A positioning and deviation rectification method and system based on a UAV

Abstract

This invention provides a positioning and correction method and system based on unmanned aerial vehicles (UAVs). The method involves obtaining the first historical marker position and the actual position of a first utility pole to determine the offset vector of each pole; performing clustering based on the first historical marker position to obtain each first cluster center and its corresponding first cluster; evaluating the offset vector of the corresponding utility pole within each first cluster to obtain the corresponding comprehensive offset vector; then clustering the second historical position of the second utility pole requiring subsequent correction with the first historical marker position to obtain a second cluster; matching the first and second clusters to determine the first cluster in which the second utility pole scheduled for maintenance will be located; and correcting the second historical position based on the comprehensive offset vector corresponding to the first cluster in which the second utility pole is located. This allows other maintenance personnel to accurately locate the utility poles during subsequent maintenance.

Description

Technical Field

[0001] This invention belongs to the field of positioning correction technology, and specifically relates to a positioning correction method and system based on unmanned aerial vehicles (UAVs). Background Technology

[0002] When inspecting utility poles, drones are often used to assist in the inspection. However, when maintenance personnel arrive at the location of the utility pole with the drone, guided by historical survey maps, they often find that the pole's location is not as shown on the map. For example, there may be an error distance of tens of meters between the actual utility pole and the one on the map; or the actual utility pole and the one on the map may not be on the same side of the road. Summary of the Invention

[0003] Based on this, the present invention provides a positioning correction method and system based on UAV, which aims to correct the positioning of utility poles by using UAVs during maintenance, so that other maintenance personnel can accurately locate the utility poles when they perform maintenance on the next time.

[0004] A first aspect of this invention provides a positioning correction method based on an unmanned aerial vehicle (UAV), the method comprising:

[0005] The first historical marker position of the first utility pole is obtained, and the actual position of the first utility pole is measured on-site by a drone. Based on the first historical marker position and the actual position, the offset vector of the first utility pole is determined.

[0006] The first historical marker positions are clustered to obtain each first cluster center and the corresponding first cluster group;

[0007] The offset vectors of the corresponding utility poles in each first cluster are evaluated to obtain the corresponding comprehensive offset vectors.

[0008] Obtain the second historical location of the second utility pole other than the first utility pole; based on the number of the first cluster centers, cluster the first historical location and the second historical location to obtain each second cluster center and the corresponding second cluster group.

[0009] Analyze the positional relationship between the first cluster center and the second cluster center, and match the first cluster and the second cluster based on the positional relationship to determine the first cluster in which the second utility pole is located;

[0010] The second historical position is corrected based on the comprehensive offset vector corresponding to the first cluster where the second utility pole is located.

[0011] Furthermore, in the step of evaluating the offset vectors of the corresponding utility poles in each first cluster to obtain the corresponding comprehensive offset vector, the directional correlation and spatial position correlation of the offset vectors are determined based on the offset vectors of the corresponding utility poles in each first cluster, and an evaluation is performed based on the directional correlation and spatial position correlation of the offset vectors.

[0012] Furthermore, the step of determining the directional correlation and spatial position correlation of the offset vector based on the offset vector of the corresponding utility pole within each first cluster, and performing an evaluation based on the directional correlation and spatial position correlation of the offset vector, includes:

[0013] Based on the offset vector of the utility pole and principal component analysis, the first comprehensive offset vector associated with the direction correlation is determined;

[0014] Based on the offset vector of the utility pole and the distance weighting method based on spatial location, a second comprehensive offset vector associated with spatial location correlation is determined;

[0015] Based on the first comprehensive offset vector and the second comprehensive offset vector, the comprehensive offset vector is determined by a weighted summation method. The weight coefficient of the first comprehensive offset vector is determined by the contribution rate and directional concentration of the first principal component, and the weight coefficient of the second comprehensive offset vector is determined by the regression coefficient and Moran's I index.

[0016] Furthermore, the step of determining the first comprehensive offset vector associated with the direction correlation based on the offset vector of the utility pole and principal component analysis includes:

[0017] Treat the offset vector of the utility pole as a data point and calculate the covariance matrix;

[0018] Perform eigenvalue decomposition on the covariance matrix to obtain the eigenvector corresponding to the largest eigenvalue;

[0019] Project all vectors onto the eigenvector corresponding to the largest eigenvalue to determine the average projection length;

[0020] The first comprehensive offset vector is calculated based on the eigenvector corresponding to the average projection length and the maximum eigenvalue.

[0021] Furthermore, in the step of determining the second comprehensive offset vector associated with spatial location correlation based on the offset vector of the utility pole and the distance-weighted method based on spatial location, the calculation formula is as follows:

[0022] ;

[0023] in, This is the second composite offset vector. Let be the offset vector of the i-th utility pole. Let be the distance from the i-th utility pole to the corresponding first cluster center. is the distance attenuation index, and n is the total number of utility poles in the corresponding first cluster.

[0024] Furthermore, in the step where the weight coefficients of the first composite offset vector are determined by the contribution rate and directional concentration of the first principal component, the formula for calculating the contribution rate of the first principal component is:

[0025] ;

[0026] The largest eigenvalue, Let d be the j-th eigenvalue, and d be the total number of eigenvalues.

[0027] The formula for calculating directional concentration is:

[0028] ;

[0029] ;

[0030] The average direction vector. This represents the directional concentration.

[0031] Furthermore, in the step where the weight coefficients of the second composite offset vector are determined by the regression coefficients and Moran's I index, the formula for calculating linear regression is:

[0032] ;

[0033] Let be the magnitude of the offset vector of the i-th utility pole. For the intercept term, The regression coefficients are... This is the random error term;

[0034] The formula for calculating Moran's I index is:

[0035] ;

[0036] Moran's I index, The average offset size, This is the spatial weight matrix.

[0037] A second aspect of this invention provides a UAV-based positioning correction system for implementing the UAV-based positioning correction method described in the first aspect, the system comprising:

[0038] The acquisition module is used to acquire the first historical marker position of the first utility pole, and to measure the actual position of the first utility pole in the field by means of a drone, and to determine the offset vector of the first utility pole based on the first historical marker position and the actual position.

[0039] The first clustering processing module is used to perform clustering processing on the first historical marker positions to obtain each first cluster center and the corresponding first cluster group;

[0040] The evaluation module is used to evaluate the offset vector of the corresponding utility pole in each first cluster and obtain the corresponding comprehensive offset vector.

[0041] The second clustering processing module is used to obtain the second historical location of the second utility pole other than the first utility pole, and to perform clustering processing on the first historical location and the second historical location according to the number of the first cluster centers to obtain each second cluster center and the corresponding second cluster group.

[0042] The matching module is used to analyze the positional relationship between the first cluster center and the second cluster center, and match the first cluster and the second cluster according to the positional relationship to determine the first cluster in which the second utility pole is located;

[0043] The correction module is used to correct the second historical position based on the comprehensive offset vector corresponding to the first cluster in which the second utility pole is located.

[0044] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the UAV-based positioning and correction method provided in the first aspect.

[0045] A fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the UAV-based positioning and correction method provided in the first aspect.

[0046] This invention provides a UAV-based positioning correction method and system. The method involves acquiring the first historical marker position and the actual position of a first utility pole to determine the offset vector of each pole. Based on the first historical marker position, clustering is performed to obtain first cluster centers and corresponding first clusters. The offset vectors of the corresponding utility poles within each first cluster are evaluated to obtain corresponding comprehensive offset vectors. The second historical position of the second utility pole requiring subsequent correction is then clustered with the first historical marker position to obtain a second cluster. The first and second clusters are matched to determine the first cluster where the second utility pole scheduled for maintenance will be located. Based on the comprehensive offset vector corresponding to the first cluster where the second utility pole is located, the second historical position is corrected. Specifically, this method can correct the position of utility poles that have not yet been maintained, enabling other maintenance personnel to accurately locate the poles during maintenance. It also reduces the workload of correcting utility pole positions on exploration maps to some extent. Attached Figure Description

[0047] Figure 1 This is a flowchart illustrating the implementation of a UAV-based positioning and correction method according to Embodiment 1 of the present invention.

[0048] Figure 2 This is a structural block diagram of a positioning and correction system based on an unmanned aerial vehicle (UAV) provided in Embodiment 2 of the present invention;

[0049] Figure 3 This is a structural block diagram of an electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0050] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0051] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0053] Example 1

[0054] According to an embodiment of the present invention, a positioning and correction method based on an unmanned aerial vehicle (UAV) is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0055] This first embodiment provides a positioning and correction method based on a drone, which can be used in electronic devices, such as computers. Please refer to... Figure 1 , Figure 1 The flowchart of a positioning and correction method based on a UAV provided in Embodiment 1 of the present invention is shown, specifically including steps S01 to S06.

[0056] Step S01: Obtain the first historical marker position of the first utility pole and measure the actual position of the first utility pole in the field using a drone. Based on the first historical marker position and the actual position, determine the offset vector of the first utility pole.

[0057] Understandably, the first historical marker position is the location previously marked by manual exploration or other low-precision equipment, which may differ from the actual position. In order to correct the deviation, the offset vector of the first utility pole is first determined. It should be noted that the offset vector includes the offset distance and the offset direction. The offset distance is the distance between the first historical marker position and the actual position, which can be understood as latitude and longitude positions. The offset direction is the indication direction formed by the first historical marker position as the starting point and the actual position as the ending point.

[0058] Step S02: Cluster the first historical marker positions to obtain each first cluster center and the corresponding first cluster group.

[0059] It should be noted that the comprehensive offset vector obtained from subsequent analysis only has certain reference value when the number of utility poles meets certain requirements. Therefore, when the number of utility poles is small, the original position is recalibrated sequentially using the actual position obtained by the drone. Only when the number of calibrations reaches a certain number, that is, when there is a certain sample size, is the comprehensive offset vector evaluated.

[0060] The clustering process uses the k-means clustering algorithm to obtain the first cluster centers and the first cluster group represented by each first cluster center.

[0061] Step S03: Evaluate the offset vector of the corresponding utility pole in each first cluster to obtain the corresponding comprehensive offset vector.

[0062] In this embodiment of the invention, the directional correlation and spatial position correlation of the offset vectors are determined based on the offset vectors of the corresponding utility poles within each first cluster. An evaluation is then performed based on these correlations. Specifically, a first comprehensive offset vector associated with the directional correlation is determined using the offset vectors of the utility poles and principal component analysis. It should be noted that the offset vectors of the utility poles are first treated as data points, and the covariance matrix is ​​calculated using the following formula:

[0063] ;

[0064] Let be the covariance matrix, and n be the total number of utility poles in the corresponding first cluster. Let be the offset vector of the i-th utility pole. The mean of the offset vector;

[0065] Perform eigenvalue decomposition on the covariance matrix to obtain the eigenvector corresponding to the largest eigenvalue;

[0066] Project all vectors onto the eigenvector corresponding to the largest eigenvalue, and determine the average projection length using the following formula:

[0067] ;

[0068] ;

[0069] The eigenvector corresponding to the largest eigenvalue. Let be the projected length of the i-th utility pole. The average projected length;

[0070] The first comprehensive offset vector is calculated based on the eigenvector corresponding to the average projection length and the maximum eigenvalue, using the following formula:

[0071] ;

[0072] This is the first composite offset vector;

[0073] Based on the pole offset vector and a distance-weighted method based on spatial location, a second comprehensive offset vector correlated with spatial location is determined. The calculation formula is as follows:

[0074] ;

[0075] in, This is the second composite offset vector. Let be the offset vector of the i-th utility pole. Let be the distance from the i-th utility pole to the corresponding first cluster center. Here, n is the distance attenuation index, and n is the total number of utility poles in the corresponding first cluster.

[0076] Based on the first comprehensive offset vector and the second comprehensive offset vector, the comprehensive offset vector is determined by a weighted summation method. The weight coefficient of the first comprehensive offset vector is determined by the contribution rate and directional concentration of the first principal component, and the weight coefficient of the second comprehensive offset vector is determined by the regression coefficient and Moran's I index.

[0077] It should be noted that the formula for calculating the contribution rate of the first principal component is:

[0078] ;

[0079] The largest eigenvalue, Let d be the j-th eigenvalue, and d be the total number of eigenvalues.

[0080] The formula for calculating directional concentration is:

[0081] ;

[0082] ;

[0083] The average direction vector. The directional concentration is defined as follows: if the contribution rate is significantly higher than a threshold, the offset is considered to have a clear directional trend. The first principal component direction... This refers to the trend direction. Furthermore, when R≈1, it indicates that all vector directions are highly consistent, showing a clear directional trend; when R≈0, it indicates that the vector directions are randomly distributed, with no directional trend. In this embodiment of the invention, a first mapping relationship is established, which is used to match corresponding weight coefficients based on the contribution rate and directional concentration.

[0084] Furthermore, the formula for linear regression is:

[0085] ;

[0086] Let be the magnitude of the offset vector of the i-th utility pole. For the intercept term, The regression coefficients are... As a random error term, it's understandable that the test... The significance of the independent variable is used to determine its significance. With dependent variable Is there a true linear relationship between them?

[0087] The formula for calculating Moran's I index is:

[0088] ;

[0089] Moran's I index, The average offset size, Let I be the spatial weight matrix, where I>0 indicates positive autocorrelation and spatial clustering of offsets, I≈0 indicates random distribution and no spatial correlation, and I<0 indicates negative autocorrelation and large differences in offsets between adjacent positions.

[0090] Similarly, a second mapping relationship is established, which is used to match the corresponding weight coefficients based on the regression coefficients and Moran's I index.

[0091] Step S04: Obtain the second historical location of the second utility pole other than the first utility pole; based on the number of first cluster centers, perform clustering processing on the first historical marker location and the second historical location to obtain each second cluster center and the corresponding second cluster group.

[0092] Understandably, the second utility pole is scheduled for future maintenance. It should be noted that utility poles typically have multiple voltage levels of transmission lines originating from the substation, and the poles are installed along the planned routes of these transmission lines, exhibiting a certain regularity. Therefore, based on the number of the first cluster centers, the poles at the first historical marker location and the second historical location are clustered. The resulting second cluster centers may have a slight positional shift compared to the first cluster centers, but this has a minimal impact.

[0093] Step S05: Analyze the positional relationship between the first cluster center and the second cluster center. Based on the positional relationship, match the first cluster and the second cluster to determine the first cluster in which the second utility pole is located.

[0094] Specifically, when the distance between the first cluster center and the second cluster center is less than a preset distance, the corresponding first cluster and second cluster are matched, and the first cluster in which each utility pole planned to be repaired is located is determined.

[0095] Step S06: Correct the second historical position according to the comprehensive offset vector corresponding to the first cluster where the second utility pole is located.

[0096] Since the comprehensive offset vector of the first cluster is known, and the second historical position of the second utility pole scheduled for maintenance in the corresponding second cluster is determined, the actual position of the utility pole can be inferred based on the second historical position and the corresponding comprehensive offset vector. It should be noted that if the pole position inference is correct during the actual maintenance process, it does not need to be corrected again, and if there is an error in the inference, it can be manually corrected again.

[0097] In summary, the UAV-based positioning correction method in the above embodiments of the present invention determines the offset vector of each utility pole by acquiring the first historical marker position and the actual position of the first utility pole; clustering is performed based on the first historical marker position to obtain each first cluster center and the corresponding first cluster; the offset vector of the utility pole in each first cluster is evaluated to obtain the corresponding comprehensive offset vector; the second historical position of the second utility pole that needs to be corrected is then clustered with the first historical marker position to obtain the second cluster, and the first cluster and the second cluster are matched to determine the first cluster in which the second utility pole planned to be repaired is located; the second historical position is corrected based on the comprehensive offset vector corresponding to the first cluster in which the second utility pole is located. Specifically, the above method can correct the position of utility poles that have not yet been repaired, so that other maintenance personnel can accurately find the position of the utility pole when performing maintenance, and at the same time, reduce the workload of correcting the position of utility poles on the exploration map to a certain extent.

[0098] Example 2

[0099] Please see Figure 2 , Figure 2 This is a structural block diagram of a UAV-based positioning and correction system according to Embodiment 2 of the present invention. This UAV-based positioning and correction system 200 is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0100] Specifically, the UAV-based positioning correction system 200 includes: an acquisition module 21, a first clustering processing module 22, an evaluation module 23, a second clustering processing module 24, a matching module 25, and a correction module 26, wherein:

[0101] The acquisition module 21 is used to acquire the first historical marker position of the first utility pole, and to measure the actual position of the first utility pole in the field by means of a drone, and to determine the offset vector of the first utility pole based on the first historical marker position and the actual position.

[0102] The first clustering processing module 22 is used to perform clustering processing on the first historical marker positions to obtain each first cluster center and the corresponding first cluster group;

[0103] Evaluation module 23 is used to evaluate the offset vector of the corresponding utility pole in each first cluster, obtain the corresponding comprehensive offset vector, determine the directional correlation and spatial position correlation of the offset vector based on the offset vector of the corresponding utility pole in each first cluster, and perform evaluation based on the directional correlation and spatial position correlation of the offset vector.

[0104] The second clustering processing module 24 is used to obtain the second historical location of the second utility pole other than the first utility pole, and to perform clustering processing on the first historical marker location and the second historical location according to the number of the first cluster centers to obtain each second cluster center and the corresponding second cluster group;

[0105] The matching module 25 is used to analyze the positional relationship between the first cluster center and the second cluster center, and match the first cluster and the second cluster according to the positional relationship to determine the first cluster in which the second utility pole is located;

[0106] The correction module 26 is used to correct the second historical position based on the comprehensive offset vector corresponding to the first cluster where the second utility pole is located.

[0107] Furthermore, in some optional embodiments of the present invention, the evaluation module 23 includes:

[0108] The first determining unit is used to determine the first comprehensive offset vector associated with the direction correlation based on the offset vector of the utility pole and the principal component analysis method.

[0109] The second determining unit is used to determine the second comprehensive offset vector associated with spatial location based on the offset vector of the utility pole and a distance-weighted method based on spatial location. The calculation formula is as follows:

[0110] ;

[0111] in, This is the second composite offset vector. Let be the offset vector of the i-th utility pole. Let be the distance from the i-th utility pole to the corresponding first cluster center. Here, n is the distance attenuation index, and n is the total number of utility poles in the corresponding first cluster.

[0112] The third determining unit is used to determine the comprehensive offset vector based on the first comprehensive offset vector and the second comprehensive offset vector using a weighted summation method. The weight coefficient of the first comprehensive offset vector is determined by the contribution rate and directional concentration of the first principal component, and the weight coefficient of the second comprehensive offset vector is determined by the regression coefficient and Moran's I index. The formula for calculating the contribution rate of the first principal component is:

[0113] ;

[0114] The largest eigenvalue, Let d be the j-th eigenvalue, and d be the total number of eigenvalues.

[0115] The formula for calculating directional concentration is:

[0116] ;

[0117] ;

[0118] The average direction vector. Directional concentration;

[0119] The formula for linear regression is:

[0120] ;

[0121] Let be the magnitude of the offset vector of the i-th utility pole. For the intercept term, The regression coefficients are... This is the random error term;

[0122] The formula for calculating Moran's I index is:

[0123] ;

[0124] Moran's I index, The average offset size, This is the spatial weight matrix.

[0125] Furthermore, in some optional embodiments of the present invention, the first determining unit includes:

[0126] The first calculation subunit is used to treat the offset vector of the utility pole as a data point and calculate the covariance matrix;

[0127] The decomposition subunit is used to perform eigenvalue decomposition on the covariance matrix to obtain the eigenvector corresponding to the largest eigenvalue.

[0128] The projection subunit is used to project all vectors onto the eigenvector corresponding to the largest eigenvalue and determine the average projection length.

[0129] The second calculation subunit is used to calculate the first comprehensive offset vector based on the eigenvector corresponding to the average projection length and the maximum eigenvalue.

[0130] Example 3

[0131] In another aspect, the present invention also proposes an electronic device, please refer to [link to relevant documentation]. Figure 3 The image shows an electronic device according to Embodiment 3 of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor. When the processor 10 executes the computer program 30, it implements the above-described UAV-based positioning and correction method.

[0132] In some embodiments, the processor 10 may be a central processing unit (CPU), controller, microcontroller, microprocessor or other data processing chip, used to run program code stored in memory 20 or process data, such as executing access restriction programs.

[0133] The memory 20 includes at least one type of readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 20 can be an internal storage unit of an electronic device, such as the hard disk of the electronic device. In other embodiments, the memory 20 can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. Furthermore, the memory 20 can include both internal and external storage units of the electronic device. The memory 20 can be used not only to store application software and various types of data of the electronic device, but also to temporarily store data that has been output or will be output.

[0134] It should be pointed out that, Figure 3 The structure shown does not constitute a limitation on the electronic device. In other embodiments, the electronic device may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0135] This invention also proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described UAV-based positioning and correction method.

[0136] Those skilled in the art will understand that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0137] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0138] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0139] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0140] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this patent should be determined by the appended claims.

Claims

1. A positioning and correction method based on unmanned aerial vehicles (UAVs), characterized in that, The method includes: The first historical marker position of the first utility pole is obtained, and the actual position of the first utility pole is measured on-site by a drone. Based on the first historical marker position and the actual position, the offset vector of the first utility pole is determined. The first historical marker positions are clustered to obtain each first cluster center and the corresponding first cluster group; The offset vectors of the corresponding utility poles in each first cluster are evaluated to obtain the corresponding comprehensive offset vectors. Obtain the second historical location of the second utility pole other than the first utility pole; based on the number of the first cluster centers, cluster the first historical location and the second historical location to obtain each second cluster center and the corresponding second cluster group. Analyze the positional relationship between the first cluster center and the second cluster center, and match the first cluster and the second cluster based on the positional relationship to determine the first cluster in which the second utility pole is located; The second historical position is corrected based on the comprehensive offset vector corresponding to the first cluster where the second utility pole is located; In the step of evaluating the offset vectors of the corresponding utility poles in each first cluster to obtain the corresponding comprehensive offset vector, the directional correlation and spatial position correlation of the offset vectors are determined based on the offset vectors of the corresponding utility poles in each first cluster, and the evaluation is performed based on the directional correlation and spatial position correlation of the offset vectors. The steps of determining the directional correlation and spatial position correlation of the offset vectors based on the offset vectors of the corresponding utility poles within each first cluster, and then performing an evaluation based on the directional correlation and spatial position correlation of the offset vectors, include: Based on the offset vector of the utility pole and principal component analysis, the first comprehensive offset vector associated with the direction correlation is determined. Based on the pole offset vector and a distance-weighted method based on spatial location, a second comprehensive offset vector correlated with spatial location is determined. The calculation formula is as follows: ； in, This is the second composite offset vector. Let be the offset vector of the i-th utility pole. Let be the distance from the i-th utility pole to the corresponding first cluster center. Here, n is the distance attenuation index, and n is the total number of utility poles in the corresponding first cluster. Based on the first and second comprehensive offset vectors, a weighted summation method is used to determine the comprehensive offset vector. The weight coefficients of the first comprehensive offset vector are determined by the contribution rate and directional concentration of the first principal component, while the weight coefficients of the second comprehensive offset vector are determined by the regression coefficients and Moran's I index. The formula for linear regression is as follows: ； Let be the magnitude of the offset vector of the i-th utility pole. For the intercept term, The regression coefficients are... This is the random error term; The formula for calculating Moran's I index is: ； Moran's I index, The average offset size, This is the spatial weight matrix.

2. The UAV-based positioning and correction method according to claim 1, characterized in that, The step of determining the first comprehensive offset vector associated with the direction correlation based on the offset vector of the utility pole and principal component analysis includes: Treat the offset vector of the utility pole as a data point and calculate the covariance matrix; Perform eigenvalue decomposition on the covariance matrix to obtain the eigenvector corresponding to the largest eigenvalue; Project all vectors onto the eigenvector corresponding to the largest eigenvalue to determine the average projection length; The first comprehensive offset vector is calculated based on the eigenvector corresponding to the average projection length and the maximum eigenvalue.

3. The UAV-based positioning and correction method according to claim 2, characterized in that, In the step where the weight coefficients of the first composite offset vector are determined by the contribution rate and directional concentration of the first principal component, the formula for calculating the contribution rate of the first principal component is as follows: ； The largest eigenvalue, Let d be the j-th eigenvalue, and d be the total number of eigenvalues. The formula for calculating directional concentration is: ； ； The average direction vector. This represents the directional concentration.

4. A positioning and correction system based on an unmanned aerial vehicle (UAV), characterized in that, The system for implementing the UAV-based positioning and correction method as described in any one of claims 1-3 includes: The acquisition module is used to acquire the first historical marker position of the first utility pole, and to measure the actual position of the first utility pole in the field by means of a drone, and to determine the offset vector of the first utility pole based on the first historical marker position and the actual position. The first clustering processing module is used to perform clustering processing on the first historical marker positions to obtain each first cluster center and the corresponding first cluster group; The evaluation module is used to evaluate the offset vector of the corresponding utility pole in each first cluster and obtain the corresponding comprehensive offset vector. The second clustering processing module is used to obtain the second historical location of the second utility pole other than the first utility pole, and to perform clustering processing on the first historical location and the second historical location according to the number of the first cluster centers to obtain each second cluster center and the corresponding second cluster group. The matching module is used to analyze the positional relationship between the first cluster center and the second cluster center, and match the first cluster and the second cluster according to the positional relationship to determine the first cluster in which the second utility pole is located; The correction module is used to correct the second historical position based on the comprehensive offset vector corresponding to the first cluster in which the second utility pole is located.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the UAV-based positioning and correction method as described in any one of claims 1-3.

6. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the UAV-based positioning and correction method as described in any one of claims 1-3.

Images