CN115049551A - Method, device, equipment and storage medium for filtering point cloud ground points - Google Patents
Method, device, equipment and storage medium for filtering point cloud ground points Download PDFInfo
- Publication number
- CN115049551A CN115049551A CN202210657607.1A CN202210657607A CN115049551A CN 115049551 A CN115049551 A CN 115049551A CN 202210657607 A CN202210657607 A CN 202210657607A CN 115049551 A CN115049551 A CN 115049551A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- target
- point
- clustering
- normal vector
- 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
- 238000001914 filtration Methods 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 62
- 239000013598 vector Substances 0.000 claims abstract description 78
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 5
- 239000000126 substance Substances 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a method, a device, equipment and a storage medium for filtering point cloud ground points. The method comprises the steps of obtaining target three-dimensional point cloud data to be filtered; clustering each cloud point in the target three-dimensional point cloud data according to a preset clustering algorithm to obtain a plurality of clustering sets; identifying at least one target clustering set matched with the ground in each clustering set, and calculating a normal vector mean value according to a normal vector of each target point cloud point in each target clustering set; and identifying and filtering all point cloud ground points in the target three-dimensional point cloud data according to the numerical difference between the normal vector and the normal vector mean value of each point cloud point in the target three-dimensional point cloud data. The technical scheme of the embodiment of the invention provides a method for filtering point cloud ground points, which effectively improves the non-ground point loss, improves the accuracy of ground point filtering and enlarges the application range of the method for filtering point cloud ground points.
Description
Technical Field
The invention relates to the technical field of point cloud filtering, in particular to a method, a device, equipment and a storage medium for filtering point cloud ground points.
Background
Filtering ground data is an important step of laser radar data preprocessing, and a common method at present is a method for realizing segmentation of ground points and non-ground points based on angle differentiation. The algorithm organizes point clouds in the form of rays, reduces the three-dimensional space of the point clouds to a two-dimensional plane, calculates the plane included angle from each point to the positive direction of a radar, differentiates 360 degrees by the angular resolution of the laser radar, sorts the points on a wire harness at the same angle according to the radius, and judges whether the points are ground points or not by judging whether the slopes of the front and rear points are larger than a set threshold value or not.
In the process of implementing the invention, the inventor finds that the prior art has the following defects: 1. non-ground points are easily misclassified, resulting in non-ground point loss. 2. There is a small amount of noise and the ground cannot be completely filtered. 3. The use has limitations and can only be used on mechanical lidar.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for filtering point cloud ground points, which are used for effectively improving the loss of non-ground points, improving the accuracy of ground point filtering and enlarging the application range of the method for filtering the point cloud ground points.
According to an aspect of the present invention, there is provided a method for filtering point cloud ground points, the method comprising:
acquiring target three-dimensional point cloud data to be filtered;
clustering each cloud point in the target three-dimensional point cloud data according to a preset clustering algorithm to obtain a plurality of clustering sets;
identifying at least one target clustering set matched with the ground in each clustering set, and calculating a normal vector mean value according to a normal vector of each target point cloud point in each target clustering set;
and identifying and filtering all point cloud ground points in the target three-dimensional point cloud data according to the numerical difference between the normal vector and the normal vector mean value of each point cloud point in the target three-dimensional point cloud data.
According to another aspect of the present invention, there is provided a filtering apparatus for point cloud ground points, the apparatus comprising:
the target three-dimensional point cloud data acquisition module is used for acquiring target three-dimensional point cloud data to be filtered;
the cluster set acquisition module is used for clustering each cloud point in the target three-dimensional point cloud data according to a preset clustering algorithm to obtain a plurality of cluster sets;
the normal vector mean value calculation module is used for identifying at least one target cluster set matched with the ground in each cluster set and calculating a normal vector mean value according to the normal vector of each target point cloud point in each target cluster set;
and the point cloud ground point filtering module is used for identifying and filtering all point cloud ground points in the target three-dimensional point cloud data according to the value difference between the normal vector and the normal vector mean value of each point cloud point in the target three-dimensional point cloud data.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method of filtering point cloud ground points as described in any of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the method for filtering point cloud ground points according to any one of the embodiments of the present invention.
According to the technical scheme of the embodiment of the invention, target three-dimensional point cloud data to be filtered are obtained; clustering each cloud point in the target three-dimensional point cloud data according to a preset clustering algorithm to obtain a plurality of clustering sets; identifying at least one target clustering set matched with the ground in each clustering set, and calculating a normal vector mean value according to a normal vector of each target point cloud point in each target clustering set; the technical means of identifying and filtering all point cloud ground points in the target three-dimensional point cloud data according to the numerical difference between the normal vector and the normal vector mean value of each point cloud point in the target three-dimensional point cloud data provides a point cloud ground point filtering method, which effectively improves the non-ground point missing, improves the accuracy of ground point filtering and enlarges the application range of the point cloud ground point filtering method.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a method for filtering out point cloud ground points according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a filtering apparatus for point cloud ground points according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device implementing the method for filtering point cloud ground points according to the embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present invention and the above-described drawings, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Fig. 1 is a flowchart of a filtering method for point cloud ground points according to an embodiment of the present invention, where the method is applicable to a situation of filtering ground point clouds in the point clouds, and the method may be implemented by a filtering apparatus for point cloud ground points, where the apparatus may be implemented in a form of hardware and/or software, and the apparatus may be configured in a main processor of an ROS (Robot Operating System). As shown in fig. 1, the method includes:
and S110, acquiring target three-dimensional point cloud data to be filtered.
The target three-dimensional point cloud data to be filtered can be point cloud data obtained by scanning a target scene through a laser radar. In this embodiment, the target three-dimensional point cloud data to be filtered may be obtained by down-sampling the originally acquired point cloud data.
In an optional embodiment, the target three-dimensional point cloud data to be filtered is obtained, specifically, dense point cloud data acquired by a laser radar is obtained, and the dense point cloud data is subjected to downsampling processing to obtain sparse target three-dimensional point cloud data.
The dense point cloud data may refer to original point cloud data acquired for the target scene.
The method has the advantages that the amount of point cloud data needing to be processed can be reduced, so that the workload is reduced, and the processing efficiency is improved.
And S120, clustering each cloud point in the target three-dimensional point cloud data according to a preset clustering algorithm to obtain a plurality of clustering sets.
The preset clustering algorithm may be a preset algorithm for clustering the target three-dimensional point cloud data, for example, a region growing algorithm. The point cloud points in each cluster set may have the same or similar characteristics.
In this embodiment, each cloud point in the target three-dimensional point cloud data may be analyzed according to a preset clustering algorithm, so as to obtain a plurality of clustering sets.
S130, identifying at least one target cluster set matched with the ground in each cluster set, and calculating a normal vector mean value according to the normal vector of each target point cloud point in each target cluster set.
The target cluster set may refer to a set of point cloud points with ground features, and the number of the target cluster sets may be one or more. For example, point cloud points belonging to the same object may be substantially clustered into a cluster set. The target point cloud points may refer to point cloud points in the target cluster set. The normal vector mean may refer to a mean of normal vectors of cloud points of all target points in all target cluster sets.
In this embodiment, at least one target cluster set matched with the ground may be identified from the plurality of cluster sets, and the mean value of the normal vectors of all the target point cloud points is calculated by using the total number of all the target point cloud points in all the target cluster sets as a base number according to the normal vector of each target point cloud point in each target cluster set.
In an optional embodiment, in each cluster set, identifying at least one target cluster set matching the ground, specifically by obtaining a cluster center corresponding to each cluster set; identifying a target clustering center with the lowest elevation from all clustering centers; respectively calculating an included angle and an elevation difference between each clustering center and the target clustering center, and acquiring similar clustering centers of which the included angles meet an angle similarity condition and the elevation differences meet an elevation similarity condition; and acquiring at least one target clustering set respectively corresponding to the target clustering center and the similar clustering center.
The cluster center may refer to a representative cloud point in the cluster set. Each cluster set may have a corresponding cluster center. The angle similarity condition may refer to that the included angle between the other clustering center and the target clustering center satisfies an included angle threshold, and it may be determined that the other clustering center that does not exceed the included angle threshold satisfies the angle similarity condition. The elevation similarity condition may indicate that elevation differences between other clustering centers and the target clustering center satisfy an elevation difference threshold, and it may be determined that other clustering centers that do not exceed the elevation difference threshold satisfy the elevation similarity condition. Similar cluster centers may refer to other cluster centers that have similar characteristics as the target cluster center.
In this embodiment, for each cluster set, a corresponding cluster center may be obtained, and further, according to the value of the elevation of each cluster center, a cluster center with the lowest value of the elevation is identified as a target cluster center from all cluster centers. And calculating the included angle and the elevation difference between each other clustering center except the target clustering center and the target clustering center, so that according to the set angle similarity condition and the set elevation similarity condition, the other clustering centers meeting the angle similarity condition and the elevation similarity condition are determined as similar clustering centers corresponding to the target clustering center, and the clustering sets respectively corresponding to the target clustering center and the similar clustering centers are determined as target clustering sets.
The method has the advantages that on the basis of identifying the similar clustering centers, the target clustering center and the clustering set corresponding to the similar clustering centers are determined to be the target clustering set matched with the ground, and the accuracy rate of identifying the cloud points of the ground points can be improved.
Optionally, before calculating a normal vector mean value according to the normal vector of each target point cloud point in each target cluster set, the method may further include: acquiring a cloud point of a current processing point from the target three-dimensional point cloud data, and searching a plurality of neighborhood point cloud points matched with the cloud point of the current processing point; determining a point cloud plane matched with the currently processed electric cloud point according to each neighborhood point cloud point; and calculating a normal vector corresponding to the point cloud plane as a normal vector of the cloud point of the current processing point.
The neighborhood point cloud points can refer to the nearest point cloud points around the current processing point cloud point, the neighborhood point cloud points and the current processing point cloud points can form a plane, and the number of the neighborhood point cloud points can be at least two.
Specifically, for a cloud point of a current processing point in the target three-dimensional point cloud data, a plurality of neighborhood point cloud points of the cloud point of the current processing point can be obtained, a point cloud plane matched with the cloud point of the current processing point is determined, and a normal vector of the point cloud plane is used as a normal vector of the cloud point of the current processing point.
And S140, identifying and filtering all point cloud ground points in the target three-dimensional point cloud data according to the numerical difference between the normal vector and the normal vector mean value of each point cloud point in the target three-dimensional point cloud data.
In this embodiment, all point cloud ground points can be identified and filtered according to the normal vectors of the cloud points of each point in the target three-dimensional point cloud data and the numerical difference between the normal vector means.
In an optional embodiment, all point cloud ground points are identified and filtered in the target three-dimensional point cloud data according to the numerical difference between the normal vector and the normal vector mean value of each point cloud point in the target three-dimensional point cloud data, and a ground point index value is added to the point cloud ground points with the target included angles smaller than or equal to an included angle threshold value by respectively calculating the target included angles between the normal vector and the normal vector mean value of each point cloud point in the target three-dimensional point cloud data; and filtering all point cloud ground points containing the ground point index value in the target three-dimensional point cloud data.
The ground point index value can be used for searching out ground points from a large number of point cloud points of the target three-dimensional point cloud data.
Specifically, the included angle between the normal vector of each point cloud point in the target three-dimensional point cloud data and the normal vector mean value can be respectively calculated, the magnitude relation between each included angle and the included angle threshold value is judged, and the ground point index value is added for the point cloud ground points smaller than or equal to the included angle threshold value, so that all the point cloud ground points containing the ground point index value are filtered in the target three-dimensional point cloud data.
According to the technical scheme of the embodiment of the invention, target three-dimensional point cloud data to be filtered are obtained; clustering each cloud point in the target three-dimensional point cloud data according to a preset clustering algorithm to obtain a plurality of clustering sets; identifying at least one target clustering set matched with the ground in each clustering set, and calculating a normal vector mean value according to a normal vector of each target point cloud point in each target clustering set; the technical means of identifying and filtering all point cloud ground points in the target three-dimensional point cloud data according to the numerical difference between the normal vector and the normal vector mean value of each point cloud point in the target three-dimensional point cloud data provides a point cloud ground point filtering method, which effectively improves the non-ground point missing, improves the accuracy of ground point filtering and enlarges the application range of the point cloud ground point filtering method.
On the basis of the above technical solution, before clustering each cloud point in the target three-dimensional point cloud data according to a preset clustering algorithm to obtain a plurality of cluster sets, the method may further include: and filtering noise point cloud points included in the target three-dimensional point cloud data according to a preset point cloud denoising algorithm.
The advantage of this arrangement is that the amount of data processed can be reduced and the interference caused by noise point cloud points during the process of filtering ground points can be avoided.
Before clustering each cloud point in the target three-dimensional point cloud data according to a preset clustering algorithm to obtain a plurality of cluster sets, the method may further include: and point cloud cutting is carried out on the target three-dimensional point cloud data according to the elevation data of each point cloud point in the target three-dimensional point cloud data and a preset ground elevation interval.
The preset ground elevation interval may be used to filter out point cloud points that do not necessarily participate in ground point filtering, for example, point cloud points that have a high elevation and are obviously not possible to be ground points.
The advantage that sets up like this lies in, cuts off the point cloud point outside the ground elevation interval of predetermineeing, can reduce the processing data volume, avoids making a large amount of invalid processing work.
Example two
Fig. 2 is a schematic structural diagram of a filtering apparatus for point cloud ground points according to a second embodiment of the present invention. As shown in fig. 2, the apparatus includes: the system comprises a target three-dimensional point cloud data acquisition module 210, a cluster set acquisition module 220, a normal vector mean calculation module 230 and a point cloud ground point filtering module 240.
Wherein:
a target three-dimensional point cloud data obtaining module 210, configured to obtain target three-dimensional point cloud data to be filtered;
a cluster set obtaining module 220, configured to perform cluster processing on cloud points of each point in the target three-dimensional point cloud data according to a preset clustering algorithm to obtain multiple cluster sets;
a normal vector mean calculation module 230, configured to identify, in each cluster set, at least one target cluster set that matches the ground, and calculate a normal vector mean according to a normal vector of each target point cloud point in each target cluster set;
and the point cloud ground point filtering module 240 is configured to identify and filter all point cloud ground points in the target three-dimensional point cloud data according to a numerical difference between a normal vector of each point cloud point in the target three-dimensional point cloud data and a normal vector mean.
According to the technical scheme of the embodiment of the invention, target three-dimensional point cloud data to be filtered are obtained; clustering each cloud point in the target three-dimensional point cloud data according to a preset clustering algorithm to obtain a plurality of clustering sets; identifying at least one target clustering set matched with the ground in each clustering set, and calculating a normal vector mean value according to a normal vector of each target point cloud point in each target clustering set; the technical means of identifying and filtering all point cloud ground points in the target three-dimensional point cloud data according to the numerical difference between the normal vector and the normal vector mean value of each point cloud point in the target three-dimensional point cloud data provides a point cloud ground point filtering method, which effectively improves the non-ground point missing, improves the accuracy of ground point filtering and enlarges the application range of the point cloud ground point filtering method.
Optionally, the target three-dimensional point cloud data obtaining module 210 may be specifically configured to:
and acquiring dense point cloud data acquired by a laser radar, and performing downsampling processing on the dense point cloud data to obtain sparse target three-dimensional point cloud data.
Optionally, the normal vector mean calculating module 230 may be specifically configured to:
acquiring clustering centers respectively corresponding to the clustering sets;
identifying a target clustering center with the lowest elevation from all clustering centers;
respectively calculating an included angle and an elevation difference between each clustering center and the target clustering center, and acquiring similar clustering centers of which the included angles meet an angle similarity condition and the elevation differences meet an elevation similarity condition;
and acquiring at least one target clustering set respectively corresponding to the target clustering center and the similar clustering center.
Optionally, the filtering apparatus for point cloud ground points further includes a point cloud point normal vector calculation module, configured to, before calculating a normal vector mean value according to a normal vector of each target point cloud point in each target cluster set:
acquiring a cloud point of a current processing point from the target three-dimensional point cloud data, and searching a plurality of neighborhood point cloud points matched with the cloud point of the current processing point;
determining a point cloud plane matched with the currently processed electric cloud point according to each neighborhood point cloud point;
and calculating a normal vector corresponding to the point cloud plane as a normal vector of the cloud point of the current processing point.
Optionally, the filtering apparatus for point cloud ground points further includes a noise point cloud point filtering module, configured to perform clustering processing on each cloud point in the target three-dimensional point cloud data according to a preset clustering algorithm, before obtaining a plurality of cluster sets:
and filtering noise point cloud points included in the target three-dimensional point cloud data according to a preset point cloud denoising algorithm.
Optionally, the filtering apparatus for point cloud ground points further includes a point cloud cutting module, configured to perform clustering processing on each point cloud point in the target three-dimensional point cloud data according to a preset clustering algorithm, before obtaining a plurality of cluster sets:
and point cloud cutting is carried out on the target three-dimensional point cloud data according to the elevation data of each point cloud point in the target three-dimensional point cloud data and a preset ground elevation interval.
Optionally, the point cloud ground point filtering module 240 may be specifically configured to:
respectively calculating a target included angle between a normal vector and a normal vector mean value of each point cloud point in the target three-dimensional point cloud data, and adding a ground point index value for point cloud ground points with the target included angle less than or equal to an included angle threshold value;
and filtering all point cloud ground points containing the ground point index value in the target three-dimensional point cloud data.
The filtering device for the point cloud ground points provided by the embodiment of the invention can execute the filtering method for the point cloud ground points provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE III
FIG. 3 illustrates a schematic diagram of an electronic device 300 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 3, the electronic device 300 includes at least one processor 301, and a memory communicatively connected to the at least one processor 301, such as a Read Only Memory (ROM)302, a Random Access Memory (RAM)303, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 301 may perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM)302 or the computer program loaded from the storage unit 308 into the Random Access Memory (RAM) 303. In the RAM 303, various programs and data necessary for the operation of the electronic apparatus 300 can also be stored. The processor 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.
A number of components in the electronic device 300 are connected to the I/O interface 305, including: an input unit 306 such as a keyboard, a mouse, or the like; an output unit 307 such as various types of displays, speakers, and the like; a storage unit 308 such as a magnetic disk, optical disk, or the like; and a communication unit 309 such as a network card, modem, wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The processor 301 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of processor 301 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 301 performs the various methods and processes described above, such as a filtering method of point cloud ground points.
In some embodiments, the method of filtering out point cloud ground points may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 308. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 300 via the ROM 302 and/or the communication unit 309. When the computer program is loaded into RAM 303 and executed by processor 301, one or more steps of the method for filtering out point cloud ground points described above may be performed. Alternatively, in other embodiments, the processor 301 may be configured to perform the filtering out method of the point cloud ground points by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for filtering point cloud ground points is characterized by comprising the following steps:
acquiring target three-dimensional point cloud data to be filtered;
clustering each cloud point in the target three-dimensional point cloud data according to a preset clustering algorithm to obtain a plurality of clustering sets;
identifying at least one target clustering set matched with the ground in each clustering set, and calculating a normal vector mean value according to a normal vector of each target point cloud point in each target clustering set;
and identifying and filtering all point cloud ground points in the target three-dimensional point cloud data according to the numerical difference between the normal vector and the normal vector mean value of each point cloud point in the target three-dimensional point cloud data.
2. The method of claim 1, wherein obtaining target three-dimensional point cloud data to be filtered comprises:
and acquiring dense point cloud data acquired by a laser radar, and performing downsampling processing on the dense point cloud data to obtain sparse target three-dimensional point cloud data.
3. The method of claim 1, wherein identifying, among the sets of clusters, at least one set of target clusters that match the ground comprises:
acquiring clustering centers respectively corresponding to the clustering sets;
identifying a target clustering center with the lowest elevation from all clustering centers;
respectively calculating an included angle and an elevation difference between each clustering center and the target clustering center, and acquiring similar clustering centers of which the included angles meet an angle similarity condition and the elevation differences meet an elevation similarity condition;
and acquiring at least one target clustering set respectively corresponding to the target clustering center and the similar clustering center.
4. The method of claim 1, further comprising, before calculating a mean normal vector value from normal vectors of cloud points of each target point in each target cluster set:
acquiring a cloud point of a current processing point from the target three-dimensional point cloud data, and searching a plurality of neighborhood point cloud points matched with the cloud point of the current processing point;
determining a point cloud plane matched with the currently processed electric cloud point according to each neighborhood point cloud point;
and calculating a normal vector corresponding to the point cloud plane as a normal vector of the cloud point of the current processing point.
5. The method according to any one of claims 1 to 4, wherein before clustering each cloud point in the target three-dimensional point cloud data according to a preset clustering algorithm to obtain a plurality of cluster sets, the method further comprises:
and filtering noise point cloud points included in the target three-dimensional point cloud data according to a preset point cloud denoising algorithm.
6. The method according to any one of claims 1 to 4, wherein before clustering each cloud point in the target three-dimensional point cloud data according to a preset clustering algorithm to obtain a plurality of cluster sets, the method further comprises:
and point cloud cutting is carried out on the target three-dimensional point cloud data according to the elevation data of each point cloud point in the target three-dimensional point cloud data and a preset ground elevation interval.
7. The method according to any one of claims 1 to 4, wherein identifying and filtering out all point cloud ground points in the target three-dimensional point cloud data according to the numerical difference between the normal vector and the normal vector mean of each point cloud point in the target three-dimensional point cloud data comprises:
respectively calculating a target included angle between a normal vector and a normal vector mean value of each point cloud point in the target three-dimensional point cloud data, and adding a ground point index value for point cloud ground points with the target included angle less than or equal to an included angle threshold value;
and filtering all point cloud ground points containing the ground point index value in the target three-dimensional point cloud data.
8. A filtering device for point cloud ground points, comprising:
the target three-dimensional point cloud data acquisition module is used for acquiring target three-dimensional point cloud data to be filtered;
the cluster set acquisition module is used for clustering each point cloud point in the target three-dimensional point cloud data according to a preset clustering algorithm to obtain a plurality of cluster sets;
the normal vector mean value calculation module is used for identifying at least one target cluster set matched with the ground in each cluster set and calculating a normal vector mean value according to the normal vector of each target point cloud point in each target cluster set;
and the point cloud ground point filtering module is used for identifying and filtering all point cloud ground points in the target three-dimensional point cloud data according to the numerical difference between the normal vector and the normal vector mean value of each point cloud point in the target three-dimensional point cloud data.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of filtering point cloud ground points of any one of claims 1-7.
10. A computer-readable storage medium having stored thereon computer instructions for causing a processor to execute the method for filtering point cloud ground points of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210657607.1A CN115049551A (en) | 2022-06-10 | 2022-06-10 | Method, device, equipment and storage medium for filtering point cloud ground points |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210657607.1A CN115049551A (en) | 2022-06-10 | 2022-06-10 | Method, device, equipment and storage medium for filtering point cloud ground points |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115049551A true CN115049551A (en) | 2022-09-13 |
Family
ID=83162367
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210657607.1A Pending CN115049551A (en) | 2022-06-10 | 2022-06-10 | Method, device, equipment and storage medium for filtering point cloud ground points |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115049551A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115311457A (en) * | 2022-10-09 | 2022-11-08 | 广东汇天航空航天科技有限公司 | Point cloud data processing method, computing equipment, flight device and storage medium |
-
2022
- 2022-06-10 CN CN202210657607.1A patent/CN115049551A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115311457A (en) * | 2022-10-09 | 2022-11-08 | 广东汇天航空航天科技有限公司 | Point cloud data processing method, computing equipment, flight device and storage medium |
| CN115311457B (en) * | 2022-10-09 | 2023-03-24 | 广东汇天航空航天科技有限公司 | Point cloud data processing method, computing equipment, flight device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112488060A (en) | Object detection method, device, apparatus, medium, and program product | |
| CN115049551A (en) | Method, device, equipment and storage medium for filtering point cloud ground points | |
| CN115457152A (en) | External parameter calibration method and device, electronic equipment and storage medium | |
| CN113920273B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN116012859A (en) | Text image rejection judgment method, device and equipment based on definition index | |
| CN114581711A (en) | Target object detection method, apparatus, device, storage medium, and program product | |
| CN113870428A (en) | Scene map generation method, related device and computer program product | |
| CN113920404A (en) | Training method, image processing method, device, electronic device and storage medium | |
| CN114119990A (en) | Method, apparatus and computer program product for image feature point matching | |
| CN114694138B (en) | Road surface detection method, device and equipment applied to intelligent driving | |
| CN117392631B (en) | Road boundary extraction method and device, electronic equipment and storage medium | |
| CN115361584B (en) | Video data processing method and device, electronic equipment and readable storage medium | |
| CN117392000B (en) | Noise removing method and device, electronic equipment and storage medium | |
| CN114494818B (en) | Image processing method, model training method, related device and electronic equipment | |
| EP4036861A2 (en) | Method and apparatus for processing point cloud data, electronic device, storage medium, computer program product | |
| CN116795943A (en) | Spatial data processing method, device, equipment and storage medium | |
| CN115496916B (en) | Training method of image recognition model, image recognition method and related device | |
| CN113360688B (en) | Method, device and system for constructing information base | |
| CN115564329A (en) | Typical capacity scene determining method, device, equipment and storage medium | |
| CN118072078A (en) | Target detection method, device, equipment and storage medium | |
| CN116703963A (en) | AR tracking method and device, AR equipment and storage medium | |
| CN116304635A (en) | Operation data analysis method, device and equipment of pumped storage equipment | |
| CN117539602A (en) | Method and device for task speculation behind, electronic equipment and storage medium | |
| CN116844218A (en) | Eyelid detection method, eyelid detection device, eyelid detection equipment and storage medium | |
| CN116452915A (en) | Image processing method, device, electronic equipment 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 |