Classifications

• • G—PHYSICS
  • G01—MEASURING; TESTING
  • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
  • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
  • G01S17/88—Lidar systems specially adapted for specific applications
  • G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging

Definitions

• the disclosed technology relates to an estimation device, an estimation method, and an estimation program.
• Non-Patent Document 1 Traditionally, real space has been measured using measuring devices such as LiDAR (Light Detection and Ranging) and represented as three-dimensional point cloud data (see, for example, Non-Patent Document 1). By digitizing positions in real space in this way, the data can be used for the maintenance and management of social infrastructure.
• LiDAR Light Detection and Ranging
• the disclosed technology has been developed in consideration of the above points, and aims to provide an estimation device, estimation method, and estimation program that can reduce processing costs and achieve highly efficient and high-speed model estimation.
• a first aspect of the present disclosure is an estimation device including: a division unit that divides point cloud data to be modeled into voxel groups each consisting of a plurality of voxels according to a specified hierarchical depth using a predetermined spatial division method; an estimation unit that performs model estimation using the divided voxel groups and outputs an estimation result in which the point cloud data is modeled; a range update unit that uses the divided voxel groups and the output estimation result to obtain a set of intersections to obtain a partial voxel group by updating the processing target of the voxel group; and an iterative processing unit that repeats the model estimation and the update of the partial voxel group until the hierarchical depth of the processing target satisfies a predetermined condition.
• the second aspect of the present disclosure is an estimation method in which a computer executes the following processes: dividing point cloud data to be modeled into voxel groups each consisting of a plurality of voxels according to a specified hierarchical depth using a predetermined spatial division method; performing model estimation using the divided voxel groups; outputting an estimation result in which the point cloud data is modeled; determining a set of intersections using the divided voxel groups and the output estimation result to determine a partial voxel group in which the processing target of the voxel group is updated; and repeating the model estimation and the updating of the partial voxel group until the hierarchical depth of the processing target satisfies a predetermined condition.
• a third aspect of the present disclosure is an estimation program that causes a computer to execute the following processes: divide point cloud data to be modeled into voxel groups each consisting of a plurality of voxels according to a specified hierarchical depth using a predetermined spatial division method; perform model estimation using the divided voxel groups; output an estimation result in which the point cloud data is modeled; obtain a set of intersections using the divided voxel groups and the output estimation result to obtain a partial voxel group in which the processing target of the voxel group is updated; and repeat the model estimation and the update of the partial voxel group until the hierarchical depth of the processing target satisfies a predetermined condition.
• the disclosed technology makes it possible to reduce processing costs and achieve highly efficient and fast model estimation.
• FIG. 1 is a diagram showing an example of modeling using model estimation of point cloud data according to a conventional method.
• FIG. 2 is a block diagram showing a hardware configuration of the estimation device.
• FIG. 3 is a block diagram showing a functional configuration of the estimation device.
• FIG. 4 is a flowchart showing the flow of the estimation process performed by the estimation device.
• FIG. 5 shows a group of voxels before and after estimation when the specified hierarchical depth is six hierarchical levels.
• FIG. 6 shows a group of voxels after estimation when the specified hierarchical depth is eight hierarchical levels.
• FIG. 7 is a table showing a comparison of the number of estimation targets and model estimation time between the conventional method and the present method.
• Figure 1 shows an example of modeling using model estimation of point cloud data using a conventional method.
• modeling was performed by simply performing RANSAC model estimation from point cloud data. This type of model estimation consumes excessive memory and processing time, resulting in huge costs.
• a highly efficient model estimation is achieved by combining the octree hierarchical structure of point cloud data with model estimation.
• model estimation is performed for each layer in turn for a predetermined start and end layer, and the process of excluding voxels outside the model for that layer is repeated. This makes it possible to reduce processing costs and achieve highly efficient and high-speed model estimation.
• Figure 2 is a block diagram showing the hardware configuration of the estimation device 100.
• the estimation device 100 has 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.
• a CPU Central Processing Unit
• ROM Read Only Memory
• RAM Random Access Memory
• storage 14 an input unit 15, a display unit 16, and a communication interface (I/F) 17.
• I/F communication interface
• 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 storage 14, and executes the program using the RAM 13 as a working area. The CPU 11 controls each of the above components and performs various calculation processes according to the program stored in the ROM 12 or storage 14. In this embodiment, an estimation program is stored in the ROM 12 or storage 14.
• ROM 12 stores various programs and data.
• RAM 13 temporarily stores programs or data as a working area.
• Storage 14 is composed of a storage device such as an HDD (Hard Disk Drive) or SSD (Solid State Drive), and stores various programs including an operating system, and various data.
• HDD Hard Disk Drive
• SSD Solid State Drive
• the input unit 15 includes a pointing device such as a mouse and a keyboard, and is used to perform various input operations.
• 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.
• the communication interface 17 is an interface for communicating with other devices such as terminals.
• a wired communication standard such as Ethernet (registered trademark) or FDDI
• a wireless communication standard such as 4G, 5G, or Wi-Fi (registered trademark) is used.
• FIG. 3 is a block diagram showing the configuration of the estimation device of this embodiment. Each functional component is realized by the CPU 11 reading out an estimation program stored in the ROM 12 or storage 14, expanding it in the RAM 13, and executing it. As shown in FIG. 3, the estimation device 100 includes a point cloud data storage unit 102, a division unit 110, an extraction unit 112, an estimation unit 114, a range update unit 116, and an iterative processing unit 118.
• the point cloud data storage unit 102 stores the point cloud data of the estimation target. In the processing of each part of the estimation device 100, the point cloud data is read from the point cloud data storage unit 102 and processed.
• the division unit 110 receives point cloud data as input and divides the point cloud data into voxel groups each consisting of a plurality of voxels according to a specified hierarchical depth using an octree space division method.
• the octree space division method is a method of recursively dividing the three-dimensional space in which the point cloud data exists so that the space of eight child nodes belongs to the space of a parent node.
• the specified hierarchical depth (depth) is d
• the voxel group i.e. each voxel) corresponding to the hierarchical depth d is V(d).
• the hierarchical depth d may be specified by input from the user. Note that the octree space division method is just one example, and any method capable of dividing a point cloud into voxel groups can be used.
• the extraction unit 112 extracts a set C(d) of center points of each voxel obtained by thinning the point group by extracting center points from each voxel of the divided voxel group V(d) of the hierarchical level d to be processed.
• Each center point of the group extracted by the extraction unit 112 corresponds to each voxel of the voxel group.
• the processing of the extraction unit 112 may be omitted under conditions such as when the number of points contained in the voxel group is small and below a certain number, and model estimation, which will be described later, may be performed using the voxel group V(d).
• the estimation unit 114 performs model estimation using the set C(d) of center points extracted by the extraction unit 112, and outputs the estimation result P(d) that models the point cloud data.
• the estimation result P(d) is output to the range update unit 116 and is also stored in the model storage unit 104.
• the model estimation method uses RANSAC, but any method that can model point cloud data may be used.
• the range update unit 116 uses the divided voxel group V(d) and the output estimation result P(d) to obtain a set of intersections between V(d) and P(d), and obtains a partial voxel group V'(d) by updating the processing target of the voxel group.
• the processing of the range update unit 116 obtains a partial voxel group V'(d) in which voxels outside the model of layer d have been excluded. In other words, the voxels in the range of the processing target are narrowed down as the layer becomes deeper with each iteration.
• the iterative processing unit 118 repeats the extraction by the extraction unit 112, the model estimation by the estimation unit 114, and the updating of the voxel group by the range update unit 116 until the partial voxel group V'(d) satisfies a predetermined condition.
• FIG. 4 is a flowchart showing the flow of the estimation process by the estimation device 100.
• the estimation process is performed by the CPU 11 reading out an estimation process program from the ROM 12 or storage 14, expanding it in the RAM 13 and executing it.
• the estimation device 100 receives designation of the point cloud data to be estimated and the hierarchical depth from the user, reads out the point cloud data from the point cloud data storage unit 102, and performs the following processes.
• step S100 the CPU 11, acting as the division unit 110, inputs point cloud data and divides the point cloud data into voxel groups V(d) each consisting of a plurality of voxels according to the specified hierarchical depth by using a spatial division method using an octree.
• step S102 the CPU 11, functioning as the extraction unit 112, extracts center points from each of the voxels in the divided voxel group V(d) of the hierarchical level d to be processed, thereby extracting a set C(d) of center points of each voxel obtained by thinning out the point group.
• step S104 the CPU 11, as the estimation unit 114, performs model estimation using the set of extracted center points C(d) and outputs the estimation result P(d) that models the point cloud data.
• step S106 the CPU 11, acting as the range update unit 116, uses the divided voxel group V(d) and the output estimation result P(d) to obtain a set of intersections between V(d) and P(d) and obtains a partial voxel group V'(d) by updating the processing target of the voxel group.
• step S108 the CPU 11, functioning as the iterative processing unit 118, determines whether the partial voxel group V'(d) satisfies a condition.
• the condition is satisfied when, for example, the set of intersections, i.e., the number of points in the partial voxel group V'(d), falls below the number of samples required for model estimation.
• the required number of samples may be specified as the termination condition according to a predetermined required accuracy. In the case of a planar model, the required number of samples may be "3", for example. If the condition is satisfied, the estimation result of the model estimated in step S104 and the hierarchical depth d are finally output, and the processing ends. If the condition is not satisfied, the process proceeds to step S110.
• the estimation device 100 of this embodiment can reduce processing costs and achieve highly efficient and fast model estimation.
• Figure 5 shows the voxel group before and after estimation when the specified hierarchical depth is 6 levels.
• (a) in Figure 5 shows the voxel group before estimation, and the modeled voxel group after estimation.
• the voxel group in (b) has been estimated and modeled from (a). Since (a) is before estimation, all of the point clouds of buildings, roads, etc. are included in the voxels. In (b), a plane has been obtained by modeling, and it can be confirmed that the point clouds of the high points of the buildings are not included in the voxel group.
• FIG. 6 shows the voxel group after estimation when the specified hierarchical depth is 8 levels.
• the example shown in FIG. 6 shows the voxel group of the estimation result, which is modeled by iteratively going up to 8 levels.
• the voxel size is reduced to 1/64 of 6 levels, and the point group contained in the voxel approaches a plane.
• the plane of the estimation result is drawn, and it can be seen that most of the point group of a large building is not contained in the voxel.
• the voxel contains something other than a building, and represents an area close to a road.
• the method of this embodiment enables such object detection, i.e., model estimation, at high speed.
• Figure 7 shows a comparison of the number of points to be estimated and the model estimation time between the conventional method and this method.
• the number of points to be estimated was approximately 3 million, and the model estimation time was 25 minutes 46 seconds 529 msec.
• the method of this embodiment can also handle more complex shapes by increasing the number of model types.
• layers 4-6 can handle planar models.
• Layers 7-9 can handle cylindrical models.
• the voxel exclusion process performed by the range update unit 116 can be used as a point cloud segmentation function.
• the excluded voxels are considered as a separate set, and hierarchical model estimation can be applied to segment a wide-area point cloud.
• the estimation process executed by the CPU by reading the software may be executed by various processors other than the CPU.
• the processor in this case include a PLD (Programmable Logic Device) whose circuit configuration can be changed after manufacture such as an FPGA (Field-Programmable Gate Array), a GPU (Graphics Processing Unit), and a dedicated electric circuit that is a processor having a circuit configuration designed exclusively to execute a specific process such as an ASIC (Application Specific Integrated Circuit).
• the estimation process may be executed by one of these various processors, or may be executed by a combination of two or more processors of the same or different types (for example, multiple FPGAs, a combination of a CPU and an FPGA, etc.). More specifically, the hardware structure of these various processors is an electrical circuit that combines circuit elements such as semiconductor devices.
• the estimation 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.
• Memory at least one processor coupled to the memory; Including, The processor, Dividing the point cloud data to be modeled into voxel groups each consisting of a plurality of voxels according to a specified hierarchical depth using a predetermined spatial division method; Performing model estimation using the divided voxel group, and outputting an estimation result in which the point cloud data is modeled; determining a set of intersections using the divided voxel group and the output estimation result to determine a partial voxel group in which a processing target for the voxel group is updated; repeating the model estimation and the updating of the partial voxel group until the hierarchy of the depth to be processed satisfies a predetermined condition;
• the estimation device is configured as follows.
• a non-transitory storage medium storing a program executable by a computer to execute an estimation process, Dividing the point cloud data to be modeled into voxel groups each consisting of a plurality of voxels according to a specified hierarchical depth using a predetermined spatial division method; Performing model estimation using the divided voxel group, and outputting an estimation result in which the point cloud data is modeled; determining a set of intersections using the divided voxel group and the output estimation result to determine a partial voxel group in which a processing target for the voxel group is updated; repeating the model estimation and the updating of the partial voxel group until the hierarchy of the depth to be processed satisfies a predetermined condition; Non-transitory storage media.

Landscapes

• Physics & Mathematics (AREA)
• Engineering & Computer Science (AREA)
• Computer Networks & Wireless Communication (AREA)
• Electromagnetism (AREA)
• General Physics & Mathematics (AREA)
• Radar, Positioning & Navigation (AREA)
• Remote Sensing (AREA)
• Image Generation (AREA)

Priority Applications (2)

Applications Claiming Priority (1)

Publications (1)

Family

ID=91323175

Family Applications (1)

Country Status (2)

Citations (4)

• 2022
  • 2022-12-02 JP JP2024561132A patent/JP7827169B2/ja active Active
  • 2022-12-02 WO PCT/JP2022/044631 patent/WO2024116415A1/ja not_active Ceased

Patent Citations (4)

Also Published As

Similar Documents

Legal Events