Method and Device for Tower Tilt Detection Based on Airborne LiDAR Point Cloud

Abstract

This invention discloses a method and apparatus for pole tilt detection based on airborne lidar point clouds. The method includes: acquiring pole point cloud data collected by an airborne lidar; extracting side edge point cloud data from the pole point cloud data; counting the number of pole point cloud data in the neighborhood of each side edge point cloud data; determining the number of pole point cloud data in the neighborhood of each side edge point cloud data as a local density index; normalizing the local density index of each side edge point cloud data, and determining the normalized local density index as the weight of the side edge point cloud data; performing linear fitting on the side edge point cloud data according to the weight of the side edge point cloud data to obtain a side edge fitted line; calculating the angle between the side edge fitted line and the vertical plane, and determining the pole tilt as when the absolute value of the angle is greater than a preset angle. This invention can improve the accuracy and efficiency of pole tilt detection.

Description

Technical Field

[0001] This invention relates to the field of pole and tower detection technology, and in particular to a method and apparatus for pole and tower tilt detection based on airborne lidar point clouds. Background Technology

[0002] When transmission line towers are damaged by external forces or under special weather conditions, uneven stress on the conductors on both sides of the tower can cause a tension difference between the two sides of the tower. This imbalance in stress can lead to tilting and slippage of the tower base, which can affect the normal operation of the transmission line.

[0003] Currently, tower tilt detection mainly relies on regular inspections by patrol personnel along the transmission lines. This involves visually observing the tower's appearance, foundation condition, and surrounding environment, as well as using theodolites and plumb bobs to determine if the tower is tilted. However, manual inspection has limitations: it is inefficient, labor-intensive, and greatly affected by weather, terrain, and other natural conditions, making it difficult to detect early, subtle tilt changes. Theodolite and plumb bob measurements require professional personnel, are complex, and pose certain safety risks during operation. Summary of the Invention

[0004] This invention provides a method for detecting tower tilt based on airborne lidar point clouds, which improves the accuracy and efficiency of tower tilt detection and reduces the workload and potential risks of manual inspection. The method includes:

[0005] Acquire tower point cloud data collected by airborne lidar, and extract side edge point cloud data from the tower point cloud data; the side edge point cloud data constitutes the side edges of the tower body;

[0006] The number of pole point cloud data in the neighborhood of each edge point cloud data is counted; the neighborhood of the edge point cloud data is a spatial region with a fixed volume centered on the edge point cloud data; the number of pole point cloud data in the neighborhood of each edge point cloud data is determined as the local density index of each edge point cloud data.

[0007] The local density index of each edge point cloud data is normalized, and the normalized local density index is determined as the weight of the edge point cloud data. Based on the weight of the edge point cloud data, a straight line is fitted to the edge point cloud data to obtain the edge fitting line.

[0008] Calculate the angle between the fitted line of the side edge and the vertical plane. When the absolute value of the angle is greater than the preset angle, it is determined that the tower is tilted.

[0009] This invention also provides a tower tilt detection device based on airborne lidar point clouds, which improves the accuracy and efficiency of tower tilt detection and reduces the workload and potential risks of manual inspection. The device includes:

[0010] The side edge recognition module is used to: acquire tower point cloud data collected by airborne lidar, and extract side edge point cloud data from the tower point cloud data; wherein the side edge point cloud data constitutes the side edges of the tower body;

[0011] The data density analysis module is used to: count the number of pole point cloud data in the neighborhood of each edge point cloud data; the neighborhood of edge point cloud data is a spatial region with a fixed volume centered on the edge point cloud data; and determine the number of pole point cloud data in the neighborhood of each edge point cloud data as the local density index of each edge point cloud data.

[0012] The side edge fitting module is used to: normalize the local density index of each side edge point cloud data, and determine the normalized local density index as the weight of the side edge point cloud data; and perform linear fitting on the side edge point cloud data according to the weight of the side edge point cloud data to obtain the side edge fitting line.

[0013] The tilt determination module is used to calculate the angle between the fitted straight line of the side edge and the vertical plane. When the absolute value of the angle is greater than the preset angle, the tower is determined to be tilted.

[0014] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for detecting tower tilt based on airborne lidar point clouds.

[0015] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for detecting tower tilt based on airborne lidar point clouds.

[0016] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described method for detecting tower tilt based on airborne lidar point clouds.

[0017] Compared with existing technologies that rely on manual measurement to determine tower tilt, this invention improves the accuracy of extracting side edge point cloud data from tower point cloud data; it designs weights for each side edge point cloud data based on the local density of the point cloud data; and it performs linear fitting on the side edge point cloud data based on these weights. This avoids interference from outliers in the point cloud data caused by environmental vibrations and other factors, thus improving the accuracy and efficiency of tower tilt detection. It also significantly reduces the workload and potential risks of manual inspections. Attached Figure Description

[0018] 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. In the drawings:

[0019] Figure 1 This is a flowchart of the tower tilt detection method based on airborne lidar point cloud in an embodiment of the present invention;

[0020] Figure 2 This is a three-dimensional example diagram of the four side edges of the tower in an embodiment of the present invention;

[0021] Figure 3 This is an example diagram illustrating the tower tilt conversion theory in an embodiment of the present invention;

[0022] Figure 4 This is an example diagram of the tilt state of the tower in an embodiment of the present invention;

[0023] Figure 5 This is a schematic diagram of a tower tilt detection device based on airborne lidar point cloud in an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0025] To reduce the workload and potential risks associated with manually measuring tower tilt, this invention proposes a tower tilt detection method based on airborne lidar point clouds. Figure 1 This is a flowchart of a tower tilt detection method based on airborne lidar point clouds, as described in an embodiment of the present invention. Figure 1 The method includes the following steps:

[0026] Step 101: Obtain the tower point cloud data collected by the airborne lidar, and extract the side edge point cloud data from the tower point cloud data; the side edge point cloud data constitutes the side edge of the tower body;

[0027] Step 102: Count the number of pole point cloud data in the neighborhood of each edge point cloud data; the neighborhood of edge point cloud data is a spatial region with a fixed volume centered on the edge point cloud data; the number of pole point cloud data in the neighborhood of each edge point cloud data is determined as the local density index of each edge point cloud data.

[0028] Step 103: Normalize the local density index of each edge point cloud data, and determine the normalized local density index as the weight of the edge point cloud data; according to the weight of the edge point cloud data, perform linear fitting on the edge point cloud data to obtain the edge fitting line.

[0029] Step 104: Calculate the angle between the fitted line of the side edge and the vertical plane. When the absolute value of the angle is greater than the preset angle, it is determined that the tower is tilted.

[0030] Compared with existing technologies that rely on manual measurement to determine tower tilt, this invention improves the accuracy of extracting side edge point cloud data from tower point cloud data; it designs weights for each side edge point cloud data based on the local density of the point cloud data; and it performs linear fitting on the side edge point cloud data based on these weights. This avoids interference from outliers in the point cloud data caused by environmental vibrations and other factors, thus improving the accuracy and efficiency of tower tilt detection. It also significantly reduces the workload and potential risks of manual inspections.

[0031] A typical power pole tower consists of three parts: the tower head, the tower body, and the supporting legs. Starting from the supporting legs, the section above the point where the tower cross-section changes abruptly (appearing a broken line) is the tower head. If the cross-section does not change abruptly, the section above the lower chord of the lower crossarm is the tower head. The tower head includes insulators, hangers, etc. The overall point cloud distribution of the tower head is irregular. The first section of the tower above the foundation is called the supporting legs, and the section between the supporting legs and the tower body is called the tower body. The tower body is extracted using a preset threshold, starting from the lowest point of the tower point cloud, extracting the point cloud between 2m and 15m in the tower point cloud. This extracted point cloud is the tower body point cloud (the extraction spatial range can be freely set according to the tower body height). The tower body is generally a regular truncated pyramid.

[0032] By dividing the complex structure of the tower, the side edge point cloud data that makes up the side edge of the tower body is effectively extracted. In this embodiment of the invention, the tower point cloud data collected by the airborne lidar is obtained, and the side edge point cloud data is extracted from the tower point cloud data; wherein the side edge point cloud data makes up the side edge of the tower body.

[0033] The laser point cloud data itself is three-dimensional data. Due to the very regular quadrangular frustum structure of the tower body point cloud data, and the straight side edges, it is quite difficult to extract the point cloud that makes up the four side edges of the tower body in three dimensions. Compared with three-dimensional space, it is relatively simple and accurate to extract the side edges in a two-dimensional plane. Therefore, the three-dimensional tower body point cloud data is projected onto a two-dimensional plane that is perpendicular to the horizontal plane in various directions (various directions: in some embodiments, 18 projections are performed between 0 degrees and 180 degrees in 10-degree units. The angle of this direction can be arbitrarily selected. If higher accuracy is required, a smaller angle can be selected).

[0034] When using drones equipped with LiDAR to scan power line corridors, factors such as drone vibration, weather conditions, and limitations of the laser scanner hardware can lead to incomplete or inaccurate scanning of power line towers. When the original tower point cloud data is relatively dense, the tower body point cloud data projected onto a two-dimensional plane presents a regular, approximately isosceles trapezoid, while the projection of the side edge point cloud data is denser and appears as a straight line. In this case: using the horizontal axis centerline of the point cloud data as the axis, the relatively regular, approximately isosceles trapezoid in the two-dimensional plane is divided into two right-angled trapezoids, left and right. Then, a layering threshold is set, dividing the horizontal axis into intervals, and the left and right right-angled trapezoids are processed layer by layer. Within the set layering intervals, values ​​are taken layer by layer using an extreme value approach to extract the left and right edges.

[0035] However, when the original tower point cloud contains a large number of missing data, directly using the aforementioned side edge point cloud data extraction method will result in the extraction of non-tower side edges. In this case, some embodiments will perform convexity analysis on the tower point cloud data to improve the extraction accuracy of the tower side edges.

[0036] In one embodiment, tower point cloud data collected by airborne lidar is acquired, and tower body point cloud data is extracted from the tower point cloud data; the tower body point cloud data is projected onto a two-dimensional plane perpendicular to the horizontal plane to obtain a planar point set composed of projected points in the two-dimensional plane; the convex set of the planar point set is calculated, and side edge point cloud data is extracted from the minimum convex set.

[0037] In one embodiment, tower point cloud data collected by airborne lidar is acquired, and tower body point cloud data is extracted from the tower point cloud data; a convex hull is used to calculate the tower body point cloud data, and the convex hull is projected onto a two-dimensional plane perpendicular to the horizontal plane to obtain a planar point set composed of projected points in the two-dimensional plane; side edge point cloud data is extracted from the planar point set.

[0038] In addition to performing convexity analysis on the tower point cloud data, the accuracy of extracting side edges can be further improved based on local data density. In straight line fitting, regions with high point cloud density are given greater weight, as these regions have a greater impact on the fitted line, thereby reducing the influence of low-density point cloud regions on the fitting and improving the fitting accuracy.

[0039] In this embodiment of the invention, the number of pole point cloud data in the neighborhood of each edge point cloud data is counted; the neighborhood of the edge point cloud data is a spatial region with a fixed volume centered on the edge point cloud data; the number of pole point cloud data in the neighborhood of each edge point cloud data is determined as the local density index of each edge point cloud data.

[0040] For example, for each side edge point cloud data point corresponding to a data point in a two-dimensional plane, a local neighborhood is defined centered on this data point, and the number of point clouds within this local neighborhood is denoted as . Ni and will N i As a local density index for this data point (where within the neighborhood) N i The larger the value, the denser the point cloud in that area.

[0041] In this embodiment of the invention, the local density index of each edge point cloud data is normalized, and the normalized local density index is determined as the weight of the edge point cloud data; according to the weight of the edge point cloud data, a straight line is fitted to the edge point cloud data to obtain the edge fitting straight line.

[0042] For example, considering the large amount of data and strong dispersion in tower structure measurement, a dynamic weight correction algorithm is proposed. The data points corresponding to the side edge point cloud data in a two-dimensional plane are used as sample data. Linear fitting is performed on the sample data, and the error summation is calculated for each sample data. Specifically: Under the basic least squares framework, an adaptive weight factor based on the point cloud distribution density is introduced, and the error function is reconstructed as shown in formula (1):

[0043] (1)

[0044] In the formula, err The sum of errors for each edge point cloud data, For the first i The weights of each side edge point cloud data For the first i The x-coordinate of the projection point of each side edge point cloud data; No. i The ordinate of the projection points of the side edge point cloud data a The slope of the fitted line, b This is the intercept of the fitted line.

[0045] The weights of the extracted side edge point cloud data are positively correlated with the local density, as defined in formula (2):

[0046] (2)

[0047] In the formula, Let be the local density index of the i-th side edge point cloud data. This represents the maximum local density index of the side edge point cloud data. For the first i The weights of each side edge point cloud data ∈[0,1].

[0048] The error function value is determined by the parameter values ​​obtained from linear fitting, while the adaptive weighting factor is dynamically adjusted according to the local density of adjacent data points. Therefore, the error sum can be calculated by constructing a weighted partial differential equation system. When each partial differential value is 0, the error sum is minimized. The calculation method is shown in formulas (3) and (4):

[0049] (3)

[0050] (4)

[0051] The parameters in the formula have the same meanings as in formulas (1) and (2).

[0052] The parameter expressions after adaptive weight factor correction are derived, as shown in formulas (5) and (6). In one embodiment, according to formulas (5) and (6), a straight line is fitted to the side edge point cloud data based on the weights of the side edge point cloud data to obtain the side edge fitted straight line:

[0053] (5)

[0054] (6)

[0055] In the formula, N is the number of side edge point cloud data, and the interpretation of the other parameters is the same as that of formula (1) and formula (2).

[0056] Using the dynamic weighted least squares method based on local density, the fitted straight line of the side edge of the tower body can be obtained. In this embodiment of the invention, the angle between the fitted straight line of the side edge and the vertical plane is calculated. When the absolute value of the angle is greater than a preset angle, the tower is determined to be tilted.

[0057] For example, in a 3D tower point cloud, extract the 3D point cloud dataset of the four side edges of the tower body. P i (x i y i , z i By using the dynamic weighted least squares method based on local density to obtain the fitted two-dimensional straight lines under multiple angles, and combining the fitted two-dimensional straight lines under multiple angles to obtain the fitted three-dimensional straight lines, the vector representation of the side edge can be obtained. Figure 2 This is a three-dimensional example diagram of the four side edges of the tower in an embodiment of the present invention. Figure 2 As shown: ( j =1, 2, 3, 4 correspond to the four lateral edges respectively. x j For vectors exist x Rate of change along the axial direction y j For vectors exist y Rate of change along the axial direction z j For vectors exist z Rate of change in the axial direction).

[0058] Figure 3 This is an example diagram illustrating the tower tilt transformation theory in an embodiment of the present invention. Figure 3 As shown: the normal vector of the horizontal plane is defined as... Define the lateral edge vector The angle between the vector and the horizontal plane normal is ,∠ That is, the angle of inclination.

[0059] In one embodiment, the angle between the fitted line and the vertical plane is calculated based on the arctangent of the slope of the fitted line; the arctangent of the slope of the fitted line is the complementary angle of the angle between the fitted line and the vertical plane; when the absolute value of the angle is greater than a preset angle, it is determined that the tower is tilted.

[0060] Figure 4 This is an example diagram illustrating the tilt state of a tower in an embodiment of the present invention. In one embodiment, as shown... Figure 4 As shown, the angle between the fitted line of the lateral edge and the vertical plane is calculated according to formula (7):

[0061] (7)

[0062] In the above formula: The vector representation of the fitted line for the lateral edge; It is the normal vector of the horizontal plane; for and The included angle; when the absolute value of the included angle is greater than the preset angle, it is determined that the tower is tilted.

[0063] This invention also provides a pole tilt detection device based on airborne lidar point clouds, as described in the following embodiments. Since the principle behind this device is similar to that of the pole tilt detection method based on airborne lidar point clouds, the implementation of this device can refer to the implementation of the pole tilt detection method based on airborne lidar point clouds; repeated details will not be elaborated further.

[0064] Figure 5 This is a schematic diagram of a tower tilt detection device based on airborne lidar point clouds in an embodiment of the present invention. Figure 5 As shown, the device also includes:

[0065] The side edge recognition module 501 is used to: acquire tower point cloud data collected by airborne lidar, and extract side edge point cloud data from the tower point cloud data; wherein the side edge point cloud data constitutes the side edge of the tower body;

[0066] The data density analysis module 502 is used to: count the number of pole point cloud data in the neighborhood of each edge point cloud data; the neighborhood of the edge point cloud data is a spatial region with a fixed volume centered on the edge point cloud data; and determine the number of pole point cloud data in the neighborhood of each edge point cloud data as the local density index of each edge point cloud data.

[0067] The side edge fitting module 503 is used to: normalize the local density index of each side edge point cloud data, determine the normalized local density index as the weight of the side edge point cloud data; and perform linear fitting on the side edge point cloud data according to the weight of the side edge point cloud data to obtain the side edge fitting line.

[0068] The tilt determination module 504 is used to calculate the angle between the fitted straight line of the side edge and the vertical plane. If the absolute value of the angle is greater than the preset angle, the tower is determined to be tilted.

[0069] In one embodiment, the side edge recognition module 501 is specifically used for:

[0070] Acquire tower point cloud data collected by airborne lidar, and extract tower body point cloud data from the tower point cloud data;

[0071] Projecting the tower's point cloud data onto a two-dimensional plane perpendicular to the horizontal plane yields a set of planar points composed of projected points in the two-dimensional plane.

[0072] Calculate the convex set of the planar point set and extract the side edge point cloud data from the minimum convex set.

[0073] In one embodiment, the side edge recognition module 501 is specifically used for:

[0074] Acquire tower point cloud data collected by airborne lidar, and extract tower body point cloud data from the tower point cloud data;

[0075] The convex hull of the tower body point cloud data is calculated, and the convex hull is projected onto a two-dimensional plane perpendicular to the horizontal plane to obtain a set of planar points composed of the projected points in the two-dimensional plane;

[0076] Extract lateral edge point cloud data from the planar point set.

[0077] In one embodiment, the side ridge fitting module 503 is specifically used for:

[0078] Using the following formula, a straight line is fitted to the side edge point cloud data according to the weights of the side edge point cloud data to obtain the side edge fitted straight line:

[0079]

[0080] In the above formula: For the first i The x-coordinate of the projection point of each side edge point cloud data; No. i The ordinate of the projection points of the side edge point cloud data; For the first i Weights of each side edge point cloud data; N The number of side edge point cloud data; a The slope of the fitted line; b This is the intercept of the fitted line.

[0081] In one embodiment, the tilt determination module 504 is specifically used for:

[0082] Calculate the angle between the fitted line and the vertical plane based on the arctangent of the slope of the fitted line; the arctangent of the slope of the fitted line is the complementary angle between the fitted line and the vertical plane.

[0083] When the absolute value of the included angle is greater than the preset angle, the tower is judged to be tilted.

[0084] In one embodiment, the tilt determination module 504 is specifically used for:

[0085] Calculate the angle between the fitted line of the lateral edge and the vertical plane using the following formula:

[0086]

[0087] In the above formula: The vector representation of the fitted line for the lateral edge; It is the normal vector of the horizontal plane; for and The included angle;

[0088] When the absolute value of the included angle is greater than the preset angle, the tower is judged to be tilted.

[0089] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for detecting tower tilt based on airborne lidar point clouds.

[0090] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for detecting tower tilt based on airborne lidar point clouds.

[0091] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described method for detecting tower tilt based on airborne lidar point clouds.

[0092] Compared with existing technologies that rely on manual measurement to determine tower tilt, this invention divides the complex structure of the tower, extracts tower body point cloud data from the tower point cloud data, and then projects the three-dimensional tower body point cloud data onto a two-dimensional plane to improve the accuracy of extracting the tower body side edges. Based on the local density of the point cloud data, weights are designed for each side edge point cloud data. Linear fitting is then performed on the side edge point cloud data according to these weights, avoiding interference from outliers caused by environmental vibrations and other factors. This improves the accuracy and efficiency of tower tilt detection and significantly reduces the workload and potential risks of manual inspections.

[0093] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0094] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can 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, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0095] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0096] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0097] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for detecting tower tilt based on airborne lidar point clouds, characterized in that, include: Acquire tower point cloud data collected by airborne lidar, and extract side edge point cloud data from the tower point cloud data; the side edge point cloud data constitutes the side edges of the tower body; The number of pole point cloud data in the neighborhood of each edge point cloud data is counted; the neighborhood of the edge point cloud data is a spatial region with a fixed volume centered on the edge point cloud data; the number of pole point cloud data in the neighborhood of each edge point cloud data is determined as the local density index of each edge point cloud data. The local density index of each edge point cloud data is normalized, and the normalized local density index is determined as the weight of the edge point cloud data. Based on the weight of the edge point cloud data, a straight line is fitted to the edge point cloud data to obtain the edge fitting line. Calculate the angle between the fitted line of the side edge and the vertical plane. When the absolute value of the angle is greater than the preset angle, the tower is judged to be tilted. The local density index of each edge point cloud data is normalized, and the normalized local density index is determined as the weight of the edge point cloud data, including: The weights of the lateral edge point cloud data are calculated using the following formula: In the formula, Let be the local density index of the i-th side edge point cloud data. This represents the maximum local density index of the side edge point cloud data. For the first i The weights of each side edge point cloud data ∈[0,1]; The side edge point cloud data is extracted from the planar point set composed of the projection points of the tower body point cloud data onto a two-dimensional plane; Using the following formula, a straight line is fitted to the side edge point cloud data according to the weights of the side edge point cloud data to obtain the side edge fitted straight line: In the above formula: For the first i The x-coordinate of the projection point of each side edge point cloud data; No. i The ordinate of the projection points of the side edge point cloud data; For the first i Weights of each side edge point cloud data; N The number of side edge point cloud data; a The slope of the fitted line; b This is the intercept of the fitted line.

2. The method as described in claim 1, characterized in that, Acquire tower point cloud data collected by airborne lidar, and extract side edge point cloud data from the tower point cloud data, including: Acquire tower point cloud data collected by airborne lidar, and extract tower body point cloud data from the tower point cloud data; Projecting the tower's point cloud data onto a two-dimensional plane perpendicular to the horizontal plane yields a set of planar points composed of projected points in the two-dimensional plane. Calculate the convex set of the planar point set and extract the side edge point cloud data from the minimum convex set.

3. The method as described in claim 1, characterized in that, Acquire tower point cloud data collected by airborne lidar, and extract side edge point cloud data from the tower point cloud data, including: Acquire tower point cloud data collected by airborne lidar, and extract tower body point cloud data from the tower point cloud data; The convex hull of the tower body point cloud data is calculated, and the convex hull is projected onto a two-dimensional plane perpendicular to the horizontal plane to obtain a set of planar points composed of the projected points in the two-dimensional plane; Extract lateral edge point cloud data from the planar point set.

4. The method as described in claim 1, characterized in that, Calculate the angle between the fitted line of the side edge and the vertical plane. When the absolute value of the angle is greater than a preset angle, the tower is judged to be tilted, including: Calculate the angle between the fitted line and the vertical plane based on the arctangent of the slope of the fitted line; the arctangent of the slope of the fitted line is the complementary angle between the fitted line and the vertical plane. When the absolute value of the included angle is greater than the preset angle, the tower is judged to be tilted.

5. The method as described in claim 1, characterized in that, Calculate the angle between the fitted line of the side edge and the vertical plane. When the absolute value of the angle is greater than a preset angle, the tower is judged to be tilted, including: Calculate the angle between the fitted line of the lateral edge and the vertical plane using the following formula: In the above formula: The vector representation of the fitted line for the lateral edge; It is the normal vector of the horizontal plane; for and The included angle; When the absolute value of the included angle is greater than the preset angle, the tower is judged to be tilted.

6. A tower tilt detection device based on airborne lidar point clouds, characterized in that, include: The side edge recognition module is used to: acquire tower point cloud data collected by airborne lidar, and extract side edge point cloud data from the tower point cloud data; wherein the side edge point cloud data constitutes the side edges of the tower body; The data density analysis module is used to: count the number of pole point cloud data in the neighborhood of each edge point cloud data; the neighborhood of edge point cloud data is a spatial region with a fixed volume centered on the edge point cloud data; and determine the number of pole point cloud data in the neighborhood of each edge point cloud data as the local density index of each edge point cloud data. The side edge fitting module is used to: normalize the local density index of each side edge point cloud data, and determine the normalized local density index as the weight of the side edge point cloud data; and perform linear fitting on the side edge point cloud data according to the weight of the side edge point cloud data to obtain the side edge fitting line. The tilt determination module is used to calculate the angle between the fitted line of the side edge and the vertical plane. If the absolute value of the angle is greater than the preset angle, the tower is determined to be tilted. The side edge fitting module is specifically used for: The weights of the lateral edge point cloud data are calculated using the following formula: In the formula, Let be the local density index of the i-th side edge point cloud data. This represents the maximum local density index of the side edge point cloud data. For the first i The weights of each side edge point cloud data ∈[0,1]; The side edge point cloud data is extracted from the planar point set composed of the projection points of the tower body point cloud data onto a two-dimensional plane; The side edge fitting module is specifically used for: Using the following formula, a straight line is fitted to the side edge point cloud data according to the weights of the side edge point cloud data to obtain the side edge fitted straight line: In the above formula: For the first i The x-coordinate of the projection point of each side edge point cloud data; No. i The ordinate of the projection points of the side edge point cloud data; For the first i Weights of each side edge point cloud data; N The number of side edge point cloud data; a The slope of the fitted line; b This is the intercept of the fitted line.

7. The apparatus as claimed in claim 6, characterized in that, The side edge recognition module is specifically used for: Acquire tower point cloud data collected by airborne lidar, and extract tower body point cloud data from the tower point cloud data; Projecting the tower's point cloud data onto a two-dimensional plane perpendicular to the horizontal plane yields a set of planar points composed of projected points in the two-dimensional plane. Calculate the convex set of the planar point set and extract the side edge point cloud data from the minimum convex set.

8. The apparatus as claimed in claim 6, characterized in that, The side edge recognition module is specifically used for: Acquire tower point cloud data collected by airborne lidar, and extract tower body point cloud data from the tower point cloud data; The convex hull of the tower body point cloud data is calculated, and the convex hull is projected onto a two-dimensional plane perpendicular to the horizontal plane to obtain a set of planar points composed of the projected points in the two-dimensional plane; Extract lateral edge point cloud data from the planar point set.

9. The apparatus as claimed in claim 6, characterized in that, The tilt detection module is specifically used for: Calculate the angle between the fitted line and the vertical plane based on the arctangent of the slope of the fitted line; the arctangent of the slope of the fitted line is the complementary angle between the fitted line and the vertical plane. When the absolute value of the included angle is greater than the preset angle, the tower is judged to be tilted.

10. The apparatus as claimed in claim 6, characterized in that, The tilt detection module is specifically used for: Calculate the angle between the fitted line of the lateral edge and the vertical plane using the following formula: In the above formula: The vector representation of the fitted line for the lateral edge; It is the normal vector of the horizontal plane; for and The included angle; When the absolute value of the included angle is greater than the preset angle, the tower is judged to be tilted.

11. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 5.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 5.

13. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 5.

Images