CN117830330A - Road point cloud segmentation method, device, equipment and storage medium - Google Patents
Road point cloud segmentation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117830330A CN117830330A CN202311861860.XA CN202311861860A CN117830330A CN 117830330 A CN117830330 A CN 117830330A CN 202311861860 A CN202311861860 A CN 202311861860A CN 117830330 A CN117830330 A CN 117830330A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- segmentation
- point
- segmented
- road
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 230000011218 segmentation Effects 0.000 title claims abstract description 210
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000005192 partition Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 8
- 230000008447 perception Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
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
- G06T7/11—Region-based segmentation
-
- 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30256—Lane; Road marking
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a road point cloud segmentation method, a device, equipment and a storage medium, and belongs to the technical field of point cloud segmentation. The method comprises the steps of obtaining a segmentation constraint boundary of a point cloud region to be segmented; adding the segmentation constraint boundary into a preset point cloud segmentation clustering strategy to divide the point cloud region to be segmented, so as to obtain a segmentation result; the road point cloud segmentation is completed through the segmentation result, and continuous point cloud with noise and error perception can be accurately segmented rapidly and effectively, so that the effect and accuracy of subsequent point cloud processing are greatly improved.
Description
Technical Field
The present invention relates to the field of point cloud segmentation technologies, and in particular, to a road point cloud segmentation method, device, equipment, and storage medium.
Background
Existing autopilot technology often requires processing of laser point clouds or image recognition point clouds. In the point cloud processing, taking the extraction of vector features as an example, the existing point cloud segmentation algorithm often causes difficult vectorization or poor effect because of the adhesion of large-scale point clouds and wrong point clouds.
In addition, the existing processing mode is easily affected by continuous noise or false perception, and the point clouds of different road sections after turning are difficult to divide, so that the division is inaccurate.
Disclosure of Invention
The invention mainly aims to provide a road point cloud segmentation method, a device, equipment and a storage medium, which aim to solve the technical problem of low accuracy of point cloud segmentation in the prior art.
In order to achieve the above object, the present invention provides a road point cloud segmentation method, which includes the following steps:
obtaining a segmentation constraint boundary of a point cloud region to be segmented;
adding the segmentation constraint boundary into a preset point cloud segmentation clustering strategy to divide the point cloud region to be segmented, so as to obtain a segmentation result;
and completing the road point cloud segmentation through the segmentation result.
Optionally, the adding the segmentation constraint boundary to a preset point cloud segmentation clustering strategy to divide the point cloud region to be segmented to obtain a segmentation result includes:
carrying out azimuth division on each point in the point cloud area to be segmented through the segmentation constraint boundary to obtain azimuth attributes of each point in the point cloud area to be segmented;
dividing and clustering each point in the point cloud area to be divided according to a preset point cloud dividing strategy and the azimuth attribute to obtain a clustering set;
and obtaining a segmentation result through the azimuth attribute and the clustering set.
Optionally, the performing azimuth division on each point in the to-be-segmented point cloud area through the segmentation constraint boundary to obtain an azimuth attribute of each point in the to-be-segmented point cloud area, including:
acquiring a preset distance threshold;
acquiring points, in the point cloud area to be segmented, of which the distance from the segmentation constraint boundary is smaller than or equal to the preset distance threshold value, so as to obtain a first point set;
and carrying out azimuth division on the first point set according to the division constraint boundary to obtain azimuth attributes of each point in the point cloud area to be divided.
Optionally, the performing the partition clustering on each point in the to-be-partitioned point cloud area through a preset point cloud partition strategy and the azimuth attribute to obtain a cluster set includes:
determining a clustering radius and searching an origin according to a preset point cloud segmentation strategy;
clustering each point in the point cloud area to be segmented according to the searching origin and the clustering radius to obtain a searching set;
and screening the search set through the azimuth attribute to obtain a clustering set.
Optionally, the filtering the search set through the azimuth attribute to obtain a cluster set includes:
acquiring the azimuth of each point in the search set through the azimuth attribute;
and when the azimuth of the searched point in the search set is different from the azimuth of the search origin, eliminating the searched point from the search set to obtain a clustering set.
Optionally, the acquiring the segmentation constraint boundary of the point cloud region to be segmented includes:
setting a topological road network of a point cloud area to be segmented;
obtaining a skeleton connecting edge of a point cloud area to be segmented according to the topological road network;
and obtaining a segmentation constraint boundary of the point cloud region to be segmented according to the skeleton connecting edge.
Optionally, the acquiring the segmentation constraint boundary of the point cloud region to be segmented includes:
obtaining skeleton nodes of the point cloud area to be segmented according to the topological road network;
acquiring skeleton connecting edges of adjacent branches in the skeleton nodes;
and obtaining the segmentation constraint boundary of the point cloud region to be segmented according to the angle bisection line segments of the skeleton connecting edges of the adjacent branches.
In addition, in order to achieve the above object, the present invention also provides a road point cloud segmentation apparatus, including:
the acquisition module is used for acquiring the segmentation constraint boundary of the point cloud region to be segmented;
the dividing module is used for adding the dividing constraint boundary into a preset point cloud dividing and clustering strategy to divide the point cloud region to be divided, so as to obtain a dividing result;
and the segmentation module is used for completing the road point cloud segmentation according to the segmentation result.
In addition, to achieve the above object, the present invention also proposes a road point cloud segmentation apparatus including: the road point cloud segmentation method comprises a memory, a processor and a road point cloud segmentation program stored on the memory and capable of running on the processor, wherein the road point cloud segmentation program is configured to realize the steps of the road point cloud segmentation method.
In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a road point cloud segmentation program which, when executed by a processor, implements the steps of the road point cloud segmentation method as described above.
The method comprises the steps of obtaining a segmentation constraint boundary of a point cloud region to be segmented; adding the segmentation constraint boundary into a preset point cloud segmentation clustering strategy to divide the point cloud region to be segmented, so as to obtain a segmentation result; the road point cloud segmentation is completed through the segmentation result, and continuous point cloud with noise and error perception can be accurately segmented rapidly and effectively, so that the effect and accuracy of subsequent point cloud processing are greatly improved.
Drawings
Fig. 1 is a schematic structural diagram of a road point cloud segmentation device of a hardware running environment according to an embodiment of the present invention;
FIG. 2 is a flowchart of a first embodiment of the road point cloud segmentation method according to the present invention;
FIG. 3 is a schematic view of a conventional intersection road edge point cloud segmentation;
FIG. 4 is a flowchart of a second embodiment of the road point cloud segmentation method according to the present invention;
FIG. 5 is a schematic diagram illustrating the azimuth division of each point in a point cloud region to be segmented by a segmentation constraint boundary according to an embodiment of the road point cloud segmentation method of the present invention;
FIG. 6 is a schematic diagram of performing segmentation clustering on points in a point cloud region to be segmented by presetting a point cloud segmentation strategy and azimuth attributes in an embodiment of a road point cloud segmentation method of the present invention;
FIG. 7 is a flowchart of a third embodiment of the road point cloud segmentation method according to the present invention;
fig. 8 is a schematic diagram of a topology road network structure of a point cloud region to be segmented in an embodiment of a road point cloud segmentation method according to the present invention;
fig. 9 is a block diagram of a first embodiment of the road point cloud segmentation apparatus according to the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of a road point cloud segmentation device of a hardware running environment according to an embodiment of the present invention.
As shown in fig. 1, the road point cloud segmentation apparatus may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the road point cloud segmentation apparatus, and may include more or fewer components than shown, or may combine certain components, or may be a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a road point cloud segmentation program may be included in the memory 1005 as one type of storage medium.
In the road point cloud segmentation apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the road point cloud segmentation device of the present invention may be disposed in the road point cloud segmentation device, where the road point cloud segmentation device invokes the road point cloud segmentation program stored in the memory 1005 through the processor 1001, and executes the road point cloud segmentation method provided by the embodiment of the present invention.
The embodiment of the invention provides a road point cloud segmentation method, and referring to fig. 2, fig. 2 is a flow chart of a first embodiment of the road point cloud segmentation method.
In this embodiment, the road point cloud segmentation method includes the following steps:
step S10: and obtaining the segmentation constraint boundary of the point cloud region to be segmented.
It should be noted that, the execution body of the embodiment may be a road point cloud segmentation device, or may be other devices that may implement the same or similar functions, which is not limited in this embodiment, and the embodiment is described by taking the road point cloud segmentation device as an example.
It should be noted that, in this embodiment, road edge is taken as an example to divide the road point cloud, as shown in fig. 3, fig. 3 is a schematic diagram of dividing the road edge point cloud of the existing crossroad, the left road section of the crossroad is closed, the right road section has a corner, many noises and incorrect perceptions exist in the point cloud in the diagram, and even incorrect point cloud adhesion occurs in the road section below the crossroad and the road section on the right.
In order to solve the above problem, in this embodiment, by setting a topology road network, a partition constraint boundary of a point cloud area to be partitioned is set according to the topology road network, so that point cloud partition in the point cloud area to be partitioned is assisted according to the partition constraint boundary.
It should be noted that the number of the division constraint boundaries may be multiple, and the division preset boundaries may be intersected or parallel, and may be set according to specific road point cloud data.
Step S20: and adding the segmentation constraint boundary into a preset point cloud segmentation clustering strategy to divide the point cloud region to be segmented, so as to obtain a segmentation result.
In specific implementation, the segmentation constraint boundary is added into a preset point cloud segmentation clustering strategy, so that the point cloud area to be segmented can be partitioned according to the topological road section, and a segmentation result is obtained.
It can be appreciated that the preset point cloud partition clustering strategy may be a plurality of clustering algorithms such as a DBScan clustering algorithm, a spectral clustering algorithm, a KMeans algorithm, and the like, which is not limited in this embodiment.
Step S30: and completing the road point cloud segmentation through the segmentation result.
It can be understood that the segmentation result of each point cloud in the point cloud region to be segmented can be obtained through the segmentation result, so that the road point cloud segmentation is completed. The algorithm automatic segmentation can be performed quickly and efficiently by applying the segmentation constraint boundary to the automatic clustering segmentation algorithm.
The embodiment obtains the segmentation constraint boundary of the point cloud region to be segmented; adding the segmentation constraint boundary into a preset point cloud segmentation clustering strategy to divide the point cloud region to be segmented, so as to obtain a segmentation result; the road point cloud segmentation is completed through the segmentation result, and continuous point cloud with noise and error perception can be accurately segmented rapidly and effectively, so that the effect and accuracy of subsequent point cloud processing are greatly improved.
Referring to fig. 4, fig. 4 is a flowchart illustrating a road point cloud segmentation method according to a second embodiment of the present invention.
Based on the above-mentioned first embodiment, the step S20 of the road point cloud segmentation method of the present embodiment includes:
step S201: and carrying out azimuth division on each point in the point cloud area to be segmented through the segmentation constraint boundary to obtain azimuth attributes of each point in the point cloud area to be segmented.
It should be noted that, the azimuth of each point in the point cloud area to be segmented may be firstly divided by the segmentation constraint boundary, so as to obtain the azimuth attribute of each point in the point cloud area to be segmented.
It will be appreciated that the azimuthal attribute of each point in the point cloud region to be segmented may include a point to the left of the segmentation constraint boundary or a point to the right of the segmentation constraint boundary.
Optionally, the step of obtaining the azimuth attribute of each point in the point cloud area to be segmented specifically includes:
acquiring a preset distance threshold; acquiring points, in the point cloud area to be segmented, of which the distance from the segmentation constraint boundary is smaller than or equal to the preset distance threshold value, so as to obtain a first point set; and carrying out azimuth division on the first point set according to the division constraint boundary to obtain azimuth attributes of each point in the point cloud area to be divided.
It should be understood that the preset distance threshold may be flexibly set according to the range of the point cloud area to be segmented of the road and the number of points in the point cloud area, for example, 1m, 2m, etc., which is not limited in this embodiment.
And searching points with the distance smaller than or equal to the preset distance threshold value from the point cloud area to be segmented to obtain a first point set by taking the preset distance threshold value as a searching radius and the segmentation constraint boundary as an origin point of searching.
In a specific implementation, the first point set may be divided according to the segmentation constraint boundary, so as to determine whether any point P in the first point set is on the Left side or the Right side of the segmentation constraint boundary, and add an attribute p.sx e (left|right) to each point in the first point set to obtain the azimuth of each point in the to-be-segmented point cloud region in the segmentation boundary, so as to obtain the azimuth attribute of each point.
As shown in fig. 5, fig. 5 is a schematic diagram of performing azimuth division on each point in a point cloud area to be segmented through a segmentation constraint boundary, and in fig. 5, E1-E12 are all segmentation constraint boundaries, and each point in the point cloud area to be segmented is subjected to azimuth division through the segmentation constraint boundary, so that whether a certain point is located on the left side or the right side of the segmentation constraint boundary is determined, azimuth attributes are added, each road section is segmented into the left side and the right side, and the segmentation effect is improved.
Step S202: and carrying out segmentation clustering on each point in the point cloud region to be segmented through a preset point cloud segmentation strategy and the azimuth attribute to obtain a clustering set.
It should be noted that, the clustering set may be obtained by presetting a point cloud segmentation strategy and the azimuth attribute of each point to segment and cluster each point in the point cloud area to be segmented.
Further, the step of obtaining a cluster set specifically includes:
determining a clustering radius and searching an origin according to a preset point cloud segmentation strategy; clustering each point in the point cloud area to be segmented according to the searching origin and the clustering radius to obtain a searching set; and screening the search set through the azimuth attribute to obtain a clustering set.
It should be understood that, in order to improve the segmentation clustering effect, the points which do not belong to the same azimuth are prevented from being clustered, and when the point cloud segmentation clustering is performed, the points can be further screened through azimuth attributes, so that the segmentation accuracy is improved.
In specific implementation, the preset point cloud segmentation strategy is a point cloud segmentation clustering algorithm, for example, a DBScan segmentation clustering algorithm, wherein the core idea of the DBScan algorithm is to divide point cloud data by defining a neighborhood radius and a minimum density threshold, the algorithm firstly selects an unaccessed point and finds all points in the neighborhood of the point, and if the number of the points in the neighborhood of the point is greater than or equal to the minimum density threshold, the point is regarded as a core point and a new cluster is created for the point. Each core point neighborhood is then recursively traversed, adding points within its neighborhood to the same cluster. If the number of points in the neighborhood of a point is less than the minimum density threshold, but it is in the neighborhood of another core point, the point is marked as a boundary point, belonging to the cluster in which the core point is located. If a point does not belong within the neighborhood of any core point, the point is marked as a noise point.
In this embodiment, a cluster radius and a search origin may be set according to a preset point cloud segmentation policy, where the cluster radius is greater than a preset distance threshold, and the search origin may be flexibly selected, for example, the search origin may be located at the left side of the segmentation constraint boundary, and the search origin may also be located at the right side of the segmentation constraint boundary.
It can be understood that the points in the point cloud area to be segmented can be clustered through the searching origin and the clustering radius, so that a clustered searching set is obtained, and the searching set is screened through the azimuth attribute, so that a final clustering set is obtained.
In a specific implementation, each point in the point cloud area to be segmented can be clustered at the search origin point by taking the clustering radius as a search condition, and if the distance from the point to the search origin point is smaller than or equal to the clustering radius, the point is taken as the point in the search set.
It should be noted that, the points in the search set may be located at the same azimuth as the search origin, and may also be located at a different azimuth from the search origin, so that the search set needs to be screened according to the azimuth attribute, and the screening of the search set by the azimuth attribute to obtain a cluster set includes: acquiring the azimuth of each point in the search set through the azimuth attribute; and when the azimuth of the searched point in the search set is different from the azimuth of the search origin, eliminating the searched point from the search set to obtain a clustering set.
It should be understood that the azimuth of each point in the search set may be obtained through the azimuth attribute of each point, and the azimuth of each point in the search set may be compared with the azimuth of the search origin, if the azimuth of the search origin is different from the azimuth of the searched point in the search set, for example, the azimuth of the search origin is that the search origin is located on the left side of the segmentation constraint boundary, and if the azimuth of the searched point in the search set is that the point is located on the right side of the segmentation constraint boundary, the searched point is removed from the search set if the azimuth of the point in the search set is different from the azimuth of the searched point in the search set, and if the azimuth of the search origin is consistent with the azimuth of the searched point in the search set, the searched point is reserved, so that each point in the search set is traversed, and if the point different from the azimuth of the search origin is removed from the search set, so as to obtain the cluster set.
As shown in fig. 6, fig. 6 is a schematic diagram of performing segmentation clustering on each point in a point cloud area to be segmented through a preset point cloud segmentation strategy and an azimuth attribute, wherein the azimuth attribute includes that the point is located on the left side of a segmentation constraint boundary and on the right side of the segmentation constraint boundary, and the points which are located in the same azimuth with the search origin and have the distance smaller than or equal to the clustering radius are summarized through determining the search origin and the clustering radius, so as to obtain a clustering set, namely, a point a, a point B, a point C, a point D and a point E which are located in the same azimuth with the search origin in fig. 6.
Step S203: and obtaining a segmentation result through the azimuth attribute and the clustering set.
In a specific implementation, the azimuth attribute and the cluster set can be used as a segmentation result of the point cloud region to be segmented. And clustering and segmentation of each point in the point cloud area to be segmented are completed by obtaining the clustering and segmentation conditions of each point through the azimuth attribute and the clustering set.
According to the embodiment, azimuth division is carried out on each point in the point cloud area to be segmented through the segmentation constraint boundary, so that azimuth attributes of each point in the point cloud area to be segmented are obtained; dividing and clustering each point in the point cloud area to be divided according to a preset point cloud dividing strategy and the azimuth attribute to obtain a clustering set; and obtaining a segmentation result through the azimuth attribute and the clustering set, and applying a segmentation constraint boundary to a preset point cloud segmentation strategy to quickly and efficiently perform automatic point cloud segmentation.
Referring to fig. 7, fig. 7 is a flowchart illustrating a third embodiment of a road point cloud segmentation method according to the present invention.
Based on the above first embodiment, the step S10 of the road point cloud segmentation method of the present embodiment includes:
step S101: and setting a topological road network of the point cloud area to be segmented.
It should be noted that, the topology road network is a road skeleton, so the topology road network can be set according to the acquired point cloud area to be segmented.
The data sources of the topology road network generally comprise map vendor supply, algorithm generation or manual drawing by map production personnel.
Step S102: and obtaining skeleton connecting edges of the point cloud areas to be segmented according to the topological road network.
In the implementation, the skeleton connecting edge in the topological road network is called Link, and the skeleton connecting edge of the point cloud area to be segmented can be obtained through the topological road network.
Step S103: and obtaining a segmentation constraint boundary of the point cloud region to be segmented according to the skeleton connecting edge.
In a specific implementation, all Link in the point cloud area to be segmented can be used as a segmentation constraint boundary E of the point cloud area to be segmented.
Optionally, the topology road network further includes skeleton nodes besides skeleton connecting edges, and the step of obtaining the partition constraint boundary of the point cloud region to be partitioned further includes: obtaining skeleton nodes of the point cloud area to be segmented according to the topological road network; acquiring skeleton connecting edges of adjacent branches in the skeleton nodes; and obtaining the segmentation constraint boundary of the point cloud region to be segmented according to the angle bisection line segments of the skeleton connecting edges of the adjacent branches.
It should be noted that, skeleton nodes of the point cloud area to be segmented can be obtained according to a topology road network, as shown in fig. 8, fig. 8 is a schematic diagram of the topology road network structure of the point cloud area to be segmented, skeleton connecting edges are called links, and skeleton nodes are called joints.
In a specific implementation, the skeleton connecting edges of each adjacent branch in the skeleton node can be obtained, an angle bisection line segment of the skeleton connecting edge of the adjacent branch is set as a segmentation constraint boundary of the point cloud area to be segmented, the fixed length of the angle bisection line segment is set as L, and when the skeleton and the point Joint are connected with only one skeleton connecting edge Link, the segmentation constraint boundary E can be arranged according to 180-degree diagonal angles of the Link.
Alternatively, in arranging the division constraint boundary E, the arrangement may be performed by a Delauny triangle network or the like constituted by a topology road network, which is not limited in this embodiment.
The embodiment sets a topological road network of the point cloud area to be segmented; obtaining a skeleton connecting edge of a point cloud area to be segmented according to the topological road network; and obtaining a segmentation constraint boundary of the point cloud region to be segmented according to the skeleton connecting edge, and connecting the segmentation constraint boundary through a topological road network, thereby improving the segmentation effect and accuracy of the road characteristic point cloud.
Referring to fig. 9, fig. 9 is a block diagram illustrating a first embodiment of a road point cloud segmentation apparatus according to the present invention.
As shown in fig. 9, the road point cloud segmentation apparatus provided by the embodiment of the present invention includes:
the obtaining module 10 is configured to obtain a segmentation constraint boundary of the point cloud region to be segmented.
The dividing module 20 is configured to add the segmentation constraint boundary into a preset point cloud segmentation clustering policy to divide the point cloud region to be segmented, so as to obtain a segmentation result.
And the segmentation module 30 is used for completing road point cloud segmentation according to the segmentation result.
The embodiment obtains the segmentation constraint boundary of the point cloud region to be segmented; adding the segmentation constraint boundary into a preset point cloud segmentation clustering strategy to divide the point cloud region to be segmented, so as to obtain a segmentation result; the road point cloud segmentation is completed through the segmentation result, and continuous point cloud with noise and error perception can be accurately segmented rapidly and effectively, so that the effect and accuracy of subsequent point cloud processing are greatly improved.
In an embodiment, the dividing module 20 is further configured to perform azimuth division on each point in the to-be-divided point cloud area through the division constraint boundary, so as to obtain an azimuth attribute of each point in the to-be-divided point cloud area; dividing and clustering each point in the point cloud area to be divided according to a preset point cloud dividing strategy and the azimuth attribute to obtain a clustering set; and obtaining a segmentation result through the azimuth attribute and the clustering set.
In an embodiment, the dividing module 20 is further configured to obtain a preset distance threshold; acquiring points, in the point cloud area to be segmented, of which the distance from the segmentation constraint boundary is smaller than or equal to the preset distance threshold value, so as to obtain a first point set; and carrying out azimuth division on the first point set according to the division constraint boundary to obtain azimuth attributes of each point in the point cloud area to be divided.
In an embodiment, the partitioning module 20 is further configured to determine a cluster radius and a search origin according to a preset point cloud partitioning strategy; clustering each point in the point cloud area to be segmented according to the searching origin and the clustering radius to obtain a searching set; and screening the search set through the azimuth attribute to obtain a clustering set.
In an embodiment, the dividing module 20 is further configured to obtain the azimuth of each point in the search set through the azimuth attribute; and when the azimuth of the searched point in the search set is different from the azimuth of the search origin, eliminating the searched point from the search set to obtain a clustering set.
In an embodiment, the obtaining module 10 is further configured to set a topology road network of the point cloud area to be segmented; obtaining a skeleton connecting edge of a point cloud area to be segmented according to the topological road network; and obtaining a segmentation constraint boundary of the point cloud region to be segmented according to the skeleton connecting edge.
In an embodiment, the obtaining module 10 is further configured to obtain skeleton nodes of the point cloud area to be segmented according to the topology road network; acquiring skeleton connecting edges of adjacent branches in the skeleton nodes; and obtaining the segmentation constraint boundary of the point cloud region to be segmented according to the angle bisection line segments of the skeleton connecting edges of the adjacent branches.
In addition, the embodiment of the invention also provides a storage medium, wherein the storage medium stores a road point cloud segmentation program, and the road point cloud segmentation program realizes the steps of the road point cloud segmentation method when being executed by a processor.
Because the storage medium adopts all the technical schemes of all the embodiments, the storage medium has at least all the beneficial effects brought by the technical schemes of the embodiments, and the description is omitted here.
It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the invention as desired, and the invention is not limited thereto.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details not described in detail in the present embodiment may refer to the road point cloud segmentation method provided in any embodiment of the present invention, which is not described herein.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. The road point cloud segmentation method is characterized by comprising the following steps of:
obtaining a segmentation constraint boundary of a point cloud region to be segmented;
adding the segmentation constraint boundary into a preset point cloud segmentation clustering strategy to divide the point cloud region to be segmented, so as to obtain a segmentation result;
and completing the road point cloud segmentation through the segmentation result.
2. The method of claim 1, wherein adding the segmentation constraint boundary into a preset point cloud segmentation clustering strategy to divide the point cloud region to be segmented to obtain a segmentation result comprises:
carrying out azimuth division on each point in the point cloud area to be segmented through the segmentation constraint boundary to obtain azimuth attributes of each point in the point cloud area to be segmented;
dividing and clustering each point in the point cloud area to be divided according to a preset point cloud dividing strategy and the azimuth attribute to obtain a clustering set;
and obtaining a segmentation result through the azimuth attribute and the clustering set.
3. The method of claim 2, wherein the performing azimuth division on each point in the to-be-segmented point cloud region by using the segmentation constraint boundary to obtain the azimuth attribute of each point in the to-be-segmented point cloud region comprises:
acquiring a preset distance threshold;
acquiring points, in the point cloud area to be segmented, of which the distance from the segmentation constraint boundary is smaller than or equal to the preset distance threshold value, so as to obtain a first point set;
and carrying out azimuth division on the first point set according to the division constraint boundary to obtain azimuth attributes of each point in the point cloud area to be divided.
4. The method of claim 2, wherein the performing the partition clustering on the points in the to-be-partitioned point cloud region by using the preset point cloud partition strategy and the azimuth attribute to obtain the cluster set includes:
determining a clustering radius and searching an origin according to a preset point cloud segmentation strategy;
clustering each point in the point cloud area to be segmented according to the searching origin and the clustering radius to obtain a searching set;
and screening the search set through the azimuth attribute to obtain a clustering set.
5. The method of claim 4, wherein the filtering the search set by the azimuth attribute to obtain a cluster set comprises:
acquiring the azimuth of each point in the search set through the azimuth attribute;
and when the azimuth of the searched point in the search set is different from the azimuth of the search origin, eliminating the searched point from the search set to obtain a clustering set.
6. The method of claim 1, wherein the obtaining the segmentation constraint boundary of the point cloud region to be segmented comprises:
setting a topological road network of a point cloud area to be segmented;
obtaining a skeleton connecting edge of a point cloud area to be segmented according to the topological road network;
and obtaining a segmentation constraint boundary of the point cloud region to be segmented according to the skeleton connecting edge.
7. The method of road point cloud segmentation as set forth in claim 6, wherein the acquiring a segmentation constraint boundary of a point cloud region to be segmented comprises:
obtaining skeleton nodes of the point cloud area to be segmented according to the topological road network;
acquiring skeleton connecting edges of adjacent branches in the skeleton nodes;
and obtaining the segmentation constraint boundary of the point cloud region to be segmented according to the angle bisection line segments of the skeleton connecting edges of the adjacent branches.
8. A road point cloud segmentation apparatus, characterized in that the road point cloud segmentation apparatus comprises:
the acquisition module is used for acquiring the segmentation constraint boundary of the point cloud region to be segmented;
the dividing module is used for adding the dividing constraint boundary into a preset point cloud dividing and clustering strategy to divide the point cloud region to be divided, so as to obtain a dividing result;
and the segmentation module is used for completing the road point cloud segmentation according to the segmentation result.
9. A road point cloud segmentation apparatus, characterized in that the road point cloud segmentation apparatus comprises: a memory, a processor, and a road point cloud segmentation program stored on the memory and executable on the processor, the road point cloud segmentation program configured to implement the road point cloud segmentation method of any one of claims 1-7.
10. A storage medium having stored thereon a road point cloud segmentation program which, when executed by a processor, implements the road point cloud segmentation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311861860.XA CN117830330A (en) | 2023-12-29 | 2023-12-29 | Road point cloud segmentation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311861860.XA CN117830330A (en) | 2023-12-29 | 2023-12-29 | Road point cloud segmentation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117830330A true CN117830330A (en) | 2024-04-05 |
Family
ID=90516864
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311861860.XA Pending CN117830330A (en) | 2023-12-29 | 2023-12-29 | Road point cloud segmentation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117830330A (en) |
-
2023
- 2023-12-29 CN CN202311861860.XA patent/CN117830330A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10360672B2 (en) | Automated separation of binary overlapping trees | |
| US8738559B2 (en) | Graph partitioning with natural cuts | |
| CN111090712A (en) | Data processing method, device and equipment and computer storage medium | |
| CN110704560B (en) | Method and device for structuring lane line group based on road level topology | |
| CN110428386B (en) | Map grid merging method and device, storage medium and electronic device | |
| EP3608798A1 (en) | Group search method based on social network, device, server and storage medium | |
| CN112100450A (en) | Graph calculation data segmentation method, terminal device and storage medium | |
| JP2020042793A (en) | Obstacle distribution simulation method, device, and terminal based on probability plot | |
| CN104809751A (en) | Method and device for generating event group evolution diagram | |
| Li et al. | An area merging method in map generalization considering typical characteristics of structured geographic objects | |
| CN114610825A (en) | Method and device for confirming associated grid set, electronic equipment and storage medium | |
| CN110728735A (en) | Road-level topological layer construction method and system | |
| CN113285960B (en) | Data encryption method and system for service data sharing cloud platform | |
| CN112215864B (en) | Contour processing method and device of electronic map and electronic equipment | |
| KR101878213B1 (en) | Method, apparatus and computer program for summaring of a weighted graph | |
| CN112887910B (en) | Method and device for determining abnormal coverage area and computer readable storage medium | |
| CN117830330A (en) | Road point cloud segmentation method, device, equipment and storage medium | |
| CN105183810A (en) | Simplification method and apparatus for road network | |
| CN109256774B (en) | Power grid subgraph division method and device based on voltage class | |
| KR20230005070A (en) | Method for updating road information, apparatus for updating road information, electronic equipment, storage medium, and computer program | |
| CN110569546A (en) | Traffic cell division method and device | |
| US20190108289A1 (en) | System for efficiently carrying out a dynamic program for optimization in a graph | |
| CN115048412A (en) | Docking point dividing method and device, computer equipment and storage medium | |
| CN114863300A (en) | Shortest path generation method and device | |
| CN115878989A (en) | Model training method, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |