WO2021035618A1 - Procédé et système de segmentation de nuage de points, et plateforme mobile - Google Patents

Procédé et système de segmentation de nuage de points, et plateforme mobile Download PDF

Info

Publication number
WO2021035618A1
WO2021035618A1 PCT/CN2019/103314 CN2019103314W WO2021035618A1 WO 2021035618 A1 WO2021035618 A1 WO 2021035618A1 CN 2019103314 W CN2019103314 W CN 2019103314W WO 2021035618 A1 WO2021035618 A1 WO 2021035618A1
Authority
WO
WIPO (PCT)
Prior art keywords
point cloud
cloud data
dimensional
index value
preset
Prior art date
Application number
PCT/CN2019/103314
Other languages
English (en)
Chinese (zh)
Inventor
李星河
邱凡
刘寒颖
Original Assignee
深圳市大疆创新科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市大疆创新科技有限公司 filed Critical 深圳市大疆创新科技有限公司
Priority to PCT/CN2019/103314 priority Critical patent/WO2021035618A1/fr
Priority to CN201980034128.0A priority patent/CN112166457A/zh
Publication of WO2021035618A1 publication Critical patent/WO2021035618A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G06T2207/10012—Stereo images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing
    • G06T2207/10044—Radar image

Definitions

  • This application relates to the technical field of mobile platforms, and in particular to a point cloud segmentation method, system and mobile platform.
  • Lidar is a scanning sensor. Its working principle is to detect a target by emitting a laser beam, and collect the reflected beam to form point cloud data. After photoelectric processing, the point cloud data can be generated into an accurate three-dimensional image. Through lidar, high-precision physical space environment information can be accurately obtained, and the ranging accuracy can reach centimeter level. Therefore, lidar has become the most core sensor device in the fields of auto-driving, unmanned driving, positioning and navigation, space surveying and mapping, security and defense.
  • point cloud segmentation is one of the important issues in data processing.
  • the main function of point cloud segmentation is to segment the point cloud data into multiple independent entities, such as people, cars, bicycles, facades, columns, etc.
  • the point cloud data is usually clustered and segmented based on the distance threshold judgment method.
  • the real-time point cloud density generated by lidar varies greatly and varies with distance. Inconsistent point cloud density will lead to under-segmentation or over-segmentation, and the accuracy of point cloud segmentation is low.
  • the present application provides a point cloud segmentation method, system, and movable platform, which improve the accuracy of point cloud segmentation.
  • this application provides a point cloud segmentation method, including:
  • the density value of each point cloud data is obtained according to the one-dimensional index value of each point cloud data, the density value of the point cloud data is used to indicate the point cloud density in a preset three-dimensional space, and the preset three-dimensional space Including the point cloud data;
  • the point cloud data to be processed is segmented according to the density value of each point cloud data to obtain multiple point cloud clusters.
  • this application provides a point cloud segmentation system, including: a memory, a processor, and a point cloud sensor;
  • the point cloud sensor is used to obtain point cloud data to be processed in the target area
  • the memory is used to store program code
  • the processor calls the program code, and when the program code is executed, is used to perform the following operations:
  • the density value of each point cloud data is obtained according to the one-dimensional index value of each point cloud data, the density value of the point cloud data is used to indicate the point cloud density in a preset three-dimensional space, and the preset three-dimensional space Including the point cloud data;
  • the point cloud data to be processed is segmented according to the density value of each point cloud data to obtain multiple point cloud clusters.
  • the present application provides a mobile platform, including: the point cloud segmentation system provided by any one of the implementations of the second aspect of the present application.
  • the present application provides a computer storage medium in which a computer program is stored, and the computer program implements the method provided in the first aspect when executed.
  • This application provides a point cloud segmentation method, system, and movable platform.
  • the value of each point cloud data is obtained.
  • One-dimensional index value the density value of each point cloud data is obtained according to the one-dimensional index value of each point cloud data, and the point cloud data to be processed is divided according to the density value of each point cloud data to obtain multiple point cloud clusters . Since the point cloud data in the target area is segmented according to the density value of each point cloud data to obtain multiple point cloud clusters, the accuracy of point cloud segmentation is improved.
  • Figure 1 is a schematic diagram of an application scenario involved in this application
  • FIG. 2 is a flowchart of a point cloud segmentation method provided by an embodiment of the application
  • FIG. 3 is a schematic diagram of a three-dimensional map and grid resolution of a target area provided by an embodiment of the application;
  • FIG. 4 is a flowchart of another point cloud segmentation method provided by an embodiment of the application.
  • 5A-5B are schematic diagrams of the effect of point cloud data segmentation provided by embodiments of this application.
  • Fig. 6 is a schematic structural diagram of a point cloud segmentation system provided by an embodiment of the application.
  • This application can be applied to the scenario of processing point cloud data obtained by lidar.
  • it can be applied to intelligent driving fields such as automatic driving, assisted driving, and safe driving. It can detect obstacles such as vehicles and pedestrians in road scenes by processing point cloud data.
  • it can be applied to the field of drones, and can detect obstacles in the flying scene of drones.
  • it can be applied to the security field to detect objects entering a designated area.
  • FIG. 1 is a schematic diagram of an application scenario involved in this application.
  • the intelligent driving vehicle may include a lidar (not shown).
  • the lidar may be a rotary scanning type multi-line lidar with multiple transmitters and multiple receivers, and so on.
  • the lidar can obtain the point cloud data of the objects in the front lane (such as falling rocks, leftovers, dead branches, pedestrians, vehicles, etc.).
  • subsequent object recognition and detection can be performed based on the point cloud data to obtain detection information such as the three-dimensional position, orientation, and three-dimensional size of the object, and plan the state of intelligent driving based on the detection information, for example, For changing lanes, slowing down, or stopping, etc.
  • FIG. 1 is a schematic diagram of an application scenario of this application, and the application scenario of this application includes but is not limited to that shown in FIG. 1.
  • words such as “first” and “second” are used to distinguish the same items or similar items with basically the same function and effect. . Those skilled in the art can understand that words such as “first” and “second” do not limit the quantity and execution order, and words such as “first” and “second” do not limit the difference.
  • Fig. 2 is a flowchart of a point cloud segmentation method provided by an embodiment of the application.
  • the execution subject may be a point cloud segmentation system.
  • the point cloud segmentation system may be a separate device, such as a point cloud sensor with data processing functions.
  • the point cloud segmentation system may also be a distributed system, such as a memory, a processor, and a point cloud sensor set in different positions of the vehicle.
  • the point cloud segmentation method provided in this embodiment may include:
  • S201 Acquire point cloud data to be processed in the target area.
  • the target area can be different.
  • the target area in the field of vehicle intelligent driving, the target area may be the road area in front of the vehicle detected by the point cloud sensor.
  • the target area In the UAV field, the target area can be the area detected by the point cloud sensor in the UAV flight scene.
  • the point cloud sensor may be a lidar, a time of flight (TOF) sensor, etc., which are mounted on or integrated on a movable platform.
  • TOF time of flight
  • S202 Obtain a one-dimensional index value of each point cloud data according to the boundary information and the grid resolution of the three-dimensional map of the target area.
  • the range of the target area is greater than or equal to the range of the three-dimensional map of the target area.
  • the target area may be the area that can be detected by the lidar on the vehicle, and the three-dimensional map of the target area may be the three-dimensional map of the bridge.
  • the grid resolution is used to divide the three-dimensional map of the target area into grids.
  • the grid is a basic unit in a three-dimensional coordinate system. According to the boundary information and grid resolution of the three-dimensional map of the target area, the three-dimensional map of the target area can be divided into multiple grids, so as to obtain the one-dimensional index value of each point cloud data.
  • the one-dimensional index value of each point cloud data is related to the grid where the point cloud data is located, and the one-dimensional index value of each point cloud data also reflects the three-dimensional index value of the point cloud data in the target area or in the target area. The relative position on the map.
  • the one-dimensional index value of the point cloud data included in the same grid may be the same.
  • the boundary information of the three-dimensional map of the target area is used to define the three-dimensional position of the three-dimensional map, and this embodiment does not limit the implementation of the boundary information.
  • the boundary information of the three-dimensional map of the target area may include the coordinate values of the boundary points of the three-dimensional map, and the boundary points of the three-dimensional map may uniquely determine the three-dimensional map.
  • the boundary information of the three-dimensional map of the target area may include the minimum and maximum values of the three-dimensional map of the target area on three coordinate axes in the three-dimensional coordinate system.
  • the minimum and maximum values on the X axis are expressed as X min and X max in turn
  • the minimum and maximum values on the Y axis are expressed as Y min and Y max in turn
  • the minimum and maximum values on the Z axis Denoted as Z min and Z max in turn .
  • the grid resolution may include the unit resolution of three coordinate axes in the three-dimensional coordinate system, and this embodiment does not limit the specific value of the unit resolution.
  • FIG. 3 is a schematic diagram of a three-dimensional map and grid resolution of a target area provided by an embodiment of the application.
  • the grid resolution may include the unit resolution X res of the X axis, the unit resolution Y res of the Y axis, and the unit resolution Z res of the Z axis in the three-dimensional coordinate system.
  • the three-dimensional map of the target area may be divided into 8 grids. Among them, this embodiment does not limit the identification information of each grid. For example, they may be marked as grid 1 to grid 8, or they may be marked as grid A to grid H, respectively.
  • the density value of the point cloud data is used to indicate the point cloud density in a preset three-dimensional space, and the preset three-dimensional space includes the point cloud data.
  • Fig. 3 is also taken as an example to illustrate the density value of the point cloud data.
  • the density value of the point cloud data A is used to indicate the point cloud density in the preset three-dimensional space.
  • the preset three-dimensional space may include grid 3, grid 1, grid 4, and grid 7.
  • the density value of the point cloud data B is used to indicate the point cloud density in the preset three-dimensional space.
  • the preset three-dimensional space may include grid 8, grid 6, grid 7, and grid 4.
  • this embodiment does not limit the preset three-dimensional space.
  • S204 Segment the point cloud data to be processed according to the density value of each point cloud data to obtain multiple point cloud clusters.
  • the density of point cloud data obtained by lidar is not uniform, and the density of point cloud data changes with the change of distance. The closer to the lidar, the greater the density of the point cloud data. The farther away from the lidar, the lower the density of the point cloud data is usually. If the point cloud data is segmented based on the distance threshold judgment method, the accuracy of the point cloud segmentation will be low.
  • the one-dimensional index value of each point cloud data is obtained according to the boundary information and grid resolution of the three-dimensional map of the target area. The one-dimensional index value can reflect the relative positional relationship of the point cloud data in the target area.
  • the point cloud data to be processed in the target area may be point cloud data other than the ground point cloud data among the point cloud data obtained by lidar.
  • the point cloud data obtained by the lidar includes the point cloud data corresponding to the ground part, and the point cloud data of this part is useless for subsequent object detection and recognition. Therefore, removing the ground point cloud data not only reduces the amount of point cloud data, reduces the amount of calculation, but also improves the accuracy of point cloud data segmentation.
  • the point cloud segmentation method in S203, before obtaining the density value of each point cloud data according to the one-dimensional index value of each point cloud data, it may further include:
  • the invalid point cloud data is the point cloud data that is not in the three-dimensional map.
  • the point cloud data to be processed in the target area is not necessarily all valid point cloud data, and only the point cloud data located in the three-dimensional map of the target area is valid point cloud data.
  • the point cloud data to be processed in the target area is not necessarily all valid point cloud data, and only the point cloud data located in the three-dimensional map of the target area is valid point cloud data.
  • the point cloud segmentation method provided in this embodiment may further include:
  • the point cloud cluster is deleted.
  • the probability that the point cloud cluster is an invalid point cloud cluster is relatively high.
  • the accuracy and effectiveness of the obtained point cloud clusters are further improved.
  • obtaining the density value of each point cloud data according to the one-dimensional index value of each point cloud data may include:
  • the preset three-dimensional space is the first three-dimensional space.
  • the density value of the point cloud data is obtained.
  • the one-dimensional index value of the point cloud data can reflect the relative positional relationship of the point cloud data in the target area. For each point cloud data, according to the one-dimensional index value of all point cloud data in the target area, search for other point cloud data adjacent to the point cloud data in the preset three-dimensional space corresponding to the point cloud data, and obtain The number of other nearby point cloud data.
  • the preset three-dimensional space may be referred to as a first three-dimensional space. Then, according to the number of adjacent point cloud data and the first three-dimensional space, the density value of the point cloud data is obtained.
  • each point cloud data corresponds to a one-dimensional index value.
  • the first three-dimensional space corresponding to the point cloud data A may be referred to as the space H.
  • search the number of other point cloud data adjacent to the point cloud data A in the space H assuming that the number is 200.
  • the density value of the point cloud data A can be obtained according to the number of adjacent point cloud data 200 and the space H.
  • this embodiment does not limit the shape and size of the first three-dimensional space.
  • the first three-dimensional space may be a spherical space with the point cloud data as the center and the first preset distance as the radius.
  • obtaining the density value of the point cloud data includes:
  • the density value of the point cloud data is obtained.
  • this embodiment does not limit the specific value of the first preset distance.
  • the point cloud segmentation method provided in this embodiment may further include:
  • the one-dimensional index value of each point cloud data is sorted in ascending order or descending order to obtain a sequence of index values.
  • searching for neighboring point cloud data in the preset three-dimensional space according to the one-dimensional index value of each point cloud data may include:
  • the grids included in the preset three-dimensional space are determined.
  • the preset three-dimensional space is the first preset three-dimensional space. Since the one-dimensional index value of the point cloud data can reflect the relative positional relationship of the point cloud data in the target area, by sorting the one-dimensional index value of the point cloud data in ascending or descending order, the obtained index value sequence can further reflect the target The proximity relationship between point cloud data in the area. According to the index value sequence and the first preset three-dimensional space, the grids included in the first preset three-dimensional space are determined. Thus, the adjacent point cloud data is searched in the grid included in the first preset three-dimensional space.
  • This embodiment provides a point cloud segmentation method, including: obtaining point cloud data to be processed in a target area, and obtaining a one-dimensional index value of each point cloud data according to the boundary information and grid resolution of the three-dimensional map of the target area , Obtain the density value of each point cloud data according to the one-dimensional index value of each point cloud data, and divide the point cloud data to be processed according to the density value of each point cloud data to obtain multiple point cloud clusters.
  • the point cloud segmentation method provided in this embodiment segments the point cloud data based on the density of the point cloud data, which improves the accuracy of point cloud segmentation.
  • an implementation manner of obtaining a one-dimensional index value of point cloud data is provided.
  • obtaining the one-dimensional index value of each point cloud data according to the boundary information and the grid resolution of the three-dimensional map of the target area may include:
  • the position information of the point cloud data, the boundary information of the three-dimensional map and the grid resolution are used to obtain the data of each point cloud data.
  • One-dimensional index value is used.
  • the point cloud data is not in the three-dimensional map, it is determined that the one-dimensional index value of the point cloud data is a preset invalid value.
  • each point cloud data in the target area it is first determined whether the point cloud data is located in the three-dimensional map of the target area. If it is located in a three-dimensional map, it can be determined that the point cloud data is valid point cloud data, and further based on the position information of the point cloud data, the boundary information of the three-dimensional map, and the grid resolution, one part of each point cloud data can be obtained. Dimension index value. If it is not located in the three-dimensional map, determine that the point cloud data is invalid point cloud data, and directly determine that the one-dimensional index value of the invalid point cloud data is a preset invalid value.
  • the amount of calculation is reduced, the processing speed and efficiency are improved, and the accuracy and effectiveness of the one-dimensional index value of the point cloud data are improved.
  • this embodiment does not limit the specific value of the preset invalid value.
  • it can be any negative integer, such as -1.
  • obtaining the one-dimensional index value of each point cloud data may include:
  • the three-dimensional index value of the point cloud data is obtained.
  • the three-dimensional index value includes the index value of the grid where the point cloud data is located on the three-dimensional coordinate axis corresponding to the three-dimensional map.
  • the one-dimensional index value of the point cloud data is obtained.
  • the grid resolution may include the unit resolution X res of the X axis, the unit resolution Y res of the Y axis, and the unit resolution Z res of the Z axis in the three-dimensional coordinate system.
  • the numbers of the three-dimensional map on the X-axis, Y-axis and Z-axis in the three-dimensional coordinate system are expressed as (X num , Y num , Z num ).
  • the three-dimensional index value of the point cloud data is expressed as (Px i , Py i , Pz i ).
  • the minimum and maximum values of the three-dimensional map of the target area on the X-axis, Y-axis, and Z-axis in the three-dimensional coordinate system are expressed as X min , X max , Y min , Y max , Z min and Z max in sequence.
  • the three-dimensional index value of the point cloud data can be obtained by the following formula:
  • each grid in a three-dimensional map has a preset index value.
  • the grid where the point cloud data is located can be determined, and further, the preset index value of the grid can be determined as the three-dimensional index value of the point cloud data.
  • the one-dimensional index value Hash p of the point cloud data can be determined by the following formula:
  • Hash p P xi *Y num *Z num +P yi *Z num +P zi
  • the one-dimensional index value Hash p of the point cloud data can be determined by the following formula:
  • Hash p P yi *X num *Z num +P xi *Z num +P zi
  • the one-dimensional index value of the point cloud data can also be obtained in other ways, which is not limited in this embodiment.
  • FIG. 4 is a flowchart of another point cloud segmentation method provided by an embodiment of the application.
  • the point cloud data to be processed is segmented according to the density value of each point cloud data to obtain multiple point cloud clusters, which may include:
  • S401 Traverse the to-be-processed point cloud data to obtain a neighbor relationship tree.
  • S402 Acquire multiple point cloud clusters according to the neighbor relationship tree.
  • S401 traversing the to-be-processed point cloud data, may include:
  • the preset three-dimensional space is the second three-dimensional space.
  • the point cloud data and the adjacent point cloud data are generated The connection relationship between the point cloud data.
  • the preset three-dimensional space is the third three-dimensional space, and the third three-dimensional space is larger than the second three-dimensional space.
  • the second three-dimensional space and the third three-dimensional space are involved. It should be noted that this embodiment does not limit the shape and size of the second three-dimensional space and the third three-dimensional space.
  • the second three-dimensional space may be a spherical space with the point cloud data as the center and the second preset distance as the radius.
  • the third three-dimensional space may be a spherical space with the point cloud data as the center and the third preset distance as the radius.
  • This embodiment does not limit the specific values of the second preset distance and the third preset distance.
  • the second preset distance may have the same value as the first preset distance.
  • the second preset distance is denoted as r2
  • the third preset distance is denoted as r3.
  • the point cloud data P is the center of the sphere and the radius is r2.
  • the neighboring point cloud data is searched in the spherical space with the point cloud data P as the center of the sphere and the radius r3 as the radius.
  • the density value of the searched neighboring point cloud data is greater than the density value of the point cloud data P
  • a connection relationship between the point cloud data P and the neighboring point cloud data is generated.
  • the point cloud density is relatively high in a space with a relatively small distance from the point cloud data.
  • the point cloud data is adjacent to other point cloud data, and the connection relationship between the point cloud data is obtained based on the distance judgment, which improves the accuracy of establishing the proximity relationship.
  • the point cloud density is relatively low.
  • the method provided in this embodiment improves the accuracy of establishing the proximity relationship, and further improves the accuracy of point cloud segmentation in subsequent processing.
  • acquiring multiple point cloud clusters according to the neighbor relationship tree may include:
  • the proximity relationship between the point cloud data is established. Therefore, multiple point cloud data with the same root node in the neighbor relationship tree can be divided into the same point cloud cluster, thereby The segmentation of point cloud data is completed.
  • it may further include:
  • the one-dimensional index value of each point cloud data is sorted in ascending order or descending order to obtain a sequence of index values.
  • searching for neighboring point cloud data in the preset three-dimensional space according to the one-dimensional index value of each point cloud data may include:
  • the grids included in the preset three-dimensional space are determined.
  • the preset three-dimensional space can be called the first three-dimensional space. In this embodiment, it is applied to obtain point cloud clusters.
  • the preset three-dimensional space involved may be referred to as the second three-dimensional space and the third three-dimensional space.
  • FIGS. 5A-5B are schematic diagrams of the effect of point cloud data segmentation provided by embodiments of this application.
  • a lidar can be set on the vehicle to obtain point cloud data in a road scene.
  • point cloud data does not include ground point cloud data.
  • Fig. 5B shows a point cloud cluster obtained according to the point cloud segmentation method provided by the present application.
  • Fig. 6 is a schematic structural diagram of a point cloud segmentation system provided by an embodiment of the application.
  • the point cloud segmentation system provided in this embodiment is used to implement the point cloud segmentation method provided in any implementation manner of FIG. 2 to FIG. 4.
  • the point cloud segmentation system provided in this embodiment may include: a memory 62, a processor 61, and a point cloud sensor 63.
  • the point cloud segmentation system can be a separate sensor device, such as a point cloud sensor with data processing functions; in other embodiments, the point cloud segmentation system can also be a distributed system, such as a set Memory, processor and point cloud sensors at different locations in the vehicle.
  • the point cloud sensor 63 is used to obtain point cloud data to be processed in the target area
  • the memory 62 is used to store program codes
  • the processor 61 calls the program code, and when the program code is executed, is configured to perform the following operations:
  • the density value of each point cloud data is obtained according to the one-dimensional index value of each point cloud data, the density value of the point cloud data is used to indicate the point cloud density in a preset three-dimensional space, and the preset three-dimensional space Including the point cloud data;
  • the point cloud data to be processed is segmented according to the density value of each point cloud data to obtain multiple point cloud clusters.
  • the processor 61 is specifically configured to:
  • the point cloud data in the to-be-processed point cloud data if the point cloud data is in the three-dimensional map, then according to the position information of the point cloud data, the boundary information of the three-dimensional map, and all the point cloud data According to the grid resolution, the one-dimensional index value of each point cloud data is obtained.
  • the processor 61 is specifically configured to:
  • the three-dimensional index value of the point cloud data is acquired;
  • the three-dimensional index value includes the grid where the point cloud data is located.
  • the index values of the grids respectively on the three-dimensional coordinate axis corresponding to the three-dimensional map;
  • the processor 61 is further configured to:
  • the point cloud data is not in the three-dimensional map, it is determined that the one-dimensional index value of the point cloud data is a preset invalid value.
  • the processor 61 is specifically configured to:
  • the preset three-dimensional space is the first three-dimensional space
  • the first three-dimensional space is a spherical space with the point cloud data as a center and a first preset distance as a radius; the processor 61 is specifically configured to:
  • the density value of the point cloud data is acquired.
  • the processor 61 is specifically configured to:
  • the traversing the to-be-processed point cloud data includes:
  • the preset three-dimensional space is a second three-dimensional space
  • the adjacent point cloud data is searched in the preset three-dimensional space according to the one-dimensional index value of each point cloud data, and the density value of the adjacent point cloud data is greater than the density value of the point cloud data, then A connection relationship between the point cloud data and the adjacent point cloud data is generated; wherein the preset three-dimensional space is a third three-dimensional space, and the third three-dimensional space is larger than the second three-dimensional space.
  • the processor 61 is specifically configured to:
  • the multiple point cloud data with the same root node in the neighbor relationship tree are divided into the same point cloud cluster.
  • the processor 61 is further configured to:
  • the searching for neighboring point cloud data in a preset three-dimensional space according to the one-dimensional index value of each point cloud data includes:
  • the adjacent point cloud data is searched in the grid included in the preset three-dimensional space.
  • the processor 61 is further configured to
  • the invalid point cloud data is Point cloud data not in the three-dimensional map.
  • the point cloud data to be processed is point cloud data other than ground point cloud data among the point cloud data obtained by lidar.
  • the processor 61 is further configured to:
  • the point cloud cluster is deleted.
  • the point cloud segmentation system is a lidar.
  • the point cloud segmentation system provided in this embodiment is used to implement the point cloud segmentation method provided in any of the implementation manners of FIG. 2 to FIG. 4, and the technical solutions and technical effects are similar, and will not be repeated here.
  • the memory 62, the processor 61, and the point cloud sensor 63 may be integrated in one device, for example, integrated in a lidar.
  • the lidar can segment point cloud data.
  • the memory 62, the processor 61, and the point cloud sensor 63 may also be integrated in different devices.
  • the memory 62 and the processor 61 may be integrated in an electronic device with data processing capability, and the point cloud sensor 63 may be provided in a lidar. After the lidar obtains the point cloud data, it can send the point cloud data to the electronic device.
  • This application also provides a movable platform, which may include the point cloud segmentation system provided in the embodiment shown in FIG. 6. It should be noted that this embodiment does not limit the type of the movable platform, and it may be any device that can realize the segmentation of point cloud data. For example, it can be a drone, a vehicle, or other means of transportation.
  • a person of ordinary skill in the art can understand that all or part of the steps in the foregoing method embodiments can be implemented by a program instructing relevant hardware.
  • the aforementioned program can be stored in a computer readable storage medium. When the program is executed, it executes the steps including the foregoing method embodiments; and the foregoing storage medium includes: ROM, RAM, magnetic disk, or optical disk and other media that can store program codes.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Optical Radar Systems And Details Thereof (AREA)
  • Traffic Control Systems (AREA)

Abstract

La présente invention concerne un procédé et un système de segmentation de nuage de points et une plateforme mobile, le procédé de segmentation de nuage de points consistant à : acquérir, dans une région cible, des éléments de données de nuage de points à traiter (S201) ; acquérir, selon des informations de limite et une résolution de grille d'une carte tridimensionnelle de la région cible, des valeurs d'indice unidimensionnel des éléments respectifs de données de nuage de points (S202) ; acquérir, en fonction des valeurs d'indice unidimensionnel des éléments respectifs de données de nuage de points, des valeurs de densité des éléments respectifs de données de nuage de points (S203) ; et réaliser une segmentation, en fonction des valeurs de densité des éléments respectifs de données de nuage de points, sur les éléments de données de nuage de points à traiter, de façon à obtenir une pluralité de grappes de nuages de points (S204). Les données de nuage de points sont segmentées sur la base de la densité des données de nuage de points, améliorant ainsi la précision de la segmentation de nuage de points.
PCT/CN2019/103314 2019-08-29 2019-08-29 Procédé et système de segmentation de nuage de points, et plateforme mobile WO2021035618A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2019/103314 WO2021035618A1 (fr) 2019-08-29 2019-08-29 Procédé et système de segmentation de nuage de points, et plateforme mobile
CN201980034128.0A CN112166457A (zh) 2019-08-29 2019-08-29 点云分割方法、系统和可移动平台

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/103314 WO2021035618A1 (fr) 2019-08-29 2019-08-29 Procédé et système de segmentation de nuage de points, et plateforme mobile

Publications (1)

Publication Number Publication Date
WO2021035618A1 true WO2021035618A1 (fr) 2021-03-04

Family

ID=73860466

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/103314 WO2021035618A1 (fr) 2019-08-29 2019-08-29 Procédé et système de segmentation de nuage de points, et plateforme mobile

Country Status (2)

Country Link
CN (1) CN112166457A (fr)
WO (1) WO2021035618A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116797704A (zh) * 2023-08-24 2023-09-22 山东云海国创云计算装备产业创新中心有限公司 点云数据处理方法、系统、装置、电子设备及存储介质
CN116862985A (zh) * 2023-09-01 2023-10-10 江苏中安建设集团有限公司 一种土地高精度定位电子信息化监测方法

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112415490A (zh) * 2021-01-25 2021-02-26 天津卡雷尔机器人技术有限公司 一种基于2d激光雷达3d点云扫描装置及配准算法
CN113269897B (zh) * 2021-07-19 2021-11-09 深圳市信润富联数字科技有限公司 表面点云的获取方法、装置、设备及存储介质
CN113885567B (zh) * 2021-10-22 2023-08-04 北京理工大学 一种基于冲突搜索的多无人机的协同路径规划方法
CN115205717B (zh) * 2022-09-14 2022-12-20 广东汇天航空航天科技有限公司 障碍物点云数据处理方法以及飞行设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105354829A (zh) * 2015-10-08 2016-02-24 西北农林科技大学 一种自适应的点云数据分割方法
US20170023473A1 (en) * 2015-07-21 2017-01-26 Airbus Ds Electronics And Border Security Gmbh Method for segmenting the data of a 3d sensor produced in the presence of aerosol clouds for increasing the situational awareness and the location detection of obstacles
CN106600622A (zh) * 2016-12-06 2017-04-26 西安电子科技大学 一种基于超体素的点云数据分割方法
CN107239794A (zh) * 2017-05-18 2017-10-10 深圳市速腾聚创科技有限公司 点云数据分割方法和终端
CN107292276A (zh) * 2017-06-28 2017-10-24 武汉大学 一种车载点云聚类方法及系统
CN108596860A (zh) * 2018-05-10 2018-09-28 芜湖航飞科技股份有限公司 一种基于三维激光雷达的地面点云分割方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170023473A1 (en) * 2015-07-21 2017-01-26 Airbus Ds Electronics And Border Security Gmbh Method for segmenting the data of a 3d sensor produced in the presence of aerosol clouds for increasing the situational awareness and the location detection of obstacles
CN105354829A (zh) * 2015-10-08 2016-02-24 西北农林科技大学 一种自适应的点云数据分割方法
CN106600622A (zh) * 2016-12-06 2017-04-26 西安电子科技大学 一种基于超体素的点云数据分割方法
CN107239794A (zh) * 2017-05-18 2017-10-10 深圳市速腾聚创科技有限公司 点云数据分割方法和终端
CN107292276A (zh) * 2017-06-28 2017-10-24 武汉大学 一种车载点云聚类方法及系统
CN108596860A (zh) * 2018-05-10 2018-09-28 芜湖航飞科技股份有限公司 一种基于三维激光雷达的地面点云分割方法

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116797704A (zh) * 2023-08-24 2023-09-22 山东云海国创云计算装备产业创新中心有限公司 点云数据处理方法、系统、装置、电子设备及存储介质
CN116797704B (zh) * 2023-08-24 2024-01-23 山东云海国创云计算装备产业创新中心有限公司 点云数据处理方法、系统、装置、电子设备及存储介质
CN116862985A (zh) * 2023-09-01 2023-10-10 江苏中安建设集团有限公司 一种土地高精度定位电子信息化监测方法
CN116862985B (zh) * 2023-09-01 2023-11-10 江苏中安建设集团有限公司 一种土地高精度定位电子信息化监测方法

Also Published As

Publication number Publication date
CN112166457A (zh) 2021-01-01

Similar Documents

Publication Publication Date Title
WO2021035618A1 (fr) Procédé et système de segmentation de nuage de points, et plateforme mobile
CN109961440B (zh) 一种基于深度图的三维激光雷达点云目标分割方法
CN109509210B (zh) 障碍物跟踪方法和装置
WO2020043041A1 (fr) Procédé et dispositif de partitionnement de données en nuage de points, support de stockage, et dispositif électronique
EP3920095A1 (fr) Procédé et appareil de traitement d'image, plateforme mobile, engin volant sans pilote embarqué et support de stockage
US8199977B2 (en) System and method for extraction of features from a 3-D point cloud
WO2016106955A1 (fr) Procédé de navigation et reconnaissance de formation de sol composite par infrarouge au laser
CN112184736B (zh) 一种基于欧式聚类的多平面提取方法
CN113506318B (zh) 一种车载边缘场景下的三维目标感知方法
WO2024012211A1 (fr) Procédé de perception environnementale à conduite autonome, support et véhicule
CN111142514B (zh) 一种机器人及其避障方法和装置
CN113345008A (zh) 一种考虑轮式机器人位姿估计的激光雷达动态障碍物检测方法
CN111915517A (zh) 一种适用于室内光照不利环境下rgb-d相机全局定位方法
WO2024012212A1 (fr) Procédé de perception environnementale, contrôleur de domaine, support de stockage et véhicule
CN115718305A (zh) 一种激光点云公路断面处理方法、装置、设备及存储介质
CN113281782A (zh) 一种基于无人驾驶车的激光雷达雪点滤除方法
AU2022259832A1 (en) Target detection in a point cloud
CN113096181B (zh) 设备位姿的确定方法、装置、存储介质及电子装置
CN114973191A (zh) 基于点云密度和间距的动态阈值确定方法及欧式聚类方法
CN114187418A (zh) 回环检测方法、点云地图构建方法、电子设备及存储介质
CN108629315B (zh) 一种针对三维点云的多平面识别方法
CN104898106B (zh) 面向复杂地形机载激光雷达数据的地面点提取方法
CN111736167A (zh) 一种获取激光点云密度的方法和装置
WO2020248118A1 (fr) Procédé, système et dispositif de traitement de nuage de points, et support de stockage
CN117288177A (zh) 一种解决动态残影的激光slam方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19943451

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19943451

Country of ref document: EP

Kind code of ref document: A1