Search

JP-7855107-B1 - Background data management device, background data management method, and background data management program

JP7855107B1JP 7855107 B1JP7855107 B1JP 7855107B1JP-7855107-B1

Abstract

[Challenge] To enable the preparation of appropriate background point cloud data. [Solution] The difference identification unit 24 identifies difference cells among a plurality of voxels, which are voxels that have a difference between the new voxel data of the newly acquired point cloud data and the background voxel data of the background point cloud data. The background update unit 26 updates the background point cloud data by adding the data of points included in the new point cloud data that are associated with neighboring cells among the difference cells, which are voxels in the background voxel data whose distance from the voxel containing the point cloud is less than a reference distance, to the background point cloud data. [Selection Diagram] Figure 1

Inventors

  • 井ノ口 裕也
  • 阿部 紘和
  • 中尾 尭理
  • 山足 光義

Assignees

  • 三菱電機デジタルイノベーション株式会社

Dates

Publication Date
20260507
Application Date
20250324

Claims (8)

  1. A point cloud acquisition unit acquires point cloud data including data of multiple points obtained by irradiating a target area with light and receiving the reflected light reflected at the reflection point, A voxelization unit generates voxel data corresponding to the point cloud data by associating each point of the point cloud data acquired by the point cloud acquisition unit with the voxel containing the position of the target point among a plurality of voxels obtained by dividing the target region, A difference identification unit identifies only the voxels among the plurality of voxels that have a difference between the new voxel data, which is the voxel data for the newly acquired point cloud data, and the background voxel data, which is the voxel data for the background point cloud data composed of previously acquired point cloud data, and for which the number of points associated in the new voxel data is less than a standard number, as difference cells. A background data management device comprising: a background update unit that updates the background point cloud data by adding the data of points included in the new point cloud data, which are associated with neighboring cells among the difference cells identified by the difference identification unit, where the distance from the voxel containing the point cloud in the background voxel data is less than a reference distance; and the distance of these points from the voxel containing the point cloud in the background voxel data.
  2. The background data management device according to claim 1, wherein the background update unit defines only the voxels included in the range extended by less than a reference distance around the voxel containing the point cloud in the background point cloud data as the neighboring cells among the difference cells.
  3. The background data management device further, A reference background generation unit generates a reference background using the point cloud data acquired by the point cloud acquisition unit at a reference timing, The system includes an initial data acquisition unit that acquires the reference background generated by the reference background generation unit as the initial value of the background point cloud data when the background data management device is started up, The background data management device according to claim 1, wherein the reference background generation unit updates the reference background with the background point cloud data updated by the background update unit.
  4. The background data management device further, A reference background generation unit generates a reference background using the point cloud data acquired by the point cloud acquisition unit at a reference timing, An initial data acquisition unit acquires the reference background generated by the reference background generation unit as the initial value of the background point cloud data when the background data management device is started up, The background data management device according to claim 1, further comprising a notification unit that notifies when the number of voxels with a difference between the voxel data for the background point cloud data updated by the background update unit and the voxel data for the reference background is greater than or equal to a threshold number.
  5. The background data management device further, The background data management device according to claim 3 or 4 , further comprising a display unit that displays the difference between the background point cloud data updated by the background update unit and the reference background.
  6. The background data management device according to claim 1, wherein the background update unit updates the background point cloud data by adding not only the data of points associated with the neighboring cells but also the data of points associated with the extended cells to the background point cloud data, using a standard number of voxels around the neighboring cells as extended cells.
  7. The computer obtains point cloud data containing data from multiple points obtained by irradiating a target area with light and receiving the reflected light reflected at the reflection points. The computer generates voxel data corresponding to the point cloud data by associating each point in the point cloud data with a voxel containing the location of the target point among a plurality of voxels obtained by dividing the target region, The computer identifies as difference cells only those voxels among the plurality of voxels that have a difference between the new voxel data, which is the voxel data for the newly acquired point cloud data, and the background voxel data, which is the voxel data for the background point cloud data , which is composed of previously acquired point cloud data, and for which the number of points associated in the new voxel data is less than a certain number . A background data management method in which a computer updates the background point cloud data by adding the data of points included in the new point cloud data, which are associated with neighboring cells among the difference cells that are voxels in the background voxel data whose distance from the voxel containing the point cloud is less than a reference distance, to the background point cloud data.
  8. A point cloud acquisition process that obtains point cloud data containing data from multiple points obtained by irradiating a target area with light and receiving the reflected light reflected at the reflection points, A voxelization process generates voxel data corresponding to the point cloud data by associating each point in the point cloud data acquired by the point cloud acquisition process with the voxel containing the position of the target point among a plurality of voxels obtained by dividing the target region, and A difference identification process that identifies only the voxels among the plurality of voxels that have a difference between the new voxel data, which is the voxel data for the newly acquired point cloud data, and the background voxel data , which is the voxel data for the background point cloud data, which is composed of previously acquired point cloud data, and for which the number of points associated in the new voxel data is less than a standard number, as difference cells. A background data management program that causes a computer to function as a background data update device, which performs a background update process to update the background point cloud data by adding the data of points included in the new point cloud data, which are associated with neighboring cells that are voxels in the background voxel data whose distance from the voxel containing the point cloud is less than a reference distance, among the difference cells identified by the difference identification process, to the background point cloud data.

Description

This disclosure relates to a technology for detecting objects using point cloud data. There is a technology that uses visible light cameras to detect objects such as discarded objects. However, when using visible light cameras to detect objects, they cannot properly detect objects in environments with insufficient light, such as at night, or in environments where direct sunlight shines on the visible light camera, causing flare. There are optical sensors, such as LiDAR, that collect point cloud data by irradiating an object with light and receiving the reflected light at the reflection point. LiDAR stands for Light Detection and Ranging. Optical sensors can obtain point cloud data even in environments with insufficient light, such as at night, and in environments where direct sunlight shines into a visible light camera, causing flare. Therefore, detecting objects based on point cloud data obtained using optical sensors is being considered. Patent Document 1 describes a method for identifying the appearance of an object by comparing background point cloud data stored in memory with the current point cloud data and detecting any difference. Japanese Patent Publication No. 2020-118619 Configuration diagram of the background data management device 10 according to Embodiment 1.An explanatory diagram of the voxel definition 31 according to Embodiment 1.Flowchart of the background generation process according to Embodiment 1.An explanatory diagram of the reference background 42 according to Embodiment 1.An explanatory diagram of the voxelization method according to Embodiment 1.A flowchart of the background update process according to Embodiment 1.An explanatory diagram of the difference identification process according to Embodiment 1.Diagram illustrating the filtering process according to Embodiment 1.An explanatory diagram of the background candidate extraction process according to Embodiment 1.Configuration diagram of the background data management device 10 according to modified example 2.Flowchart of the background update process related to Modification Example 2.Configuration diagram of the background data management device 10 according to modified example 3.An explanatory diagram of the display content related to the modified example 3.An explanatory diagram of the display content related to the modified example 4.An explanatory diagram of the background candidate extraction process related to Modification 5.An explanatory diagram of the background candidate extraction process related to Modification 5.Configuration diagram of the background data management device 10 according to Embodiment 2.A flowchart of the background update process according to Embodiment 2.A diagram illustrating the effects of Embodiment 2.A diagram illustrating the effects of Embodiment 2.An explanatory diagram of the display content related to the modified example 8.An explanatory diagram of the display content related to the modified example 8. Embodiment 1. ***Explanation of the structure*** Referring to Figure 1, the configuration of the background data management device 10 according to Embodiment 1 will be described. The background data management device 10 is a computer. The background data management device 10 comprises hardware including a processor 11, memory 12, storage 13, and a communication interface 14. The processor 11 is connected to the other hardware via signal lines and controls this other hardware. Processor 11 is an integrated circuit (IC) that performs processing. IC stands for Integrated Circuit. Specific examples of processors 11 include CPUs, DSPs, and GPUs. CPU stands for Central Processing Unit. DSP stands for Digital Signal Processor. GPU stands for Graphics Processing Unit. Memory 12 is a storage device that temporarily stores data. Specific examples of memory 12 include SRAM and DRAM. SRAM stands for Static Random Access Memory. DRAM stands for Dynamic Random Access Memory. Storage 13 is a storage device for storing data. Specific examples of storage 13 include HDDs and SSDs. HDD stands for Hard Disk Drive. SSD stands for Solid State Drive. Storage 13 may also be a portable recording medium such as an SD® memory card, CompactFlash®, NAND flash, flexible disk, optical disk, compact disk, Blu-ray® disc, or DVD. SD stands for Secure Digital. DVD stands for Digital Versatile Disk. The communication interface 14 is an interface for communicating with external devices. Specific examples of the communication interface 14 include Ethernet®, USB, and HDMI® ports. USB stands for Universal Serial Bus. HDMI stands for High-Definition Multimedia Interface. The background data management device 10 is connected to the optical sensor 40 via a communication interface 14. The optical sensor 40 is a device that acquires point cloud data 41 by irradiating a target area with light and receiving the reflected light at the reflection points. The position of each point in the point cloud data 41 is determined from the irradiat