A method, system, electronic device and storage medium for checking electric power tower accounts

Abstract

The present invention relates to the technical field of pole tower verification, and in particular to a method, system, electronic device and storage medium for verifying an electric pole tower ledger. The method comprises: acquiring multiple groups of satellite remote sensing images in an area to be verified, and performing image processing on the multiple groups of satellite remote sensing images to obtain panoramic satellite images of pole towers in the area to be verified; performing pole tower feature recognition on the panoramic satellite images of the pole towers to obtain pole tower image recognition feature information of all pole towers in the area to be verified; the pole tower image recognition feature information comprises the coordinates of the center point of the pole tower, the height of the pole tower and the type of the pole tower; based on the pole tower image recognition feature information, performing conductor feature recognition on the panoramic satellite images of the pole towers, and performing power line connection based on the conductor feature recognition result to obtain a power line distribution map in the area to be verified; the method can timely discover and correct errors and missing information in the pole tower ledger, and provide accurate and reliable power grid architecture and equipment status information for operation and maintenance personnel.

Description

Technical Field

[0001] The present invention relates to the technical field of pole tower verification, and in particular to a method, system, electronic equipment and storage medium for verifying an electric power pole tower ledger. Background Art

[0002] With the rapid development of the power industry, the scale of the power grid continues to expand. As a key infrastructure, the number and distribution of transmission towers have also expanded accordingly. The tower inventory is an important document that records in detail the basic information such as the location, model, height and material of the tower. Accurate tower inventory information provides operation and maintenance personnel with a basis for in-depth understanding of the power grid architecture and equipment status, which helps to promptly identify and resolve potential safety risks. When a fault occurs, the fault location can be quickly determined, reducing maintenance time, thereby enhancing the reliability and stability of the power system. Therefore, ensuring the accuracy and completeness of the tower inventory information is extremely important for ensuring the safe and stable operation of the power system.

[0003] However, due to various factors, such as data input errors during construction, failure to update information in a timely manner after equipment upgrades, and changes in tower information caused by changes in the natural environment, the information in the tower ledger may be biased or missing, making the correction of tower ledger information an urgent task for power companies. The existing drone inspections and manual inspection methods, although effective to a certain extent, are often limited by limited search range, poor real-time performance and high labor intensity.

[0004] Therefore, there is an urgent need for a power tower inventory verification method to solve the above problems. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a power tower inventory verification method, system, electronic device and storage medium that can timely discover and correct errors and missing information in the tower inventory, and provide accurate and reliable power grid architecture and equipment status information to operation and maintenance personnel.

[0006] In a first aspect, the present invention provides a method for checking an electric power tower account, the method comprising:

[0007] Acquire multiple sets of satellite remote sensing images in the area to be verified, and perform image processing on the multiple sets of satellite remote sensing images to obtain panoramic satellite images of the towers in the area to be verified;

[0008] Performing tower feature recognition on the tower panoramic satellite image to obtain tower image recognition feature information of all towers in the area to be verified; the tower image recognition feature information includes the coordinates of the tower center point, the tower height and the tower type;

[0009] Based on the pole tower image recognition feature information, the conductor feature recognition is performed on the pole tower panoramic satellite image, and the power line connection is performed based on the conductor feature recognition result to obtain the power line distribution map in the area to be verified; for each power line in the power line distribution map, a pole tower information database corresponding to the power line is constructed;

[0010] For each pole tower in the pole tower information database, obtain the corresponding pole tower ledger record feature information, and match it with the pole tower image recognition feature information, mark the pole tower that successfully matches as a correct pole tower, and mark the pole tower that fails to match as an incorrect pole tower;

[0011] For each power line, all wrong towers on the power line are checked twice by step-by-step span matching. If the check succeeds, the towers are corrected to be correct towers.

[0012] The tower information marked as erroneous towers shall be verified on site and corrected in the tower record.

[0013] Furthermore, for each power line, all the wrong towers on the power line are checked twice by using step-by-step span matching, including:

[0014] Get the correct span corresponding to the tower;

[0015] Take the first correct tower in the power line as the benchmark and the corresponding account span as the search range;

[0016] In response to an adjacent erroneous pole tower being within the search range, comparing the pole tower height check and the pole tower type in the pole tower image recognition feature information corresponding to the adjacent erroneous pole tower with the pole tower ledger record feature information;

[0017] If the comparison is successful, the adjacent erroneous pole tower is corrected to a correct pole tower;

[0018] If the comparison fails, the next correct tower in the power line is used as a reference, and the corresponding ledger span is used as the search range until all towers in the power line are searched.

[0019] Furthermore, when searching with the corresponding ledger span as the search range, a span search error is set to take into account factors affecting image clarity, resulting in size errors of the tower in the image.

[0020] Furthermore, the method for setting the gear span search error includes:

[0021] Acquire multiple known correct towers from the same power line as error adjustment reference points for adjusting the search error;

[0022] For each error adjustment reference point, extract the coordinates of the center point of the tower on the tower panoramic satellite image and the coordinates of the center point of the tower on the tower ledger information to form a reference point coordinate set corresponding to the error adjustment reference point;

[0023] Calculate the difference between the two reference point coordinate sets corresponding to any pair of adjacent error adjustment reference points to obtain the image distance vector and the ledger distance vector respectively;

[0024] Subtract the image distance vector from the record distance vector to obtain an error vector;

[0025] Characteristic value extraction is performed on multiple error vectors to obtain the span search error used for secondary calibration.

[0026] Furthermore, the image distance vector is obtained by calculating the difference between the coordinates of the center point of the pole tower of two adjacent error adjustment reference points on the panoramic satellite image of the pole tower;

[0027] The record distance vector is obtained by calculating the difference between the coordinates of the center points of the towers of two adjacent error adjustment reference points on the tower record information;

[0028] The image distance vector is expressed as:

[0029] ;

[0030] in, represents the coordinates of the center point of the tower of the ith error adjustment reference point on the tower panoramic satellite image, Represents the coordinates of the center point of the tower of the i-th error adjustment reference point in the tower ledger information; represents the coordinates of the center point of the tower of the i+1th error adjustment reference point on the tower panoramic satellite image, Represents the coordinates of the center point of the tower of the i+1th error adjustment reference point in the tower inventory information.

[0031] Furthermore, the error vector is composed of a horizontal error and a vertical error; the error vector is expressed as:

[0032] ;

[0033] in, represents the horizontal error, Indicates the vertical error.

[0034] Furthermore, based on the pole tower image recognition feature information, the pole tower panoramic satellite image is used for conductor feature recognition, and the power line connection is performed based on the conductor feature recognition result to obtain the power line distribution map in the area to be verified, including:

[0035] Identify conductor features from panoramic satellite images of pole towers, including conductor direction, thickness and color contrast;

[0036] Starting from the identified wire starting point, trace along the wire direction, connect adjacent wire segments, and form a continuous wire path;

[0037] Associating the conductor paths with the identified tower locations so that each conductor segment can be connected to the corresponding tower;

[0038] According to the conductor path and tower location, the topological structure of the power line is constructed and the power line distribution map is generated.

[0039] On the other hand, the present application also provides a power tower ledger verification system, the system comprising:

[0040] A satellite image processing module is used to obtain multiple sets of satellite remote sensing images in the area to be verified, and perform image processing on the multiple sets of satellite remote sensing images to obtain panoramic satellite images of the towers in the area to be verified;

[0041] The tower feature recognition module is used to perform tower feature recognition on the tower panoramic satellite image and extract the tower image recognition feature information of all towers in the area to be verified, including the coordinates of the tower center point, tower height and tower type;

[0042] The power line construction module performs conductor feature recognition on the panoramic satellite image of the tower based on the pole tower image recognition feature information, and connects the power lines according to the conductor feature recognition results to obtain the power line distribution map in the area to be verified; and for each power line in the power line distribution map, a corresponding tower information database is constructed;

[0043] The pole tower information matching module obtains the pole tower ledger record feature information corresponding to each pole tower in the pole tower information database, and matches the pole tower ledger record feature information with the pole tower image recognition feature information; marks the pole tower that successfully matches as a correct pole tower, and marks the pole tower that fails to match as an incorrect pole tower;

[0044] The step-by-step span matching verification module uses the step-by-step span matching method to perform a secondary verification on all incorrect towers on each power line. If the verification is successful, it will be corrected to the correct tower.

[0045] The ledger correction module conducts on-site verification of the tower information marked as erroneous towers and makes corrections in the tower ledger.

[0046] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0047] In a fourth aspect, the present application further provides a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps in any one of the above methods are implemented.

[0048] Compared with the prior art, the invention has the following beneficial effects: by acquiring and processing multiple sets of satellite remote sensing images, a panoramic satellite image of the tower is obtained, which can quickly cover a large area and improve the efficiency of data acquisition; by identifying the characteristics of the tower and the conductor, the center point coordinates, height, type and power line distribution of the tower are automatically extracted, which reduces manual intervention and improves the recognition speed and accuracy; a power line distribution map is constructed based on the recognition results, and a tower information database is constructed for each power line, which helps to systematically analyze the power tower information and facilitate subsequent comparison and verification; the characteristic information recorded in the tower ledger is compared with the tower image Identify feature information for matching, quickly identify erroneous poles, perform secondary verification on erroneous poles through step-by-step span matching, and further improve the accuracy of verification; conduct on-site verification of pole information marked as erroneous poles, and make corrections in the pole tower ledger, combining automated processing and on-site verification to ensure the accuracy and completeness of the final ledger information; through the above method, it is possible to promptly discover and correct errors and missing information in the pole tower ledger, provide accurate and reliable grid architecture and equipment status information to operation and maintenance personnel, and help to promptly identify and resolve potential safety risks, thereby improving the reliability and stability of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a flow chart of a method for checking a power tower account in an embodiment;

[0050] Figure 2 is a flow chart of step-by-step gear spacing matching in an embodiment;

[0051] Figure 3 It is a structural diagram of the power tower inventory verification system in the embodiment. DETAILED DESCRIPTION

[0052] In the description of this application, those skilled in the art should know that this application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, this application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, this application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0053] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0054] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0055] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0056] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0057] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0058] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0059] The present application is described below in conjunction with the drawings in the present application.

[0060] Embodiment 1: Figure 1 to Figure 2 As shown, a method for checking the electric power tower account book of the present invention specifically comprises the following steps:

[0061] Step S1, obtaining multiple sets of satellite remote sensing images in the area to be verified, and performing image processing on the multiple sets of satellite remote sensing images to obtain panoramic satellite images of towers in the area to be verified;

[0062] Step S1 is the starting step of the power tower ledger verification method. Its core task is to obtain multiple sets of satellite remote sensing images in the area to be verified and process these images to obtain panoramic satellite images of the towers in the area to be verified. The following is a detailed introduction to step S1:

[0063] Step S11: Determine the satellite shooting task according to the specific area to be checked, including selecting the operating satellite, shooting time, weather conditions, etc.; the satellite uses the high-resolution sensor on board to shoot the target area according to the predetermined time and orbit parameters; when shooting, factors such as lighting conditions and cloud cover need to be considered to ensure image quality; after the satellite completes shooting, the collected image data is transmitted back to the ground station through a communication link;

[0064] Step S12, receiving the original image data transmitted by the satellite, and decoding it, obtaining the metadata of each image, including observation angle information, satellite orbit parameters, attitude information, shooting time, location, etc., selecting images shot by the same satellite, at the same time, and at the same altitude angle, and if the images are shot at different altitude angles, performing geometric correction processing on the images, confirming a unified observation angle, using a geometric correction tool, setting a target observation angle, performing geometric correction on the images, and obtaining satellite images at the same observation angle; eliminating geometric distortion caused by factors such as satellite attitude and orbit parameters;

[0065] Step S13, further improving the geometric accuracy of the image after geometric correction through regional block adjustment technology, regional block adjustment involves joint adjustment between multiple images to ensure the accuracy of the relative position relationship between the images; orthorectifying the image to eliminate the projection deformation caused by terrain undulation; orthorectifying requires the use of digital elevation model (DEM) data;

[0066] Step S14: select control points with known coordinates on the image and perform registration to ensure the absolute position accuracy of the image; if the acquired image is a multi-band image, image fusion is required to synthesize images of different bands into a high-resolution color image; perform color and light uniformity processing on the fused image to ensure that the color, brightness and contrast of the image are consistent, thereby improving the visual effect and the accuracy of subsequent processing;

[0067] Step S15: In order to more easily identify and extract the features of the pole tower, the image needs to be enhanced; this includes edge detection, texture analysis, color enhancement and other steps to highlight the features of the pole tower in the image;

[0068] Step S16, mosaicking and splicing multiple pre-processed images to generate a panoramic satellite image of the towers in the area to be verified; the panoramic satellite image of the towers will clearly display the location, shape, height and other information of all towers in the area, providing accurate basic data for subsequent feature recognition and ledger verification.

[0069] Through step S1, a panoramic satellite image of the pole towers in the area to be verified can be obtained, which provides basic data for subsequent pole tower feature identification and inventory verification work. It is the basis of the entire power pole tower inventory verification method. Its accuracy and completeness directly affect the execution effect of subsequent steps. Through satellite remote sensing technology, the search range can be effectively expanded and the timeliness and accuracy of the data can be improved.

[0070] Step S2, performing tower feature recognition on the tower panoramic satellite image to obtain tower image recognition feature information of all towers in the area to be verified; the tower image recognition feature information includes the coordinates of the tower center point, the tower height and the tower type;

[0071] Step S2 involves performing tower feature recognition on the tower panoramic satellite image to obtain tower image recognition feature information of all towers in the area to be verified, ensuring that relevant information of the towers is accurately extracted from the satellite image. The following is a detailed introduction to step S2:

[0072] Step S21, tower type identification: tower type identification is to determine the type of tower by analyzing the surface texture characteristics of the tower; by loading the color remote sensing image of the tower panoramic satellite image, the color image is separated into three channels: red, green, and blue. Using the weighted average method, different weights are given to the RGB channels. The weighted formula is as follows:

[0073] ;

[0074] Among them: gray is a grayscale image; R, G, B are the three channels of red, green and blue;

[0075] Adjust the grayscale range of the image so that it falls within a fixed grayscale level, usually 256 levels of grayscale, and use Gaussian filtering to remove image noise in order to improve the accuracy of feature extraction; construct a grayscale co-occurrence matrix based on the defined distance and direction, select the relative distance and direction between a pair of pixels, traverse each pixel in the image, and calculate the grayscale value of each pixel i and its neighbor pixel j at the defined direction and distance; in the grayscale co-occurrence matrix, the number of occurrences of grayscale values ​​i and j is recorded; after constructing the grayscale co-occurrence matrix, extract statistics such as contrast, homogeneity, and correlation from it to form feature vectors. Based on these feature vectors, extract the texture features of the tower, classify different types of towers, and obtain the type information of the identified towers;

[0076] Step S22, tower height calculation: according to the shooting time, determine the current date, clarify the date of the year, and use the formula to calculate the solar declination, the formula is as follows:

[0077] ;

[0078] in: is the solar declination (unit: degrees), N is the day of the year;

[0079] According to the time zone and standard time of the location of the tower and the tree barrier, the mean solar time, i.e. the standard time, is determined; according to the longitude information of the area and the difference from the central meridian of the time zone, the time difference of the longitude is corrected, and the correction value = 4 minutes * (central meridian longitude - local longitude); the true mean solar time difference data is obtained according to the astronomical table; according to the mean solar time, the longitude correction value, and the true mean solar time difference, the true solar time is calculated, and the true solar time = mean solar time + longitude correction value + true mean solar time difference; according to the true solar time, the solar hour angle is calculated, and the formula is as follows:

[0080] ;

[0081] Where: ω is the solar hour angle (unit: degrees); LST is the local true solar time; 12 represents noon, when the sun is at its highest point in the sky;

[0082] According to the latitude information of the solar declination and solar hour angle observation target, the solar altitude angle is calculated as follows:

[0083] ;

[0084] Where: θ is the solar altitude angle (unit: degree); is the solar declination; is the geographical latitude of the observation site; ω is the solar hour angle;

[0085] According to the solar altitude angle and the shadow length of the tower at the time of shooting, the height of the tower is calculated using the following formula:

[0086] ;

[0087] Where: h is the height of the tower; L is the shadow length of the tower; θ is the solar altitude angle (unit: degree);

[0088] Step S23, determine the coordinates of the center point of the tower: use computer vision technology (such as SIFT, HOG, CNN, etc.) to extract the features of the tower, and use the pre-trained tower template to match the image to find the location of the suspected tower, use the Canny edge detection method and other methods to detect the edges in the image to assist in identifying the outline of the tower; confirm the coordinates of the center point of the tower by using either the frame method or the centroid method, as follows:

[0089] Frame method: Draw a rectangular bounding box around the identified tower outline. The rectangular bounding box should connect the four corners of the tower as much as possible, namely the upper left corner, upper right corner, lower left corner and lower right corner. Record the coordinates of the four corners of the bounding box and confirm that each annotation box accurately covers the tower; calculate the coordinates of the center point of each tower based on the marked bounding box coordinates. The formula is as follows:

[0090] ;

[0091] in, , , and are the corner coordinates of the four corners of the rectangular bounding box, and the coordinates of the center point are ;

[0092] Centroid method: Calculate the centroid of pixels in the tower area as the center coordinate of the tower, use segmentation algorithms (such as GrabCut, Watershed, etc.) to separate the tower from the background, and calculate the centroid of pixels in the segmented tower area. The formula is as follows:

[0093] ;

[0094] in, is the coordinate of the i-th pixel in the tower area, n is the total number of pixels in the tower area, and the center point coordinate is ;

[0095] Then, control points with known geographic coordinates are selected on the panoramic satellite image of the tower, and a transformation model from the center point coordinates to the geographic coordinates is established based on the control points. Commonly used models include affine transformation and polynomial transformation. The transformation model is used to convert the center point coordinates of the tower into geographic coordinates.

[0096] By combining image processing and astronomical principles, step S2 can accurately identify the type of tower, calculate the height of the tower, and determine the coordinates of the center point of the tower; the grayscale co-occurrence matrix is ​​used to extract texture features for tower type identification to improve classification accuracy; the tower height is obtained by calculating the solar altitude angle and shadow length, which is a scientific method with small errors; the determination of the center point coordinates combines computer vision technology and geographic coordinate conversion model to ensure the accuracy of the coordinates.

[0097] Step S3: Based on the pole tower image recognition feature information, the pole tower panoramic satellite image is used for conductor feature recognition, and the power line connection is performed based on the conductor feature recognition result to obtain a power line distribution map in the area to be verified; for each power line in the power line distribution map, a pole tower information database corresponding to the power line is constructed;

[0098] On the basis of pole tower feature recognition, we further identify conductor features, connect power lines, generate power line distribution maps, and build a pole tower information database corresponding to each power line. Conductor feature recognition and power line connection ensure the accuracy and completeness of pole tower information and help form a complete power line topology. Specifically:

[0099] Step S31, identifying the features of the wire from the panoramic satellite image of the tower, using image processing technology and algorithms to identify the features of the wire connected to the tower from the satellite image, including the direction, thickness, color contrast and other visual features of the wire; by comparing and analyzing these features, the position of the wire in the satellite image can be accurately identified;

[0100] Step S32, after identifying the wire features, it is necessary to connect the identified wires to form a complete power line; starting from the identified wire starting point, trace along the direction of the wire, connect adjacent wire segments, and form a continuous wire path; associate the wire path with the identified tower position to ensure that each wire is connected to the corresponding tower; construct the topological structure of the power line according to the wire path and the tower position, and generate a power line distribution map; the power line distribution map is used to show the location, direction and connection relationship of all power lines with the tower; mark the name, number and other information of each power line on the power line distribution map for subsequent management and verification;

[0101] Step S33: For each power line in the power line distribution map, a corresponding pole tower information database needs to be constructed for it; the pole tower information database contains detailed information on all pole towers on the power line, including the pole tower image recognition feature information identified in step S2, i.e., key information such as the center point coordinates, height, and type of the pole tower. At the same time, it ensures that the pole tower information of each power line matches the conductor path in the power line distribution map to form a complete power line topology structure; the purpose of constructing the pole tower information database is to subsequently match and verify the feature information recorded in the pole tower ledger, so as to identify potential errors or missing information.

[0102] In this step, through image processing technology and algorithms, the conductor features in the panoramic satellite images of pole towers, such as direction, thickness, color contrast, etc., can be accurately identified, so as to connect them into a complete power line and generate a detailed power line distribution map; at the same time, a corresponding pole tower information database is built for each power line to ensure the accuracy and completeness of the pole tower information, which helps to form a complete power line topology structure and provide a data basis for subsequent information matching and verification.

[0103] Step S4: for each pole tower in the pole tower information database, obtain the corresponding pole tower account record feature information, and match it with the pole tower image recognition feature information, mark the pole tower that successfully matches as a correct pole tower, and mark the pole tower that fails to match as an incorrect pole tower;

[0104] The purpose of step S4 is to compare the tower feature information identified from the satellite image with the existing tower record to identify and correct any errors or inconsistencies; the following is a detailed description of step S4:

[0105] Step S41, extracting the characteristic information of the ledger records of each tower from the tower ledger system of the power company, including key data such as the center point coordinates, height, and type of the tower;

[0106] Step S42, matching with the pole tower image recognition feature information:

[0107] Center point coordinate matching: Compare the center point coordinates in the tower ledger with the center point coordinates in the tower image recognition feature information, and calculate the distance error between the two; if the error is within the preset threshold range, the center point coordinate matching is considered successful;

[0108] Pole tower height matching: compare the pole tower height in the pole tower record with the pole tower height in the pole tower image recognition feature information; if the difference between the two is within the allowable error range, the height matching is considered successful;

[0109] Pole tower type matching: Check whether the pole tower type (such as steel tower, cement pole, etc.) in the pole tower ledger is consistent with the pole tower type in the pole tower image recognition feature information; if they are consistent, the pole tower type matching is successful;

[0110] Step S43: If the pole tower inventory record feature information matches the pole tower image recognition feature information in terms of center point coordinates, height and type, the pole tower is marked as a "correct pole tower"; if the match in any aspect is unsuccessful, the pole tower is marked as an "incorrect pole tower".

[0111] In this step, accurate verification of the tower information is achieved by comparing the characteristic information recorded in the tower inventory with the characteristic information of the tower image recognition. This not only takes into account quantitative data such as the center point coordinates and height, but also covers qualitative information such as the tower type to ensure the comprehensiveness and accuracy of the match. By marking the correct towers and the wrong towers, it helps to promptly discover and correct information inconsistencies or errors.

[0112] Step S5: for each power line, all wrong towers on the power line are checked twice by step-by-step span matching. If the check succeeds, the tower is corrected to a correct tower;

[0113] Step S5 is a key secondary verification step in the power tower ledger verification method, which aims to further verify and correct the towers marked as errors. The specific implementation is as follows:

[0114] Step S51, obtaining the corresponding table span of the correct tower; extracting the span information of each correct tower from the tower table, the span refers to the horizontal distance between two adjacent towers, and the span information is used to determine the search range to find and verify the adjacent wrongly marked towers;

[0115] Step S52, taking the first correct pole tower in the power line as a reference and the corresponding ledger span as a search range for searching; selecting the first correct pole tower in the power line as a reference; setting the search range according to the ledger span of the reference pole tower; for example, if the ledger span is 100 meters, the search range can be set to 100 meters; searching for adjacent pole towers within the search range, especially pole towers marked as errors;

[0116] Step S53, in response to the adjacent erroneous pole tower being within the search range, comparing the pole tower height check and the pole tower type in the pole tower image recognition feature information corresponding to the adjacent erroneous pole tower with the pole tower ledger record feature information;

[0117] Compare the height of the adjacent wrong tower in the tower image recognition feature information with the height in the tower ledger record feature information. If the difference between the two is within the allowable error range, the height verification is successful.

[0118] Compare the type in the pole tower image recognition feature information of the adjacent error pole tower with the type in the pole tower ledger record feature information to see if they are consistent. If they are consistent, the type verification is successful.

[0119] If the height and type verification are both successful, the adjacent wrong tower is corrected to a correct tower;

[0120] If the height or type check fails, the next correct tower in the power line is used as a new reference, and steps S52 and S53 are repeated until all towers in the power line are searched.

[0121] In this step, through step-by-step span matching, the record span of the correct tower is used as the search range to effectively narrow the verification range of the erroneous tower and improve the verification efficiency. At the same time, combined with the comparison of the tower image recognition feature information with the record feature information, dual verification of the height and type of the erroneous tower is achieved to ensure the accuracy of the verification. The search range and verification standard can be adjusted according to actual conditions, which is suitable for the verification requirements of different power lines and tower types.

[0122] Furthermore, considering possible blur or other factors that affect image clarity, the towers may appear in a certain size range on the image, so it is necessary to set a search error and use the known tower positions as reference points to verify and adjust the search error. The following is a specific adjustment method:

[0123] Acquire multiple known correct towers from the same power line as error adjustment reference points for adjusting the search error;

[0124] For each error adjustment reference point, extract the coordinates of the center point of the tower on the tower panoramic satellite image and the center point of the tower on the tower ledger information to form a reference point coordinate set corresponding to the error adjustment reference point; the reference point coordinate set is as follows:

[0125] ;

[0126] in, represents the coordinates of the center point of the tower of the ith error adjustment reference point on the tower panoramic satellite image, Represents the coordinates of the center point of the tower of the i-th error adjustment reference point in the tower ledger information;

[0127] Calculate the difference between the two reference point coordinate sets corresponding to any pair of adjacent error adjustment reference points to obtain the image distance vector and the ledger distance vector respectively; the image distance vector is obtained by calculating the difference between the coordinates of the center point of the tower of the two adjacent error adjustment reference points on the tower panoramic satellite image; the ledger distance vector is obtained by calculating the difference between the coordinates of the center point of the tower of the two adjacent error adjustment reference points on the tower ledger information; the image distance vector is expressed as:

[0128] ;

[0129] in, represents the coordinates of the center point of the tower of the i+1th error adjustment reference point on the tower panoramic satellite image, Indicates the coordinates of the center point of the tower of the i+1th error adjustment reference point in the tower ledger information;

[0130] The image distance vector and the ledger distance vector are subtracted to obtain the error vector, which consists of horizontal error and vertical error. The error vector is expressed as:

[0131] ;

[0132] in, represents the horizontal error, Indicates the vertical error;

[0133] Characteristic value extraction is performed on multiple error vectors to obtain the span search error used for secondary calibration.

[0134] In the above-mentioned error adjustment process, by introducing the known correct tower position as the error adjustment reference point, the error in the search process can be accurately evaluated and adjusted, which helps to improve the accuracy of searching and locating towers in satellite images and reduce false alarms and missed alarms; taking into account the possible size changes and clarity effects of towers in the image, by setting the search error and dynamically adjusting it, it can adapt to the tower search needs in different situations and enhance practicality and flexibility; by extracting the coordinates and calculating the difference of multiple error adjustment reference points, the search error can be systematically evaluated, which can not only find the problem of a single error point, but also reveal the distribution and trend of the overall error, providing a basis for further optimization; by extracting the eigenvalues ​​of multiple error vectors and obtaining the span search error used for secondary verification, the reliability of the search results can be further improved, which helps to further verify and adjust the results after the initial search to ensure the accuracy of the final positioning.

[0135] More specifically, the average value, standard deviation, etc. of multiple error vectors are calculated to count the eigenvalues; if the average value and standard deviation are close to 0, it means that the image and the ledger are matched as a whole, and the search error can be set to a smaller value, such as ±1 meter;

[0136] If the mean and standard deviation are large, it means that there is a large random error between the image and the ledger, and the search error needs to be set to a larger value, such as ±3 meters, to cover the possible error range;

[0137] If the mean and standard deviation are significantly different from 0, it means that there is a systematic offset between the image and the ledger, and the coordinate system of the image or ledger needs to be adjusted to eliminate this offset.

[0138] Step S6, conducting on-site verification of the pole tower information marked as an erroneous pole tower, and making corrections in the pole tower record book;

[0139] Step S6 is the final on-site verification and correction step, which aims to ensure that all tower information marked as erroneous is accurately corrected. The specific implementation is as follows:

[0140] Step S61: Form a professional field verification team, whose members should include experts and technicians who are familiar with the structure of power towers, ledger management, and field survey experience; prepare necessary measuring tools (such as rangefinders, altimeters, GPS locators, etc.), recording equipment (such as tablet computers, laptops, etc.) and safety equipment (such as helmets, safety belts, reflective clothing, etc.); assign field verification tasks to team members according to the number and distribution of faulty towers to ensure that each faulty tower has a dedicated person in charge;

[0141] Step S62: Use a GPS locator or other positioning tools to accurately find the actual location of each erroneous pole tower, and compare it with the satellite remote sensing image to confirm whether its location is consistent; use measurement tools to measure key information such as the height, type, and material of the pole tower on the spot, and record relevant data; observe the environment around the pole tower, including terrain, vegetation, other facilities, etc., to evaluate its impact on the pole tower information;

[0142] Step S63: compare the data measured on site with the records in the tower ledger to find out the differences and errors; analyze the causes of the errors in the ledger information, such as construction errors, untimely information updates, changes in the natural environment, etc.; evaluate the impact of the wrong tower on the safe and stable operation of the power grid, and determine whether it is necessary to repair or adjust it immediately;

[0143] Step S64: According to the results of the field survey and data comparison, the erroneous information in the tower ledger is corrected, including the tower location, height, type, etc.; the date, personnel, measurement data and corrected information of the field verification are recorded in the ledger to ensure the integrity and traceability of the ledger; the corrected ledger information is promptly notified to the operation and maintenance personnel, management personnel and other relevant parties to ensure that they have the latest tower information;

[0144] Step S65: Regularly track and monitor the corrected towers to ensure that they are in a stable state and meet the grid operation requirements; establish a feedback mechanism to encourage operation and maintenance personnel and other relevant personnel to find problems when using the ledger and report them in a timely manner for further correction and optimization.

[0145] Through the on-site verification and ledger correction in step S6, the accuracy and completeness of the tower ledger information can be ensured, providing a strong guarantee for the safe and stable operation of the power system and helping to improve the operation and maintenance management level of the power company.

[0146] Embodiment 2: Figure 3 As shown, a power tower inventory verification system of the present invention specifically includes the following modules:

[0147] A satellite image processing module is used to obtain multiple sets of satellite remote sensing images in the area to be verified, and perform image processing on the multiple sets of satellite remote sensing images to obtain panoramic satellite images of the towers in the area to be verified;

[0148] The tower feature recognition module is used to perform tower feature recognition on the tower panoramic satellite image and extract the tower image recognition feature information of all towers in the area to be verified, including the coordinates of the tower center point, tower height and tower type;

[0149] The power line construction module performs conductor feature recognition on the panoramic satellite image of the tower based on the pole tower image recognition feature information, and connects the power lines according to the conductor feature recognition results to obtain the power line distribution map in the area to be verified; and for each power line in the power line distribution map, a corresponding tower information database is constructed;

[0150] The pole tower information matching module obtains the pole tower ledger record feature information corresponding to each pole tower in the pole tower information database, and matches the pole tower ledger record feature information with the pole tower image recognition feature information; marks the pole tower that successfully matches as a correct pole tower, and marks the pole tower that fails to match as an incorrect pole tower;

[0151] The step-by-step span matching verification module uses the step-by-step span matching method to perform a secondary verification on all incorrect towers on each power line. If the verification is successful, it will be corrected to the correct tower.

[0152] The ledger correction module conducts on-site verification of the tower information marked as erroneous towers and makes corrections in the tower ledger.

[0153] In this embodiment, the system realizes the automated process of power tower ledger verification through modules such as satellite image processing, tower feature recognition, and power line construction, thereby improving verification efficiency, reducing manual intervention, and reducing labor intensity; the system uses image processing and feature recognition technology to accurately extract tower image recognition feature information and accurately match it with the tower ledger record feature information, thereby effectively identifying erroneous towers and improving the accuracy of ledger information; the system can verify all towers in the verification area, regardless of the number and distribution of towers, to ensure that no tower is missed, and improve the integrity of ledger information; the system uses a step-by-step span matching method to perform secondary verification of erroneous towers, and can flexibly adjust the verification strategy according to actual conditions to improve the flexibility and adaptability of verification; the erroneous tower information is verified on-site through the ledger correction module and corrected in the ledger, and the tower ledger information can be updated in real time to ensure the timeliness and accuracy of the ledger information; accurate tower ledger information helps operation and maintenance personnel to timely understand the power grid architecture and equipment status, timely discover and solve potential safety risks, reduce power grid operation risks, and improve the reliability and stability of the power system.

[0154] The various variations and specific embodiments of the power pole tower inventory verification method in the aforementioned embodiment 1 are also applicable to the power pole tower inventory verification system of this embodiment. Through the aforementioned detailed description of the power pole tower inventory verification method, those skilled in the art can clearly know the implementation method of the power pole tower inventory verification system in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0155] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0156] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for checking the inventory of power towers, characterized in that: The method comprises: Acquire multiple sets of satellite remote sensing images in the area to be verified, and perform image processing to obtain panoramic satellite images of the towers in the area to be verified; Perform tower feature recognition on the tower panoramic satellite image to obtain tower image recognition feature information, including the tower center point coordinates, tower height and tower type; Based on the pole tower image recognition feature information, the conductor feature recognition is performed on the pole tower panoramic satellite image, and the power line connection is performed based on the recognition result to obtain the power line distribution map; for each power line in the map, a pole tower information database is constructed; For each pole in the pole information database, obtain the pole record record feature information, and match it with the pole image recognition feature information, and mark the successfully matched pole as a correct pole, otherwise, mark it as an incorrect pole; For each power line, all wrong towers are checked twice using step-by-step span matching. If the check succeeds, they are corrected to the correct towers. Conduct on-site verification of the tower information marked as incorrect towers and make corrections in the tower records; Secondary verification, including: Get the correct span corresponding to the tower; Take the first correct tower as the benchmark and the corresponding table span as the search range; In response to the adjacent erroneous pole tower being within the search range, the pole tower height check and the pole tower type in the pole tower image recognition feature information corresponding to the adjacent erroneous pole tower are compared with the pole tower ledger record feature information; if the comparison is successful, it is corrected to the correct pole tower; otherwise, the next correct pole tower in the power line is used as a reference and the search is performed again until all the towers are searched.

2. A method for checking the electric power tower account book according to claim 1, characterized in that: When searching with the corresponding ledger span as the search range, a span search error is set to take into account factors affecting image clarity, which may cause size errors of the tower in the image.

3. A method for checking the electric power tower account as claimed in claim 2, characterized in that: The method for setting the span search error comprises: Acquire multiple known correct towers from the same power line as error adjustment reference points for adjusting the search error; For each error adjustment reference point, extract the coordinates of the center point of the tower on the tower panoramic satellite image and the coordinates of the center point of the tower on the tower ledger information to form a reference point coordinate set corresponding to the error adjustment reference point; Calculate the difference between the two reference point coordinate sets corresponding to any pair of adjacent error adjustment reference points to obtain the image distance vector and the ledger distance vector respectively; Subtract the image distance vector from the record distance vector to obtain an error vector; Characteristic value extraction is performed on multiple error vectors to obtain the span search error used for secondary calibration.

4. A method for checking the electric power tower account as claimed in claim 3, characterized in that: The image distance vector is obtained by calculating the difference between the coordinates of the center point of the tower of two adjacent error adjustment reference points on the panoramic satellite image of the tower; The record distance vector is obtained by calculating the difference between the coordinates of the center points of the towers of two adjacent error adjustment reference points on the tower record information; The image distance vector is expressed as: ； in, represents the coordinates of the center point of the tower of the ith error adjustment reference point on the tower panoramic satellite image, Represents the coordinates of the center point of the tower of the i-th error adjustment reference point in the tower ledger information; represents the coordinates of the center point of the tower of the i+1th error adjustment reference point on the tower panoramic satellite image, Represents the coordinates of the center point of the tower of the i+1th error adjustment reference point in the tower inventory information.

5. A method for checking the electric power tower account book as claimed in claim 4, characterized in that: The error vector is composed of horizontal error and vertical error; the error vector is expressed as: ； in, represents the horizontal error, Indicates the vertical error.

6. A method for checking the electric power tower account as claimed in claim 1, characterized in that: Based on the pole tower image recognition feature information, the conductor feature recognition is performed on the pole tower panoramic satellite image, and the power line connection is performed based on the conductor feature recognition result to obtain the power line distribution map in the area to be verified, including: Identify conductor features from panoramic satellite images of pole towers, including conductor direction, thickness and color contrast; Starting from the identified wire starting point, trace along the wire direction, connect adjacent wire segments, and form a continuous wire path; Associating the conductor paths with the identified tower locations so that each conductor segment can be connected to the corresponding tower; According to the conductor path and tower location, the topological structure of the power line is constructed and the power line distribution map is generated.

7. A power tower inventory verification system, characterized in that: The system is applied to the power tower inventory verification method according to claim 1, and the system comprises: A satellite image processing module is used to obtain multiple sets of satellite remote sensing images in the area to be verified, and perform image processing on the multiple sets of satellite remote sensing images to obtain panoramic satellite images of the towers in the area to be verified; The tower feature recognition module is used to perform tower feature recognition on the tower panoramic satellite image and extract the tower image recognition feature information of all towers in the area to be verified, including the coordinates of the tower center point, tower height and tower type; The power line construction module performs conductor feature recognition on the panoramic satellite image of the tower based on the pole tower image recognition feature information, and connects the power lines according to the conductor feature recognition results to obtain the power line distribution map in the area to be verified; and for each power line in the power line distribution map, a corresponding tower information database is constructed; The pole tower information matching module obtains the pole tower ledger record feature information corresponding to each pole tower in the pole tower information database, and matches the pole tower ledger record feature information with the pole tower image recognition feature information; marks the pole tower that successfully matches as a correct pole tower, and marks the pole tower that fails to match as an incorrect pole tower; The step-by-step span matching verification module uses the step-by-step span matching method to perform a secondary verification on all incorrect towers on each power line. If the verification is successful, it will be corrected to the correct tower. The ledger correction module conducts on-site verification of the tower information marked as erroneous towers and makes corrections in the tower ledger.

8. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps in the method according to any one of claims 1 to 6 are implemented.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 6 are implemented.

Images