CN116012399A - Point cloud plane identification and edge detection method - Google Patents
Point cloud plane identification and edge detection method Download PDFInfo
- Publication number
- CN116012399A CN116012399A CN202211339969.2A CN202211339969A CN116012399A CN 116012399 A CN116012399 A CN 116012399A CN 202211339969 A CN202211339969 A CN 202211339969A CN 116012399 A CN116012399 A CN 116012399A
- Authority
- CN
- China
- Prior art keywords
- points
- point
- plane
- point cloud
- calculating
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a point cloud plane identification and edge detection method. The method mainly comprises a novel multi-subsynchronous growth algorithm for identifying the middle plane of the complex background and a circular edge extraction algorithm considering the mixing point cloud. Compared with the traditional region growing algorithm, the multiple sub-synchronous growing algorithms provided by the invention have better robustness in the aspect of initial point selection, and the calculation efficiency is improved by nearly 5 times compared with the efficiency of the traditional region growing algorithm. Aiming at the problem of more manually selected parameters in the point cloud processing algorithm, the method derives the entropy threshold of the proposed algorithm through the thickness of the point cloud, and reduces the influence of manual selection on the calculation result.
Description
Technical Field
The invention belongs to the field of structural health monitoring and measurement, and particularly relates to a point cloud plane identification and edge detection method considering mixed point clouds.
Background
The quality evaluation of the embedded part is common construction operation before concrete pouring. If the positioning or the size deviation of the embedded components causes problems in the installation of the later-stage equipment, the positioning and the size acceptance of all the embedded components are necessary according to the drawing. Currently, quality assessment of embedded components mainly relies on manual detection. The method based on manual detection is time-consuming and labor-consuming, and the detection effect is not accurate enough. Therefore, there is a need to provide a solution that enables accurate and efficient quality assessment of embedded components.
The laser scanning technology is used as a non-contact measuring method, the measuring precision of the method is high, the measuring efficiency is high, and the laser scanning technology is gradually applied to engineering quality detection, three-dimensional model reconstruction, structural health monitoring and construction precision tracking at present. Visual information such as space coordinates, color information and the like of the structure can be obtained more quickly and accurately based on the three-dimensional laser scanning technology, so that service information of the structure is effectively monitored, and serious dependence on human interaction and lighting conditions is reduced. The traditional region growing algorithm is easy to cause over-segmentation phenomenon and low single seed growing efficiency, and parameters requiring manual intervention are too many, such as neighborhood point number, curvature threshold value, normal vector included angle threshold value and the like. The problem of partial edge information is also true in calculating geometric information because mixed pixels are not considered.
Disclosure of Invention
Based on the problems of over-segmentation, more artificial parameters and the like existing in the traditional region growing algorithm, the invention provides a novel point cloud plane and geometric information calculating method. The multi-seed joint growth algorithm (Simultaneous Growth of Multi-seeds, SGM) provided by the invention has the advantage of multi-plane simultaneous growth, can detect multiple target planes simultaneously, and greatly improves the plane detection efficiency. When calculating the target edge, a circular target edge detection algorithm considering the mixing point cloud is provided, and compared with the traditional algorithm, the circular target edge detection algorithm is more accurate. The geometric information calculating method provided by the invention can identify the information such as the geometric dimension of the structure with high efficiency and high precision, is an economical and efficient structural dimension measuring method, and has a prospect of being widely applied to actual bridge performance evaluation.
The invention adopts the following technical scheme for solving the technical problems:
the invention provides a point cloud plane identification and edge detection method considering mixed point cloud, which comprises the following steps:
s1, acquiring point cloud information of a wall surface embedded plate before pouring in a nuclear power construction site by a standing type laser scanner, and then transmitting the point cloud information to a computer in real time for data processing;
s2, obtaining a target plane through multiple iterations of a plurality of sub-Synchronous Growth (SGM) algorithms;
s3, calculating all information of the target plate, including center, side length/radius and deflection, of the frame of the target geometric information;
and S4, registering the construction coordinate system and the three-dimensional scanning coordinate system to the same coordinate system, calculating the deviation of all geometric information, and providing reference for practical engineering construction acceptance.
As a further technical scheme of the invention, the model of the standing laser scanner in S1 is an Austria RIEGL VZ-400i remote three-dimensional laser scanner.
Collecting wall surface embedded plate point cloud data of a construction site based on a standing scanner, downsampling the collected data to 20%, and adopting a high-pass diagram filtering method for downsampling, wherein the downsampling method has the advantages of high speed and low sampling rate;
a new strategy of M estimation random sampling consistency (M-estimator SAmple Consensus, MSAC for short) is provided to select an initial point. The basic idea is to estimate regression coefficients by adopting iterative weighted least square, and determine weights of all points according to the sizes of regression residual errors, thereby achieving the purpose of robustness. Assuming that the existing point cloud set is { P }, firstly selecting a point P in the point cloud P i E, P, finding P by using K nearest neighbor algorithm i K points around the point and performing plane fitting. Because the RANSAC method is easily affected by parameters and the least square method is difficult to effectively eliminate the influence of outliers, the invention introduces an M estimation algorithm to solve the problems. The robust M estimation eliminates the influence of outliers on the model parameter estimation results by adaptively assigning different weights to the samples.
And realizing accurate point cloud segmentation through an iterative growth strategy. Firstly, calculating K points around all initial points, then screening Ineligible by using normal vector quantity and normal vector quantity corresponding to the K points around the initial points and included angles between the K points and the normal vector quantity, deleting the Ineligible, completing first iteration, repeating the process until the number of newly added points after deleting the Ineligible angle after iteration is 0, and completing growth.
Preferably, the multiple sub-Synchronous Growth (SGM) algorithm and the conventional point cloud region growth algorithm are compared, and the method has the following characteristics: in terms of parameters, the algorithm provided by the invention only needs to set the number K of the neighbor points of all points, and the region growing algorithm needs to calculate the threshold value of the included angle between normal vectors and the threshold value of the curvature besides the K, and the selection of the two threshold values is very dependent on experience. In terms of algorithm robustness, the algorithm provided by the invention has stronger robustness, and the over-segmentation exists due to improper parameter selection of the region growing algorithm.
The plane identification method for synchronous growth of various seeds in S2 specifically comprises the following steps:
s21, collecting wall surface embedded plate point cloud data of a construction site based on a standing scanner, and downsampling the collected data to 20%;
s22, finding out K points around all points, dividing the K points into inner points and outer points by using MSAC, then restoring downsampling, taking the points with the number of 0 corresponding to all points as initial points of a plurality of sub-synchronous growth algorithms, and completing the selection of the initial points;
s23, calculating K points around all initial points, screening Ineligible by using normal vector quantity and normal vector quantity calculated by the normal vector quantity corresponding to the K points around the initial points and included angles between the K points and the normal vector quantity, deleting the Ineligible, completing first iteration, repeating the process until the number of newly added points is 0 after deleting the Ineligible angle after iteration, and completing growth.
Deducing an entropy value and an included angle by using the thickness of the point cloud caused by the comprehensive error, wherein the method specifically comprises the following steps:
s31, calculating the mean value and variance of the point cloud, approximately distributing the point cloud into Gaussian distribution, taking 6σ as the thickness of the point cloud, and taking e=3σ as p i ＝(x i ,y i ,z i ) Single point precision error of (a);
s32, assuming that all adjacent points are on an error-free tangential plane, fitting the tangential plane T (X), wherein the normal vector of the plane is V 0 . Because each point has the maximum value e, p of the point position error of point position accuracy i At the adjacent point p i ∈(0,e)In the interval range, a tangential plane with the largest error is obtained as T (X '), and the normal vector of the tangential plane is V'; t (X) in the tangential plane, assuming that the point from the neighboring point to the farthest point from the center of the neighboring point is P i 'the included angle between the tangential plane T (X') with the largest error and the tangential plane T (X) without error is theta; calculating the included angle between the tangential plane with the largest error and the tangential plane without error
S33, setting adjacent point p i ＝(x i ,y i ,z i ) Calculating the local entropy in the field
/>
Wherein->
S34, if the information entropy satisfies: h C (θ k ) Log (K), then the neighborhood is planar; affected by scanning accuracy, if H C (θ k ) Not equal to log (K), 2 times the error
As its limit value and the local entropy log (m') as the initial reference, if point p i Local entropy of->
Satisfy +.>
Delete the point, otherwise preserve p i Then H closest to the local entropy log (m') pi As a reference.
In S3, all information of the target plate is acquired based on the calculation target geometric information frame, specifically:
s41, clustering all target plane point clouds based on a Gaussian mixture model;
s42, respectively acquiring edges of the straight line and the round target by using an edge detection method considering the mixing point, and calculating geometric information of all the targets;
and S43, finally registering the three-dimensional scanning coordinate system to a construction coordinate system, and comparing the difference value of the construction information and the design information.
The simplified method for directly determining boundary points on the surface through the distribution of adjacent points in S42 specifically comprises the following steps:
s421, considering that the surface of pc is mostly flat, the PCA algorithm can be used for dimension reduction firstly;
s422, dividing adjacent points of each detection point in the input data into 8 areas, wherein a point with at least one blank area is defined as a boundary point;
s423, dividing the periphery of each central point into eight areas by using four straight lines, and taking the central point without NP in at least two areas as a boundary point;
s424, on the basis of the inner boundary points obtained in S412 and S413, selecting and adding points close to the circular holes in the PC data, and estimating the sizes of the circular holes based on an iterative correction method of the extracted circle centers and the radii.
In S43, the scanning coordinate system is converted into the construction coordinate system by ICP algorithm, specifically:
s431, calculating the center coordinates of the design values and the recognized center coordinates to obtain the three-dimensional position information deviation of all target plates;
s432, calculating normal vectors of all the identification target plates in the positive direction of the x axis;
s433, projecting the normal vector to a yoz plane, and calculating the vector included angle between the projection vector and the vector perpendicular to the xoy plane.
According to another aspect of the present invention, there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the steps in the point cloud plane identification and edge detection method taking into account hybrid point clouds of the present invention.
According to a further aspect of the present invention there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, said processor implementing the steps in the point cloud plane identification and edge detection method taking into account the hybrid point cloud of the present invention when executing said program.
Compared with the prior art, the invention has at least the following beneficial effects:
(1) Compared with the traditional region growing algorithm, the multi-seed combined growing algorithm provided by the invention has better robustness in the aspect of initial point selection, all initial points can be iterated at the same time, the calculation efficiency is improved by nearly 5 times, and the problems of over-segmentation, low single seed growing efficiency and the like are effectively avoided;
(2) The entropy threshold of the proposed algorithm is deduced through the thickness of the point cloud, so that the influence of manually selected parameters on a calculation result is effectively reduced;
(3) The round edge extraction algorithm considering the mixing point cloud is provided, the measurement result is closer to the theoretical value, the precision is higher, and the application prospect of wide actual engineering structure monitoring is provided.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following brief description of the drawings of the embodiments will make it apparent that the drawings in the following description relate only to some embodiments of the present invention and are not limiting of the present invention.
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of an iterative process of a multiple sub-joint growth algorithm of the present invention;
FIG. 3 is a schematic diagram of the present invention that considers the principle of mixing point cloud boundary separation;
fig. 4 is a boundary point judgment principle diagram of the present invention: FIG. 4 (a) is a center point; fig. 4 (b) is a mixing point; fig. 4 (c) is a boundary point;
FIG. 5 is a graph of measurement error of geometric information in an embodiment of the invention
Detailed Description
As shown in fig. 1-5:
example 1:
the invention provides a point cloud plane recognition and edge detection method based on a joint growth algorithm, as shown in figure 1,
it should be further noted that the standing laser scanner model in step 1 is the austria RIEGL VZ-400i remote three-dimensional laser scanner.
as shown in fig. 1, the various sub-synchronous growth algorithms proposed by the present invention mainly include:
1) Based on a standing scanner, collecting the point cloud data of the embedded plate of the wall surface of the construction site, downsampling the collected data to 20%, and adopting a high-pass diagram filtering method for downsampling, wherein the downsampling method has the advantages of high speed and low sampling rate;
2) A new strategy of M estimation random sampling consistency (M-estimator SAmple Consensus, MSAC for short) is provided to select an initial point. The basic idea is to estimate regression coefficients by adopting iterative weighted least square, and determine weights of all points according to the sizes of regression residual errors, thereby achieving the purpose of robustness. Assuming that the existing point cloud set is { P }, firstly selecting a point P in the point cloud P i E, P, finding P by using K nearest neighbor algorithm i K points around the point and performing plane fitting. Because the RANSAC method is easily affected by parameters and the least square method is difficult to effectively eliminate the influence of outliers, the invention introduces an M estimation algorithm to solve the problems. The robust M estimation eliminates the influence of outliers on the model parameter estimation results by adaptively assigning different weights to the samples.
M-estimation is generally defined as:
where n is the total number of points in the plane, ρ is the objective function, and ρ is the residual of the loss function;
is a residual term;
is a robust scale estimate of the residual, relying on the unknown regression coefficient β.
The plane equation obtained by fitting is:
ax+by+cz+d＝0(2)
MSAC compensates for the effect of parameter selection and can divide K into interior points and O pi . When calculating the fitting plane of all points, the points corresponding to the outer points 0 are used as the initial point set { I }, and the rest point sets are { N }, namely
Wherein p is i Is the normal vector of (2)
3) And realizing accurate point cloud segmentation through an iterative growth strategy. Firstly, calculating K points around all initial points, then screening Ineligible by using normal vector quantity and normal vector quantity corresponding to the K points around the initial points and included angles between the K points and the normal vector quantity, deleting the Ineligible, completing first iteration, repeating the process until the number of newly added points after deleting the Ineligible angle after iteration is 0, and completing growth. The iterative process is shown in fig. 2:
firstly, calculating to obtain all initial seed points I i ＝(x i ,y i ,z i ) And its corresponding normal vector
All seed points are then added to the target set { T } and all I are selected i M B's around a point and not within a T set m M epsilon {1,2, …, M } points, and finally calculating all B by using MSAC m Normal vector of point->
The normal vector of the plane passing through K points around the P point is taken as the normal vector of the P point. In calculating the vector, assuming that the number of the internal points I is K and the number of the external points O is K-K, taking the normal vector of the geometric calculation P point formed by the internal points into account as a true value, calculating the normal vector of the P by the internal points, calculating the normal vectors of all the internal points by the same method, and then calculating the included angles between the P and the normal vectors of all the K surrounding internal points and the standard plane
Wherein:
in the above 3) implementation of the accurate point cloud segmentation process by the iterative growth strategy, the method utilizes the point cloud thickness induced by the comprehensive error to deduce the entropy value and the included angle, so as to reduce the influence of manually selected parameters on the calculation result. The method comprises the following steps:
1) Calculating the mean and variance of the point cloud, approximately distributing the point cloud into gaussian distribution, using 6σ as the thickness of the point cloud, and e=3σ as p i ＝(x i ,y i ,z i ) Single point precision error of (a).
2) Assuming that the neighboring points are all on an error-free tangent plane, then a fitted tangent plane T (X) is fitted, the normal vector of which is V 0 . Because each point has the maximum value e, p of the point position error of point position accuracy i At the adjacent point p i Within the E (0, e) interval, the tangential plane with the largest error is obtained as T (X '), and the normal vector of the plane is V'. Cutting flatT (X) in the plane, assuming that the point from the neighboring point to the farthest point from the center of the neighboring point is P i 'the angle between the tangential plane T (X') with the greatest error and the tangential plane T (X) without error is θ. Calculating the included angle between the tangential plane with the largest error and the tangential plane without error
3) Let the neighboring point p i ＝(x i ,y i ,z i ) Calculating the local entropy in the field
4) If the information entropy satisfies: h C (θ k ) Log (K), then the neighborhood is planar. Affected by scanning accuracy, if H C (θ k ) Not equal to log (K), 2 times the error
As its limit value and the local entropy log (m') as the initial reference, if point p i Local entropy of->
Satisfy +.>
Delete the point, otherwise preserve p i Then H closest to the local entropy log (m') pi As a reference.
Preferably, the multiple sub-Synchronous Growth (SGM) algorithm and the conventional point cloud region growth algorithm are compared, and the method has the following characteristics: in terms of parameters, the algorithm provided by the invention only needs to set the number K of the neighbor points of all points, and the region growing algorithm needs to calculate the threshold value of the included angle between normal vectors and the threshold value of the curvature besides the K, and the selection of the two threshold values is very dependent on experience. In terms of algorithm robustness, the algorithm provided by the invention has stronger robustness, and the over-segmentation exists due to improper parameter selection of the region growing algorithm.
And 3, acquiring all information of the target plate based on the framework for calculating the geometric information of the target, wherein the information comprises center, side length (radius) and deflection.
1) And clustering all target plane point clouds based on the Gaussian mixture model. Each gaussian mixture model consists of iv gaussian distributions, each of which is called a cluster, which are combined to form the probability density function of the gaussian mixture model:
wherein N is the number of models; pi n Represents the weight coefficient, meaning the probability that each cluster is selected, an
N(x|μ n ,Σ n ) Is Gaussian distribution Density->
The square of the standard deviation of the nth class is indicated.
The nth sub-model may be expressed as:
assuming that K acquired sample data are present, which data points can be considered to be generated by a certain gaussian distribution, the likelihood function of the GMM can be expressed as:
since the maximum cannot be directly obtained by solution, the result is obtained by iteration using the EM algorithm.
2) And respectively acquiring the edges of the straight line and the circular target by using a circular edge extraction algorithm considering the mixing point cloud, and calculating geometric information such as side length (radius), center, corner and the like of all the targets. The simplified method for directly determining boundary points on the surface through adjacent point distribution comprises the following specific steps:
a) Considering that the surface of pc is mostly flat, the dimension reduction can be performed first using the PCA algorithm.
B) As shown in fig. 3, the origin cloud model is divided into two parts by using a boundary extraction algorithm considering the mixing point cloud, and the true edge can be more accurately described by the boundary with the mixing point cloud on the outer ring.
B) As shown in fig. 4, the neighboring points of each detection point in the input data are divided into 8 areas, and a point having at least one blank area is defined as a boundary point.
C) Dividing the periphery of each central point into eight areas by four straight lines, and taking the central point without point cloud in at least two areas as a boundary point.
D) On the basis of the obtained inner boundary points, close to the circular holes, in the PC data are selected and added, and the sizes of the circular holes are estimated based on an iterative correction method of the extracted circle centers and the radii.
And 4, registering the construction coordinate system and the three-dimensional scanning coordinate system to the same coordinate system, calculating the deviation of all geometric information, and providing reference for practical engineering construction acceptance.
It should be further described that, the method mainly adopts ICP algorithm to convert the scanning coordinate system to the construction coordinate system, specifically:
a) Calculating the center coordinates of the design values and the recognized center coordinates to obtain three-dimensional position information deviations of all target plates;
b) The normal vectors of all the identification target plates in the positive direction of the x axis are calculated, and the deviation of the rotation angle is generally not more than 15 degrees, so that the acute angle of the included angle of the two normal vectors is calculated.
C) And projecting the normal vector to a yoz plane, and calculating the vector included angle between the projection vector and the vector perpendicular to the xoy plane, wherein only an acute angle is required to be considered.
Examples
Taking a wall body at a construction stage as an example to illustrate a specific implementation flow of the invention, a vertical scanner is used for scanning a target wall body, a three-dimensional model is built, and the feasibility of a plurality of sub-synchronous growth algorithms and geometric information calculation frames provided by the invention is further verified.
and 2, carrying out multiple iterations on the basis of multiple sub-Synchronous Growth (SGM) algorithms provided by the invention to obtain a target plane. The target area only needs 4 iterations to cover the entire plane, and a total of 11 targets are identified in the figure.
And 3, acquiring all information of the target plate based on the framework for calculating the geometric information of the target, wherein the information comprises center, side length (radius) and deflection. Firstly, classifying all target areas by using a Gaussian mixture model, and performing plane fitting by using MSAC after obtaining all targets. For a circular target, if no mixing point is generated in scanning, MSAC circle fitting is directly carried out by utilizing point clouds at the outermost layer of a circular area to obtain a circle center and a radius; if the scan produces a blended point, then the MSAC is used to calculate a circular fit plane, dividing all points into inner and outer points, the inner points being used as a plane fit and the outer points being understood as noise, i.e. a blended point cloud. And (3) projecting all outer points generated by the MSAC algorithm to the plane, excluding points of the projection falling in a circular area, calculating the innermost layer points of all projection points, and obtaining the circle center and the radius by using MSAC circle fitting. And the square targets are the same and are not repeated. The error of the mixing point cloud and the design value is taken into account and not taken of the mixing point cloud is shown in fig. 4. As can be seen from fig. 5, the algorithm provided by the invention has higher calculation accuracy as found in the comparison of the algorithm of the invention and the algorithm without considering the mixing point.
And 4, registering the construction coordinate system and the three-dimensional scanning coordinate system to the same coordinate system, calculating the deviation of all geometric information, and providing reference for practical engineering construction acceptance.
Example 2:
the computer-readable storage medium of the present embodiment has stored thereon a computer program which, when executed by a processor, implements the steps in the point cloud plane identification and edge detection method of embodiment 1.
The computer readable storage medium of the present embodiment may be an internal storage unit of the terminal, for example, a hard disk or a memory of the terminal; the computer readable storage medium of the present embodiment may also be an external storage device of the terminal, for example, a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, etc. provided on the terminal; further, the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device.
The computer-readable storage medium of the present embodiment is used to store a computer program and other programs and data required for a terminal, and the computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
Example 3:
the computer device of the present embodiment includes a memory, a processor, and a computer program stored on the memory and executable on the processor, which when executed implements the steps in the point cloud plane identification and edge detection method of embodiment 1.
In this embodiment, the processor may be a central processing unit, or may be other general purpose processors, digital signal processors, application specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like, where the general purpose processor may be a microprocessor or the processor may also be any conventional processor, or the like; the memory may include read only memory and random access memory, and provide instructions and data to the processor, and a portion of the memory may also include non-volatile random access memory, e.g., the memory may also store information of the device type.
It will be appreciated by those skilled in the art that the embodiment(s) disclosure may be provided as a method, system, or computer program product. Thus, the present approach may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present aspects may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present aspects are described with reference to flowchart illustrations and/or block diagrams of methods and computer program products according to embodiments of the invention, it being understood that each flowchart illustration and/or block diagram illustration, and combinations of flowcharts and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions; these computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-only memory (ROM), a random access memory (RandomAccessMemory, RAM), or the like.
The examples of the present invention are merely for describing the preferred embodiments of the present invention, and are not intended to limit the spirit and scope of the present invention, and those skilled in the art should make various changes and modifications to the technical solution of the present invention without departing from the spirit of the present invention.
Claims (8)
1. A method for point cloud plane identification and edge detection, the method comprising the steps of:
s1, acquiring point cloud information of a wall surface embedded plate before pouring in a nuclear power construction site by a standing type laser scanner, and then transmitting the point cloud information to a computer in real time for data processing;
s2, obtaining a target plane through multiple iterations of multiple sub-synchronous growth algorithms;
s3, calculating all information of the target plate, including center, side length/radius and deflection, of the frame of the target geometric information;
and S4, registering the construction coordinate system and the three-dimensional scanning coordinate system to the same coordinate system, calculating the deviation of all geometric information, and providing reference for practical engineering construction acceptance.
2. The method according to claim 1, wherein the plane recognition method for the synchronous growth of the plurality of sub-species in S2 comprises the following steps:
s21, collecting wall surface embedded plate point cloud data of a construction site based on a standing scanner, and downsampling the collected data to 20%;
s22, finding out K points around all points, dividing the K points into inner points and outer points by using MSAC, then restoring downsampling, taking the points with the number of 0 corresponding to all points as initial points of a plurality of sub-synchronous growth algorithms, and completing the selection of the initial points;
s23, calculating K points around all initial points, screening Ineligible by using normal vector quantity and normal vector quantity calculated by the normal vector quantity corresponding to the K points around the initial points and included angles between the K points and the normal vector quantity, deleting the Ineligible, completing first iteration, repeating the process until the number of newly added points is 0 after deleting the Ineligible angle after iteration, and completing growth.
3. The method according to claim 1, wherein the entropy and the angle are derived by using the thickness of the point cloud caused by the integrated error, in particular:
s31, calculating the mean value and variance of the point cloud, approximately distributing the point cloud into Gaussian distribution, taking 6σ as the thickness of the point cloud, and taking e=3σ as p i ＝(x i ,y i ,z i ) Single point precision error of (a);
s32, assuming that all adjacent points are on an error-free tangential plane, fitting the tangential plane T (X), wherein the normal vector of the plane is V 0 . Because each point has the maximum value e, p of the point position error of point position accuracy i At the adjacent point p i In the range of the E (0, e) interval, obtaining a tangential plane with the largest error as T (X '), wherein the normal vector of the plane is V'; t (X) in the tangential plane, assuming that the point furthest from the adjacent point to the center of the adjacent point is P' i The included angle between the tangential plane T (X') with the largest error and the tangential plane T (X) without error is theta; calculating the included angle between the tangential plane with the largest error and the tangential plane without error
S33, setting adjacent point p i ＝(x i ,y i ,z i ) Calculating the local entropy in the field
Wherein->
S34, if the information entropy satisfies: h C (θ k ) Log (K), then the neighborhood is planar; affected by scanning accuracy, if H C (θ k ) Not equal to log (K), 2 times the error
As its limit value and the local entropy log (m') as the initial reference, if point p i Local entropy of->
Satisfy +.>
Delete the point, otherwise preserve p i Then the nearest local entropy log (m') is added>
As a reference.
4. The method according to claim 1, wherein in S3 all information of the target plate is acquired based on the calculation target geometry information frame, specifically:
s41, clustering all target plane point clouds based on a Gaussian mixture model;
s42, respectively acquiring edges of the straight line and the round target by using an edge detection method considering the outer points, and calculating geometric information of all the targets;
and S43, finally registering the three-dimensional scanning coordinate system to a construction coordinate system, and comparing the difference value of the construction information and the design information.
5. The method according to claim 4, wherein the simplified method of directly determining boundary points on the surface by the distribution of neighboring points in S42 is as follows:
s421, considering that the surface of pc is mostly flat, the PCA algorithm can be used for dimension reduction firstly;
s422, dividing adjacent points of each detection point in the input data into 8 areas, wherein a point with at least one blank area is defined as a boundary point;
s423, dividing the periphery of each central point into eight areas by using four straight lines, and taking the central point without NP in at least two areas as a boundary point;
s424, on the basis of the inner boundary points obtained in S412 and S413, selecting and adding points close to the circular holes in the PC data, and estimating the sizes of the circular holes based on an iterative correction method of the extracted circle centers and the radii.
6. The method according to claim 4, wherein the scanning coordinate system is converted into the construction coordinate system by ICP algorithm in S43, in particular:
s431, calculating the center coordinates of the design values and the recognized center coordinates to obtain the three-dimensional position information deviation of all target plates;
s432, calculating normal vectors of all the identification target plates in the positive direction of the x axis;
s433, projecting the normal vector to a yoz plane, and calculating the vector included angle between the projection vector and the vector perpendicular to the xoy plane.
7. A computer-readable storage medium having stored thereon a computer program, characterized by: the program when executed by a processor implements the steps in the point cloud plane identification and edge detection method as claimed in any one of claims 1 to 5.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps in the point cloud plane identification and edge detection method according to any of claims 1-5 when the program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211339969.2A CN116012399A (en) | 2022-10-27 | 2022-10-27 | Point cloud plane identification and edge detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211339969.2A CN116012399A (en) | 2022-10-27 | 2022-10-27 | Point cloud plane identification and edge detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116012399A true CN116012399A (en) | 2023-04-25 |
Family
ID=86036080
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211339969.2A Pending CN116012399A (en) | 2022-10-27 | 2022-10-27 | Point cloud plane identification and edge detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116012399A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116740060A (en) * | 2023-08-11 | 2023-09-12 | 安徽大学绿色产业创新研究院 | Method for detecting size of prefabricated part based on point cloud geometric feature extraction |
| CN117553723A (en) * | 2024-01-12 | 2024-02-13 | 中铁大桥局集团有限公司 | Positioning method for embedded part assembly plate hole group based on three-dimensional scanning technology |
| CN118196171A (en) * | 2024-05-20 | 2024-06-14 | 法奥意威(苏州)机器人系统有限公司 | Method and device for detecting circles, storage medium and electronic equipment |
| CN118196110A (en) * | 2024-05-20 | 2024-06-14 | 法奥意威(苏州)机器人系统有限公司 | Point cloud data plane detection method and device, storage medium and electronic equipment |
-
2022
- 2022-10-27 CN CN202211339969.2A patent/CN116012399A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116740060A (en) * | 2023-08-11 | 2023-09-12 | 安徽大学绿色产业创新研究院 | Method for detecting size of prefabricated part based on point cloud geometric feature extraction |
| CN116740060B (en) * | 2023-08-11 | 2023-10-20 | 安徽大学绿色产业创新研究院 | Method for detecting size of prefabricated part based on point cloud geometric feature extraction |
| CN117553723A (en) * | 2024-01-12 | 2024-02-13 | 中铁大桥局集团有限公司 | Positioning method for embedded part assembly plate hole group based on three-dimensional scanning technology |
| CN117553723B (en) * | 2024-01-12 | 2024-04-23 | 中铁大桥局集团有限公司 | Positioning method for embedded part assembly plate hole group based on three-dimensional scanning technology |
| CN118196171A (en) * | 2024-05-20 | 2024-06-14 | 法奥意威(苏州)机器人系统有限公司 | Method and device for detecting circles, storage medium and electronic equipment |
| CN118196110A (en) * | 2024-05-20 | 2024-06-14 | 法奥意威(苏州)机器人系统有限公司 | Point cloud data plane detection method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116012399A (en) | Point cloud plane identification and edge detection method | |
| CN107038717B (en) | A method of 3D point cloud registration error is automatically analyzed based on three-dimensional grid | |
| CN110807781B (en) | Point cloud simplifying method for retaining details and boundary characteristics | |
| CN116167668B (en) | BIM-based green energy-saving building construction quality evaluation method and system | |
| CN110222642B (en) | Plane building component point cloud contour extraction method based on global graph clustering | |
| CN110060338B (en) | Prefabricated part point cloud identification method based on BIM model | |
| CN110766719B (en) | Target tracking method, device and storage medium | |
| Lange et al. | Dld: A deep learning based line descriptor for line feature matching | |
| CN113822278B (en) | License plate recognition method for unlimited scene | |
| CN113628263A (en) | Point cloud registration method based on local curvature and neighbor characteristics thereof | |
| CN114612665B (en) | Pose estimation and dynamic vehicle detection method based on normal vector histogram features | |
| CN102169581A (en) | Feature vector-based fast and high-precision robustness matching method | |
| CN112991389A (en) | Target tracking method and device and mobile robot | |
| JPWO2018207334A1 (en) | Image recognition apparatus, image recognition method, and image recognition program | |
| CN113409332B (en) | Building plane segmentation method based on three-dimensional point cloud | |
| CN113487722A (en) | Automatic concrete member detection method based on three-dimensional laser scanning method | |
| CN112232248B (en) | Method and device for extracting plane features of multi-line LiDAR point cloud data | |
| CN110851978B (en) | Camera position optimization method based on visibility | |
| CN114742849B (en) | Leveling instrument distance measuring method based on image enhancement | |
| CN115546116A (en) | Method and system for extracting and calculating spacing of discontinuous surface of fully-covered rock mass | |
| CN114972882A (en) | Wear surface damage depth estimation method and system based on multi-attention machine system | |
| CN110942077B (en) | Feature line extraction method based on weight local change degree and L1 median optimization | |
| CN117635615B (en) | Defect detection method and system for realizing punching die based on deep learning | |
| Zang et al. | Density-adaptive and geometry-aware registration of TLS point clouds based on coherent point drift | |
| CN117854060A (en) | Tunnel rock body planar crack identification method and system based on deep learning |
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 |