A power distribution line pole extraction method and system based on laser point cloud

Abstract

The application discloses a power distribution line pole extraction method and system based on laser point cloud, and the method comprises the following steps: acquiring laser point cloud data of a straight power distribution line and performing pretreatment to obtain pretreated power distribution line laser point cloud data; performing space conversion on the pretreated power distribution line laser point cloud data to obtain power distribution line laser point cloud data parallel to the x-axis; obtaining conductor representative coordinates in a partition of the power distribution line laser point cloud data parallel to the x-axis, and combining maximum value and maximum constraint to obtain power distribution line pole coordinates. The application can effectively extract the power distribution pole tower from the laser point cloud data.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of line inspection, and relates to a power distribution line pole extraction method and system based on laser point clouds. BACKGROUND

[0002] Line inspection is a key work of power grid operation and maintenance, and a large amount of manpower and material resources need to be invested. The transmission line is high, and the poles can be roughly extracted through the different spatial features of the ground points, wire points and tower points, and then further extracted. The channel of the distribution line is very complex, and the poles are relatively low, so that the pole, wire, tree and ground point cloud are mixed together, unlike the transmission tower which is much larger than the trees and other objects in the channel, so the method for extracting the transmission tower from the laser point cloud data is no longer applicable to extracting the distribution tower. SUMMARY

[0003] To solve the problems in the prior art, the application provides a power distribution line pole extraction method and system based on laser point clouds, which selects representative points to form wire coordinates from the spatial features of the wire and tower of the power distribution line, determines the position of the power distribution line pole in combination with maximum value and maximum value constraints, and finally obtains the three-dimensional coordinates of the power distribution line pole.

[0004] The application adopts the following technical solutions.

[0005] The application provides a power distribution line pole extraction method based on laser point clouds, which comprises the following steps:

[0006] Step 1: obtaining laser point cloud data of a straight-line power distribution line and pre-processing to obtain pre-processed power distribution line laser point cloud data;

[0007] Step 2: performing spatial conversion on the pre-processed power distribution line laser point cloud data to obtain power distribution line laser point cloud data parallel to the x-axis;

[0008] Step 3: obtaining wire representative coordinates from the power distribution line laser point cloud data parallel to the x-axis, and obtaining power distribution line pole coordinates in combination with maximum value and maximum value constraints.

[0009] Preferably, the pre-processing in step 1 comprises:

[0010] Extracting x, y and z coordinates of the laser point cloud data of the straight-line power distribution line, and the coordinate unit is meter;

[0011] Rounding the extracted x, y and z coordinates to two decimal places, and removing the data with the same x, y and z coordinates;

[0012] The laser point cloud data whose z coordinate is between the upper and lower limits of the elevation threshold is filtered out, wherein the upper and lower limits of the elevation threshold are set according to the average ground elevation and the height of the power line pole, so as to filter out the ground point cloud and the noise points in the air.

[0013] Preferably, the spatial conversion of the preprocessed power line laser point cloud data in step 2 comprises:

[0014] The preprocessed power line laser point cloud data is projected onto the x-o-y two-dimensional plane and fitted to obtain a plane first equation of the power line, and the included angle θ between the power line and the x axis is obtained according to the plane first equation.

[0015] The preprocessed power line laser point cloud data is rotated by an angle θ clockwise in the plane range, so that the strike of the power line is parallel to the x axis, and laser point cloud data parallel to the x axis is obtained.

[0016] Preferably, the step 3 comprises:

[0017] Step 3.1, the power line laser point cloud data parallel to the x axis is sorted according to the x axis coordinates from small to large, and the sorted laser point cloud data is obtained;

[0018] Step 3.2, the minimum x axis coordinate in the laser point cloud data is marked as x_min, and the maximum x axis coordinate is marked as x_max;

[0019] Step 3.3, setting a variable x_state and initializing it to x_min;

[0020] Step 3.4, filtering out the laser point cloud data whose x coordinate is between x_state and x_state + step from the sorted laser point cloud data, and marking it as data, wherein step is the filtering step;

[0021] Step 3.5, for data, interval division is carried out in the x axis direction, and data variance is analyzed to obtain the traverse and vertical coordinates of the representative traverse, and the traverse and vertical coordinate values are recorded in the list x_list and z_list;

[0022] Step 3.6, based on the maximum value and maximum value constraint analysis list z_list, x_list, the x axis position of the power line pole is obtained;

[0023] Step 3.7, according to the x axis position of the power line pole, taking a meters before and after the x axis position, the laser point cloud data within the range of 2a meters is the three-dimensional coordinates of the power line pole, wherein a is the x axis position value parameter;

[0024] Step 3.8, rotate the three-dimensional coordinates of the power distribution line pole counterclockwise by an angle θ to restore the three-dimensional coordinates of the power distribution line pole in the original coordinate system, wherein θ is the included angle between the power distribution line and the x-axis;

[0025] Step 3.9, update x_state to x_state + step / 2, and determine whether x_state is greater than x_max. If yes, terminate the program, otherwise go to step 3.4.

[0026] Preferably, step 3.5 includes:

[0027] Step 3.5.1, setting lists x_list and z_list respectively used to record the representative horizontal and vertical coordinate values of the wire, and initializing them as empty lists;

[0028] Step 3.5.2, dividing the interval with a length of 2a meters and an overlap length of a meters in the x-axis direction starting from x_state for data;

[0029] Step 3.5.3, for each interval, further dividing it into b small intervals, and going to step 3.5.4; if the length of the power distribution line in the x direction in the interval is less than 2a meters, do not further divide it into small intervals, and directly skip the interval, wherein b is the number of small interval divisions;

[0030] Step 3.5.4, for each interval, obtaining the laser point cloud data point with the maximum z coordinate value in each small interval, obtaining a total of b laser point cloud data points with the maximum z coordinate value, and calculating the variance of the z coordinate values of the b laser point cloud data points with the maximum z coordinate value:

[0031] If the variance is less than c, calculating the average of the z coordinate values of the b laser point cloud data points with the maximum z coordinate value and adding it to z_list as the representative z coordinate value of the wire, and calculating the average of the x coordinate values of the b laser point cloud data points with the maximum z coordinate value and adding it to x_list as the representative x coordinate value of the wire;

[0032] If the variance is greater than or equal to c, the interval and its small intervals are not considered, wherein c is the variance threshold.

[0033] Preferably, the value of step is in the range of 150-250, the value of a is in the range of 0.4-0.6, the value of b is in the range of 8-15, and the value of c is in the range of 0.1-1.

[0034] Preferably, step 3.6 analyzes the lists x_list and z_list based on the maximum value and maximum value constraint to obtain the x-axis position of the power distribution line pole, including:

[0035] Step 3.6.1, remove the points in z_list and the corresponding points in x_list which are out of the discrete limit range according to the variance of the elements in z_list, and set the list xg_list for recording the x-axis position of the power line pole and initialize it as an empty list;

[0036] Step 3.6.2, traverse all elements of z_list, for the i-th element point, take the maximum value of 0 and i-d, denoted as left, and take the minimum value of len(z_list) and i+d, denoted as right, where len(z_list) represents the number of elements of z_list, and d is a traversal parameter;

[0037] If the i-th element point satisfies the maximum value and maximum value constraint, the value x i is added to xg_list as the x-axis position of the power line pole, and the maximum value and maximum value constraint is:

[0038] z i > z i-1 and z i > z i+1 , z i is the maximum value of z_list from left to right.

[0039] In the formula, z i-1 , z i+1 are the values of the points adjacent to the left and right of the maximum value z i from left to right in z_list.

[0040] Preferably, the value range of d is 15-30.

[0041] The second aspect of the application provides a power line pole extraction system based on laser point cloud, comprising:

[0042] A data acquisition module is configured to acquire laser point cloud data of a straight power line and perform preprocessing to obtain preprocessed power line laser point cloud data.

[0043] A space conversion module is configured to perform space conversion on the preprocessed power line laser point cloud data to obtain power line laser point cloud data parallel to the x-axis.

[0044] A coordinate extraction module is configured to obtain conductor representative coordinates by partitioning the power line laser point cloud data parallel to the x-axis, and obtain power line pole coordinates by combining the maximum value and maximum value constraint.

[0045] The third aspect of the present application provides a terminal, comprising a processor and a storage medium; the storage medium is used for storing instructions; the processor is used for operating according to the instructions to execute the steps of the method.

[0046] The fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the steps of the method.

[0047] Compared with the prior art, the present application has at least the following beneficial effects:

[0048] The present application takes into account the difference between distribution lines and transmission lines. The distribution lines may have trees higher than the conductors, so the highest point is not necessarily the conductor. By calculating and analyzing local variance, overall variance, and maximum value, the maximum value, etc. represented by coordinates, the false detection of towers caused by noise points such as trees with a high tip is excluded. The present application is suitable for positioning the tower position from complex distribution line point clouds, has a high fault tolerance, and solves the problem that the current technology for extracting transmission towers from transmission line point clouds is completely unsuitable for distribution lines. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 The present application is a method flowchart;

[0050] Figure 2 The present application is a two-dimensional projection of a distribution line;

[0051] Figure 3 The present application is a representative conductor and extreme point position;

[0052] Figure 4 The present application is a three-dimensional diagram of a distribution line pole. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. The embodiments described in the present application are only a part of the embodiments of the present application, not all embodiments. Based on the spirit of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0054] Embodiment 1 of the present application provides a distribution line pole extraction method based on laser point cloud, as shown in Figure 1 , comprising:

[0055] Step 1, obtain the laser point cloud data of a straight distribution line and pre-process it to obtain the pre-processed distribution line laser point cloud data;

[0056] Further preferably, the unmanned aerial vehicle is used to collect laser point cloud data of the straight section of the power distribution line, the data format is las, and when a corner tower with a corner greater than a threshold value is encountered, the data is re-archived. In practice, only an approximate straight section is required, and the power distribution line between adjacent towers is definitely straight, and the corner of the corner tower is generally not more than 10°. When a corner tower with a particularly large corner (greater than a set threshold value) is encountered during collection, the current data can be archived, and a new data collection record can be started.

[0057] The obtained power distribution line laser point cloud data is preprocessed to obtain preprocessed power distribution line laser point cloud data, including:

[0058] (1) The x, y, and z coordinates of the laser point cloud data are extracted using the laspy library of the python language, and the coordinate unit is meters;

[0059] (2) According to the results of (1), the x, y, and z coordinates are rounded to two decimal places, i.e., each coordinate is accurate to the centimeter level, and then the data with the same x, y, and z coordinates is de-duplicated;

[0060] (3) According to the results of (2), a height threshold is set, and laser point cloud data with z coordinates in a reasonable interval is filtered out. Taking A city as an example, the average elevation of A city is 7 meters (laser point cloud data takes sea level as the starting point of elevation, and the starting point of the power distribution pole can be considered as the average elevation of A city), and the height of the power distribution pole is generally 8-15 meters. Therefore, the lower limit of the height threshold is set to 10 meters, and the upper limit of the height threshold is set to 30 meters, which can filter out most of the ground point cloud and noise points in the air.

[0061] Step 2, spatial conversion is performed on the preprocessed power distribution line laser point cloud data to obtain power distribution line laser point cloud data parallel to the x-axis;

[0062] Further preferably, the preprocessed power distribution line laser point cloud data obtained in step 1 is spatially converted to obtain power distribution line laser point cloud data parallel to the x-axis, including:

[0063] Step 2.1, according to the results of step 1, the laser point cloud data is projected onto the x-o-y plane;

[0064] Step 2.2, using the RANSACRegressor function of the python language, the projection results of step 2.1 are fitted to obtain a plane first equation of the power distribution line, and the angle θ between the power distribution line and the x-axis is obtained according to the plane first equation; wherein the plane first equation is a one-dimensional first equation of the point cloud data in the x-o-y plane, and the angle θ is the counterclockwise angle between the equation and the x-axis.

[0065] Step 2.3, rotate the laser point cloud data obtained in step 1 clockwise by an angle θ in the plane range, so that the power line direction is parallel to the x-axis, to obtain laser point cloud data parallel to the x-axis. Along the x-axis direction, its projection in the y-o-z plane is shown in FIG. 2b. Figure 2 .

[0066] Step 3, obtain the conductor representative coordinates of the power line laser point cloud data parallel to the x-axis, and obtain the power pole coordinates by combining the maximum value and maximum value constraints.

[0067] Further preferably, based on the spatial features of the power pole and the conductor, the power pole coordinates are obtained from the laser point cloud data parallel to the x-axis obtained in step 2, including:

[0068] Step 3.1, since the laser point cloud data is disordered, the laser point cloud data obtained in step 2 is sorted by x-axis coordinates from small to large;

[0069] Step 3.2, the minimum x-axis coordinate is obtained by using the min function of the python language, denoted as x_min, and the maximum x-axis coordinate is obtained by using the max function of the python language, denoted as x_max;

[0070] Step 3.3, set the variable x_state to the initial value x_min;

[0071] Step 3.4, according to the result of step 3.1, filter out the laser point cloud data whose x coordinate is between x_state and x_state+ step, denoted as data, step can be taken as 150~250;

[0072] Step 3.5, according to the data obtained in step 3.4, segment the conductor representative coordinate value in the x-axis direction to obtain the conductor representative coordinates of the corresponding segment, including:

[0073] Step 3.5.1, set the variables x_list and z_list to empty lists, which are used to record the conductor representative coordinates;

[0074] Step 3.5.2, according to the data obtained in step 3.4, divide the interval by taking x_state as the starting point, the interval length of 2a meters, and the overlapping length of a meters, to obtain [x_state, x_state+2a], [x_state+a, x_state+3a], [x_state+2a, x_state+4a]…, the overlapping length is set to increase the fault tolerance rate and prevent local noise data such as tall trees from affecting the subsequent tower point cloud extraction, a can be taken as 0.4~0.6;

[0075] Step 3.5.3, according to the interval division result obtained in step 3.5.2, for each interval, continue to divide into b small intervals, each small interval length is a / b meters, for example, for the interval [x_state+i, x_state+i+2a], continue to divide into [x_state+i, x_state+i+a / b], [x_state+i+a / b, x_state+i+2a / b], …, [x_state+i+9a / b, x_state+i+2a] b small intervals, enter step 3.5.4; if the length of the distribution line in the x direction in the interval is less than 2a meters, do not further divide into small intervals, and directly skip the interval; wherein b can be 8-15;

[0076] Step 3.5.4, according to the b small intervals obtained in step 3.5.3, use the max function to obtain the laser point cloud data point with the maximum z coordinate value in each small interval, if the variance of the z coordinate values of the b laser point cloud data points is less than c, calculate the average value of the b z coordinate values and add it to z_list, and calculate the average value of the x coordinate values of the b laser point cloud data points and add it to x_list, if the variance of the z coordinate values of the b laser point cloud data points is greater than or equal to c, do not consider the b small intervals, because there are noise points such as trees with sharp tips, and c can be 0.1-1;

[0077] Actually, taking step=200 as an example, the length of the straight line segment line is not necessarily a multiple of 200, so every time 200 meters are extracted, the last part will not be 200 meters, according to the actual situation, the last part is merged into the last part of the data, or it is established as a separate part. For example, less than 100 meters is merged into the last part, and greater than or equal to 100 meters is established as a separate part. The value of step can also be selected according to the length of the straight line segment line in advance, so that the straight line segment line can be divided into equal segments, and there is no remaining part.

[0078] Step 3.6, based on the maximum value and maximum value constraint analysis list x_list, z_list, obtain the x-axis position of the distribution line pole;

[0079] Further preferably, according to the conductor representative coordinates obtained in step 3.5, the maximum position of the x-o-z plane projection curve is calculated (z i > z i-1 And z i > z i+1 ), judge to obtain the x-axis position of the distribution pole (the maximum position is not necessarily the tower position, and further judgment is required whether it is the tower position by z i is the maximum value of z_list from left to right interval), including:

[0080] Step 3.6.1: Calculate the variance of the elements in z_list, remove particularly discrete points in z_list and points at corresponding positions in x_list to avoid false detections, and set the variable xg_list with an initial value of an empty list to record the coordinates of the tower positions;

[0081] Step 3.6.2: Based on the coordinates of the wire obtained in step 3.5, including x_list and z_list, iterate through all elements of z_list. For the i-th point, take the larger value of 0 and id, denoted as left, and take the smaller value of len(z_list) and i + d, denoted as right. Here, len(z_list) represents the number of elements in z_list, and d can be 15~30.

[0082] If the i-th point satisfies: z i > z i-1 And z i > z i+1 , z i If x is the maximum value in the interval from left to right of z_list, then x i Add it to xg_list because the conductor will produce sag, and the tower location must be a maximum point of the z-coordinate curve. Since there may be noise points in local locations, such as protruding trees, condition two must be met: the extreme point must be the highest point within d / 2 meters before and after it in the x-direction, where z... i-1 z i+1 The maximum value z in the interval from left to right of z_list. i Values ​​of adjacent points on the left and right; see the final tower location. Figure 3 .

[0083] Step 3.7: Based on the x-axis position of the power distribution pole obtained in Step 3.6, take 'a' meters before and after the x-axis position. The laser point cloud data within this 2'a' meter range is the three-dimensional coordinate of the power distribution pole; the three-dimensional coordinate of a single tower is shown in [link to relevant documentation]. Figure 4 .

[0084] Step 3.8: Based on the three-dimensional coordinates of the power distribution pole obtained in Step 3.7, rotate counterclockwise by an angle θ to restore the three-dimensional coordinates of the power distribution pole in the original coordinate system;

[0085] Step 3.9: Update x_state to x_state + step / 2, and check if x_state is greater than x_max. If it is, terminate the program; otherwise, proceed to step 3.4.

[0086] Embodiment 2 of the present invention provides a power distribution line pole extraction system based on laser point cloud, comprising:

[0087] The data acquisition module is used for acquiring laser point cloud data of the linear distribution line and pre-processing to obtain pre-processed distribution line laser point cloud data.

[0088] The space conversion module is used for performing space conversion on the pre-processed distribution line laser point cloud data to obtain distribution line laser point cloud data parallel to the x-axis.

[0089] The coordinate extraction module is used for acquiring wire representative coordinates in each partition of the distribution line laser point cloud data parallel to the x-axis, and obtaining distribution line pole coordinates by combining maximum value and maximum value constraints.

[0090] Embodiment 3 of the present application provides a terminal, comprising a processor and a storage medium;The storage medium is used for storing instructions;The processor is used for operating according to the instructions to execute the steps of the method.

[0091] Embodiment 4 of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the steps of the method.

[0092] Compared with the prior art, the beneficial effects of the present application at least include:

[0093] The present application considers the difference between distribution line and transmission line, and the distribution line may have trees higher than the wire, so the highest point is not necessarily the wire. By coordinate representative value calculation, analysis of local variance, overall variance and maximum value, maximum value and other parameters, the false detection of tower caused by noise points such as trees with high peaks is excluded. The channel trees are the biggest obstacle to extract the tower position, which is suitable for positioning the tower position from the complex distribution line point cloud, has high fault tolerance, and solves the problem that the current technology of extracting transmission tower from transmission line point cloud is completely not suitable for distribution line.

[0094] The present disclosure can be a system, a method and / or a computer program product. The computer program product can include a computer readable storage medium having computer readable program instructions stored therein, which are used to enable a processor to implement various aspects of the present disclosure.

[0095] Computer readable storage media can be tangible storage media which can retain and store instructions for use by an instruction execution device. Computer readable storage media can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer readable storage media include the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

[0096] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0097] Computer readable program instructions for carrying out operations of the present disclosure can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages such as the "C" programming language or similar programming languages. The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate array (FPGA), or programmable logic array (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0098] Finally, it should be noted that the above-mentioned embodiments are merely used to illustrate the technical solutions of the present application, rather than limiting the present application. Although the present application has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that the specific embodiments of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and any modification or equivalent replacement without departing from the spirit and scope of the present application should be covered in the protection scope of the claims of the present application.

Claims

1. A method for extracting power line poles based on laser point clouds, characterized in that, include: Step 1: Obtain laser point cloud data of straight power distribution lines and perform preprocessing to obtain preprocessed laser point cloud data of power distribution lines; Step 2: Spatial transformation is performed on the preprocessed power distribution line laser point cloud data to obtain power distribution line laser point cloud data parallel to the x-axis; Step 3: Divide the laser point cloud data of the power distribution line parallel to the x-axis into intervals to obtain the representative coordinates of the conductors. Combine the maximum and minimum value constraints to obtain the coordinates of the power distribution line poles, including: Step 3.1: Sort the laser point cloud data of the power distribution lines parallel to the x-axis in ascending order of x-axis coordinates to obtain the sorted laser point cloud data; Step 3.2: Denote the smallest x-axis coordinate in the laser point cloud data as x_min and the largest x-axis coordinate as x_max; Step 3.3: Set the variable x_state and initialize it to x_min; Step 3.4: Select laser point cloud data whose x-coordinate is between x_state and x_state + step from the sorted laser point cloud data, and denote it as data, where step is the selection step size; Step 3.5: For data, divide the data into intervals along the x-axis and analyze the data variance to obtain the corresponding x and y coordinates of the conductor. Record the x and y coordinate values ​​of the conductor in lists x_list and z_list. Step 3.6: Based on the maximum and maximum value constraint analysis lists z_list and x_list, obtain the x-axis position of the power distribution line poles; Step 3.7: Based on the x-axis position of the power distribution line pole, take 'a' meters before and after the x-axis position. The laser point cloud data within the corresponding 2a-meter range is the three-dimensional coordinate of the power distribution line pole, where 'a' is the x-axis position parameter. Step 3.8: Rotate the three-dimensional coordinates of the power distribution line pole counterclockwise by an angle θ to restore the three-dimensional coordinates of the power distribution line pole in the original coordinate system, where θ is the angle between the power distribution line and the x-axis; Step 3.9: Update x_state to x_state + step / 2, and check if x_state is greater than x_max. If it is, terminate the program; otherwise, proceed to step 3.

4.

2. The method for extracting power line poles based on laser point clouds according to claim 1, characterized in that: The preprocessing described in step 1 includes: Extract the x, y, and z coordinates of the laser point cloud data of the straight section of the power distribution line, with the coordinate unit being meters; The extracted x, y, and z coordinates are rounded to two decimal places, and duplicate data with identical x, y, and z coordinates are removed. Laser point cloud data with z-coordinates located between the upper and lower limits of the elevation threshold are filtered out. The upper and lower limits of the elevation threshold are set according to the average ground altitude and the height of power line poles to filter out ground point clouds and noise points in the air.

3. The method for extracting power line poles based on laser point clouds according to claim 1, characterized in that: Step 2, which involves spatial transformation of the preprocessed laser point cloud data of power distribution lines, includes: The preprocessed laser point cloud data of the power distribution line is projected onto the xoy two-dimensional plane and fitted to obtain the plane linear equation of the power distribution line. The angle θ between the power distribution line and the x-axis is obtained based on the plane linear equation. The preprocessed laser point cloud data of the power distribution line is rotated clockwise by an angle θ in the plane so that the direction of the power distribution line is parallel to the x-axis, thus obtaining laser point cloud data parallel to the x-axis.

4. The method for extracting power line poles based on laser point clouds according to claim 1, characterized in that: Step 3.5 includes: Step 3.5.1: Set up lists x_list and z_list to record the horizontal and vertical coordinate values ​​of the wires, respectively, and initialize them to empty lists; Step 3.5.2: For data, divide the data into intervals along the x-axis, starting from x_state, with an interval length of 2a meters and an overlap length of a meters; Step 3.5.3: For each interval, further divide it into b smaller intervals and proceed to step 3.5.4; if the length of the power distribution line in the x direction within the interval is less than 2a meters, then do not further divide it into smaller intervals and skip the interval directly, where b is the number of smaller intervals. Step 3.5.4: For each interval, obtain the laser point cloud data point with the largest z-coordinate value within each sub-interval, resulting in a total of b laser point cloud data points with the largest z-coordinate values. Calculate the variance of the z-coordinate values ​​of these b laser point cloud data points with the largest z-coordinate values: If the variance is less than c, then calculate the average z-coordinate value of the b laser point cloud data points with the largest z-coordinate values ​​and add it to z_list as a guide to represent the z-coordinate value. At the same time, calculate the average x-coordinate value of the b laser point cloud data points with the largest z-coordinate values ​​and add it to x_list as a guide to represent the x-coordinate value. If the variance is greater than or equal to c, then the interval and its subintervals are not considered, where c is the variance threshold.

5. The method for extracting power line poles based on laser point clouds according to claim 4, characterized in that: The value range of step is 150~250, the value range of a is 0.4~0.6, the value range of b is 8~15, and the value range of c is 0.1~1.

6. The method for extracting power line poles based on laser point clouds according to claim 1, characterized in that: Step 3.6, based on the maximum and maximum constraint analysis lists x_list and z_list, obtains the x-axis position of the power distribution line poles, including: Step 3.6.1: Remove points in z_list that exceed the discrete limit and points in x_list that are at the corresponding positions based on the variance of the elements in z_list, and set up a list xg_list to record the x-axis positions of the power distribution line poles and initialize it to an empty list. Step 3.6.2: Traverse all elements of z_list. For the i-th element, take the larger value of 0 and id, denoted as left, and take the smaller value of len(z_list) and i+d, denoted as right. Here, len(z_list) represents the number of elements in z_list, and d is the traversal parameter. If the i-th element satisfies the maximum and maximum value constraints, then change the value of the i-th element in x_list to x. i The x-axis positions of the power distribution line poles are added to xg_list, where the maximum and maximum values ​​are constrained as follows: z i > z i-1 And z i > z i+1 , z i The maximum value in z_list from left to right; In the formula, z i-1 z i+1 The maximum value z in the interval from left to right of z_list. i The values ​​of the left and right adjacent points.

7. The method for extracting power line poles based on laser point clouds according to claim 6, characterized in that: The value of d ranges from 15 to 30.

8. A power line pole extraction system based on laser point clouds, comprising the method described in any one of claims 1-7, characterized in that, The system includes: The data acquisition module is used to acquire laser point cloud data of linear power distribution lines and perform preprocessing to obtain preprocessed laser point cloud data of power distribution lines. The spatial transformation module is used to perform spatial transformation on the preprocessed power distribution line laser point cloud data to obtain power distribution line laser point cloud data parallel to the x-axis. The coordinate extraction module is used to obtain the representative coordinates of the conductors from the laser point cloud data of the power distribution line parallel to the x-axis by dividing it into intervals. Combined with the maximum and maximum value constraints, the coordinates of the power distribution line poles are obtained.

9. A terminal, comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method according to any one of claims 1-7.

Images