0013] In A1, there is a point cloud corresponding to a cylindrical object. In A2, the point cloud in A1 is divided and grouped into arbitrary ranges in any height direction. In A3, circles are detected on the XY plane within the grouped range, and each group is processed. When a circle is detected, its center coordinates and radius are calculated. In A4, if a certain percentage or more of the divided sections contain circles, it is determined to be a cylindrical object. Further refinement is possible based on the deviation in the position of the center coordinates or the deviation in the radius. In A5, deflection, tilt, etc. are calculated from the center coordinates of the detected circle. In addition to the above percentages, the method of determining whether an object is cylindrical can also use the error in the center coordinates or radius of the detected circle. A combination of these determination methods can also be used.

[0014] The method of this embodiment described above makes it possible to extract cylindrical objects even from a low-density point cloud. In addition, the processing time is short, enabling real-time detection.

[0015] The configuration of this embodiment will be described below.

[0016] FIG. 2 is a block diagram showing the hardware configuration of the extraction device 100. As shown in FIG.

[0017] 2, the extraction device 100 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 19 so as to be able to communicate with each other.

[0018] The CPU 11 is a central processing unit that executes various programs and controls each part. That is, the CPU 11 reads a program from the ROM 12 or the storage 14 and executes the program using the RAM 13 as a work area. The CPU 11 controls each of the above components and performs various arithmetic processing in accordance with the program stored in the ROM 12 or the storage 14. In this embodiment, an extraction program is stored in the ROM 12 or the storage 14.

[0019] 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 a storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive) and stores various programs including the operating system and various data.

[0020] The input unit 15 includes a pointing device such as a mouse and a keyboard, and is used to perform various inputs.

[0021] The display unit 16 is, for example, a liquid crystal display, and displays various information. The display unit 16 may function as the input unit 15 by adopting a touch panel system.

[0022] The communication interface (I / F) 17 is an interface for communicating with other devices such as terminals, etc. For this communication, for example, a wired communication standard such as Ethernet (registered trademark) or FDDI, or a wireless communication standard such as 4G, 5G, or Wi-Fi (registered trademark) is used.

[0023] Next, a description will be given of each functional configuration of the extraction device 100. Fig. 3 is a block diagram showing the configuration of the extraction device 100 of this embodiment. Each functional configuration is realized by the CPU 11 reading out an extraction program stored in the ROM 12 or storage 14, expanding it in the RAM 13, and executing it.

[0024] 3, the extraction device 100 is configured with processing units including a reading unit 110, a setting unit 112, a first calculation unit 114, a second calculation unit 116, and a storage unit 118. Note that each processing unit may be configured as an apparatus. Furthermore, the reading unit 110, the setting unit 112, the second calculation unit 116, and the storage unit 118 can be configured using techniques used in conventional methods.

[0025] The reading unit 110 reads point cloud data from an external point cloud measuring instrument 90 as external data.

[0026] Parameters used in the process of calculating a cylindrical object model (extracting a cylindrical object) are stored in the setting unit 112. The parameters are, for example, threshold values ​​used in each unit of the first calculation unit 114, arbitrary height values ​​used in height division, etc.

[0027] The first calculation unit 114 is a processing unit that narrows down candidate point clouds, divides point cloud heights, detects circles, calculates circle center coordinates and radii, and determines whether a cylindrical object exists. The first calculation unit 114 is configured to include a narrowing down unit 120, a dividing unit 122, a circle information calculation unit 124, and a cylindrical object determination unit 126. Aspects of each component of the first calculation unit 114 will be described later.

[0028] The second calculation unit 116 is a processing unit that calculates the deflection and inclination of the utility pole. The second calculation unit 116 also determines whether or not the predetermined circle information is equal to or less than a threshold value. The determination of the predetermined circle information will be described later. The second calculation unit 116 also repeats the calculation processes of the division unit 122, the circle information calculation unit 124, and the second calculation unit 116 until the predetermined circle information for the cylindrical object to be extracted becomes equal to or less than the threshold value.

[0029] The storage unit 118 stores the values ​​calculated by the first calculation unit 114 and the second calculation unit 116. The calculated values ​​are the extraction results of the cylindrical object.

[0030] Generally, the Z coordinate of a point cloud is 0 at the height where the point cloud measurement device is placed. If the point cloud measurement device is mounted on a tripod or similar and point cloud measurement is performed, it is desirable to set the arbitrary height to 0 minus the height of the tripod. Since the density of a point cloud depends on the characteristics of the point cloud measurement device, it is desirable to keep the point cloud division height constant for devices that can acquire point clouds evenly in the vertical direction. On the other hand, if the density varies in the vertical direction, it is desirable to have a small cut-out height for high-density areas and a large cut-out height for low-density areas.

[0031] Next, each part of the first calculation unit 114 will be described.

[0032] The narrowing unit 120 excludes, from each of the points included in the point cloud data read by the reading unit 110, points whose Z coordinates are equal to or less than an arbitrary height.

[0033] The dividing unit 122 divides the point cloud in the height direction (z-axis direction) by N number of height groups, where N is an arbitrary number.

[0034] For each height group, the circle information calculation unit 124 projects the point cloud of the height group onto an XY plane including the x-axis and y-axis, and performs circle detection for each group. For circle detection, a known method such as RANSAC (Random Sample Consensus) processing is used. Furthermore, when a circle is detected from the group, the circle information calculation unit 124 calculates the center coordinates and the circle radius.

[0035] The cylindrical object determination unit 126 determines whether or not the circle detected for each height group satisfies a predetermined condition. The predetermined condition is, for example, at least one of the following conditions 1 to 3, or a combination of any two or more of them. This determines whether or not the detected circle is a cylindrical object. Note that the conditions 1 to 3 may be used alone or in combination. 1. Is the number of detected groups equal to or greater than a certain percentage of the N divided groups? 2. Are the detected center coordinates (x, y) within a given error range? 3. Check whether the radius of each detected circle is within a given error range.

[0036] 1. is an example of the number of circle-detected groups for the divided height groups of the present disclosure. 2. is an example of the center coordinate error of the detected circle of the present disclosure. 3. is an example of the radius error of the detected circle of the present disclosure. Next, the operation of the extraction device 100 will be described.

[0037] 4 is a flowchart showing the flow of extraction processing by the extraction device 100. The extraction processing is performed by the CPU 11 reading out an extraction program from the ROM 12 or storage 14, expanding it into the RAM 13, and executing it. The CPU 11 executes the extraction processing by performing processing as each unit of the extraction device 100. The extraction processing is executed by the reading unit 110 reading point cloud data as external data from the external point cloud measuring instrument 90.

[0038] In step S100, the CPU 11 excludes points whose Z coordinates are equal to or less than an arbitrary height from each of the points included in the read point cloud data.

[0039] In step S102, the point cloud is divided in the height direction (z-axis direction) by N number of height groups to generate. Here, the height direction of the z-axis is updated based on the gradient in step S112, which will be described later.

[0040] In step S104, for each height group, the point cloud of the height group is projected onto the XY plane, and circle detection is performed for each group.

[0041] In step S106, for each height group, if a circle is detected from the group, the center coordinates and the circle radius are calculated.

[0042] In step S108, it is determined whether or not the circles detected for each height group satisfy predetermined conditions (criteria 1 to 3). If the conditions are satisfied, the process proceeds to step S110, and if the conditions are not satisfied, the process ends without extracting any cylindrical objects.

[0043] In step S110, a cylindrical object is detected based on the calculation results from steps S100 to S106.

[0044] In step S112, the deflection and tilt of the detected cylindrical object are calculated.

[0045] In step S114, it is determined whether or not the predetermined circle information is equal to or smaller than a threshold value. If the circle information is equal to or smaller than the threshold value, the process proceeds to step S116, and if the circle information is equal to or larger than the threshold value, the process returns to step S102.

[0046] In the determination of a cylindrical object in step S108, an error may occur between the detected circle and the actual radius of a cylindrical object that is significantly tilted, such as a pillar. Therefore, to reduce the error, steps S102 to S110 are repeated, with the tilt calculated in step S112 (second calculation unit 116) used as the new Z-axis height direction. The predetermined circle information includes values ​​such as the newly calculated circle radius, center coordinates, and tilt of the cylindrical object. If each value of the circle information is equal to or less than a given value compared to the previously calculated value, the cylindrical object extraction result is stored in the storage unit 118, and the process ends. Figure 5 shows an example of a cylindrical object extracted in the height direction from a point cloud. R1 in Figure 5 indicates the extracted cylindrical object.

[0047] In step S116, the extraction result of the cylindrical object is stored in the storage unit 118, and the process ends.

[0048] As described above, the extraction device 100 of this embodiment makes it possible to extract a cylindrical object even from a low-density point cloud.

[0049] In the above embodiment, the extraction process executed by the CPU after reading the software (program) may be executed by various processors other than the CPU. 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, graphics processing units (GPUs), and application-specific integrated circuits (ASICs) that are processors with circuit configurations specifically designed to execute specific processes. The extraction 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.

[0050] In the above embodiment, the extraction program is pre-stored (installed) in the storage 14, but the present invention is not limited to this. The 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 program may also be downloaded from an external device via a network.

[0051] The following additional notes are provided regarding the above-described embodiments.

[0052] (Additional note 1) Memory and at least one processor coupled to said memory; Including, The processor: Divide the point cloud in the height direction and generate height groups. For each height group of the divided point clouds, the point cloud of that height group is projected onto the XY plane including the x-axis and y-axis, and circle detection is performed for each group. determining whether or not the circles detected for each height group satisfy a predetermined condition, and extracting cylindrical objects that satisfy the predetermined condition; The extraction device is configured as follows.

[0053] (Additional note 2) A non-transitory storage medium storing a program executable by a computer to perform an extraction process, Divide the point cloud in the height direction and generate height groups. For each height group of the divided point clouds, the point cloud of that height group is projected onto the XY plane including the x-axis and y-axis, and circle detection is performed for each group. determining whether or not the circles detected for each height group satisfy a predetermined condition, and extracting cylindrical objects that satisfy the predetermined condition; Non-transitory storage medium.

Claims

1. a division unit that divides the point cloud in a height direction and generates height groups; a circle information calculation unit that projects the point cloud of each height group onto an XY plane including the x-axis and the y-axis and performs circle detection for each group of the divided point clouds; a cylindrical object determination unit that determines whether the circle detected for each height group satisfies a predetermined condition and extracts cylindrical objects that satisfy the predetermined condition; a second calculation unit that calculates the deflection and tilt of the detected cylindrical object, The second calculation unit repeats the calculation process of the division unit, the circle information calculation unit, and the second calculation unit until predetermined circle information for the cylindrical object to be extracted becomes equal to or less than a threshold, and in each repetition, the division unit divides the point cloud using a new height direction based on the slope calculated by the second calculation unit.

2. The extraction device according to claim 1 , wherein the cylindrical object determination unit extracts the cylindrical objects using a ratio of the number of groups into which circles are detected to the divided height groups as the predetermined condition.

3. The extraction device according to claim 1 , wherein the cylindrical object determination unit extracts the cylindrical object using a central coordinate error of the detected circle as the predetermined condition.

4. The extraction device according to claim 1 , wherein the cylindrical object determination unit extracts the cylindrical object using a radius error of the detected circle as the predetermined condition.

5. 2. The extraction device according to claim 1, wherein the cylindrical object determination unit extracts the cylindrical objects using a combination of two or more of the following as the predetermined condition: a ratio of the number of circle-detected groups to the divided height groups; a central coordinate error of the detected circles; and a radius error of the detected circles.

6. Divide the point cloud in the height direction and generate height groups. For each of the divided point clouds, the point cloud of the height group is projected onto an XY plane including the x-axis and y-axis, and circle detection is performed for each group. determining whether the detected circle for each height group satisfies a predetermined condition, and extracting a cylindrical object that satisfies the predetermined condition; Calculate the deflection and tilt of the detected cylindrical object, repeating the processes of dividing, detecting the circle, and calculating the cylindrical object until predetermined circle information about the cylindrical object to be extracted becomes equal to or less than a threshold, and in each repetition, dividing the point cloud using the new height direction based on the calculated inclination. An extraction method in which processing is performed by a computer.

7. Divide the point cloud in the height direction and generate height groups. For each of the divided point clouds, the point cloud of the height group is projected onto an XY plane including the x-axis and y-axis, and circle detection is performed for each group. determining whether the detected circle for each height group satisfies a predetermined condition, and extracting a cylindrical object that satisfies the predetermined condition; Calculate the deflection and tilt of the detected cylindrical object, repeating the processes of dividing, detecting the circle, and calculating the cylindrical object until predetermined circle information about the cylindrical object to be extracted becomes equal to or less than a threshold, and in each repetition, dividing the point cloud using the new height direction based on the calculated inclination. An extraction program that causes a computer to perform the processing.

Images