Tree obstacle early warning method, device, medium and system for power transmission line corridor

By using the entropy weight method to separate the power line and the landform characteristic point cloud in the point cloud data processing of the transmission line corridor, and correcting the tree distance with meteorological and load factors, the problem of inaccurate judgment results in the existing technology is solved and the tree barrier is improved Accuracy of early warning.

CN119068249APending Publication Date: 2024-12-03GUANGDONG POWER GRID CO LTD +1
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411149255.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-21
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing solution does not classify the point cloud data in the point cloud data processing of the transmission line corridor, resulting in poor accuracy of the final judgment results.

Method used

The entropy weight method is used to process the point cloud data, separate the power line point cloud and the landform characteristic point cloud, and correct the tree distance of the transmission line with meteorological and load factors to generate early warning information.

Benefits of technology

The calculation accuracy of the distance between the transmission line and the trees is improved, and the scientificity and accuracy of tree barrier warning is enhanced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119068249A_ABST
    Figure CN119068249A_ABST
Patent Text Reader

Abstract

The invention provides a tree obstacle early warning method, device, medium and system for a power transmission line corridor. The method comprises the following steps: acquiring point cloud data of a power transmission line corridor to obtain initial point cloud data, and preprocessing the initial point cloud data to obtain target point cloud data; processing the target point cloud data by adopting an entropy weight method to separate power line point cloud and landform feature point cloud in the target point cloud data to obtain power line point cloud data and landform feature point cloud data; and obtaining a power transmission line tree distance according to the power line point cloud data and the landform feature point cloud data, and determining whether to generate early warning information at least according to the power transmission line tree distance and a corresponding preset safety distance. The calculation accuracy of the distance between the power transmission line and the tree is improved, that is, the problem that the accuracy of a final judgment result is poor due to the fact that point cloud data are not classified in a refined mode in the processing of the point cloud data of a power transmission line corridor in an existing scheme is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and in particular to a tree barrier early warning method, device, medium and system for transmission line corridors. Background Art

[0002] In order to adapt to the needs of the rapidly developing economy and meet the growing demand for electricity, the transmission network has developed rapidly, which has put forward higher requirements for the safe operation of the power grid. The problem of how to efficiently maintain the transmission corridor and its infrastructure has become increasingly prominent. In areas with complex terrain, there are often dense growth of trees and bamboos, which aggravates the complexity of the terrain and makes it more difficult for workers to patrol the lines. Failure to patrol the lines in time may cause the trees and bamboos around the transmission lines to grow into the safe distance of the lines, which will endanger the safe operation of the transmission lines. Since the high-voltage lines are directly exposed to the air, when the trees are too close to the transmission lines, the air acts as a conductor and there is a risk of flashover. At this time, the trees become good conductors, connecting the transmission lines to the earth, causing single-phase grounding faults, causing power outages and even fires.

[0003] In the existing scheme, tree obstacle warning is generally achieved by collecting point cloud data of the transmission line corridor. For example, tree obstacle warning is achieved by considering meteorological factors. However, it takes fewer factors into consideration and does not consider the impact of meteorological, load and other factors on it, resulting in inaccurate calculation of the suspension distance of the transmission line. At the same time, it uses the thinning method to pre-process the point cloud data, and then restores it to the original point cloud data when the transmission line is reconstructed, resulting in a large amount of data processing.

[0004] That is, the existing solutions do not perform detailed classification of point cloud data when processing point cloud data of transmission line corridors, resulting in poor accuracy of the final judgment result. Summary of the invention

[0005] The main purpose of the present application is to provide a tree barrier warning method, device, medium and system for transmission line corridors, so as to at least solve the problem that the existing solutions do not perform detailed classification of point cloud data in the processing of point cloud data of transmission line corridors, resulting in poor accuracy of the final judgment result.

[0006] In order to achieve the above object, according to one aspect of the present application, a tree barrier early warning method for a transmission line corridor is provided, the method comprising:

[0007] Acquire point cloud data of the transmission line corridor to obtain initial point cloud data, and pre-process the initial point cloud data to obtain target point cloud data, wherein the pre-processing includes at least filtering processing;

[0008] The target point cloud data is processed by using an entropy weight method to separate the power line point cloud and the landform feature point cloud in the target point cloud data to obtain the power line point cloud data and the landform feature point cloud data;

[0009] The transmission line-tree distance is obtained based on the power line point cloud data and the topographic feature point cloud data. Whether to generate early warning information is determined at least based on the size of the transmission line-tree distance and the corresponding preset safety distance. The early warning information is used to prompt that there is a fire risk in the current transmission line. The transmission line-tree distance is the shortest distance between the transmission line and the tree.

[0010] Optionally, in the process of determining whether to generate warning information based at least on the distance between the transmission line and the tree and the corresponding preset safety distance, the method further includes:

[0011] According to σ-(L1 2 g 2 E / 24σ 2 )=σ m -(L1 2 g m 2 E / 24σ m 2 )-αE(tt m -t c ), correct the transmission line-tree distance to obtain the final transmission line-tree distance; wherein, σ is the stress of the transmission line when the specific load is g and the air temperature is t, σm is the stress of the transmission line when the specific load is gm and the air temperature is tm, α is the expansion temperature coefficient of the transmission line, E is the elastic module of the transmission line, L1 is the span of the transmission line, g is the gravitational acceleration; tc is the temperature change caused by the current in the transmission line.

[0012] Optionally, whether to generate warning information is determined at least based on the size of the transmission line-tree distance and the corresponding preset safety distance, including: when the final transmission line-tree distance is smaller than the corresponding preset safety distance, determining to generate the warning information; when the final transmission line-tree distance is greater than or equal to the corresponding preset safety distance, determining not to generate the warning information.

[0013] Optionally, the initial point cloud data is preprocessed to obtain target point cloud data, including: segmenting the initial point cloud data according to the segmentation result of the transmission line corridor to obtain multiple segments of intermediate point cloud data; classifying the intermediate point cloud data to obtain a first type of point cloud data and a second type of point cloud data, the first type of point cloud data representing a risk level of safety hazards to the transmission line in the landform is greater than the second type of point cloud data representing a risk level of safety hazards to the transmission line in the landform; using a radius filtering method to filter the first type of point cloud data, and using a statistical filtering method and a thinning preprocessing method to filter the second type of point cloud data to obtain the target point cloud data.

[0014] Optionally, the target point cloud data is processed using an entropy weight method to separate the power line point cloud and the topographic feature point cloud in the target point cloud data to obtain the power line point cloud data, including: constructing a covariance matrix and determining height eigenvalues ​​and covariance eigenvalues ​​based on the target point cloud data, the covariance eigenvalues ​​including vertical angle, linearity, surface change value and curvature; normalizing the height eigenvalues ​​and the covariance eigenvalues ​​to obtain a feature evaluation matrix; determining the entropy weight of each feature based on the feature evaluation matrix; and determining the power line point cloud data using the height feature above the ground with an entropy weight of 1.

[0015] Optionally, determining the entropy weight of each feature according to the feature evaluation matrix includes:

[0016] according to and Determining the entropy weight of each of the features;

[0017] Among them, P ij is the weight of the feature evaluation of the i-th point in the j-th feature, e ij is the feature evaluation of the i-th point on the j-th feature, S j is the weight of the jth feature; m is the total number of points, and n is the total number of features.

[0018] Optionally, acquiring point cloud data of the transmission line corridor to obtain initial point cloud data includes: determining the coordinates of each point cloud in the initial point cloud data as: Among them, x i is the 3D physical space coordinate of the point cloud, X i is the phase center coordinate of the airborne GPS receiver, is the rotation matrix, ω i ,φ i and are the azimuth, pitch and roll angles of the inertial navigation unit, h i is the distance vector.

[0019] According to another aspect of the present application, a tree barrier warning device for a transmission line corridor is provided, the device comprising:

[0020] An acquisition unit, used to acquire point cloud data of the transmission line corridor, obtain initial point cloud data, and pre-process the initial point cloud data to obtain target point cloud data, wherein the pre-processing at least includes filtering processing;

[0021] A first processing unit is used for using an entropy weight method to separate the power line point cloud and the landform feature point cloud in the target point cloud data to obtain the power line point cloud data and the landform feature point cloud data;

[0022] The second processing unit is used to obtain the transmission line-tree distance based on the power line point cloud data and the topographic feature point cloud data, and determine whether to generate warning information at least based on the size of the transmission line-tree distance and the corresponding preset safety distance, wherein the warning information is used to prompt that there is a fire risk in the current transmission line, and the transmission line-tree distance is the shortest distance between the transmission line and the tree.

[0023] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute any one of the tree barrier warning methods for the transmission line corridor.

[0024] According to another aspect of the present application, a tree barrier warning system for a transmission line corridor is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the tree barrier warning methods for the transmission line corridor.

[0025] By applying the technical solution of the present application, the point cloud data of the transmission line corridor is obtained to obtain the initial point cloud data, and the initial point cloud data is preprocessed to obtain the target point cloud data; the target point cloud data is processed by the entropy weight method to separate the power line point cloud and the landform feature point cloud in the target point cloud data to obtain the power line point cloud data and the landform feature point cloud data; the distance between the transmission line and the tree is obtained according to the power line point cloud data and the landform feature point cloud data, and whether to generate warning information is determined at least according to the distance between the transmission line and the tree and the corresponding preset safety distance. The calculation accuracy of the distance between the transmission line and the tree is improved, that is, the problem that the existing solution does not refine and classify the point cloud data in the processing of the point cloud data of the transmission line corridor, thereby solving the problem that the accuracy of the final judgment result is poor. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings constituting part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0027] Figure 1 A schematic flow chart of a tree barrier early warning method for a transmission line corridor provided according to an embodiment of the present application is shown;

[0028] Figure 2 A schematic flow chart of another tree barrier early warning method for a transmission line corridor provided according to an embodiment of the present application is shown;

[0029] Figure 3 A structural block diagram of a tree barrier warning device for a transmission line corridor provided according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0030] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0031] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0034] Specific load refers to the mechanical load acting on the conductor in power engineering, including deadweight, ice weight and wind pressure, etc. Although these loads may be unevenly distributed, they are usually regarded as evenly distributed in calculations. The calculation and consideration of conductor specific load is crucial to the design and operation of power systems, especially in live operations, because it directly affects the safety of the conductors and the stability of the system.

[0035] Radius filtering is a commonly used filtering method in image processing. It filters each pixel by calculating the average or weighted average of the pixels within a certain radius around the pixel, thereby reducing the noise in the image.

[0036] Statistical filtering is a filtering method based on statistical principles. It performs statistical analysis on the pixel values ​​in the image, such as calculating statistical features such as mean and variance, and then filters the image based on these statistical features.

[0037] The thinning preprocessing method is a data processing method that reduces the amount and complexity of data by sampling or downsampling the original data, while retaining the main features of the original data as much as possible to improve the efficiency and accuracy of subsequent data processing or analysis.

[0038] Sag refers to the natural bending of a conductor or insulator between two posts in a power line.

[0039] Point cloud data refers to a 3D data set containing a large number of points, which is usually used to represent the surface shape of an object or the structure of a scene. Point cloud data usually consists of a large number of coordinate points, each of which contains its position information in 3D space. In point cloud data, each point can contain other attribute information, such as color, normal direction, etc., to describe the appearance and structure of the object in more detail.

[0040] The canopy height model refers to the distribution pattern of the tree canopy in the vertical direction. By measuring the canopy height model of trees, the growth status, growth rate and competitiveness of trees can be evaluated.

[0041] The Entropy Weight Method is a multi-attribute decision-making method that evaluates the contribution of each attribute to the decision result by calculating the entropy value and weight of the attribute, and makes a comprehensive evaluation and decision. This method introduces the concept of information entropy into weight distribution, and uses information entropy to represent the uncertainty and information content of the attribute, thereby determining the weight of the attribute.

[0042] The vertical angle represents the angle relationship between the change directions in the data set. The smaller the vertical angle, the closer the change directions in the data set are, and vice versa, the relationship between the change directions is more dispersed.

[0043] Linearity describes the degree of linearity of the direction of change in a data set, that is, whether the change in the data set presents a linear relationship. When the linearity is high, it means that the direction of change in the data set presents a more obvious linear relationship; when the linearity is low, it means that the direction of change in the data set is more random or nonlinear.

[0044] Surface change refers to the magnitude or rate of change in the direction of change in a data set, that is, whether the change in the data set is gradual or drastic. A larger surface change indicates a larger magnitude or rate of change in the data set, while a smaller surface change indicates a more gradual change in the data set.

[0045] Curvature describes the degree of curvature of the direction of change in a data set, that is, the change in the data set is curved or curvilinear. The larger the curvature, the more curved the change direction in the data set is; while the smaller the curvature, the more straight or smooth the change direction in the data set is.

[0046] Height above ground is the difference in height between the ground or terrain and sea level, usually expressed in meters or feet.

[0047] The voxel height ratio refers to the ratio of the height change of voxels (volume pixels in 3D images) in the vertical direction within a certain area of ​​the terrain or surface.

[0048] As introduced in the background technology, the prior art generally realizes tree obstacle warning by collecting point cloud data of the transmission line corridor. For example, tree obstacle warning is realized by considering meteorological factors. However, it considers fewer factors and does not consider the influence of factors such as meteorology and load, resulting in inaccurate calculation of the suspension distance of the transmission line. At the same time, it uses the thinning method to pre-process the point cloud data, and then restores it to the original point cloud data when the transmission line is reconstructed, resulting in a large amount of data processing. That is, the existing scheme does not refine and classify the point cloud data in the processing of the point cloud data of the transmission line corridor, resulting in poor accuracy of the final judgment result. In order to solve the problem that the existing scheme does not refine and classify the point cloud data in the processing of the point cloud data of the transmission line corridor, resulting in poor accuracy of the final judgment result, the embodiments of the present application provide a tree obstacle warning method, device, medium and system for the transmission line corridor.

[0049] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0050] In this embodiment, a tree barrier warning method for a transmission line corridor is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0051] Figure 1 FIG. 1 is a flow chart of a tree barrier warning method for a transmission line corridor provided according to an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0052] Step S101, acquiring point cloud data of the transmission line corridor to obtain initial point cloud data, and preprocessing the initial point cloud data to obtain target point cloud data, wherein the preprocessing at least includes filtering processing;

[0053] Specifically, the initial point cloud data can be obtained through the airborne laser radar measurement system. In recent years, with the continuous development of laser radar and drone technology, the airborne laser radar measurement system, as an emerging earth observation technology, has been widely used in power and surveying and mapping. Its advantages are that the dense dot matrix data can fully describe the structural information of the object; in the natural environment, the multiple echo performance of the laser can fully capture the detailed information of the measured area; the high-precision ranging of the laser radar ensures the quality of the data; the multiple flights and coordinated operation of the airborne laser radar improve the efficiency of data acquisition.

[0054] In one embodiment of the present application, the above-mentioned step S101 pre-processes the above-mentioned initial point cloud data to obtain target point cloud data, including: segmenting the above-mentioned initial point cloud data according to the segmentation result of the transmission line corridor to obtain multiple segments of intermediate point cloud data; classifying the above-mentioned intermediate point cloud data to obtain a first type of point cloud data and a second type of point cloud data, the first type of point cloud data representing the risk level of the landform causing safety hazards to the transmission line is greater than the second type of point cloud data representing the risk level of the landform causing safety hazards to the transmission line; using a radius filtering method to filter the above-mentioned first type of point cloud data, and using a statistical filtering method and a thinning preprocessing method to filter the above-mentioned second type of point cloud data to obtain the above-mentioned target point cloud data.

[0055] Specifically, the laser radar point cloud data has the characteristics of high density and large data volume. The average number of point clouds in a 1 square meter space of the laser equipment used in the present invention is 40. During the flight acquisition process, the data is affected by factors such as flight conditions and equipment defects, which will generate a large number of noisy point clouds. For example, the spatial discrete point cloud is completely redundant point cloud data that is completely separated from the observed subject. Failure to filter these point clouds will interfere with the subsequent single tree segmentation and single tree spatial feature extraction. Therefore, it is necessary to filter and denoise the laser radar point cloud data.

[0056] The filtering method in the prior art is to use a filtering method for all the collected point cloud data as a whole. However, for the point cloud data of the transmission line corridor, since the transmission line corridor is generally a long line, the collected point cloud data is also very "long". In such a long data, the landforms of different sections are different. Some landforms are characterized by lush trees, some are characterized by overgrown weeds, and some are characterized by no vegetation, etc., which have no substantial impact on the early warning of the transmission line corridor. Therefore, adopting a filtering method for the point cloud data of the above-mentioned entire transmission line corridor will undoubtedly lead to a lack of targeting of the different landform sections of the corridor, resulting in poor filtering effect.

[0057] In the present invention, an adaptive filtering method is designed for the different characteristics of the landforms in the transmission line corridor, specifically: the transmission line corridor is divided into different segments according to the actual landforms of the transmission line corridor to be monitored; wherein the coordinates of the landform change points in the transmission line corridor are the endpoints of different segments; illustratively, there are dense trees in some sections of the transmission line corridor, and then gradually change to weeds after a transition section, then the segment endpoints are manually set in the transition section between the dense trees and the weeds, and the endpoint coordinates are recorded to facilitate the subsequent segmentation of the point cloud data. Among them, the classification of landforms is mainly the classification of trees; in the present invention, the canopy height model is used to classify trees.

[0058] The specific method of radius filtering is: if there are more than or equal to k point clouds in the r radius space domain of any point Dn in the segment of point cloud data, it is considered to be a normal point cloud, otherwise it is considered to be a discrete point, and all points in the segment of point cloud data are traversed, and the discrete points are filtered out; the specific method of statistical filtering is: for any point in the segment of point cloud data, the average distance between the point and the k points in the space domain is calculated to be in the normal distribution space, and it is considered to be a normal point, otherwise it is an outlier, and the outlier will be removed; the thinning preprocessing is to reduce the amount of original point cloud data as much as possible while ensuring that the point cloud data has a certain accuracy. The present invention adopts the spatial distance thinning method to achieve thinning preprocessing. The spatial distance thinning method belongs to the spatial thinning algorithm. The spatial thinning algorithm quickly constructs an octree index structure for massive point cloud data, and combines the nearest search method to determine the retention of data foot points, so as to achieve the purpose of fast thinning of point cloud data.

[0059] In one embodiment of the present application, the step S101 of acquiring the point cloud data of the transmission line corridor to obtain the initial point cloud data includes: determining the coordinates of each point cloud in the initial point cloud data as:

[0060] Among them, x i is the 3D physical space coordinate of the point cloud, X i is the phase center coordinate of the airborne GPS receiver, is the rotation matrix, ωi ,φ i and are the azimuth, pitch and roll angles of the inertial navigation unit, h i is the distance vector.

[0061] Specifically, the airborne laser radar measurement system includes a laser scanner, a distance measurement unit, a storage unit, a global positioning system (GPS), a control and monitoring unit, and an inertial measurement unit (IMU). The laser scanner of the airborne laser radar measurement system is responsible for controlling the scanning mode, the distance measurement unit is responsible for obtaining and calculating the distance from the object to be measured to the airborne platform, and the control and monitoring unit is responsible for obtaining the working status of the drone to ensure that the drone works normally and receives external control instructions normally. GPS and IMU can obtain the real-time position and flight attitude of the drone in real time. Finally, the distance measurement unit is combined to write the point cloud data into the storage unit in a specific format to facilitate offline solution and verification of the three-dimensional coordinates of the point cloud. Among them, when the airborne laser radar measurement system collects point cloud data, the instantaneous coordinates of the position of the measured transmission line corridor can be obtained through GPS, and the three-dimensional coordinates can be inverted by recording the instantaneous flight attitude of the drone through IMU.

[0062] Furthermore, in this step, the point cloud data is segmented and classified according to the topographical characteristics of the transmission line corridor, and then different preprocessing methods are used to implement point cloud data preprocessing, so as to achieve "slimming" of point cloud data volume while ensuring the accuracy of point cloud data as much as possible.

[0063] Step S102, using an entropy weight method to process the target point cloud data to separate the power line point cloud and the landform feature point cloud in the target point cloud data to obtain the power line point cloud data and the landform feature point cloud data;

[0064] Specifically, processing the above-mentioned target point cloud data refers to extracting power line point clouds from the power corridor point cloud data for realizing the reconstruction of the power line three-dimensional model; the present invention analyzes the geometric distribution characteristics of the power line point clouds, introduces the entropy weight method to quantify the feature weight ratio, and proposes a power line extraction algorithm based on the entropy weight method feature evaluation to achieve high-precision power line extraction.

[0065] In one embodiment of the present application, the entropy weight method is used in the above-mentioned step S102 to process the above-mentioned target point cloud data to separate the power line point cloud and the terrain feature point cloud in the above-mentioned target point cloud data to obtain the power line point cloud data, including: constructing a covariance matrix and determining the height eigenvalue and the covariance eigenvalue according to the above-mentioned target point cloud data, and the above-mentioned covariance eigenvalue includes the vertical angle, linearity, surface change value and curvature; normalizing the above-mentioned height eigenvalue and the above-mentioned covariance eigenvalue to obtain a feature evaluation matrix; determining the entropy weight of each feature according to the above-mentioned feature evaluation matrix; and using the height feature above the ground with an entropy weight of 1 to determine the above-mentioned power line point cloud data.

[0066] In the present invention, six features, namely, the height eigenvalue (height from the ground, voxel height ratio) and covariance eigenvalue (vertical angle, linearity, surface change, curvature) of the point cloud data are selected to form a eigenvector for power line extraction calculation. The calculation process of the covariance eigenvalue is as follows: the point cloud is stored in a kd tree, the covariance matrix is ​​calculated by searching the neighborhood points through k nearest neighbors, and the specific values ​​of the vertical angle, linearity, surface change and curvature are calculated by constructing the covariance matrix. The above-mentioned height eigenvalue and the above-mentioned covariance eigenvalue are normalized to eliminate the defect that the values ​​of different features cannot be compared.

[0067] kd (short for k-dimensional tree) is a data structure that organizes points in k-dimensional Euclidean space. kd trees can be used in many applications, such as multidimensional key-value searches (e.g. range searches and nearest neighbor searches).

[0068] In one embodiment of the present application, the step S102 of determining the entropy weight of each feature according to the feature evaluation matrix includes: and Determine the above entropy weights of each of the above features; where P ij is the weight of the feature evaluation of the i-th point in the j-th feature, e ij is the feature evaluation of the i-th point on the j-th feature, S j is the weight of the jth feature; m is the total number of points, and n is the total number of features.

[0069] Specifically, after the entropy weight of each feature is determined according to the formula, the height-to-ground feature with an entropy weight of 1 (in order to distinguish the power line point cloud data from the landform point cloud data) can be used to determine the subsequent power line point cloud data.

[0070] Step S103, obtaining the transmission line-tree distance based on the power line point cloud data and the topographic feature point cloud data, and determining whether to generate warning information at least based on the size of the above transmission line-tree distance and the corresponding preset safety distance. The above warning information is used to prompt that there is a fire risk in the current transmission line. The above transmission line-tree distance is the shortest distance between the above transmission line and the tree.

[0071] In the above steps, the initial point cloud data is obtained by acquiring the point cloud data of the transmission line corridor, and the initial point cloud data is preprocessed to obtain the target point cloud data; the target point cloud data is processed by using the entropy weight method to separate the power line point cloud and the landform feature point cloud in the target point cloud data, and the power line point cloud data and the landform feature point cloud data are obtained; the transmission line tree distance is obtained according to the power line point cloud data and the landform feature point cloud data, and whether to generate warning information is determined at least according to the transmission line tree distance and the corresponding preset safety distance. The calculation accuracy of the distance between the transmission line and the tree is improved, that is, the problem that the existing solution does not refine and classify the point cloud data in the processing of the point cloud data of the transmission line corridor, resulting in poor accuracy of the final judgment result is solved.

[0072] Specifically, the point cloud data is used to collect the instantaneous distance between the transmission line and the trees. However, the transmission line is often affected by meteorological factors, which causes the shape and sag of the transmission line to change, and then causes the distance from the trees to change. That is to say, under normal weather conditions, it is possible that trees will not form tree barriers that affect the transmission line corridor, but under certain extreme weather conditions, tree barriers may form in the transmission line corridor, thus affecting the safety of power transmission. This step calculates the distance between the transmission line and the trees under the influence of weather, and then finds possible tree barrier risk points, thereby improving the scientificity and accuracy of the early warning.

[0073] In the specific implementation process, in the process of determining whether to generate warning information at least according to the distance between the transmission line and the tree and the corresponding preset safety distance in step S103, the method further includes: according to σ-(L1 2 g 2 E / 24σ 2 )=σ m -(L1 2 g m 2 E / 24σ m 2 )-αE(tt m -t c ), the distance between the transmission line and the tree is corrected to obtain the final distance between the transmission line and the tree; where σ is the stress of the transmission line when the load is g and the temperature is t, σ m The specific load is g m And the temperature is tm The stress of the transmission line at t, α is the expansion temperature coefficient of the transmission line, E is the elastic module of the transmission line, L1 is the span of the transmission line, and g is the acceleration of gravity; t c is the temperature change caused by the current carried in the above transmission line.

[0074] Specifically, when meteorological conditions change, the temperature and load on the transmission line will also change, resulting in changes in the stress of the transmission line, and therefore, changes in the distance between the transmission line and the trees; when the current in the transmission line changes, it also affects the stress change of the transmission line. The present invention improves the transmission line state equation in the prior art, not only considering meteorological factors, but also considering the impact of current changes on the transmission line, so that the calculated distance between the transmission line and the tree under the influence of meteorology is more accurate.

[0075] Specifically, when collecting point cloud data, the temperature data at the same time is also collected, and then the local maximum temperature data is obtained. The maximum temperature data and the temperature data collected at the same time are input into the above-mentioned state equation, and the distance between the transmission line and the tree corrected by meteorological factors is solved by Newton's iteration method.

[0076] In one embodiment of the present application, in the above step S103, whether to generate a warning message is determined at least based on the size of the above transmission line-tree distance and the corresponding preset safety distance, including: when the above final transmission line-tree distance is less than the corresponding above preset safety distance, determining to generate the above warning message; when the above final transmission line-tree distance is greater than or equal to the corresponding above preset safety distance, determining not to generate the above warning message.

[0077] Specifically, the above-mentioned preset safety distance is determined based on the safety distance between trees and wires under different voltage registrations recorded in the national standard. Combined with the accurate calculation of the distance between the above-mentioned trees and wires, a highly accurate tree obstacle warning is achieved.

[0078] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the tree barrier warning method for the transmission line corridor of the present application will be described in detail below in combination with specific embodiments.

[0079] This embodiment relates to a specific tree barrier early warning method for transmission line corridors, such as Figure 2 As shown, including:

[0080] Acquire point cloud data of the transmission line corridor to obtain initial point cloud data;

[0081] And preprocessing the initial point cloud data to obtain target point cloud data, the preprocessing at least includes filtering processing;

[0082] The target point cloud data is processed by using the entropy weight method to separate the power line point cloud and the landform feature point cloud in the target point cloud data, and the power line point cloud data and the landform feature point cloud data are obtained;

[0083] According to the power line point cloud data and the topographic feature point cloud data, the distance between the power line and the tree is obtained;

[0084] At least based on the distance between the transmission line and the tree and the corresponding preset safety distance, it is determined whether to generate an early warning message, the early warning message is used to prompt that there is a fire risk in the current transmission line, and the distance between the transmission line and the tree is the shortest distance between the transmission line and the tree.

[0085] By acquiring the point cloud data of the transmission line corridor, the initial point cloud data is obtained, and the initial point cloud data is preprocessed to obtain the target point cloud data; the target point cloud data is processed by the entropy weight method to separate the power line point cloud and the landform feature point cloud in the target point cloud data, and the power line point cloud data and the landform feature point cloud data are obtained; according to the power line point cloud data and the landform feature point cloud data, the distance between the transmission line and the tree is obtained, and whether to generate warning information is determined at least according to the distance between the transmission line and the tree and the corresponding preset safety distance. The calculation accuracy of the distance between the transmission line and the tree is improved, that is, the problem that the existing solution does not refine and classify the point cloud data in the processing of the point cloud data of the transmission line corridor, resulting in poor accuracy of the final judgment result is solved.

[0086] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0087] The embodiment of the present application also provides a tree barrier warning device for a transmission line corridor. It should be noted that the tree barrier warning device for a transmission line corridor of the embodiment of the present application can be used to execute the tree barrier warning method for a transmission line corridor provided by the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and those that have been explained will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0088] The following is an introduction to the tree barrier warning device for the transmission line corridor provided in the embodiment of the present application.

[0089] Figure 3 It is a structural block diagram of a tree barrier warning device for a transmission line corridor provided according to an embodiment of the present application.

[0090] like Figure 3 As shown, the device comprises:

[0091] An acquisition unit 31 is used to acquire point cloud data of the transmission line corridor to obtain initial point cloud data, and pre-process the initial point cloud data to obtain target point cloud data, wherein the pre-processing at least includes filtering processing;

[0092] The first processing unit 32 is used to process the target point cloud data by using an entropy weight method to separate the power line point cloud and the landform feature point cloud in the target point cloud data to obtain the power line point cloud data and the landform feature point cloud data;

[0093] The second processing unit 33 is used to obtain the transmission line-tree distance based on the power line point cloud data and the topographic feature point cloud data, and determine whether to generate warning information at least based on the size of the above-mentioned transmission line-tree distance and the corresponding preset safety distance. The above-mentioned warning information is used to prompt that there is a fire risk in the current transmission line. The above-mentioned transmission line-tree distance is the shortest distance between the above-mentioned transmission line and the tree.

[0094] In the above device, the initial point cloud data is obtained by acquiring the point cloud data of the transmission line corridor, and the initial point cloud data is preprocessed to obtain the target point cloud data; the target point cloud data is processed by using the entropy weight method to separate the power line point cloud and the landform feature point cloud in the target point cloud data, and the power line point cloud data and the landform feature point cloud data are obtained; the distance between the transmission line and the tree is obtained according to the power line point cloud data and the landform feature point cloud data, and whether to generate warning information is determined at least according to the distance between the transmission line and the tree and the corresponding preset safety distance. The calculation accuracy of the distance between the transmission line and the tree is improved, that is, the problem that the existing solution does not refine and classify the point cloud data in the processing of the point cloud data of the transmission line corridor, thereby solving the problem that the accuracy of the final judgment result is poor.

[0095] In one embodiment of the present application, the device further includes a correction unit, which is used to determine whether to generate warning information in the process of at least determining the distance between the transmission line and the tree and the corresponding preset safety distance: 2 g 2 E / 24σ 2 )=σ m -(L1 2 g m 2 E / 24σ m 2 )-αE(tt m -t c ), the distance between the transmission line and the tree is corrected to obtain the final distance between the transmission line and the tree; where σ is the stress of the transmission line when the load is g and the temperature is t, σ m The specific load is gm And the temperature is t m The stress of the transmission line at t, α is the expansion temperature coefficient of the transmission line, E is the elastic module of the transmission line, L1 is the span of the transmission line, and g is the acceleration of gravity; t c is the temperature change caused by the current carried in the above transmission line.

[0096] In one embodiment of the present application, the second processing unit includes a first determination module and a second determination module. The first determination module is used to determine whether to generate the above-mentioned warning information when the above-mentioned final transmission line-to-tree distance is less than the corresponding above-mentioned preset safety distance; the second determination module is used to determine whether to generate the above-mentioned warning information when the above-mentioned final transmission line-to-tree distance is greater than or equal to the corresponding above-mentioned preset safety distance.

[0097] In one embodiment of the present application, the acquisition unit includes a segmentation module, a classification module and a filtering module. The segmentation module is used to segment the above-mentioned initial point cloud data according to the segmentation result of the transmission line corridor to obtain multiple segments of intermediate point cloud data; the classification module is used to classify the above-mentioned intermediate point cloud data to obtain a first type of point cloud data and a second type of point cloud data, and the risk level of the above-mentioned first type of point cloud data representing the topography causing safety hazards to the transmission line is greater than the risk level of the above-mentioned second type of point cloud data representing the topography causing safety hazards to the transmission line; the filtering module is used to filter the above-mentioned first type of point cloud data using a radius filtering method, and filter the above-mentioned second type of point cloud data using a statistical filtering method and a thinning preprocessing method to obtain the above-mentioned target point cloud data.

[0098] In one embodiment of the present application, the first processing unit includes a construction module, a processing module, a third determination module and a fourth determination module. The construction module is used to construct a covariance matrix and determine the height eigenvalue and the covariance eigenvalue according to the above-mentioned target point cloud data, and the above-mentioned covariance eigenvalue includes the vertical angle, linearity, surface change value and curvature; the processing module is used to normalize the above-mentioned height eigenvalue and the above-mentioned covariance eigenvalue to obtain a feature evaluation matrix; the third determination module is used to determine the entropy weight of each feature according to the above-mentioned feature evaluation matrix; the fourth determination module is used to determine the above-mentioned power line point cloud data using the above-mentioned height feature with an entropy weight of 1.

[0099] In one embodiment of the present application, the first processing unit includes a fifth determining module, the fifth determining module is used to determine the and Determine the above entropy weights of each of the above features; where P ij is the weight of the feature evaluation of the i-th point in the j-th feature, e ij is the feature evaluation of the i-th point on the j-th feature, S jis the weight of the jth feature; m is the total number of points, and n is the total number of features.

[0100] In one embodiment of the present application, the acquisition unit includes a sixth determination module, which is used to determine the coordinates of each point cloud in the initial point cloud data as follows: Among them, x i is the 3D physical space coordinate of the point cloud, X i is the phase center coordinate of the airborne GPS receiver, is the rotation matrix, ω i ,φ i and are the azimuth, pitch and roll angles of the inertial navigation unit, h i is the distance vector.

[0101] The tree obstacle warning device for the transmission line corridor includes a processor and a memory. The acquisition unit, the first processing unit, the second processing unit, etc. are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0102] The processor includes a kernel, and the kernel retrieves the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters are adjusted to solve the problem that the existing solution does not classify the point cloud data in detail when processing the point cloud data of the transmission line corridor, resulting in poor accuracy of the final determination result.

[0103] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0104] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the tree barrier warning method for the transmission line corridor.

[0105] Specifically, tree barrier warning methods for transmission line corridors include:

[0106] Step S101, acquiring point cloud data of the transmission line corridor to obtain initial point cloud data, and preprocessing the initial point cloud data to obtain target point cloud data, wherein the preprocessing at least includes filtering processing;

[0107] Specifically, the initial point cloud data can be obtained through the airborne laser radar measurement system. In recent years, with the continuous development of laser radar and drone technology, the airborne laser radar measurement system, as an emerging earth observation technology, has been widely used in power and surveying and mapping. Its advantages are that the dense dot matrix data can fully describe the structural information of the object; in the natural environment, the multiple echo performance of the laser can fully capture the detailed information of the measured area; the high-precision ranging of the laser radar ensures the quality of the data; the multiple flights and coordinated operation of the airborne laser radar improve the efficiency of data acquisition.

[0108] Step S102, using an entropy weight method to process the target point cloud data to separate the power line point cloud and the landform feature point cloud in the target point cloud data to obtain the power line point cloud data and the landform feature point cloud data;

[0109] Specifically, processing the above-mentioned target point cloud data refers to extracting power line point clouds from the power corridor point cloud data for realizing the reconstruction of the power line three-dimensional model; the present invention analyzes the geometric distribution characteristics of the power line point clouds, introduces the entropy weight method to quantify the feature weight ratio, and proposes a power line extraction algorithm based on the entropy weight method feature evaluation to achieve high-precision power line extraction.

[0110] Step S103, obtaining the transmission line-tree distance based on the power line point cloud data and the topographic feature point cloud data, and determining whether to generate warning information at least based on the size of the above transmission line-tree distance and the corresponding preset safety distance. The above warning information is used to prompt that there is a fire risk in the current transmission line. The above transmission line-tree distance is the shortest distance between the above transmission line and the tree.

[0111] Specifically, the point cloud data is used to collect the instantaneous distance between the transmission line and the trees. However, the transmission line is often affected by meteorological factors, which causes the shape and sag of the transmission line to change, and then causes the distance from the trees to change. That is to say, under normal weather conditions, it is possible that trees will not form tree barriers that affect the transmission line corridor, but under certain extreme weather conditions, tree barriers may form in the transmission line corridor, thus affecting the safety of power transmission. This step calculates the distance between the transmission line and the trees under the influence of weather, and then finds possible tree barrier risk points, thereby improving the scientificity and accuracy of the early warning.

[0112] Optionally, in the process of determining whether to generate warning information based at least on the distance between the transmission line and the tree and the corresponding preset safety distance, the method further includes:

[0113] According to σ-(L1 2 g 2 E / 24σ 2 )=σ m -(L1 2 gm 2 E / 24σ m 2 )-αE(tt m -t c ), the transmission line-tree distance is corrected to obtain the final transmission line-tree distance; wherein, σ is the stress of the transmission line when the specific load is g and the temperature is t, σm is the stress of the transmission line when the specific load is gm and the temperature is tm, α is the expansion temperature coefficient of the transmission line, E is the elastic module of the transmission line, L1 is the span of the transmission line, g is the acceleration of gravity; tc is the temperature change caused by the current in the transmission line.

[0114] Optionally, whether to generate warning information is determined at least based on the size of the above-mentioned transmission line-tree distance and the corresponding preset safety distance, including: when the above-mentioned final transmission line-tree distance is smaller than the corresponding above-mentioned preset safety distance, determining to generate the above-mentioned warning information; when the above-mentioned final transmission line-tree distance is greater than or equal to the corresponding above-mentioned preset safety distance, determining not to generate the above-mentioned warning information.

[0115] Optionally, the above-mentioned initial point cloud data are preprocessed to obtain target point cloud data, including: segmenting the above-mentioned initial point cloud data according to the segmentation result of the transmission line corridor to obtain multiple segments of intermediate point cloud data; classifying the above-mentioned intermediate point cloud data to obtain first-category point cloud data and second-category point cloud data, the risk level of the above-mentioned first-category point cloud data representing the landform causing safety hazards to the transmission line is greater than the risk level of the above-mentioned second-category point cloud data representing the landform causing safety hazards to the transmission line; using a radius filtering method to filter the above-mentioned first-category point cloud data, and using a statistical filtering method and a thinning preprocessing method to filter the above-mentioned second-category point cloud data to obtain the above-mentioned target point cloud data.

[0116] Optionally, the target point cloud data is processed using an entropy weight method to separate the power line point cloud and the topographic feature point cloud in the target point cloud data to obtain the power line point cloud data, including: constructing a covariance matrix and determining the height eigenvalue and the covariance eigenvalue based on the target point cloud data, wherein the covariance eigenvalue includes the vertical angle, linearity, surface change value and curvature; normalizing the height eigenvalue and the covariance eigenvalue to obtain a feature evaluation matrix; determining the entropy weight of each feature based on the feature evaluation matrix; and determining the power line point cloud data using the height feature with an entropy weight of 1.

[0117] Optionally, according to the feature evaluation matrix, the entropy weight of each feature is determined, including:

[0118] according to and Determine the above entropy weight of each of the above features;

[0119] Among them, P ij is the weight of the feature evaluation of the i-th point in the j-th feature, e ij is the feature evaluation of the i-th point on the j-th feature, S j is the weight of the jth feature; m is the total number of points, and n is the total number of features.

[0120] Optionally, acquiring point cloud data of the transmission line corridor to obtain initial point cloud data includes: determining the coordinates of each point cloud in the initial point cloud data as: Among them, x i is the 3D physical space coordinate of the point cloud, X i is the phase center coordinate of the airborne GPS receiver, is the rotation matrix, ω i ,φ i and are the azimuth, pitch and roll angles of the inertial navigation unit, h i is the distance vector.

[0121] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the tree barrier early warning method for the transmission line corridor is executed when the program is run.

[0122] The embodiment of the present invention provides a device, the device includes a processor, a memory and a program stored in the memory and can be run on the processor, and the processor implements at least the following steps when executing the program: acquiring point cloud data of the transmission line corridor to obtain initial point cloud data, and preprocessing the initial point cloud data to obtain target point cloud data, wherein the preprocessing at least includes filtering processing; using the entropy weight method to process the target point cloud data to separate the power line point cloud and the landform feature point cloud in the target point cloud data to obtain power line point cloud data and landform feature point cloud data; according to the power line point cloud data and the landform feature point cloud data, obtaining the transmission line tree distance, at least according to the size of the transmission line tree distance and the corresponding preset safety distance, determining whether to generate warning information, the warning information is used to prompt that the current transmission line has a fire risk, and the transmission line tree distance is the shortest distance between the transmission line and the tree. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0123] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes at least the following method steps: acquiring point cloud data of a transmission line corridor to obtain initial point cloud data, and preprocessing the initial point cloud data to obtain target point cloud data, wherein the preprocessing at least includes filtering processing; processing the target point cloud data using an entropy weight method to separate the power line point cloud and the landform feature point cloud in the target point cloud data to obtain power line point cloud data and landform feature point cloud data; obtaining the transmission line-tree distance based on the power line point cloud data and the landform feature point cloud data, and determining whether to generate warning information based at least on the transmission line-tree distance and the corresponding preset safety distance, wherein the warning information is used to prompt that the current transmission line has a fire risk, and the transmission line-tree distance is the shortest distance between the transmission line and the tree.

[0124] The present application also provides a tree barrier warning system for a transmission line corridor, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the above-mentioned tree barrier warning methods for the transmission line corridor.

[0125] By acquiring the point cloud data of the transmission line corridor, the initial point cloud data is obtained, and the initial point cloud data is preprocessed to obtain the target point cloud data; the target point cloud data is processed by the entropy weight method to separate the power line point cloud and the landform feature point cloud in the target point cloud data, and the power line point cloud data and the landform feature point cloud data are obtained; according to the power line point cloud data and the landform feature point cloud data, the distance between the transmission line and the tree is obtained, and whether to generate warning information is determined at least according to the distance between the transmission line and the tree and the corresponding preset safety distance. The calculation accuracy of the distance between the transmission line and the tree is improved, that is, the problem that the existing solution does not refine and classify the point cloud data in the processing of the point cloud data of the transmission line corridor, resulting in poor accuracy of the final judgment result is solved.

[0126] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0127] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0128] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0129] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0130] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0131] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0132] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0133] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0134] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0135] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0136] 1) The tree obstacle warning method for the transmission line corridor of the present application obtains the point cloud data of the transmission line corridor to obtain the initial point cloud data, and pre-processes the initial point cloud data to obtain the target point cloud data; the target point cloud data is processed by the entropy weight method to separate the power line point cloud and the landform feature point cloud in the target point cloud data to obtain the power line point cloud data and the landform feature point cloud data; the distance between the transmission line and the tree is obtained according to the power line point cloud data and the landform feature point cloud data, and whether to generate warning information is determined at least according to the size of the transmission line tree distance and the corresponding preset safety distance. The calculation accuracy of the distance between the transmission line and the tree is improved, that is, the problem that the existing solution does not refine and classify the point cloud data in the processing of the point cloud data of the transmission line corridor, thereby solving the problem that the accuracy of the final judgment result is poor.

[0137] 2) The tree obstacle warning device for the transmission line corridor of the present application obtains the point cloud data of the transmission line corridor to obtain the initial point cloud data, and pre-processes the initial point cloud data to obtain the target point cloud data; the target point cloud data is processed by the entropy weight method to separate the power line point cloud and the landform feature point cloud in the target point cloud data to obtain the power line point cloud data and the landform feature point cloud data; the distance between the transmission line and the tree is obtained according to the power line point cloud data and the landform feature point cloud data, and whether to generate warning information is determined at least according to the size of the transmission line tree distance and the corresponding preset safety distance. The calculation accuracy of the distance between the transmission line and the tree is improved, that is, the problem that the existing solution does not perform detailed classification of the point cloud data in the processing of the point cloud data of the transmission line corridor, thereby solving the problem that the accuracy of the final judgment result is poor.

[0138] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A tree barrier early warning method for transmission line corridors, It is characterized in that include: Acquire point cloud data of the transmission line corridor to obtain initial point cloud data, and pre-process the initial point cloud data to obtain target point cloud data, wherein the pre-processing includes at least filtering processing; The target point cloud data is processed by using an entropy weight method to separate the power line point cloud and the landform feature point cloud in the target point cloud data to obtain the power line point cloud data and the landform feature point cloud data; The transmission line-tree distance is obtained based on the power line point cloud data and the topographic feature point cloud data. Whether to generate early warning information is determined at least based on the size of the transmission line-tree distance and the corresponding preset safety distance. The early warning information is used to prompt that there is a fire risk in the current transmission line. The transmission line-tree distance is the shortest distance between the transmission line and the tree.

2. The method according to claim 1, It is characterized in that In the process of determining whether to generate warning information at least based on the distance between the transmission line and the tree and the corresponding preset safety distance, the method further includes: According to σ-(L 1 2 g 2 E / 24σ 2 )=σ m -(L 1 2 g m 2 E / 24σ m 2 )-αE(tt m -t c ), correcting the transmission line-tree distance to obtain a final transmission line-tree distance; Where, σ is the stress of the transmission line when the load is g and the temperature is t, σ m The specific load is g m And the temperature is t m The stress of the transmission line at , α is the expansion temperature coefficient of the transmission line, E is the elastic module of the transmission line, L 1 is the span of the transmission line, g is the acceleration due to gravity; t c is the temperature change caused by the current carried in the transmission line.

3. The method according to claim 2, It is characterized in that At least according to the distance between the transmission line and the tree and the corresponding preset safety distance, determining whether to generate warning information includes: In the case where the final transmission line tree distance is less than the corresponding preset safety distance, determining to generate the warning information; In a case where the final transmission line-tree distance is greater than or equal to the corresponding preset safety distance, it is determined not to generate the warning information.

4. The method according to claim 1, It is characterized in that Preprocessing the initial point cloud data to obtain target point cloud data includes: Segmenting the initial point cloud data according to the segmentation result of the transmission line corridor to obtain multiple segments of intermediate point cloud data; Classifying the intermediate point cloud data to obtain first-category point cloud data and second-category point cloud data, wherein the first-category point cloud data represents a risk level of a potential safety hazard to the transmission line in the landform that is represented by the landform, which is greater than the risk level of a potential safety hazard to the transmission line in the landform represented by the second-category point cloud data; The first type of point cloud data is filtered by using a radius filtering method, and the second type of point cloud data is filtered by using a statistical filtering method and a thinning preprocessing method to obtain the target point cloud data.

5. The method according to claim 1, It is characterized in that The target point cloud data is processed by using an entropy weight method to separate the power line point cloud and the landform feature point cloud in the target point cloud data to obtain the power line point cloud data, including: According to the target point cloud data, a covariance matrix is ​​constructed and a height eigenvalue and a covariance eigenvalue are determined, wherein the covariance eigenvalue includes a vertical angle, a linearity, a surface change value, and a curvature; Normalizing the height eigenvalue and the covariance eigenvalue to obtain a feature evaluation matrix; Determining the entropy weight of each feature according to the feature evaluation matrix; The height-to-ground feature whose entropy weight is 1 is used to determine the power line point cloud data.

6. The method according to claim 5, It is characterized in that According to the feature evaluation matrix, the entropy weight of each feature is determined, including: according to and Determining the entropy weight of each of the features; Among them, P ij is the weight of the feature evaluation of the i-th point in the j-th feature, e ij is the feature evaluation of the i-th point on the j-th feature, S j is the weight of the jth feature; m is the total number of points, and n is the total number of features.

7. The method according to any one of claims 1 to 6, It is characterized in that Obtain the point cloud data of the transmission line corridor and obtain the initial point cloud data, including: Determine the coordinates of each point cloud in the initial point cloud data as: Among them, x i is the 3D physical space coordinate of the point cloud, X i is the phase center coordinate of the airborne GPS receiver, is the rotation matrix, ω i ,φ i and are the azimuth, pitch and roll angles of the inertial navigation unit, h i is the distance vector.

8. A tree barrier warning device for transmission line corridors, It is characterized in that include: An acquisition unit, used to acquire point cloud data of the transmission line corridor, obtain initial point cloud data, and pre-process the initial point cloud data to obtain target point cloud data, wherein the pre-processing at least includes filtering processing; A first processing unit is used to process the target point cloud data by using an entropy weight method to separate the power line point cloud and the landform feature point cloud in the target point cloud data to obtain the power line point cloud data and the landform feature point cloud data; The second processing unit is used to obtain the transmission line-tree distance based on the power line point cloud data and the topographic feature point cloud data, and determine whether to generate warning information at least based on the size of the transmission line-tree distance and the corresponding preset safety distance, wherein the warning information is used to prompt that there is a fire risk in the current transmission line, and the transmission line-tree distance is the shortest distance between the transmission line and the tree.

9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the tree obstacle warning method for the transmission line corridor as described in any one of claims 1 to 7.

10. A tree barrier warning system for transmission line corridors, It is characterized in that include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing a tree obstacle warning method for a transmission line corridor as described in any one of claims 1 to 7.

Citation Information

Patent Citations

  • Method for predicting tree barrier threat by using point cloud data in transmission line channel

    CN109390873A

  • Tree barrier hidden danger identification method in power transmission line corridor area

    CN111929698A

  • Tree obstacle early warning method and early warning system for power grid transmission line

    CN112466104A

  • Point cloud single-tree segmentation method and apparatus, device and computer-readable medium

    WO2021232467A1