Overhead line point cloud extraction method, system, device, medium and product

Abstract

The invention relates to the technical field of electric power systems, and discloses an overhead line point cloud extraction method, system and device, a medium and a product, and the method comprises the steps: collecting three-dimensional point cloud data of a target area where an overhead line and a telegraph pole are located, carrying out the point cloud detection of the three-dimensional point cloud data, and obtaining the point cloud data of the telegraph pole; obtaining a projection plane of the direction of the overhead line according to the telegraph pole point cloud data, projecting the three-dimensional point cloud data to the projection plane to obtain plane point clouds, and extracting the plane point clouds with parabola characteristics in the plane point clouds as parabola plane point clouds of the overhead line, so as to obtain the parabola plane point clouds of the overhead line in a two-dimensional parabola fitting mode. The three-dimensional point cloud data of the overhead line is obtained by mapping the parabola plane point cloud of the overhead line back to the three-dimensional point cloud data, and the real-time performance and the reliability of the extraction process of the overhead line are guaranteed.

Description

Technical Field

[0001] This invention relates to the field of power system technology, and in particular to a method, system, equipment, medium and product for extracting point clouds of overhead lines. Background Technology

[0002] In live-line work near overhead power lines, the risk of electric shock is high, making it crucial to ensure a safe distance between workers and live conductors. Fusion lidar ranging technology can dynamically and accurately determine this safe distance, providing timely warnings of electric shock risks.

[0003] In practical applications, accurately distinguishing overhead lines from point cloud data is a challenge. Traditional overhead line fitting methods have extremely low computational efficiency, and the real-time performance and reliability of the overhead line extraction process are also poor. Summary of the Invention

[0004] In view of this, the present invention provides a method, system, device, medium and product for extracting point clouds of overhead lines, which solves the technical problems of extremely low computational efficiency of traditional overhead line fitting methods, as well as poor real-time performance and reliability of the overhead line extraction process.

[0005] The first aspect of this invention provides a method for extracting point clouds of overhead power lines, comprising:

[0006] Collect 3D point cloud data of the target area containing overhead lines and utility poles;

[0007] Point cloud detection is performed on the three-dimensional point cloud data to obtain the point cloud data of the utility pole;

[0008] Based on the point cloud data of the utility poles, the projection plane of the overhead line route is obtained;

[0009] The three-dimensional point cloud data is projected onto the projection plane to obtain a planar point cloud. The planar point cloud with parabolic features is extracted from the planar point cloud and used as the parabolic planar point cloud of the overhead line.

[0010] The parabolic plane point cloud of the overhead line is mapped back to the three-dimensional point cloud data to obtain the three-dimensional point cloud data of the overhead line.

[0011] Preferably, the method further includes:

[0012] The three-dimensional point cloud data is then filtered.

[0013] Preferably, the step of performing point cloud detection on the three-dimensional point cloud data to obtain utility pole point cloud data includes:

[0014] The 3D point cloud data is downsampled using a grid downsampling method to obtain downsampled 3D point cloud data.

[0015] Extract the cylindrical geometric features from the downsampled 3D point cloud data;

[0016] Based on the cylindrical geometric features, the centerline, radius, and height of the utility pole are determined;

[0017] Based on the centerline, radius, and height of the utility pole, the utility pole region in the three-dimensional point cloud data is determined, and based on the three-dimensional point cloud data contained in the utility pole region, the utility pole point cloud data is determined.

[0018] Preferably, obtaining the projection plane of the overhead line route based on the point cloud data of the utility poles includes:

[0019] Based on the point cloud data of the utility poles at two adjacent locations, determine the coordinates of the center of the cylindrical cross-section corresponding to the utility poles at two adjacent locations.

[0020] Utilizing the physical property that the utility pole is perpendicular to the ground, the horizontal baseline vector and vertical direction vector of the utility pole are determined based on the coordinates of the center of the cylindrical cross-section.

[0021] The normal vector of the projection plane is determined based on the horizontal baseline vector and the vertical direction vector.

[0022] The equation of the projection plane is determined by the normal vector and the coordinates of the center of the cylindrical section of any utility pole.

[0023] The projection plane of the overhead line's direction is obtained based on the equation of the projection plane.

[0024] Preferably, the step of projecting the three-dimensional point cloud data onto the projection plane to obtain a planar point cloud, and extracting planar point clouds with parabolic features from the planar point cloud as the parabolic planar point cloud of the overhead line, includes:

[0025] The three-dimensional point cloud data is projected onto the projection plane to obtain the planar point cloud; wherein, a point cloud index is constructed between the three-dimensional point cloud data and the planar point cloud, and the point cloud index is used to characterize the mapping position relationship between the three-dimensional point cloud data projected onto the planar point cloud;

[0026] Using the geometrically constrained random sampling consistency method, the planar point cloud with parabolic features identified in the planar point cloud is taken as the parabolic planar point cloud of the overhead line.

[0027] Preferably, the step of mapping the parabolic plane point cloud of the overhead line back to the three-dimensional point cloud data to obtain the three-dimensional point cloud data of the overhead line includes:

[0028] The parabolic plane point cloud of the overhead line is fitted to obtain the parabolic equation of the overhead line;

[0029] Based on the parabola equation and the point cloud index, the parabolic plane point cloud is mapped back into the three-dimensional point cloud data to obtain the three-dimensional point cloud data of the overhead line.

[0030] Secondly, the present invention also provides an overhead line point cloud extraction system, comprising:

[0031] The point cloud data acquisition module is used to acquire three-dimensional point cloud data of the target area containing overhead lines and utility poles;

[0032] The point cloud detection module is used to perform point cloud detection on the three-dimensional point cloud data to obtain the point cloud data of the utility pole;

[0033] The projection plane determination module is used to obtain the projection plane of the overhead line route based on the point cloud data of the utility poles;

[0034] The parabolic point cloud extraction module is used to project the three-dimensional point cloud data onto the projection plane to obtain a planar point cloud. By extracting the planar point cloud with parabolic features from the planar point cloud, it is used as the parabolic planar point cloud of the overhead line.

[0035] The point cloud mapping module is used to map the parabolic plane point cloud of the overhead line back to the three-dimensional point cloud data to obtain the three-dimensional point cloud data of the overhead line.

[0036] Thirdly, the present invention also provides an electronic device, the electronic device including a memory and a processor, the memory storing a computer program, the computer program being executed by the processor causing the processor to perform the steps of the overhead line point cloud extraction method as described in the first aspect.

[0037] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the steps of the overhead line point cloud extraction method as described in the first aspect.

[0038] Fifthly, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein, when the program instructions are executed by a computer, the computer performs the steps of the overhead line point cloud extraction method as described in the first aspect.

[0039] As can be seen from the above technical solution, the present invention collects three-dimensional point cloud data of the target area containing overhead lines and utility poles, performs point cloud detection on the three-dimensional point cloud data to obtain utility pole point cloud data, obtains the projection plane of the overhead line direction based on the utility pole point cloud data, projects the three-dimensional point cloud data onto the projection plane to obtain planar point cloud, and extracts planar point cloud with parabolic features from the planar point cloud as the parabolic planar point cloud of the overhead line. This reduces the computational complexity and improves the computational efficiency of the overhead line fitting method by using a two-dimensional parabolic fitting method. At the same time, by mapping the parabolic planar point cloud of the overhead line back to the three-dimensional point cloud data to obtain the three-dimensional point cloud data of the overhead line, the real-time performance and reliability of the overhead line extraction process are ensured. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is an application environment diagram of an overhead line point cloud extraction method provided in an embodiment of the present invention;

[0042] Figure 2 A flowchart of a point cloud extraction method for overhead power lines provided in an embodiment of the present invention;

[0043] Figure 3 This is a schematic diagram of the structure of an overhead line point cloud extraction system provided in an embodiment of the present invention;

[0044] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0045] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] The overhead line point cloud extraction method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 101 communicates with server 102 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be integrated onto server 102 or placed on the cloud or other network servers. Terminal 101 or server 102 collects 3D point cloud data containing the target area where overhead lines and utility poles are located; performs point cloud detection on the 3D point cloud data to obtain utility pole point cloud data; based on the utility pole point cloud data, obtains the projection plane of the overhead line's direction; projects the 3D point cloud data onto the projection plane to obtain a planar point cloud; extracts planar point clouds with parabolic features from the planar point cloud as the parabolic planar point cloud of the overhead line; maps the parabolic planar point cloud of the overhead line back to the 3D point cloud data to obtain the 3D point cloud data of the overhead line.

[0047] Terminal 101 can be, but is not limited to, various personal computers, laptops, smartphones, and tablets.

[0048] Server 102 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0049] like Figure 2 As shown in the embodiment of this application, a method for extracting point clouds of overhead power lines is provided, which is then applied to... Figure 1 Taking terminal 101 or server 102 as an example, the explanation includes the following steps S1 to S5. Wherein:

[0050] Step S1: Collect 3D point cloud data of the target area containing overhead lines and utility poles.

[0051] The 3D point cloud data is obtained by scanning the target area with LiDAR. This data contains the 3D coordinate information of overhead lines and utility poles within the target area. This 3D coordinate information exists in the form of points, hence the name point cloud data.

[0052] In practical applications, point clouds acquired by radar are subject to various factors and contain various noise points. Most of these noise points are isolated outliers, so filtering is performed on the 3D point cloud data.

[0053] Specifically, radius filtering can be used to remove isolated outliers. Isolated outliers typically don't have many other points around them. Therefore, the idea behind radius filtering is to specify a filtering radius *r* and a neighbor threshold *N*. It iterates through each point in the point cloud, finding the number of neighboring points within the filtering radius for each point. If the number of neighboring points is greater than the threshold, the current point is retained; otherwise, it is discarded.

[0054] Step S2: Perform point cloud detection on the 3D point cloud data to obtain the point cloud data of the utility pole.

[0055] One method is to use a cylindrical fitting algorithm to perform point cloud detection on 3D point cloud data to obtain point cloud data of utility poles.

[0056] Step S3: Based on the point cloud data of the utility poles, obtain the projection plane of the overhead line route.

[0057] The projection plane of the overhead line route is determined based on the spatial positional relationship of the utility poles. This plane is the projection plane of the overhead line route, thereby reducing the dimensionality of the three-dimensional point cloud to a two-dimensional planar point cloud, thus reducing the amount of computation required for subsequent processing.

[0058] Step S4: Project the three-dimensional point cloud data onto the projection plane to obtain a planar point cloud. Extract the planar point cloud with parabolic features from the planar point cloud to obtain the parabolic planar point cloud of the overhead line.

[0059] Among them, the parabolic feature is a typical geometric feature of overhead lines in the projection plane. By identifying this feature, the planar point cloud of overhead lines can be accurately extracted.

[0060] Specifically, a geometrically constrained random sampling consistency method can be used to identify point cloud data with parabolic features in the projected planar point cloud. This method randomly samples the point cloud data, fits a parabolic model, and, in conjunction with geometric constraints, filters out point cloud data that conforms to parabolic features, thereby achieving accurate extraction of planar point clouds of overhead lines.

[0061] Step S5: Map the parabolic plane point cloud of the overhead line back to the three-dimensional point cloud data to obtain the three-dimensional point cloud data of the overhead line.

[0062] It should be noted that, in this embodiment, three-dimensional point cloud data containing the target area where overhead lines and utility poles are located is collected, and point cloud detection is performed on the three-dimensional point cloud data to obtain utility pole point cloud data. Based on the utility pole point cloud data, the projection plane of the overhead line's direction is obtained. The three-dimensional point cloud data is projected onto the projection plane to obtain a planar point cloud. By extracting planar point clouds with parabolic features from the planar point cloud, parabolic planar point clouds of the overhead line are used as parabolic planar point clouds. This reduces computational complexity and improves computational efficiency of the overhead line fitting method by utilizing a two-dimensional parabolic fitting method. At the same time, by mapping the parabolic planar point clouds of the overhead line back to the three-dimensional point cloud data, the three-dimensional point cloud data of the overhead line is obtained, ensuring the real-time performance and reliability of the overhead line extraction process.

[0063] In some embodiments, point cloud detection is performed on the 3D point cloud data to obtain utility pole point cloud data, including:

[0064] Step S201: Use the grid downsampling method to downsample the 3D point cloud data to obtain the downsampled 3D point cloud data.

[0065] By using a grid downsampling method to downsample 3D point cloud data, the point cloud density can be reduced, thus lowering computational complexity.

[0066] Step S202: Extract the cylindrical geometric features of the downsampled 3D point cloud data.

[0067] The geometric features of a cylinder include curvature and normal vector.

[0068] Specifically, KD-trees are used to process each point p in the 3D point cloud P. i Select k points within a preset neighborhood radius and calculate the neighborhood centroid as follows:

[0069]

[0070] In the formula, For the neighborhood centroid, For the j-th neighboring point, It is the set of neighboring points.

[0071] Construct a covariance matrix, which describes the degree of dispersion of neighborhood points relative to the centroid. For a set of neighborhood points... The covariance matrix is ​​constructed as follows:

[0072]

[0073] In the formula, C is the covariance matrix.

[0074] Eigenvalue decomposition of the covariance matrix yields three eigenvalues. , , and 3 eigenvalues , , The corresponding feature vectors , , , ≥ ≥ Eigenvalues ​​reflect the degree of dispersion of the neighborhood along the direction of the corresponding eigenvector. Corresponding to the "most dispersed" direction, the eigenvalue To correspond to the direction of maximum concentration, the eigenvector is the dominant direction of the neighborhood distribution (such as the normal to a plane, the direction of a line, etc.). The normal vector describes the perpendicular direction of the local surface where the point is located. For a utility pole (cylindrical), the surface normal vector points radially (perpendicular to the cylinder axis), therefore the normal vector is the eigenvalue. corresponding feature vector .

[0075] Curvature describes the degree of bending of a local surface. The curvature of a cylindrical surface is constant and can be approximated using eigenvalues.

[0076]

[0077] In the formula, For curvature.

[0078] Step S203: Determine the centerline, radius, and height of the utility pole based on the geometric characteristics of the cylinder.

[0079] Candidate points for utility poles that satisfy the following constraints are selected from 3D point cloud data: points with curvature less than a threshold σ are retained. max The point (the cylindrical surface with curvature close to zero) and the angle between the normal vector and the vertical direction (such as the z-axis) is greater than 80°.

[0080] Two points p are randomly selected from the candidate points. a p b Meanwhile, the normal vectors n corresponding to the two points have already been calculated above. a n b The direction of the axis (centerline) is then:

[0081]

[0082] In the formula, It is the axis vector.

[0083] Given the direction vector of the axis, solve the following system of equations to find that points X1 and X2 are both points on the axis:

[0084]

[0085] The process of calculating the radius includes:

[0086]

[0087] In the formula, d j For distance.

[0088] Calculate p using the above formula. a p b The distance d between the two points j The average value is taken as the radius r.

[0089] The height of the utility pole is the projected length of its axis in the vertical direction (assuming the pole is vertical):

[0090] Calculate the projection point X of all support points onto the axis. i Through parameter t i Represents: Xi =X0+t i ×V unit Where X0 is the original projection point, t i V is the projection parameter. unit It is a unit vector.

[0091] Find the maximum value t of the projection parameter max (Parameter values ​​of the top of the utility pole in the axial direction) and minimum value t min (Parameters of the base of the utility pole along the axial direction), height is the projected length:

[0092] .

[0093] Step S204: Based on the centerline, radius, and height of the utility pole, determine the utility pole region in the 3D point cloud data, and based on the 3D point cloud data contained in the utility pole region, determine the utility pole point cloud data.

[0094] The cylindrical region, i.e., the three-dimensional region of the utility pole, can be determined by its centerline, radius, and height.

[0095]

[0096] In the formula, p is a point in the three-dimensional region of the utility pole, P is the original three-dimensional point cloud data, d is the distance from point p to the axis (center line), and r is the radius. For distance tolerance, Let be the projection parameters of point p.

[0097] For each point p in the 3D point cloud data, the points that satisfy the 3D region of the utility pole are determined as the utility pole point cloud data.

[0098] In some embodiments, the projection plane of the overhead line route is obtained based on the point cloud data of the utility poles, including:

[0099] Step S301: Based on the point cloud data of the utility poles at two adjacent locations, determine the coordinates of the center of the cylindrical cross-section corresponding to the utility poles at the two adjacent locations.

[0100] For each utility pole, a cylindrical model can be fitted based on its point cloud data to determine the coordinates of the center of the cylindrical cross-section. Specifically, by performing planar fitting on the utility pole's point cloud data, the plane equation of the pole's base can be obtained. Then, the utility pole's point cloud data is projected onto this plane to obtain a set of projected points. By performing circle fitting on the projected point set, the coordinates of the center of the cylindrical cross-section can be obtained. The coordinates of the center of the cylindrical cross-section of two adjacent utility poles are recorded as (x1, y1, z1) and (x2, y2, z2).

[0101] Step S302: Utilize the physical property that the utility pole is perpendicular to the ground, and determine the horizontal baseline vector and vertical direction vector of the utility pole based on the coordinates of the center of the cylindrical cross-section.

[0102] Since utility poles are typically perpendicular to the ground, this physical characteristic can be used to determine their orientation. Specifically, the horizontal baseline vector of a utility pole can be determined by the coordinates of the centers of the cylindrical cross-sections of two adjacent poles, i.e., the vector (x2-x1, y2-y1, 0). The vertical direction vector can be any direction perpendicular to the horizontal baseline vector. To simplify calculations, (0, 0, 1) is typically chosen as the vertical direction vector, representing vertically upward.

[0103] Step S303: Determine the normal vector of the projection plane based on the horizontal baseline vector and the vertical direction vector.

[0104] Two non-collinear vectors can determine the direction of a plane's normal vector; therefore, the cross product of the horizontal baseline vector and the vertical direction vector can be chosen as the normal vector of the projection plane. Let the horizontal baseline vector be (d... x ,d y If the perpendicular direction vector is (0,0,1), then the normal vector of the projection plane is (d,0). y ,-d x This is because the cross product of two vectors equals a new vector perpendicular to both vectors, and the normal vector of the projection plane is precisely such a vector.

[0105] Step S304: Determine the equation of the projection plane using the normal vector and the coordinates of the center of the cylindrical section of any utility pole.

[0106] Wherein, the normal vector of the projection plane is known to be (d y ,-d x Given the coordinates of the center of the cylindrical section of any utility pole (x0, y0, z0), we can use the point normal form of the plane to determine the equation of the projection plane. The point normal form equation of the plane is: Ax + By + Cz + D = 0, where (A, B, C) are the normal vectors of the plane, and D is a constant term, which can be obtained by substituting the known points into the equation. The normal vector (d...) y ,-d x Substituting the points (x0, y0, z0) and (x0, y0, z0) into the equation, we obtain the equation of the projection plane as: dy×x - dx×y + D = 0. To solve for D, we substitute the points (x0, y0, z0) into the equation, obtaining D = -(dy×x0 - dx×y0). Therefore, the equation of the projection plane is: dy×x - dx×y - (dy×x0 - dx×y0) = 0. Thus, we obtain the equation of the projection plane for the overhead power line route determined based on the power pole point cloud data.

[0107] Step S305: Obtain the projection plane of the overhead line route based on the equation of the projection plane.

[0108] Once the equation of the projection plane is determined, its specific location and shape can be determined based on this equation. This projection plane is a two-dimensional plane, and all points on it satisfy its equation. By projecting three-dimensional point cloud data onto this projection plane, the point cloud data in three-dimensional space can be transformed into point cloud data on a two-dimensional plane, thus simplifying the complexity of subsequent processing. During the projection process, it is necessary to ensure the accuracy and completeness of the projection to guarantee the precision and reliability of subsequent processing. Through this projection plane, the planar point cloud of overhead power lines can be further extracted.

[0109] Compared to traditional fixed or random projection planes, the optimal plane is automatically generated based on the geometric features and physical constraints (perpendicularity) of the utility poles, so that the projected two-dimensional point cloud retains the curvature features (such as parabolic shape) of the overhead lines to the greatest extent.

[0110] In some embodiments, three-dimensional point cloud data is projected onto a projection plane to obtain a planar point cloud. The planar point cloud with parabolic features is extracted from the planar point cloud to serve as the parabolic planar point cloud for the overhead line, including:

[0111] Step S401: Project the 3D point cloud data onto the projection plane to obtain a planar point cloud; wherein, a point cloud index is constructed between the 3D point cloud data and the planar point cloud, and the point cloud index is used to characterize the mapping position relationship between the 3D point cloud data projected onto the planar point cloud.

[0112] During the projection process, to ensure that each 3D point is accurately mapped to its corresponding 2D plane, a point cloud index needs to be constructed. This index records in detail the specific position of each 3D point after projection, i.e., its coordinates in the 2D point cloud. This step is crucial because it not only guarantees the accuracy of the projection but also facilitates subsequent parabolic feature extraction. Using the point cloud index, we can quickly locate the corresponding position of any 3D point on the 2D plane, thus avoiding the tedious coordinate transformation process.

[0113] For example, suppose the three-dimensional coordinates of a point in the original point cloud P are: , Let N be the number of points in point cloud P, and let... Project the point cloud onto the projection plane and obtain the points on the projection plane. .

[0114] Here, while calculating the projection, a point cloud index is constructed, that is, each point is assigned a number, and each number i corresponds to an original 3D coordinate point. With a projected plane point .

[0115] Step S402: Using the geometric constraint random sampling consistency method, the planar point cloud with parabolic features identified in the planar point cloud is used as the parabolic planar point cloud of the overhead line.

[0116] Among them, the geometrically constrained random sampling consistency method is an effective approach for identifying specific geometric shapes (such as parabolas) in point clouds. This method combines random sampling and geometric constraints, enabling accurate identification of target shapes in data containing noise and outliers. Specifically, the method first randomly selects a set of planar points as a candidate parabolic point set, and then uses the geometric properties of the parabola (such as symmetry and vertex position) to constrain and verify these points. Through multiple iterations and consistency checks, the planar point cloud that satisfies the parabolic characteristics is finally selected and used as the parabolic planar point cloud for the overhead power line. This method not only improves the accuracy of identification but also enhances the robustness of the algorithm, enabling it to adapt to various complex scenarios.

[0117] Specifically, the process of identifying planar point clouds with parabolic features using the geometrically constrained random sampling consistency method includes:

[0118] 1) From planar point clouds Three points are randomly selected from the middle. , , , , , , and The equation of the parabola formed for:

[0119]

[0120] In the formula, , , All are equation coefficients, and (u, c) are point coordinates.

[0121] It is important to note that in the process of randomly selecting three points, they must be selected sequentially and meet specific constraints, namely, specifying a distance threshold L. The newly selected point must be more than L away from any previous point.

[0122]

[0123] In the formula, , For planar point clouds Two points in the middle.

[0124] calculate The remaining points arrive distance ;

[0125] statistics fractions Statistics The remaining points arrive distance Less than the threshold Number of

[0126]

[0127]

[0128] 4) Repeat steps 1) to 3) M times to select the parabola with the highest score. ;

[0129] 5) Record and Point cloud index of points in ,from Remove from The point in the middle;

[0130] 6) Repeat steps 1 through 5) until no more fractions can be selected. Less than the threshold parabola To obtain the parabola All planar point clouds with parabolic features.

[0131] In some embodiments, mapping the parabolic plane point cloud of the overhead line back to three-dimensional point cloud data to obtain the three-dimensional point cloud data of the overhead line includes:

[0132] Step S501: Fit the parabolic plane point cloud of the overhead line to obtain the parabolic equation of the overhead line.

[0133] By fitting the identified parabolic planar point cloud, a parabolic equation describing the morphology of overhead power lines can be obtained. This equation, calculated based on the planar point cloud data, accurately reflects the shape characteristics of the overhead power lines on the projection plane. The fitting process can employ mathematical methods such as the least squares method to ensure the accuracy and reliability of the fitting results. Once the parabolic equation is obtained, its spatial orientation and morphology can be described.

[0134] Step S502: Based on the parabola equation and point cloud index, map the parabola plane point cloud back into the three-dimensional point cloud data to obtain the three-dimensional point cloud data of the overhead line.

[0135] Among them, the aforementioned point cloud index is determined. The 3D point cloud of the overhead line is extracted from the original point cloud (3D point cloud data) using the parabolic equation and point cloud index. That is, based on the point cloud index, the identified parabolic plane point cloud is mapped one by one back to the points in the original three-dimensional point cloud data, thereby obtaining the three-dimensional point cloud data describing the overhead line.

[0136] Based on the same inventive concept, this application also provides an overhead line point cloud extraction system for implementing the overhead line point cloud extraction method described above.

[0137] The solution provided by this system is similar to the solution described in the above method. Therefore, the specific limitations of one or more overhead line point cloud extraction system embodiments provided below can be found in the limitations of the overhead line point cloud extraction method described above, and will not be repeated here.

[0138] like Figure 3 As shown in the figure, this application provides an overhead line point cloud extraction system, including:

[0139] The point cloud data acquisition module 100 is used to acquire three-dimensional point cloud data containing the target area where overhead lines and utility poles are located.

[0140] The point cloud detection module 200 is used to perform point cloud detection on the three-dimensional point cloud data to obtain the point cloud data of the utility pole.

[0141] The projection plane determination module 300 is used to obtain the projection plane of the overhead line route based on the point cloud data of the utility poles.

[0142] The parabolic point cloud extraction module 400 is used to project three-dimensional point cloud data onto a projection plane to obtain a planar point cloud. By extracting planar point clouds with parabolic features from the planar point cloud, it is used as the parabolic planar point cloud of the overhead line.

[0143] The point cloud mapping module 500 is used to map the parabolic plane point cloud of the overhead line back to three-dimensional point cloud data to obtain the three-dimensional point cloud data of the overhead line.

[0144] In some embodiments, the system further includes a filtering module, used for:

[0145] Filtering is performed on the 3D point cloud data.

[0146] In some embodiments, the point cloud detection module 200 is used for:

[0147] The 3D point cloud data is downsampled using a grid downsampling method to obtain the downsampled 3D point cloud data.

[0148] Extracting cylindrical geometric features from downsampled 3D point cloud data;

[0149] Based on the geometric characteristics of a cylinder, determine the centerline, radius, and height of the utility pole;

[0150] Based on the centerline, radius, and height of the utility pole, the utility pole region in the 3D point cloud data is determined, and the utility pole point cloud data is determined based on the 3D point cloud data contained in the utility pole region.

[0151] In some embodiments, the projection plane determination module 300 is configured to:

[0152] Based on the point cloud data of the utility poles at two adjacent locations, determine the coordinates of the center of the cylindrical cross-section corresponding to the utility poles at two adjacent locations.

[0153] Utilizing the physical property that utility poles are perpendicular to the ground, the horizontal baseline vector and vertical direction vector of the utility pole are determined based on the coordinates of the center of the cylindrical cross-section.

[0154] Determine the normal vector of the projection plane based on the horizontal baseline vector and the vertical direction vector;

[0155] Determine the equation of the projection plane using the normal vector and the coordinates of the center of the cylindrical section of any utility pole;

[0156] Based on the equation of the projection plane, the projection plane of the overhead line route is obtained.

[0157] In some embodiments, the parabolic point cloud extraction module 400 is used for:

[0158] The 3D point cloud data is projected onto the projection plane to obtain the planar point cloud; a point cloud index is constructed between the 3D point cloud data and the planar point cloud, and the point cloud index is used to characterize the mapping position relationship between the 3D point cloud data and the planar point cloud.

[0159] Using the geometrically constrained random sampling consistency method, planar point clouds with parabolic features identified in planar point clouds are used as parabolic planar point clouds for overhead lines.

[0160] In some embodiments, the point cloud mapping module 500 is used for:

[0161] By fitting the parabolic plane point cloud of the overhead line, the parabolic equation of the overhead line is obtained;

[0162] Based on the parabola equation and point cloud index, the parabolic plane point cloud is mapped back into the three-dimensional point cloud data to obtain the three-dimensional point cloud data of the overhead line.

[0163] like Figure 4As shown in the figure, this application provides an electronic device. The electronic device 10 includes a memory 20 and a processor 30. The memory 20 stores a computer program. When the computer program is executed by the processor 30, the processor 30 performs the steps of the overhead line point cloud extraction method as described in the above embodiment.

[0164] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed, implements the steps of the overhead line point cloud extraction method as described in the above embodiments.

[0165] This application provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer performs the steps of the overhead line point cloud extraction method described in the above embodiments.

[0166] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, electronic devices, and computer storage media described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0167] It should be noted that the terms "comprising" and "having" and any variations thereof in the specification, claims and accompanying drawings of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such processes, methods, products or devices.

[0168] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0169] In the embodiments provided by this invention, it should be understood that the disclosed systems, electronic devices, computer storage media, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units through some interfaces, and may be electrical, mechanical, or other forms.

[0170] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0171] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0172] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the methods described in the various embodiments of the present invention through a computer device (which may be a personal computer, a server, or a network device, etc.). The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0173] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for extracting point clouds from overhead power lines, characterized in that, include: Collect 3D point cloud data of the target area containing overhead lines and utility poles; Point cloud detection is performed on the three-dimensional point cloud data to obtain the point cloud data of the utility pole; Based on the point cloud data of the utility poles, the projection plane of the overhead line route is obtained; The three-dimensional point cloud data is projected onto the projection plane to obtain a planar point cloud. The planar point cloud with parabolic features is extracted from the planar point cloud and used as the parabolic planar point cloud of the overhead line. The parabolic plane point cloud of the overhead line is mapped back to the three-dimensional point cloud data to obtain the three-dimensional point cloud data of the overhead line.

2. The overhead line point cloud extraction method according to claim 1, characterized in that, Also includes: The three-dimensional point cloud data is then filtered.

3. The overhead line point cloud extraction method according to claim 1, characterized in that, The step of performing point cloud detection on the three-dimensional point cloud data to obtain utility pole point cloud data includes: The 3D point cloud data is downsampled using a grid downsampling method to obtain downsampled 3D point cloud data. Extract the cylindrical geometric features from the downsampled 3D point cloud data; Based on the cylindrical geometric features, the centerline, radius, and height of the utility pole are determined; Based on the centerline, radius, and height of the utility pole, the utility pole region in the three-dimensional point cloud data is determined, and based on the three-dimensional point cloud data contained in the utility pole region, the utility pole point cloud data is determined.

4. The overhead line point cloud extraction method according to claim 1, characterized in that, The step of obtaining the projection plane of the overhead line route based on the point cloud data of the utility poles includes: Based on the point cloud data of the utility poles at two adjacent locations, determine the coordinates of the center of the cylindrical cross-section corresponding to the utility poles at two adjacent locations. Utilizing the physical property that the utility pole is perpendicular to the ground, the horizontal baseline vector and vertical direction vector of the utility pole are determined based on the coordinates of the center of the cylindrical cross-section. The normal vector of the projection plane is determined based on the horizontal baseline vector and the vertical direction vector. The equation of the projection plane is determined by the normal vector and the coordinates of the center of the cylindrical section of any utility pole. The projection plane of the overhead line's direction is obtained based on the equation of the projection plane.

5. The overhead line point cloud extraction method according to claim 1, characterized in that, The step of projecting the three-dimensional point cloud data onto the projection plane to obtain a planar point cloud, and extracting planar point clouds with parabolic features from the planar point cloud as the parabolic planar point cloud of the overhead line, includes: The three-dimensional point cloud data is projected onto the projection plane to obtain the planar point cloud; wherein, a point cloud index is constructed between the three-dimensional point cloud data and the planar point cloud, and the point cloud index is used to characterize the mapping position relationship between the three-dimensional point cloud data projected onto the planar point cloud; Using the geometrically constrained random sampling consistency method, the planar point cloud with parabolic features identified in the planar point cloud is taken as the parabolic planar point cloud of the overhead line.

6. The overhead line point cloud extraction method according to claim 5, characterized in that, The process of mapping the parabolic plane point cloud of the overhead line back to the three-dimensional point cloud data to obtain the three-dimensional point cloud data of the overhead line includes: The parabolic plane point cloud of the overhead line is fitted to obtain the parabolic equation of the overhead line; Based on the parabola equation and the point cloud index, the parabolic plane point cloud is mapped back into the three-dimensional point cloud data to obtain the three-dimensional point cloud data of the overhead line.

7. A point cloud extraction system for overhead power lines, characterized in that, include: The point cloud data acquisition module is used to acquire three-dimensional point cloud data of the target area containing overhead lines and utility poles; The point cloud detection module is used to perform point cloud detection on the three-dimensional point cloud data to obtain the point cloud data of the utility pole; The projection plane determination module is used to obtain the projection plane of the overhead line route based on the point cloud data of the utility poles; The parabolic point cloud extraction module is used to project the three-dimensional point cloud data onto the projection plane to obtain a planar point cloud. By extracting the planar point cloud with parabolic features from the planar point cloud, it is used as the parabolic planar point cloud of the overhead line. The point cloud mapping module is used to map the parabolic plane point cloud of the overhead line back to the three-dimensional point cloud data to obtain the three-dimensional point cloud data of the overhead line.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, the processor performs the steps of the overhead line point cloud extraction method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed, it implements the steps of the overhead line point cloud extraction method as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, wherein when the program instructions are executed by a computer, the computer performs the steps of the overhead line point cloud extraction method as described in any one of claims 1-6.

Images