Electric power facility ledger data calibration method, system and device and storage medium

Abstract

The invention relates to an electric power facility ledger data calibration method, system and device and a storage medium, and the method comprises the steps: controlling an unmanned plane to fly according to a planned route, and collecting a target inclined image and navigation data of an electric power facility; the collected inclined image is processed, and an electric power facility target and pixel coordinates of the target in the inclined image are identified; resolving to obtain a target three-dimensional coordinate of the electric power facility; importing a GIS platform to calculate the error between the three-dimensional coordinate of the electric power facility target and the initial coordinate in the machine account data; synchronously updating the corrected target position data of the electric power facility into a machine account database; and outputting a report containing the accurate three-dimensional coordinates of the electric power facility target and the machine account updating information.

Description

Technical Field

[0001] The present invention relates to the field of target positioning technology, and in particular to a method, system, device and storage medium for calibrating electric power facility ledger data. Background Art

[0002] As the power facility network continues to expand, the location of power facilities in geographic space and their characteristic data are becoming more and more complex. Traditional power facility location measurement and management methods mainly rely on manual measurement and ground control points, which is not only time-consuming and labor-intensive, but also difficult to cope with the precise measurement needs of large-scale areas.

[0003] In recent years, drones equipped with high-precision sensors (such as GPS and IMU) have been used to collect aerial images. GPS (Global Positioning System) and IMU (Inertial Measurement Unit) are two commonly used positioning and navigation technologies. Combined with artificial intelligence (AI) target recognition technology, it has become a new solution.

[0004] For example, the patent announcement number CN108801225B discloses a method, system, medium and device for positioning oblique images of unmanned aerial vehicles. It obtains the POS information of the oblique images of unmanned aerial vehicles; uses the POS information to locate the oblique images of unmanned aerial vehicles to obtain the first position coordinates; uses the stereo satellite image to extract the second position coordinates of the ground control point; uses the second position coordinates to optimize the first position coordinates to obtain the third position coordinates of the oblique images of unmanned aerial vehicles. It can greatly reduce the measurement cost when positioning the oblique images of unmanned aerial vehicles;

[0005] This method has problems such as insufficient accuracy in identifying the location of power facilities in complex environments, the inability to accurately correspond image data to geographic coordinates, and deviations from the original ledger data.

[0006] For example, the patent publication number CN118896593A discloses a "target positioning method based on oblique photography of unmanned aerial vehicles". By building a target detection model based on a neural network, the Swin-Transformer block module is introduced to enhance the feature extraction and fusion capabilities. The mapping relationship between pixel coordinates, image plane coordinates and geographic coordinates is established by combining information such as the state parameters of the unmanned aerial vehicle, the internal parameters of the camera, and the UTM projection / Gauss-Krüger projection, so as to realize the conversion of the target positioning results from the relative coordinates in the field of computer vision to practical geographic coordinates.

[0007] This method can only obtain the longitude and latitude coordinate information of the ground object, but cannot obtain the elevation information of the ground object. For power grid inspection application scenarios, power grid equipment (such as poles, wires, substations, etc.) are often distributed at different elevations, and longitude and latitude alone cannot reflect the actual spatial position of the equipment.

[0008] Therefore, how to achieve high-precision calculation of the location and height of power facilities, and effectively match and correct them with the line corridor inventory data, has become a technical problem that needs to be solved urgently. Summary of the invention

[0009] In view of the deficiencies in the prior art, the present invention provides a method, system, device and storage medium for calibrating electric power facility inventory data to solve the above problems.

[0010] The present invention provides the following technical solutions:

[0011] A method for updating the three-dimensional position of electric power facilities and calibrating the topological data of ledgers comprises the following steps:

[0012] Plan the flight path of the drone, which covers the area where the power facilities are located;

[0013] Control the drone to fly according to the planned route and collect target images and navigation data of power facilities;

[0014] Process the collected images to identify the power facility target and the pixel coordinates of the target in the image;

[0015] Combining pixel coordinates and navigation data, the three-dimensional coordinates of the power facility target are calculated;

[0016] Import the three-dimensional coordinates of the power facilities into the GIS platform, select the corresponding ledger data according to the identified power facilities, and calculate the error between the three-dimensional coordinates of the power facilities and the initial coordinates in the ledger data;

[0017] If the error is within the allowable error range, the solved coordinates are used to replace the coordinate data in the original ledger; if the error exceeds the allowable error, correction is performed; and the corrected power facility location data is synchronously updated to the ledger database.

[0018] Preferably, the heading overlap of the flight routes is above 50%.

[0019] Preferably, after image acquisition, the acquired oblique image is processed by an AI target recognition algorithm to automatically identify the target of the power facility and mark the corresponding bounding box. By analyzing the target information in the image, the pixel coordinates of the target in the image are extracted.

[0020] Preferably, the drone simultaneously collects oblique images of the power facilities through the high-resolution oblique photography camera it carries, and records the navigation data during shooting through the high-precision GPS and IMU system.

[0021] Preferably, the pixel coordinates of the power facility are converted into coordinates in the camera coordinate system by combining the internal and external parameters of the high-resolution oblique photography camera and the geographic reference information.

[0022] Preferably, based on the navigation data of the UAV, direct geolocation technology is used to convert the coordinates in the camera coordinate system into the coordinates in the earth coordinate system; and the ground elevation information is obtained through a digital elevation model.

[0023] Preferably, after the three-dimensional coordinates of the power facilities are imported into the GIS platform, the solved three-dimensional coordinates of the power facilities are superimposed on the initial coordinates in the ledger data, and a visual comparison is performed using GIS tools to check the differences between the two sets of data.

[0024] Preferably, the difference between the two sets of data is calculated by a nearest neighbor analysis method, the data points with larger errors are identified, and it is confirmed whether the error is within a set tolerance range.

[0025] Preferably, the collected power facility images include orthophotos and oblique images.

[0026] A power facility ledger data calibration system, comprising:

[0027] UAV data acquisition module, used for flight control, image data acquisition and location information recording;

[0028] The data processing and analysis module is used to perform three-dimensional reconstruction and position calculation on the collected image data and position information;

[0029] GIS correction and analysis module, which uses the GIS platform to perform data overlay, error detection and topological relationship analysis to identify and correct spatial errors of power facilities;

[0030] The data update and storage module is used to synchronize the corrected data to the power facility ledger database.

[0031] After image acquisition, the collected oblique images are processed using an AI target recognition algorithm to automatically identify the targets of the power facilities and mark the corresponding bounding boxes. By analyzing the target information in the image, the pixel coordinates of the target in the image are extracted.

[0032] Preferably, the drone simultaneously collects oblique images of the power facilities through a high-resolution oblique photography camera carried by the drone, and records navigation data during shooting through a high-precision GPS and IMU system;

[0033] Combining the internal and external parameters of the high-resolution oblique photography camera and the geographic reference information, the pixel coordinates of the power facility are converted into coordinates in the camera coordinate system;

[0034] According to the navigation data of the UAV, the direct geo-positioning technology is used to convert the coordinates in the camera coordinate system into the coordinates in the earth coordinate system; the ground elevation information is obtained through the digital elevation model.

[0035] Preferably, after the three-dimensional coordinates of the power facility are imported into the GIS platform, the three-dimensional coordinates of the power facility obtained by calculation are superimposed on the initial coordinates in the ledger data, and a visual comparison is performed using GIS tools to check the difference between the two sets of data;

[0036] The nearest neighbor analysis method is used to calculate the difference between two sets of data, identify data points with large errors, and confirm whether the error is within the set tolerance range.

[0037] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, a method for calibrating electric power facility inventory data is implemented.

[0038] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method for calibrating electric power facility inventory data.

[0039] The present invention has the following beneficial technical effects:

[0040] The present invention uses orthophoto data and supplementary oblique image data, combined with the high-precision navigation system of the unmanned aerial vehicle, to calculate the geographical location and altitude of the power facilities and match them with the existing ledger data; it further improves the accuracy of the target location data of the power facilities, and provides reliable technical support for the planning, maintenance and management of the power facility targets.

[0041] The oblique image data is collected by drones, the target is located based on high-precision positioning and attitude information, and the digital elevation model is combined to calculate accurate three-dimensional coordinates. The power facility target is automatically identified through the AI ​​algorithm, and the conversion from the image pixel coordinates to the ground real geographic coordinates is implemented in combination with the drone's positioning system and the internal and external parameters of the camera, thereby achieving accurate spatial positioning and elevation measurement of the power facility. This method can overcome the dependence on traditional ground control points and ensure that high-precision three-dimensional positioning can still be achieved in complex terrain and occlusion conditions.

[0042] Through this method, the coordinate data in the power facility ledger is automatically updated, the spatial error of the power facility is corrected, and the consistency and accuracy of the power facility ledger data and the actual geographical location are ensured, thereby providing efficient and accurate data support for power grid inspection, maintenance and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] Example:

[0046] A method for updating the three-dimensional position of power facilities and calibrating the topological data of the ledger, such as Figure 1 As shown:

[0047] Method for calculating the location of power facilities based on orthophoto data:

[0048] Currently, after being processed by the AI ​​target recognition algorithm, the power facility targets in the orthophoto data are identified and marked, and the bounding box of the power facility or other forms of location marks are usually output. The precise location of the power facility marker point has not yet been obtained, and further processing is required to obtain the precise coordinates of the power facility marker point. According to the geographic reference information of the image, the pixel position of the target can be converted into actual geographic coordinates or projection coordinates. Existing GIS processing software and algorithms can easily and accurately perform automated conversion to obtain the latitude and longitude coordinate information of the power facility marker point.

[0049] Method for calculating the location of blocked power facilities based on oblique image data:

[0050] Based on the oblique image data collected by the UAV, the direct geolocation method is used to solve the location of the power facilities. Direct geolocation is the process of directly determining the geographical location of pixels on aerial images without the need for ground control points. This method relies on the high-precision navigation and positioning equipment carried by the UAV. During the flight, the surface image and the corresponding navigation data (navigation data includes GPS location information and IMU information) are collected simultaneously; GPS is used to record the precise geographical location when each picture is taken, and IMU records the aircraft attitude when the image is taken, including pitch angle, roll angle and yaw angle. Combined with the internal parameters of the camera, including focal length, principal point offset, pixel size, etc., the pixel coordinates on the image are converted to points in the camera coordinate system with the camera optical center as the origin. Using the attitude information (pitch, roll, yaw) provided by the IMU, the above-obtained coordinates are converted from the camera coordinate system to the aircraft coordinate system. Using GPS data, the above-obtained points in the aircraft coordinate system are converted to the longitude and latitude positions in the earth coordinate system (such as WGS-84). Height information is adjusted using a digital elevation model (DEM) to account for actual elevation changes on the ground, ensuring that the final geographic coordinates reflect the true ground location.

[0051] Supplementary data collection for calculating the height of power facilities:

[0052] Select images of power facilities taken from two or more different locations to ensure that there is enough overlap between the two images (more than 60%). Extract feature points from each image, such as the top of the tower, cross arm, etc. Find the corresponding feature points in the stereo image pair, and use the triangulation principle to calculate the spatial position of the feature points based on the position difference (parallax) of the matching feature points in the two images. Using the known camera parameters, accurately calculate the position and posture of the camera, perform accurate spatial stereoscopic solution, obtain the three-dimensional coordinates of the power facility landmarks, and combine the DEM data of the power facility location to obtain the height difference, that is, the height of the power facility.

[0053] The pixel position on each image can be converted to the camera coordinate system through the camera's internal parameters (such as focal length, principal point offset, pixel size, etc.). Assume that the coordinates of a pixel on the image are (u, v) and the camera's internal parameter matrix is ​​K. The conversion formula from pixel coordinates to camera coordinate system is:

[0054]

[0055] Where K is the camera intrinsic parameter matrix;

[0056]

[0057] f x and f y is the focal length of the camera in the horizontal and vertical directions, c x and cy is the camera's principal point offset.

[0058] Using the attitude information (pitch angle θ, roll angle φ, yaw angle ψ) in the IMU data, the coordinates in the camera coordinate system are transformed to the aircraft coordinate system; assuming that the rotation matrix from the camera coordinate system to the aircraft coordinate system is R, the conversion formula is:

[0059]

[0060] The rotation matrix R is based on the attitude information of the IMU and can be obtained in the following way:

[0061] R=R z (ψ)·R y (θ)·R x (φ)

[0062] Among them, R z (ψ), R y (θ) and R x (φ) are the rotation matrices around the Z, Y, and X axes, respectively, as follows:

[0063]

[0064] Using the geographic location information in the GPS data and the point in the aircraft coordinate system, the coordinates of the aircraft are converted to the earth coordinate system (such as WGS-84); assuming that the point in the aircraft coordinate system is (X f ,Y f ,Z f ), the GPS position of the aircraft is (longitude, latitude and altitude in the Earth coordinate system), using the Earth ellipsoid model, geographic coordinates Convert to the coordinates (X ecef,0 ,Y ecef,0 ,Z ecef,0 ), the conversion formula is:

[0065]

[0066] Where a is the semi-major axis of the Earth, e is the eccentricity of the Earth, and λ0 are the latitude and longitude of the geographical coordinates, h0 is the altitude of the aircraft;

[0067] The rotation matrix R from the aircraft coordinate system to the geocentric coordinate system gps , the point (X f ,Y f ,Z f ) to the geocentric coordinate system:

[0068]

[0069] in, It is the geocentric coordinate corresponding to the GPS position of the aircraft.

[0070] Finally, by using the coordinates in the geocentric coordinate system (X ecef ,Y ecef ,Z ecef ) is converted back to the geographic coordinate system (latitude, longitude and altitude), and the inverse conversion formula is used to finally obtain the geographic coordinates corresponding to the pixels on the image.

[0071] λ=atan2(Y ecef ,X ecef )

[0072]

[0073] Preferably, the ground elevation is adjusted by a digital elevation model to ensure that the calculated height information reflects the actual ground elevation.

[0074] Assume that the ground elevation obtained by DEM is h DEM , then the final height h final The adjustment formula is:

[0075] h final =h GPS -h DEM .

[0076] Power facility ledger topology data matching and calibration method:

[0077] GIS (Geographic Information System) platform is a tool for capturing, storing, analyzing, managing and visualizing geospatial data. In the GIS platform, the solved power facility coordinate data and the initial coordinate data in the ledger are layered, and the visual comparison function of the GIS tool is used to check the position difference between the two sets of coordinates and preliminarily identify possible errors and deviations. The solved power facility coordinates are matched with the initial coordinates using the nearest neighbor analysis tool to determine the closest correspondence between them. The core of the nearest neighbor analysis is to calculate the distance measurement between points in space to determine the relative closeness of a point to other points. These distance measurements include but are not limited to Euclidean distance (straight-line distance) and Manhattan distance (grid distance); for ledger data matching correction, firstly, according to the specific category of the power facility identified by the target, the corresponding ledger data is automatically screened for nearest neighbor analysis, and the distance error between the matched coordinate pairs is calculated. Based on the results of the error analysis, the original initial power facility coordinates are adjusted. If the error is systematically within the set range, the solved coordinates are considered to match the initial coordinates, and the solved coordinates are used to replace the initial coordinates to obtain more accurate ledger data for future planning, maintenance and management work.

[0078] The system has the following modules:

[0079] UAV data collection module: responsible for the UAV’s route planning, flight control, image data collection and location information recording.

[0080] Data processing and analysis module: responsible for image processing, target recognition, three-dimensional reconstruction and position calculation to ensure the three-dimensional spatial positioning of the target facility.

[0081] GIS correction and analysis module: Through the GIS platform, data overlay, error detection and topological relationship analysis are performed to automatically identify and correct spatial errors of power facilities.

[0082] Data update and storage module: synchronize the corrected data to the power facility ledger database and generate an update log to ensure timely updating and accurate storage of data.

[0083] Step 1: Pre-flight inspection and route planning

[0084] Before the drone flies, the operator conducts a comprehensive inspection of the flight equipment to ensure that the equipment is in normal condition. Then, the flight route of the drone is planned using geographic information system (GIS) software. The route covers the area where the target power facilities (such as power towers) are located, ensuring that the image acquisition area covers the entire target facility and setting a reasonable overlap interval (such as more than 50%) in the flight path.

[0085] Step 2: Data Collection

[0086] The drone flies along the planned route, using the high-resolution oblique camera to collect orthophotos, oblique images and POS positioning data of the target power facilities. The high-precision GPS and IMU systems carried by the drone record the geographic location (latitude and longitude) and the attitude of the aircraft (pitch angle, roll angle, yaw angle) when each frame of the image is taken. These data will be recorded synchronously and used for geometric correction of subsequent images.

[0087] Step 3: Image processing and object recognition

[0088] After the image is collected, the AI ​​target recognition algorithm is first used to process the collected oblique image, automatically identify the target of the power facility (such as towers, lines, etc.), and mark the corresponding bounding box. By analyzing the target information in the image, the spatial position of the power facility is extracted. At this time, the system outputs the pixel coordinates of the target in the image.

[0089] Step 4: 3D reconstruction and position calculation

[0090] The system converts the pixel coordinates of the target into coordinates in the camera coordinate system by combining the internal and external parameters of the camera (focal length, principal point offset, etc.), the pixel coordinates of the image and the geographic reference information. Based on the positioning information (GPS data) and attitude information (IMU data) of the drone, the system uses direct geolocation technology to convert the coordinates in the camera coordinate system into longitude and latitude coordinates on the ground. The system also obtains ground elevation information through the digital elevation model (DEM) and adjusts the height of the target to ensure that the target position reflects the actual ground conditions.

[0091] Step 5: GIS data correction and error analysis

[0092] Import the solved three-dimensional coordinate data of the power facilities (including longitude, latitude and elevation) into the GIS platform. First, the corresponding ledger data is automatically screened out through the target identified power facility category, and the solved coordinates are layered with the initial coordinates in the ledger data. GIS tools are used for visual comparison to check the differences between the two sets of data. The system calculates the error between the solved coordinates and the initial coordinates through the nearest neighbor analysis method, automatically identifies data points with large errors, and confirms whether the error is within the set tolerance range (for example, 3 meters).

[0093] Step 6: Coordinate adjustment and ledger update

[0094] Based on the error analysis, if the difference between the solution result and the ledger data is within the allowable error range (such as 3 meters), the solution coordinates are considered to match the initial coordinates, and the system will automatically replace the coordinate data in the original ledger. For data points with large errors, manual intervention is required for correction. The corrected power facility location data will be synchronously updated to the ledger database, and an update log will be generated to ensure the accuracy and timeliness of data storage.

[0095] Step 7: System output and result verification

[0096] The system ultimately outputs a report containing the precise three-dimensional coordinates (latitude, longitude, elevation) of the power facility and updated ledger information. The data in the report will be used for maintenance, management, and planning of power facilities. Operators can use the updated ledger data for subsequent facility inspections, maintenance, or expansions.

[0097] The above-mentioned embodiments only express the specific implementation of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A method for calibrating electric power facility ledger data, characterized in that: The following steps are involved: Plan the flight path of the drone, which covers the area where the power facilities are located; Control the drone to fly according to the planned route and collect target images and navigation data of power facilities; Process the collected images to identify the power facility target and the pixel coordinates of the target in the image; Combining pixel coordinates and navigation data, the three-dimensional coordinates of the power facility target are calculated; Import the three-dimensional coordinates of the power facilities into the GIS platform, select the corresponding ledger data according to the identified power facilities, and calculate the error between the three-dimensional coordinates of the power facilities and the initial coordinates in the ledger data; If the error is within the allowable error range, the solved coordinates are used to replace the coordinate data in the original ledger; if the error exceeds the allowable error, correction is performed; and the corrected power facility location data is synchronously updated to the ledger database.

2. A method for calibrating electric power facility ledger data according to claim 1, characterized in that: After image acquisition, the collected oblique images are processed using an AI target recognition algorithm to automatically identify the targets of the power facilities and mark the corresponding bounding boxes. By analyzing the target information in the image, the pixel coordinates of the target in the image are extracted.

3. A method for calibrating electric power facility ledger data according to claim 1, characterized in that: The drone uses a high-resolution oblique camera to simultaneously collect oblique images of power facilities and uses a high-precision GPS and IMU system to record navigation data during shooting; Combining the internal and external parameters of the high-resolution oblique photography camera and the geographic reference information, the pixel coordinates of the power facility are converted into coordinates in the camera coordinate system; According to the navigation data of the UAV, the direct geo-positioning technology is used to convert the coordinates in the camera coordinate system into the coordinates in the earth coordinate system; the ground elevation information is obtained through the digital elevation model.

4. A method for calibrating electric power facility ledger data according to claim 1, characterized in that: After the three-dimensional coordinates of the power facilities are imported into the GIS platform, the three-dimensional coordinates of the power facilities are solved and superimposed with the initial coordinates in the ledger data. GIS tools are used for visual comparison to check the differences between the two sets of data. The nearest neighbor analysis method is used to calculate the difference between two sets of data, identify data points with large errors, and confirm whether the error is within the set tolerance range.

5. A power facility ledger data calibration system, characterized in that: include: UAV data acquisition module, used for flight control, image data acquisition and location information recording; The data processing and analysis module is used to perform three-dimensional reconstruction and position calculation on the collected image data and position information; GIS correction and analysis module, which uses the GIS platform to perform data overlay, error detection and topological relationship analysis to identify and correct spatial errors of power facilities; The data update and storage module is used to synchronize the corrected data to the power facility ledger database.

6. A power facility ledger data calibration system according to claim 5, characterized in that: After image acquisition, the collected oblique images are processed using an AI target recognition algorithm to automatically identify the targets of the power facilities and mark the corresponding bounding boxes. By analyzing the target information in the image, the pixel coordinates of the target in the image are extracted.

7. A power facility ledger data calibration system according to claim 6, characterized in that: The drone uses a high-resolution oblique camera to simultaneously collect oblique images of power facilities and uses a high-precision GPS and IMU system to record navigation data during shooting; Combining the internal and external parameters of the high-resolution oblique photography camera and the geographic reference information, the pixel coordinates of the power facility are converted into coordinates in the camera coordinate system; According to the navigation data of the UAV, the direct geo-positioning technology is used to convert the coordinates in the camera coordinate system into the coordinates in the earth coordinate system; the ground elevation information is obtained through the digital elevation model.

8. The electric power facility ledger data calibration system according to claim 7, characterized in that: After the three-dimensional coordinates of the power facilities are imported into the GIS platform, the three-dimensional coordinates of the power facilities are solved and superimposed with the initial coordinates in the ledger data. GIS tools are used for visual comparison to check the differences between the two sets of data. The nearest neighbor analysis method is used to calculate the difference between two sets of data, identify data points with large errors, and confirm whether the error is within the set tolerance range.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, it implements a method for calibrating electric power facility inventory data as described in any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, it implements a method for calibrating electric power facility inventory data as described in any one of claims 1 to 4.

Images