CN108876885B - Point cloud data processing method and device for power equipment - Google Patents
Point cloud data processing method and device for power equipment Download PDFInfo
- Publication number
- CN108876885B CN108876885B CN201810695359.3A CN201810695359A CN108876885B CN 108876885 B CN108876885 B CN 108876885B CN 201810695359 A CN201810695359 A CN 201810695359A CN 108876885 B CN108876885 B CN 108876885B
- Authority
- CN
- China
- Prior art keywords
- cloud data
- point cloud
- cuboid
- space
- bounding box
- 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.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 238000012544 monitoring process Methods 0.000 claims abstract description 13
- 238000013499 data model Methods 0.000 claims description 72
- 238000012545 processing Methods 0.000 claims description 24
- 238000000034 method Methods 0.000 claims description 21
- 230000011218 segmentation Effects 0.000 claims description 17
- 230000003321 amplification Effects 0.000 claims description 11
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 11
- 230000009467 reduction Effects 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 239000007787 solid Substances 0.000 claims description 5
- 230000009471 action Effects 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract description 5
- 238000001514 detection method Methods 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 12
- 230000002596 correlated effect Effects 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/005—General purpose rendering architectures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Graphics (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Generation (AREA)
Abstract
The embodiment of the application discloses a point cloud data processing method and device for power equipment, wherein the point cloud data of the power equipment are spliced, divided and denoised to obtain the point cloud data containing a single power equipment, the point cloud data containing the single power equipment are matched with a point cloud data template to obtain attribute information of the power equipment represented by the point cloud data containing the single power equipment, and the point cloud data containing the single power equipment and the corresponding attribute information are stored in a correlation mode. Because the point cloud data after denoising in the cuboid space comprises the point cloud data of a single power device, the stored point cloud data in each cuboid space can be used for monitoring the characteristics of the shape, the environment and the like of the single power device, and the associated attribute information can be used for identifying the running state of the power device, such as appearance, stress deformation and the like, so that technical support is provided for the operation and the detection of the power device, and the defects of three-dimensional reconstruction are overcome.
Description
Technical Field
The present disclosure relates to the field of data processing technologies, and more particularly, to a method and an apparatus for processing point cloud data of an electrical device.
Background
In order to facilitate management of power equipment (e.g., power generation equipment, power transmission equipment, power transformation equipment or power distribution equipment), point cloud data of the power equipment is collected. At present, for the application of point cloud data of power equipment, three-dimensional reconstruction is performed to obtain a three-dimensional model. A user (generally, a power person) can simulate the actual scene of a site through the three-dimensional model, and the operation or the scheduling of the power equipment is facilitated.
However, the three-dimensional reconstruction only provides visual information for the user, but cannot provide more technical support for the user. Therefore, how to process the point cloud data of the power equipment to provide more technical support for the user becomes an urgent technical problem to be solved.
Disclosure of Invention
The application aims to provide a point cloud data processing method and device of power equipment, so as to provide more technical support for users.
In order to achieve the above purpose, the present application provides the following technical solutions:
a point cloud data processing method of an electric power device comprises the following steps:
an acquisition step: acquiring collected point cloud data of the power equipment;
splicing: splicing the point cloud data to obtain spliced point cloud data;
a segmentation step: performing space segmentation on the spliced point cloud data to obtain a plurality of cuboid spaces, wherein each cuboid space comprises the point cloud data of one power device;
denoising: denoising the point cloud data in the cuboid space;
matching: matching the denoised point cloud data in the cuboid space with each point cloud data model in a point cloud data model library to determine attribute information of the power equipment represented by the denoised point cloud data in the cuboid space;
and (3) association step: and storing the point cloud data subjected to denoising in the rectangular space in a correlated manner with the attribute information.
In the above method, preferably, the scanning of the power device by the three-dimensional laser scanner to obtain the point cloud data of the power device, and the splicing of the point cloud data includes:
and splicing the point cloud data pieces corresponding to the two adjacent coordinates according to the arrangement sequence of the coordinates in the coordinate sequence when the three-dimensional laser scanner performs scanning.
Preferably, the above method, performing spatial segmentation on the spliced point cloud data, includes:
placing a preset cuboid bounding box at the coordinate of the power equipment in the space where the spliced point cloud data is located according to the coordinate of the power equipment;
reducing or amplifying the cuboid bounding box, and calculating the difference value of the counting results of the point clouds in the first plane of the cuboid bounding box before and after the reduction or the amplification of the cuboid bounding box every time the cuboid bounding box is reduced or amplified;
if the absolute value of the difference is larger than a preset difference threshold value, determining the position of a first plane before the cuboid bounding box is reduced as the final position of the first plane if the cuboid bounding box is reduced, and determining the position of the first plane after the cuboid bounding box is enlarged as the final position of the first plane if the cuboid bounding box is enlarged;
and if the absolute value of the difference is smaller than or equal to a preset difference threshold, returning to execute the step of reducing or amplifying the cuboid bounding box until each plane of the cuboid bounding box determines the final position.
Preferably, the denoising processing of the point cloud data in the rectangular space includes:
averagely dividing the cuboid space into a plurality of cuboid grids;
counting point cloud data in the cubic grid;
if the counting result is smaller than a third preset threshold value, deleting the point cloud data in the cubic grid; otherwise, the point cloud data in the cubic grid is reserved.
The above method, preferably, further comprises:
monitoring and storing the operation duration of each step and the memory peak value during the operation of the method;
and storing the similarity between the denoised point cloud data in the cuboid space and each point cloud data model in the point cloud data model base.
A point cloud data processing device of an electric power device includes:
the acquisition module is used for acquiring the collected point cloud data of the power equipment;
splicing modules: the system is used for splicing the point cloud data to obtain spliced point cloud data;
a segmentation module: the device comprises a splicing unit, a data acquisition unit, a data processing unit and a data processing unit, wherein the splicing unit is used for splicing point cloud data of a power device;
a denoising module: the device is used for denoising the point cloud data in the cuboid space;
a matching module: the device comprises a cuboid space, a point cloud database and a data processing module, wherein the cuboid space is used for storing point cloud data which are denoised in the cuboid space and are matched with each point cloud data model in the point cloud data model database so as to determine attribute information of electric equipment represented by the denoised point cloud data in the cuboid space;
a correlation module: and storing the denoised point cloud data in the rectangular space in a correlated manner with the attribute information.
The device is preferable, the point cloud data of the power equipment is obtained by scanning the power equipment through the three-dimensional laser scanner, and the splicing module is specifically used for splicing the point cloud data pieces corresponding to two adjacent coordinates according to the arrangement sequence of the coordinates in the coordinate sequence when the three-dimensional laser scanner performs scanning.
Preferably, the segmentation module is specifically configured to place a preset rectangular bounding box at the coordinates of the power device in the space where the spliced point cloud data is located according to the coordinates of the power device;
reducing or amplifying the cuboid bounding box, and calculating the difference value of the counting results of the point clouds in the first plane of the cuboid bounding box before and after the reduction or the amplification of the cuboid bounding box every time the cuboid bounding box is reduced or amplified;
if the absolute value of the difference is larger than a preset difference threshold, determining the position of a first plane before the cuboid bounding box is reduced as the final position of the first plane if the cuboid bounding box is reduced, and determining the position of the first plane after the cuboid bounding box is enlarged as the final position of the first plane if the cuboid bounding box is enlarged;
and if the absolute value of the difference is smaller than or equal to a preset difference threshold, returning to execute the step of reducing or amplifying the cuboid bounding box until each plane of the cuboid bounding box determines the final position.
The apparatus, preferably, the denoising module is specifically configured to,
averagely dividing the cuboid space into a plurality of cuboid grids;
counting point cloud data in the cubic grid;
if the counting result is smaller than a third preset threshold value, deleting the point cloud data in the cubic grid; otherwise, the point cloud data in the cube grid is reserved.
The above apparatus, preferably, further comprises:
the monitoring module is used for monitoring and storing the operation duration of each step and the memory peak value when the method operates;
and the storage module is used for storing the similarity between the denoised point cloud data in the cuboid space and each point cloud data model in the point cloud data model base.
According to the scheme, the point cloud data of the power equipment are spliced, divided and denoised to obtain the point cloud data containing a single power equipment, the point cloud data containing the single power equipment are matched with the point cloud data template to obtain the attribute information of the power equipment represented by the point cloud data containing the single power equipment, and the point cloud data containing the single power equipment and the corresponding attribute information are stored in a correlated mode. The denoised point cloud data comprises the point cloud data of the single power equipment, so that the stored point cloud data can be used for monitoring the environment or stress deformation and other characteristics of the single power equipment, and the associated attribute information can be used for identifying or positioning the power equipment, the environment and the like, so that technical support is provided for the operation and the inspection of the power equipment, and the defect of three-dimensional reconstruction is overcome.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an implementation of a point cloud data processing method for an electrical device according to an embodiment of the present disclosure;
fig. 2 is a flowchart of an implementation of performing spatial segmentation on spliced point cloud data according to the embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a point cloud data processing apparatus of an electrical device according to an embodiment of the present disclosure.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be practiced otherwise than as specifically illustrated.
Detailed Description
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 obtained by a person skilled in the art based on the embodiments of the present invention without inventive step, are within the scope of the present invention.
Referring to fig. 1, fig. 1 is a flowchart illustrating an implementation of a point cloud data processing method of an electrical device according to an embodiment of the present disclosure, where the method includes:
step S11: and acquiring the collected point cloud data of the power equipment.
The point cloud data of the power equipment is obtained by scanning the power equipment through the three-dimensional laser scanner. In order to enable the precision of the processing result of the point cloud data to be high, a high-precision three-dimensional laser scanner can be selected to scan the electric power equipment. For example, a three-dimensional laser scanner with a sampling accuracy of the order of mm may be selected.
After the scanning of the power equipment is completed through the three-dimensional laser scanner, the collected point cloud data can be stored in a preset database, and when the point cloud data is required to be processed, the point cloud data is obtained from the preset database.
Step S12: and splicing the acquired point cloud data to obtain spliced point cloud data.
When scanning the electric power equipment through the three-dimensional laser scanner, under the influence of many objective factors, it is usually required to scan the electric power equipment from a plurality of different viewing angles (i.e. different positions), so that the point cloud data obtained by the three-dimensional laser scanner are scattered points without obvious geometric features. And performing splicing processing on the acquired point cloud data, namely converting the point cloud data acquired under different visual angles into the same coordinate system to obtain the point cloud data representing the complete outline of the power equipment. That is to say, the spliced point cloud data is the point cloud data representing the complete outline of the power equipment.
In the embodiment of the application, when the three-dimensional laser scanner carries out scanning operation, the coordinates of the three-dimensional laser scanner are recorded, and the coordinates of the scanner are associated with point cloud data scanned at the coordinates. After the scanning is finished, the recorded coordinates form a coordinate sequence according to the recorded sequence, that is, the coordinates in the coordinate sequence are arranged according to the recorded sequence of the coordinates. The point cloud data associated with each coordinate form a point cloud data piece, that is, different coordinates correspond to different point cloud data pieces, and the point cloud data pieces corresponding to different coordinates contain point cloud data with partially identical point cloud data.
Specifically, when the point cloud data pieces are spliced, the point cloud data pieces corresponding to two adjacent coordinates can be spliced according to the arrangement sequence of the coordinates in the coordinate sequence when the three-dimensional laser scanner performs scanning operation.
In the embodiment of the application, through when gathering the operation, record three-dimensional laser scanner's coordinate, and with the coordinate of scanner with the point cloud data that scans in this coordinate department be correlated with, according to the order of arrangement of coordinate among the coordinate sequence, splice the point cloud data piece that two adjacent coordinates correspond, avoid two point cloud data pieces that wait to splice that acquire from the point cloud data of gathering at random can not splice, need acquire another point cloud data piece from the point cloud data of gathering again and splice, lead to the slow problem of concatenation speed.
Step S13: and carrying out space segmentation on the spliced point cloud data to obtain a plurality of cuboid spaces, wherein each cuboid space comprises the point cloud data of one power device.
In the embodiment of the application, the outline of the power equipment is not directly extracted, the point cloud data of the single power equipment is divided into an independent cuboid space, and the outline of the power equipment is determined through cuboid space division. That is, only the point cloud data of one electric power device is contained in one rectangular space, but not the point cloud data of two or more electric power devices, that is, the point cloud data contained in the one rectangular space only represents the outline of one electric power device, but not the outlines of two or more electric power devices. In other words, each rectangular solid space is a minimum space capable of containing point cloud data of only one electric power device according to a preset rule.
Step S14: and respectively carrying out denoising treatment on the point cloud data in each cuboid space.
In the embodiment of the application, only the point cloud data in the cuboid space of the point cloud data containing the power equipment are subjected to denoising treatment, and not all the spliced point cloud data are subjected to denoising treatment, so that the processing amount of the point cloud data in the denoising process is reduced, and the point cloud data processing efficiency is improved.
Through the processing of the steps S12 to S14, effective space information in the point cloud data is reserved to the maximum extent, and the influences of shielding, defects, noise and compression are reduced.
Step S15: and respectively matching the denoised point cloud data in the cuboid space with each point cloud data model in the point cloud data model base so as to determine the attribute information of the power equipment represented by the denoised point cloud data in the cuboid space.
The point cloud data model library may include point cloud data models of various types of power equipment, for example, a point cloud data model of a wind turbine, a point cloud data model of a transformer, and the like, which are not listed here.
When the point cloud data subjected to denoising in the cuboid space is matched with each point cloud data model in the point cloud data model base, preset feature data can be extracted from the point cloud data subjected to denoising in the cuboid space and the point cloud data models, the similarity between the point cloud data subjected to denoising in the cuboid space and the point cloud data models is calculated according to the extracted feature data, and the point cloud data model corresponding to the maximum similarity is determined to be the point cloud data model matched with the point cloud data subjected to denoising in the cuboid space. And the attribute information corresponding to the determined matched point cloud data model is the attribute information of the power equipment represented by the denoised point cloud data in the cuboid space.
Wherein the attribute information of the power device may include: name (e.g., wind turbine, transformer, etc.), belonging scene level (e.g., equipment level, road level, barrier level, etc.), geometry type (e.g., point, line, plane, cuboid), geographic location, etc.
For the electric power equipment, the scene layer to which the electric power equipment belongs is the equipment layer.
The characteristic data may include at least one of the following characteristics: skeletal features, area features, volume features, projected contour features, boundary curvature features, and the like.
The following illustrates a specific implementation process of matching the denoised point cloud data in the rectangular space with the point cloud data model.
For example one
The method comprises the steps of respectively projecting denoised point cloud data in a cuboid space on three mutually perpendicular planes in a three-dimensional coordinate system, and extracting contour features (recorded as first contour features for convenience of description) and boundary point curvature features (recorded as first boundary point curvature features for convenience of description) of each projection.
And respectively projecting the point cloud data model on three mutually perpendicular planes in the same three-dimensional coordinate system, and extracting the contour feature (recorded as a second contour feature for convenience of description) and the boundary point curvature feature (recorded as a second boundary point curvature feature for convenience of description) of each projection.
Calculating a first distance between the first contour feature and the second contour feature on the same plane and a second distance between the curvature feature of the first boundary point and the curvature feature of the second boundary point on the same plane;
summing the first distance and the second distance corresponding to the same plane to obtain a first sum value; the three planes together yield three first sums.
And summing the three first sum values to obtain a second sum value. The second sum value represents the similarity between the denoised point cloud data in the cuboid space and the point cloud data model. The larger the second sum is, the lower the similarity is, and the smaller the second sum is, the higher the similarity is.
Example II
Respectively extracting a first skeleton characteristic of the denoised point cloud data in the rectangular space and a second skeleton characteristic of the point cloud data model;
and comparing the first skeleton characteristic with the second skeleton characteristic, if the path number, the node number and the communication relation between the nodes of the first skeleton characteristic and the second skeleton characteristic are consistent, the denoised point cloud data in the cuboid space is the same as the point cloud data model, otherwise, the denoised point cloud data and the point cloud data model are different.
The following description will be given of the process of extracting skeleton features by taking a point cloud data model as an example:
determining an initial surface skeleton: in the boundary points of the point cloud data model, points with curvatures greater than a preset curvature threshold are used as feature points, and for convenience of description, a total of m feature points are assumed here.
And calculating the shortest path from each feature point to the centroid of the point cloud data model in the point cloud data model to obtain m shortest paths, and taking the m shortest paths as an initial surface skeleton of the point cloud data model.
Simplifying the initial surface skeleton: connecting nodes in a triangular mode, calculating a centroid coordinate of the triangle, counting point cloud data in a cube grid to which the centroid belongs, if a counting result is larger than a first preset threshold value, determining a second node connected with a first node at three vertices of the triangle, deleting a connecting path of the first node and the second node, connecting the centroid of the triangle with the second node, and forming a new path so as to represent a skeleton of a point cloud data model by using a small number of nodes.
Preferably, the cubic grid to which the triangular centroid belongs refers to a cubic grid taking the triangular centroid as a centroid, edges of the cubic grid are parallel or perpendicular to three coordinate axes of a three-dimensional coordinate system in which the point cloud data is located, and the length of the edges of the cubic grid is a preset length, for example, 1cm.
Step S16: and storing the denoised point cloud data in the rectangular space in a correlated manner with the attribute information.
Because the point cloud data after denoising in the cuboid space only comprises the point cloud data of a single power device, the stored point cloud data in each cuboid space can be used for monitoring the environment or stress deformation and other characteristics of one power device, and the associated attribute information can be used for identifying or positioning the power device and the environment thereof, thereby providing technical support for operation and inspection of the power device and making up for the defect of three-dimensional reconstruction.
For example, the point cloud data of the power equipment can be periodically acquired, and after the point cloud data of the power equipment is acquired each time, the point cloud data is processed according to the point cloud data processing method of the power equipment provided by the application, so that the denoised point cloud data and the associated attribute information in the rectangular space are obtained. And comparing the characteristics of the point cloud data in the same cuboid space in the denoised point cloud data obtained in two adjacent periods, and determining the environment or stress deformation condition of the power equipment in the cuboid space according to the comparison result. The same cuboid space means that the geographic positions of the power devices are the same in the attribute information related to the cuboids.
In an optional embodiment, one implementation manner of performing spatial segmentation on the stitched point cloud data may be:
and placing a preset cuboid bounding box at the coordinate of the power equipment in the space where the spliced point cloud data is located according to the coordinate of the power equipment.
Here, the coordinates of the electric power equipment refer to actual geographical coordinates of the electric power equipment, and are stored in advance. The actual geographic coordinates of the power equipment can refer to the geographic coordinates of the center of the base of the power equipment, and the coordinate position of the power equipment, where the preset cuboid bounding box is placed in the space where the spliced point cloud data is located, refers to the geographic coordinate position of the center of the base of the preset cuboid bounding box, where the length, width and height of the preset cuboid bounding box are parallel to the length, width and height of the space where the power equipment is located.
And (3) reducing or amplifying the cuboid bounding box, and calculating the difference of the counting results of the point clouds in the first plane of the cuboid bounding box before and after the reduction or the amplification of the cuboid bounding box every time the reduction or the amplification is carried out.
If the absolute value of the difference is larger than the preset difference threshold value, determining the position of the first plane before the cuboid bounding box is reduced as the final position of the first plane if the cuboid bounding box is reduced, and determining the position of the first plane after the cuboid bounding box is enlarged as the final position of the first plane if the cuboid bounding box is enlarged.
And if the absolute value of the difference is smaller than or equal to the preset difference threshold, returning to execute the step of reducing or amplifying the cuboid bounding box until each plane of the cuboid bounding box determines the final position.
Specifically, an implementation flowchart of the space segmentation on the stitched point cloud data provided in the embodiment of the present application is shown in fig. 2, and may include:
step S201: and placing a preset cuboid bounding box at the coordinate position of the power equipment in the space where the spliced point cloud data is located according to the coordinate of the power equipment.
Step S202: and respectively counting the point cloud data in each plane of the cuboid bounding box.
The length, width and height of the cuboid bounding box preset in the embodiment are all smaller than the actual length, width and height of the power equipment.
Step S203: and determining a target plane, and taking each plane of the cuboid bounding box as the target plane after the cuboid bounding box is determined.
Step S204: and moving each target plane in the direction far away from the center of the cuboid bounding box according to a preset step length so as to amplify the volume of the cuboid bounding box.
Wherein the preset step length is less than or equal to a preset step length threshold value, and the step length threshold value is as follows: and 5% of the maximum side length of the preset cuboid bounding box.
Step S205: counting point cloud data in each target plane in the amplified cuboid bounding box;
step S206: the results of the counts before and after the magnification corresponding to the same target plane (for convenience of description, referred to as the first plane) are compared.
Step S207: and judging whether the position of the first plane can be determined according to the comparison result, and if so, executing the step S208. Otherwise, step S209 is performed.
Specifically, if the absolute value of the difference between the count results before and after amplification is greater than a preset difference threshold, the position of the first plane may be determined, otherwise, the position of the first plane may not be determined.
Step S208: the position of the first plane is determined. The current position of the first plane is determined as the final position of the first plane, that is, the current position of the first plane is kept unchanged.
Step S209: and taking the first plane as a new target plane, and returning to execute the step S204.
In the example shown in fig. 2, the length, width and height of the rectangular parallelepiped bounding box are preset to be smaller than those of the power equipment. In another example, the length, width and height of the preset rectangular parallelepiped enclosure may be greater than the length, width and height of the power equipment. And after the position of the preset cuboid bounding box is determined, each plane of the cuboid bounding box is moved to the direction close to the center of the cuboid bounding box according to the preset step length so as to reduce the volume of the cuboid bounding box. Counting the point cloud data in each plane in the reduced cuboid bounding box every time the cuboid bounding box is reduced; before and after the cuboid bounding box is reduced, counting results of two times before and after the cuboid bounding box corresponds to the same plane (which is recorded as a first plane for convenience of description) are compared, if the absolute value of the difference value of the counting results is larger than a preset difference threshold value, the position of the first plane before the cuboid bounding box is reduced is determined as the final position of the first plane, and if the absolute value of the difference value of the counting results is smaller than or equal to the preset difference threshold value, the first plane is continuously moved towards the direction close to the center of the cuboid bounding box until each plane in the cuboid bounding box determines the final position.
In an optional embodiment, the denoising processing on the point cloud data in the rectangular space may include:
the cuboid space is averagely divided into a plurality of cuboid grids, and the length of the side length of each cuboid grid is a preset length, such as 1cm.
And counting the point cloud data in the cubic grid.
If the counting result is smaller than a third preset threshold value, deleting the point cloud data in the cubic grid; otherwise, the point cloud data in the cubic grid is reserved.
In an optional embodiment, the processing method of the point cloud data of the power device provided by the present application may further include:
and monitoring and storing the operation duration of each step and the memory peak value of the power equipment during the operation of the point cloud data processing method.
And storing the similarity between the denoised point cloud data in the rectangular space and each point cloud data model in the point cloud data model library.
By storing the information, reference can be provided for optimization of a subsequent point cloud data processing method of similar power equipment.
Corresponding to the embodiment of the method, the application further provides a point cloud data processing device of an electrical device, and a schematic structural diagram of the point cloud data processing device of the electrical device provided by the application is shown in fig. 3, and the point cloud data processing device may include:
the device comprises an acquisition module 31, a splicing module 32, a segmentation module 33, a denoising module 34, a matching module 35 and a correlation module 36; wherein,
the acquisition module 31 is used for acquiring point cloud data of the collected power equipment;
the splicing module 32 is configured to splice the point cloud data to obtain spliced point cloud data;
the segmentation module 33 is configured to perform spatial segmentation on the spliced point cloud data to obtain a plurality of rectangular solid spaces, where each rectangular solid space includes point cloud data of an electrical device;
the denoising module 34 is configured to denoise the point cloud data in the rectangular space;
the matching module 35 is configured to match the denoised point cloud data in the rectangular space with each point cloud data model in a point cloud data model library, so as to determine attribute information of the electrical equipment represented by the denoised point cloud data in the rectangular space;
the association module 36 is configured to store the denoised point cloud data in the rectangular solid space in association with the attribute information.
The point cloud data processing device of the power equipment, provided by the application, splices, divides and denoises the point cloud data of the power equipment to obtain the point cloud data containing a single power equipment, matches the point cloud data containing the single power equipment with the point cloud data template to obtain the attribute information of the power equipment represented by the point cloud data containing the single power equipment, and stores the point cloud data containing the single power equipment in a manner of being associated with the corresponding attribute information. Because the point cloud data after denoising in the cuboid space comprises the point cloud data of a single power device, the stored point cloud data in each cuboid space can be used for monitoring the characteristics of the shape, the environment and the like of the single power device, and the associated attribute information can be used for identifying the running state of the power device, such as appearance, stress deformation and the like, so that technical support is provided for the operation and the detection of the power device, and the defects of three-dimensional reconstruction are overcome.
In an optional embodiment, the point cloud data of the power device is obtained by scanning the power device through a three-dimensional laser scanner, and the splicing module 32 may be specifically configured to splice the point cloud data pieces corresponding to two adjacent coordinates according to an arrangement order of coordinates in a coordinate sequence when the three-dimensional laser scanner performs a scanning action.
In an optional embodiment, the segmentation module 33 may specifically be configured to:
placing a preset cuboid bounding box at the coordinate of the power equipment in the space where the spliced point cloud data is located according to the coordinate of the power equipment;
reducing or amplifying the cuboid bounding box, and calculating the difference of the counting results of the point clouds in the first plane of the cuboid bounding box before and after the reduction or the amplification of the cuboid bounding box every time the reduction or the amplification is carried out;
if the absolute value of the difference is larger than a preset difference threshold value, determining the position of a first plane before the cuboid bounding box is reduced as the final position of the first plane if the cuboid bounding box is reduced, and determining the position of the first plane after the cuboid bounding box is enlarged as the final position of the first plane if the cuboid bounding box is enlarged;
and if the absolute value of the difference is smaller than or equal to a preset difference threshold, returning to execute the step of reducing or amplifying the cuboid bounding box until each plane of the cuboid bounding box determines the final position.
In an alternative embodiment, the denoising module 34 may specifically be configured to:
averagely dividing the cuboid space into a plurality of cuboid grids;
counting point cloud data in the cubic grid;
if the counting result is smaller than a third preset threshold value, deleting the point cloud data in the cubic grid; otherwise, the point cloud data in the cube grid is reserved.
In an optional embodiment, the point cloud data processing apparatus of the power device provided by the present application may further include:
the monitoring module is used for monitoring and storing the operation duration of each step and the memory peak value when the method operates;
and the storage module is used for storing the similarity between the denoised point cloud data in the cuboid space and each point cloud data model in the point cloud data model base.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
It should be understood that in the embodiments of the present application, the technical problems described above can be solved by combining and combining the features of the embodiments and the embodiments.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention or a part thereof which substantially contributes to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A point cloud data processing method of an electric power device is characterized by comprising the following steps:
an acquisition step: acquiring collected point cloud data of the power equipment;
splicing: splicing the point cloud data to obtain spliced point cloud data;
a segmentation step: performing space segmentation on the spliced point cloud data to obtain a plurality of cuboid spaces, wherein each cuboid space comprises the point cloud data of one power device;
denoising: denoising the point cloud data in the cuboid space;
matching: matching the denoised point cloud data in the cuboid space with each point cloud data model in a point cloud data model library to determine attribute information of the power equipment represented by the denoised point cloud data in the cuboid space; the point cloud data model base comprises point cloud data models of various electric power equipment;
and (3) correlation step: storing the denoised point cloud data in the rectangular space in a correlation manner with the attribute information;
the matching of the denoised point cloud data in the cuboid space and each point cloud data model in the point cloud data model library comprises the following steps:
respectively projecting the point cloud data subjected to denoising in the cuboid space on three mutually perpendicular planes in a three-dimensional coordinate system, and extracting contour features and boundary point curvature features of all projections to obtain a first contour feature and a first boundary point curvature feature;
for each point cloud data model: respectively projecting the point cloud data model on three mutually perpendicular planes in the same three-dimensional coordinate system, and extracting contour features and boundary point curvature features of all projections to obtain second contour features and second boundary point curvature features;
calculating a first distance between the first contour feature and the second contour feature on the same plane and a second distance between the first boundary point curvature feature and the second boundary point curvature feature on the same plane;
summing the first distance and the second distance corresponding to the same plane to obtain a first sum value;
summing the first sum values corresponding to the three planes to obtain a second sum value;
determining the point cloud data model corresponding to the maximum second sum as a point cloud data model matched with the denoised point cloud data in the cuboid space;
or,
the matching of the denoised point cloud data in the cuboid space and each point cloud data model in the point cloud data model library comprises the following steps:
extracting the skeleton characteristics of the denoised point cloud data in the cuboid space to obtain first skeleton characteristics,
extracting the skeleton characteristics of the cloud data models of the points to obtain second skeleton characteristics;
and comparing the first skeleton features with each second skeleton feature, determining target second skeleton features, wherein the path number, the node number and the communication relation among the nodes of the target second skeleton features are consistent with those of the first skeleton features, and determining a point cloud data model corresponding to the target second skeleton features as a point cloud data model matched with the denoised point cloud data in the cuboid space.
2. The method according to claim 1, wherein the point cloud data of the electric power equipment is obtained by scanning the electric power equipment through a three-dimensional laser scanner, and the splicing process of the point cloud data comprises:
and splicing the point cloud data pieces corresponding to the two adjacent coordinates according to the arrangement sequence of the coordinates in the coordinate sequence when the three-dimensional laser scanner performs scanning.
3. The method of claim 1, wherein the spatially segmenting the stitched point cloud data comprises:
placing a preset cuboid bounding box at the coordinate of the power equipment in the space where the spliced point cloud data is located according to the coordinate of the power equipment;
reducing or amplifying the cuboid bounding box, and calculating the difference of the counting results of the point clouds in the first plane of the cuboid bounding box before and after the reduction or the amplification of the cuboid bounding box every time the reduction or the amplification is carried out;
if the absolute value of the difference is larger than a preset difference threshold value, determining the position of a first plane before the cuboid bounding box is reduced as the final position of the first plane if the cuboid bounding box is reduced, and determining the position of the first plane after the cuboid bounding box is enlarged as the final position of the first plane if the cuboid bounding box is enlarged;
and if the absolute value of the difference is smaller than or equal to a preset difference threshold, returning to execute the step of reducing or amplifying the cuboid bounding box until each plane of the cuboid bounding box determines the final position.
4. The method according to claim 1, wherein the denoising the point cloud data in the rectangular solid space comprises:
evenly dividing the cuboid space into a plurality of cuboid grids;
counting point cloud data in the cubic grid;
if the counting result is smaller than a third preset threshold value, deleting the point cloud data in the cubic grid; otherwise, the point cloud data in the cubic grid is reserved.
5. The method of claim 1, further comprising:
monitoring and storing the operation duration of each step and the memory peak value of the power equipment during the operation of the point cloud data processing method;
and storing the similarity between the denoised point cloud data in the cuboid space and each point cloud data model in the point cloud data model library.
6. A point cloud data processing device for an electric power device, comprising:
the acquisition module is used for acquiring the collected point cloud data of the power equipment;
splicing the modules: the system is used for splicing the point cloud data to obtain spliced point cloud data;
a segmentation module: the device comprises a splicing unit, a data acquisition unit, a data processing unit and a data processing unit, wherein the splicing unit is used for splicing point cloud data of a power device;
a denoising module: the device is used for denoising the point cloud data in the cuboid space;
a matching module: the device comprises a rectangular space, a point cloud data model database and a data processing module, wherein the rectangular space is used for storing the denoised point cloud data in the rectangular space; the point cloud data model base comprises point cloud data models of various electric power equipment;
a correlation module: storing the denoised point cloud data in the rectangular space in association with the attribute information;
the matching of the denoised point cloud data in the cuboid space and each point cloud data model in the point cloud data model library comprises the following steps:
respectively projecting the denoised point cloud data in the cuboid space on three mutually perpendicular planes in a three-dimensional coordinate system, and extracting the contour characteristic and the boundary point curvature characteristic of each projection to obtain a first contour characteristic and a first boundary point curvature characteristic;
for each point cloud data model: respectively projecting the point cloud data model on three mutually perpendicular planes in the same three-dimensional coordinate system, and extracting contour features and boundary point curvature features of all projections to obtain second contour features and second boundary point curvature features;
calculating a first distance between the first contour feature and the second contour feature on the same plane and a second distance between the first boundary point curvature feature and the second boundary point curvature feature on the same plane;
summing the first distance and the second distance corresponding to the same plane to obtain a first sum value;
summing the first sum values corresponding to the three planes to obtain a second sum value;
determining the point cloud data model corresponding to the maximum second sum as a point cloud data model matched with the denoised point cloud data in the cuboid space;
or,
the matching of the denoised point cloud data in the cuboid space and each point cloud data model in the point cloud data model library comprises the following steps:
extracting the skeleton characteristics of the denoised point cloud data in the rectangular space to obtain first skeleton characteristics,
extracting the skeleton characteristics of each point cloud data model to obtain second skeleton characteristics;
and comparing the first skeleton features with each second skeleton feature, determining target second skeleton features, wherein the path number, the node number and the communication relation among the nodes of the target second skeleton features are consistent with those of the first skeleton features, and determining a point cloud data model corresponding to the target second skeleton features as a point cloud data model matched with the denoised point cloud data in the cuboid space.
7. The apparatus according to claim 6, wherein the point cloud data of the power device is obtained by scanning the power device with a three-dimensional laser scanner, and the splicing module is specifically configured to splice the point cloud data pieces corresponding to two adjacent coordinates according to an arrangement order of the coordinates in a coordinate sequence when the three-dimensional laser scanner performs a scanning action.
8. The apparatus according to claim 6, characterized in that the segmentation module is specifically configured to,
placing a preset cuboid bounding box at the coordinate of the power equipment in the space where the spliced point cloud data is located according to the coordinate of the power equipment;
reducing or amplifying the cuboid bounding box, and calculating the difference of the counting results of the point clouds in the first plane of the cuboid bounding box before and after the reduction or the amplification of the cuboid bounding box every time the reduction or the amplification is carried out;
if the absolute value of the difference is larger than a preset difference threshold, determining the position of a first plane before the cuboid bounding box is reduced as the final position of the first plane if the cuboid bounding box is reduced, and determining the position of the first plane after the cuboid bounding box is enlarged as the final position of the first plane if the cuboid bounding box is enlarged;
and if the absolute value of the difference is smaller than or equal to a preset difference threshold, returning to execute the step of reducing or amplifying the cuboid bounding box until each plane of the cuboid bounding box determines the final position.
9. The apparatus of claim 6, wherein the denoising module is specifically configured to,
averagely dividing the cuboid space into a plurality of cuboid grids;
counting point cloud data in the cubic grid;
if the counting result is smaller than a third preset threshold value, deleting the point cloud data in the cubic grid; otherwise, the point cloud data in the cubic grid is reserved.
10. The apparatus of claim 6, further comprising:
the monitoring module is used for monitoring and storing the operation duration of each step and the memory peak value of the power equipment during the operation of the processing method of the point cloud data;
and the storage module is used for storing the similarity between the denoised point cloud data in the cuboid space and each point cloud data model in the point cloud data model base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810695359.3A CN108876885B (en) | 2018-06-29 | 2018-06-29 | Point cloud data processing method and device for power equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810695359.3A CN108876885B (en) | 2018-06-29 | 2018-06-29 | Point cloud data processing method and device for power equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108876885A CN108876885A (en) | 2018-11-23 |
| CN108876885B true CN108876885B (en) | 2022-10-14 |
Family
ID=64296925
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810695359.3A Active CN108876885B (en) | 2018-06-29 | 2018-06-29 | Point cloud data processing method and device for power equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108876885B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115601565B (en) * | 2022-12-15 | 2023-03-31 | 安徽大学 | Large-span steel structure fixed feature extraction method based on minimum valley distance |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105574929A (en) * | 2015-12-15 | 2016-05-11 | 电子科技大学 | Single vegetation three-dimensional modeling method based on ground LiDAR point cloud data |
| CN105844064A (en) * | 2016-05-23 | 2016-08-10 | 厦门亿力吉奥信息科技有限公司 | Three-dimensional transformer station semi-automatic reconstruction method based on laser point cloud data |
| CN106503060A (en) * | 2016-09-28 | 2017-03-15 | 山东东电电气工程技术有限公司 | A kind of transmission line of electricity three dimensional point cloud is processed and hands over across thing acquisition methods |
| CN106504327A (en) * | 2016-11-04 | 2017-03-15 | 辽宁工程技术大学 | A kind of side slope point cloud surface is rebuild and deformation information extracting method |
| CN107146277A (en) * | 2017-03-21 | 2017-09-08 | 国网湖北省电力公司检修公司 | The method being modeled based on cloud data to transformer station |
| CN108152831A (en) * | 2017-12-06 | 2018-06-12 | 中国农业大学 | A kind of laser radar obstacle recognition method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9811714B2 (en) * | 2013-08-28 | 2017-11-07 | Autodesk, Inc. | Building datum extraction from laser scanning data |
-
2018
- 2018-06-29 CN CN201810695359.3A patent/CN108876885B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105574929A (en) * | 2015-12-15 | 2016-05-11 | 电子科技大学 | Single vegetation three-dimensional modeling method based on ground LiDAR point cloud data |
| CN105844064A (en) * | 2016-05-23 | 2016-08-10 | 厦门亿力吉奥信息科技有限公司 | Three-dimensional transformer station semi-automatic reconstruction method based on laser point cloud data |
| CN106503060A (en) * | 2016-09-28 | 2017-03-15 | 山东东电电气工程技术有限公司 | A kind of transmission line of electricity three dimensional point cloud is processed and hands over across thing acquisition methods |
| CN106504327A (en) * | 2016-11-04 | 2017-03-15 | 辽宁工程技术大学 | A kind of side slope point cloud surface is rebuild and deformation information extracting method |
| CN107146277A (en) * | 2017-03-21 | 2017-09-08 | 国网湖北省电力公司检修公司 | The method being modeled based on cloud data to transformer station |
| CN108152831A (en) * | 2017-12-06 | 2018-06-12 | 中国农业大学 | A kind of laser radar obstacle recognition method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108876885A (en) | 2018-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109059791B (en) | Deformation monitoring method and device for power equipment | |
| CN112633657B (en) | Construction quality management method, device, equipment and storage medium | |
| CN110544298B (en) | Substation modeling method, device, computer equipment and storage medium | |
| CN108846374B (en) | Power equipment inspection method and device | |
| CN112233056B (en) | Point cloud fusion method and device for multi-source data and storage medium | |
| CN113888391A (en) | Indoor structured reconstruction method and device and computer readable storage medium | |
| CN105957149A (en) | Urban three-dimensional model data preprocessing method suitable for high-efficiency rendering | |
| CN112435337A (en) | Landscape visual field analysis method and system | |
| CN111091614B (en) | Method and system for building three-dimensional live-action model of transformer substation | |
| CN115830234A (en) | Point cloud processing method and system for power transmission line modeling | |
| CN108876885B (en) | Point cloud data processing method and device for power equipment | |
| CN114972645A (en) | Three-dimensional reconstruction method and device, computer equipment and storage medium | |
| CN112687000B (en) | Correction method, system and computer readable storage medium for three-dimensional model coordinates | |
| CN114283266A (en) | Three-dimensional model adjusting method and device, storage medium and equipment | |
| CN108830256B (en) | Method and device for inspecting equipment in closed space | |
| CN108895976B (en) | Method and device for monitoring deformation of closed space equipment | |
| Rüther et al. | Challenges in heritage documentation with terrestrial laser scanning | |
| CN116051980B (en) | Building identification method, system, electronic equipment and medium based on oblique photography | |
| CN116912817A (en) | Three-dimensional scene model splitting method and device, electronic equipment and storage medium | |
| CN116863083A (en) | Method and device for processing three-dimensional point cloud data of transformer substation | |
| Amico et al. | Quality management of 3D cultural heritage replicas with CIDOC-CRM. | |
| Bletterer et al. | Towards the reconstruction of wide historical sites: A local graph-based representation to resample gigantic acquisitions | |
| CN116342825B (en) | Construction method and related device of three-dimensional visualization system of power grid | |
| US7593011B2 (en) | Light map compression | |
| CN108062794A (en) | A kind of acquisition methods of building model, device, server 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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 250000 Electric Power Intelligent Robot Production Project 101 in Jinan City, Shandong Province, South of Feiyue Avenue and East of No. 26 Road (ICT Industrial Park) Applicant after: National Network Intelligent Technology Co.,Ltd. Address before: Xinluo Avenue high tech Zone of Ji'nan City, Shandong province 250101 silver bearing No. 2008 building Applicant before: SHANDONG LUNENG INTELLIGENCE TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |