Overhead distribution line completion acceptance method based on multi-view solution rapid space reconstruction

Abstract

The invention discloses an overhead distribution line completion acceptance method based on multi-view solution and fast space reconstruction. The method comprises the steps of collecting a visible light image and image information of each base tower of an overhead distribution line to be accepted; a target detection algorithm is adopted to quickly identify and mark the pole tower, each power device and the key structure point in the visible light image, and an identification image is determined and comprises identification frames of the pole tower, each power device and the key structure point; performing spatial density clustering analysis on the spatial position of the recognition image to obtain a clustering result of each tower; based on the image information, carrying out multi-view solution and rapid spatial reconstruction on the clustering result of each tower to obtain spatial coordinate information of each tower; and according to the space coordinate information of each tower, determining the size information of the power equipment and the key structure points on the tower, and determining whether the power equipment has defects according to the size information.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) inspection for overhead distribution lines, and more specifically, to an acceptance method for overhead distribution line completion based on multi-view solution and rapid spatial reconstruction. Background Art

[0002] Facing the large-scale distribution network lines to be accepted and put into operation, the traditional manual acceptance method is difficult to meet the requirements of high-quality development of the distribution network under the new situation. Therefore, it is urgent to study a new acceptance method to improve the management level of overhead distribution line projects. UAVs have been widely used in the operation and maintenance of distribution networks due to their flexible and convenient advantages, and the application of UAVs in the field of completion acceptance has been gradually explored. In 2023, the company carried out UAV acceptance for more than 7,600 kilometers of lines and more than 95,000 poles. Through the visible light cameras mounted on UAVs, construction process quality problems at the top of poles can be found, which to a certain extent solves the problems of difficult defect detection and live operation of lines in the traditional manual acceptance method. However, the current application still faces some technical bottlenecks. For the same type of equipment in visible light images, due to the weak feature differences, it is difficult to compare multiple images and perform duplicate removal statistics; at the same time, due to the lack of necessary reference information in visible light monocular imaging, the ranging accuracy is affected to a certain extent. In addition, although the laser point cloud data provides rich three-dimensional information, the data redundancy is high and there is a lack of intuitive visible light information, resulting in low efficiency in quickly identifying and classifying equipment. These problems limit the application effects of UAVs in aspects such as accurate statistics of the engineering quantities that are the focus of completion acceptance, precise and efficient construction of line homologous data, and accurate verification of typical electrical distances during construction. Summary of the Invention

[0003] In view of the deficiencies of the prior art, the present invention provides an acceptance method for overhead distribution line completion based on multi-view solution and rapid spatial reconstruction.

[0004] According to one aspect of the present invention, there is provided an acceptance method for overhead distribution line completion based on multi-view solution and rapid spatial reconstruction, including:

[0005] Collect visible light images and image information of each pole of the overhead distribution line to be accepted;

[0006] Use an object detection algorithm to quickly identify and mark the poles, various power equipment, and key structure points in the visible light images, and determine the recognition images, where the recognition images include the identification frames of the poles, various power equipment, and key structure points;

[0007] Perform spatial density clustering analysis on the spatial positions of the recognition images to obtain the clustering results of each pole;

[0008] Based on the image information, perform multi - perspective resolution and rapid spatial reconstruction on the clustering results of each pole tower to obtain the spatial coordinate information of each pole tower;

[0009] According to the spatial coordinate information of each pole tower, determine the dimensional information of the power equipment and key structure points on the pole tower, and determine whether there are defects in the power equipment according to the dimensional information.

[0010] Optionally, collect visible - light images of each pole tower of the overhead distribution line to be accepted, including:

[0011] Collect panoramic images of each pole tower of the overhead distribution line to be accepted;

[0012] Collect multi - perspective power - equipment images of each pole tower of the overhead distribution line to be accepted;

[0013] Determine the visible - light images according to the panoramic images and the multi - perspective power - equipment images.

[0014] Optionally, the power equipment on the pole tower includes: insulators, lightning arresters, primary - secondary integrated switches, circuit breakers, earthing switches, transformers, and integrated terminals;

[0015] The key structure points include: the top of the pole tower, the bottom of the pole tower, and the cross arms installed on the pole tower.

[0016] Optionally, perform spatial density clustering analysis on the spatial positions of the recognition images to obtain the clustering results of each pole tower, including:

[0017] According to the coordinate information of the pole tower, each power equipment, and the key structure points in the recognition images, use the spatial density clustering analysis algorithm for clustering to determine the clustering results of each pole tower.

[0018] Optionally, the image information includes UAV trajectory information, UAV direction information, and the attitude information of the UAV pan - tilt head. And based on the image information, perform multi - perspective resolution and rapid spatial reconstruction on the clustering results of each pole tower to obtain the spatial coordinate information of each pole tower, including:

[0019] Based on the image information, convert the coordinates of multiple images in the clustering results of each pole tower to determine the direction vector in the rectangular coordinate system;

[0020] Construct a rotation matrix according to the direction vector, and calculate the pan - tilt deflection vector according to the rotation matrix and the initial direction vector of the pan - tilt head;

[0021] Calculate the offset of the identification frame of each power equipment of the pole tower in multiple images from the pixel center respectively, and convert the offset into an imaging deflection vector in physical dimensions;

[0022] Determine the imaging curve deflection vector formed by the pan-tilt and imaging based on the pan-tilt deflection vector and the imaging deflection vector;

[0023] Calculate the intersection coordinates of the identification frames of the same power equipment in multiple images based on the curve deflection vector;

[0024] Determine the spatial coordinate information of each pole tower according to the set of intersection coordinates.

[0025]

[0026] The rotation matrix R is

[0027]

[0028] In the formula, V0 = (x0, y0, z0) is the initial direction vector of the pan-tilt; E a is the shooting point; x, y, z are spatial coordinates.

[0029] Optionally, the calculation formula for the offset is:

[0030]

[0031] In the formula, is the image imaging parameter, P mid = (x Amid , y Amid ) is the image pixel center point of the phase plane A; is the distance in the x direction, is the distance in the y direction;

[0032] The imaging deflection vector has the expression of where

[0033]

[0034] In the formula, a is the pixel size; is the offset in the x direction; is the offset in the y direction.

[0035] According to another aspect of the present invention, there is provided an overhead distribution line completion acceptance device based on multi-viewpoint solution for fast spatial reconstruction, including:

[0036] An acquisition module for acquiring visible light images and image information of each pole tower of the overhead distribution line to be accepted;

[0037] An identification module for quickly identifying and marking the pole towers, various power equipment, and key structure points in the visible light images by using a target detection algorithm to determine an identification image, where the identification image includes identification frames of the pole towers, various power equipment, and key structure points;

[0038] An analysis module for performing spatial density clustering analysis on the spatial position of the recognized image to obtain the clustering result of each tower.

[0039] A obtaining module for performing multi-view resolution and fast spatial reconstruction on the clustering result of each tower based on the image information to obtain the spatial coordinate information of each tower.

[0040] A determining module for determining the size information of the power equipment and key structural points on the tower according to the spatial coordinate information of each tower, and determining whether there are defects in the power equipment according to the size information.

[0041] According to another aspect of the present invention, there is provided a computer-readable storage medium storing a computer program for executing the method according to any one of the above aspects of the present invention.

[0042] According to another aspect of the present invention, there is provided an electronic device including: a processor; a memory for storing executable instructions of the processor; the processor for reading the executable instructions from the memory and executing the instructions to implement the method according to any one of the above aspects of the present invention.

[0043] The method for accepting an overhead distribution line by an unmanned aerial vehicle proposed by the present invention has the following effects:

[0044] 1) Effectively avoids the safety risks brought by manual tower climbing, significantly improves the operation efficiency, and ensures the safe and efficient progress of the acceptance work;

[0045] 2) Realizes the accurate settlement of the project quantity while accurately and autonomously reconstructing the topological homologous data of the line, significantly improving the digital-physical consistency of the line;

[0046] 3) Accurately measures the typical electrical distances during construction, effectively eliminates the possible technical blind spots during the line acceptance inspection, further improves the project quality, and provides a strong guarantee for the long-term stable operation of the line. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] By referring to the following drawings, the exemplary embodiments of the present invention can be more completely understood:

[0048] Figure 1 is a schematic flowchart of a method for accepting an overhead distribution line based on multi-view resolution and fast spatial reconstruction provided by an exemplary embodiment of the present invention;

[0049] Figure 2 is a schematic diagram of the principle of multi-view resolution and reconstruction provided by an exemplary embodiment of the present invention;

[0050] Figure 3 It is a schematic diagram of an acceptance system provided by an exemplary embodiment of the present invention;

[0051] Figure 4 It is a schematic diagram of image acquisition for the acceptance of an overhead distribution line by an unmanned aerial vehicle provided by an exemplary embodiment of the present invention;

[0052] Figure 5 It is a technical roadmap for the completion acceptance of an overhead distribution line based on multi-view solution and rapid spatial reconstruction provided by an exemplary embodiment of the present invention;

[0053] Figure 6 It is a principle framework diagram of device and defect target detection based on YOLO provided by an exemplary embodiment of the present invention;

[0054] Figure 7 It is a recognition result diagram of insulators and key structure points provided by an exemplary embodiment of the present invention;

[0055] Figure 8 It is a schematic diagram of the DBSCAN algorithm provided by an exemplary embodiment of the present invention;

[0056] Figure 9 It is a schematic diagram of a multi-view solution and rapid spatial reconstruction module provided by an exemplary embodiment of the present invention;

[0057] Figure 10 It is a schematic diagram of statistical items to be measured provided by an exemplary embodiment of the present invention;

[0058] Figure 11 It is a schematic diagram of true-type verification measurement provided by an exemplary embodiment of the present invention;

[0059] Figure 12 It is a structural schematic diagram of a device for the completion acceptance of an overhead distribution line based on multi-view solution and rapid spatial reconstruction provided by an exemplary embodiment of the present invention;

[0060] Figure 13 It is the structure of an electronic device provided by an exemplary embodiment of the present invention. Detailed implementation manners

[0061] Next, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited by the exemplary embodiments described herein.

[0062] It should be noted that: Unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present invention.

[0063] Those skilled in the art can understand that terms such as "first" and "second" in the embodiments of the present invention are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate an inevitable logical order between them.

[0064] It should also be understood that in the embodiments of the present invention, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more.

[0065] It should also be understood that for any component, data or structure mentioned in the embodiments of the present invention, in the absence of a clear definition or contrary disclosure in the context, it can generally be understood as one or more.

[0066] In addition, the term "and / or" in the present invention is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present invention generally represents an "or" relationship between the associated objects before and after.

[0067] It should also be understood that the present invention emphasizes the differences between various embodiments, and their similarities or similarities can be referred to each other. For the sake of brevity, they will not be elaborated one by one.

[0068] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn in actual proportional relationships.

[0069] The following description of at least one exemplary embodiment is actually merely illustrative and in no way limits the present invention and its application or use.

[0070] Techniques, methods and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the techniques, methods and devices should be regarded as part of the specification.

[0071] It should be noted that like reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0072] Embodiments of the present invention can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate together with many other general-purpose or special-purpose computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments including any of the above systems, and so on.

[0073] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system-executable instructions (such as program modules) executed by a computer system. Generally, program modules can include routines, programs, target programs, components, logics, data structures, etc., which perform specific tasks or implement specific abstract data types. The computer system / server can be implemented in a distributed cloud computing environment where tasks are executed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0074] Exemplary Method

[0075] Figure 1 is a schematic flowchart of an overhead distribution line acceptance inspection method based on multi-view solution and fast spatial reconstruction provided by an exemplary embodiment of the present invention. This embodiment can be applied to an electronic device, such as Figure 1 As shown, the overhead distribution line acceptance inspection method 100 based on multi-view solution and fast spatial reconstruction includes the following steps:

[0076] Step 101, collect visible light images and image information of each pole tower of the overhead distribution line to be accepted;

[0077] Step 102, use an object detection algorithm to quickly identify and mark the pole towers, various power equipment, and key structure points in the visible light image, and determine the recognition image, where the recognition image includes the identification frames of the pole towers, various power equipment, and key structure points;

[0078] Step 103, perform spatial density clustering analysis on the spatial positions of the recognition images to obtain the clustering results of each pole tower;

[0079] Step 104, based on the image information, perform multi-view solution and fast spatial reconstruction on the clustering results of each pole tower to obtain the spatial coordinate information of each pole tower;

[0080] Step 105: Determine the dimensional information of the power equipment and key structure points on the pole tower according to the spatial coordinate information of each pole tower, and determine whether there are defects in the power equipment according to the dimensional information.

[0081] Specifically, the present invention aims to propose an acceptance inspection technology for overhead distribution lines based on multi-view solution and rapid spatial reconstruction. The target detection algorithm is used to quickly identify and mark the pole towers, various equipment and key structure points in the UAV images, and combined with the improved density space clustering algorithm, the precise mapping and association between the UAV images and the pole towers are realized. On this basis, the real-time data of the camera attitude of the UAV is fused, and the synchronous mapping of the equipment and key structure points in the three-dimensional space is completed based on the multi-view spatial reconstruction algorithm. Through the line analysis of the mapped space, accurate calculation of the engineering quantity, precise and efficient construction of the line homologous data, and accurate verification of the construction electrical distance are realized to ensure the compliance of the construction quality.

[0082] 1. Invention principle:

[0083] Based on the image clustering data with the pole tower as the unit, combined with the precise spatial coordinate position information of the UAV and the real-time attitude data of the pan-tilt, the normal direction of the imaging plane where the key equipment and structure points are located in each image is accurately calculated based on the visible light imaging principle, and then the intersection points of the normals under multi-view angles are solved to realize the three-dimensional analysis of the target structure. The algorithm principle is as Figure 2 shown. The UAV imaging and photographing points E a and E b The spatial coordinates are Pos(E a ) = (x1, y1, z1) and Pos(E b ) = (x2, y2, z2).

[0084] The direction vectors formed by the coordinate points A1 and B1 on the two images and the shooting points are calculated by the attitude angles of the UAV pan-tilt and the image imaging parameters . The conversion calculation between the attitude angle and the direction vector is as follows:

[0085] The rotation matrix corresponding to the pitch angle θ:

[0086]

[0087] The azimuth angle The corresponding rotation matrix:

[0088]

[0089] The rotation matrix corresponding to the roll angle ψ:

[0090]

[0091] Then the corresponding total rotation matrix:

[0092]

[0093] The initial pointing direction vector of the pan-tilt head V0 = (x0, y0, z0), at the shooting point E a The direction vector after rotation Can be calculated through the rotation matrix R: That is:

[0094]

[0095] Image imaging parameters The image pixel center point P from the imaging plane A mid =(x Amid , y Amid ) pixel distance Calculate the physical size of the imaging position according to the pixel size a of the imaging device

[0096] Then the imaging deflection vector Then the imaging curve deflection vector formed by the pan-tilt head and the imaging

[0097] Then Figure 2 In which E a The straight line L1 equation formed with A1 Similarly, it can be obtained that E b The straight line L2 equation formed with B1 Then the intersection coordinates P in space are obtained by solving L1 and L2 sec =(x sec , y sec , z sec )(14).

[0098] 2. Composition of the acceptance system:

[0099] An overhead distribution line acceptance system based on multi-viewpoint solution for fast spatial reconstruction consists of a drone, a ground remote control terminal, and a computing terminal. Among them, the drone transmits the collected data back to the remote control terminal through a self-built link with the remote control terminal. According to the transmitted data, the acceptance analysis and calculation of the overhead distribution line based on multi-viewpoint solution for fast spatial reconstruction are completed at the remote control terminal, and an acceptance report is generated. The acceptance report generated by the remote control terminal can be transmitted to the remote server through wireless transmission or through an SD card. The system composition is as Figure 3 shown.

[0100] 3. Operation process:

[0101] The drone first takes panoramic photos from a distance to provide an overall view of the tower pole conditions. Subsequently, the drone focuses on key measurement devices, ensuring that all typical objects of concern are within the viewfinder. Then, the drone is controlled to fly around the tower. The schematic diagram of its operation flight path is as Figure 4 shown.

[0102] 4. Technical implementation:

[0103] (1) Technical route:

[0104] The visible light data of each tower pole of the overhead distribution line to be accepted is collected by the drone according to the operation process described in step 3. After the collection is completed, the tower poles, various devices, and key structure points in the image are quickly identified and marked through the target detection algorithm. Combining with the improved density space clustering algorithm, the precise mapping and association between the drone images and each tower pole are realized. On this basis, the real-time data of the camera attitude of the drone is fused, and the synchronous mapping of the devices and key structure points in the three-dimensional space is completed based on the multi-view space reconstruction algorithm. Through the line analysis of the mapping space, accurate engineering quantity statistics, precise and efficient construction of line homologous data, and accurate verification of construction electrical distances are realized to ensure the compliance of construction quality. The technical route is as Figure 5 shown, which includes a total of 5 modules: the data collection module of the line to be accepted, the device and key structure point recognition module, the image and recognition result clustering module, the multi-view calculation and fast space reconstruction module, and the process and typical electrical distance verification module.

[0105] (2) Data collection module of the line to be accepted:

[0106] This module is used to collect data for the line to be accepted and prepare data for the device and key structure point detection module and the multi-view calculation and fast space reconstruction module. The specific operation is to take off the drone from near the tower pole after setting the collection frequency. As shown in ① of Figure 5 shown, first, the entire tower pole of the line to be measured is photographed from a long distance as shown in ②. Then, the drone approaches the tower pole (to reduce the data error of the multi-view calculation and fast space reconstruction), and data collection around the tower is carried out for the on-pole devices such as insulators as shown in ③ to ④. Data collection is carried out throughout the flight process at a preset fixed frequency F (ranging from 500 ms to 1200 ms, specifically determined according to the computing power and calculation accuracy requirements of the drone remote control terminal, generally defaulting to 800 milliseconds). At the same time, the drone trajectory (x, y, z) information and the drone direction information at the corresponding moment are recorded, and the attitude information of the drone pan-tilt is recorded.

[0107] Note: The value range of the frequency F is set between 500 milliseconds and 1200 milliseconds to balance the density of image collection and the data processing ability, ensuring that enough detailed information can be captured without imposing too much burden on subsequent data processing.

[0108] (3) Equipment and Key Structural Point Identification Module:

[0109] The present invention uses the YOLO (You Only Look Once) algorithm for training. This algorithm simultaneously predicts the bounding boxes and class probabilities in an image through a single neural network, achieving efficient and accurate object detection. Its algorithm architecture principle is as Figure 6 shown. Other algorithm frameworks can also be used to train the target monitoring module.

[0110] The focus of the equipment and key structural point identification module is to accurately identify a series of key pole-mounted equipment such as insulators, lightning arresters, primary-secondary integrated switches, circuit breakers, earthing switches, transformers, and integrated terminals. This identification process ensures that each piece of equipment material can be accurately detected. The specific identification results are as Figure 7 shown. At the same time, in order to accurately measure key electrical distance parameters such as the height of the crossarm from the ground and the overall height of the pole tower, this module carefully identifies the pole tower and its various key structural points, including the top of the pole tower, the bottom of the pole tower, and the crossarms installed on the pole tower.

[0111] After completing the identification task of the pole tower equipment and its key structural points, based on the specific position distribution information of the identification frames in the image, with the help of structured data processing technology, the associated data relationships among the equipment, key structural points, and pole tower in the same image are established. This process not only clarifies the spatial position relationships among various elements but also ensures the accurate logical connections among the data, providing relatively simplified support for subsequent analysis, processing, and decision-making.

[0112] (4) Image and Recognition Result Clustering Module

[0113] Since the equipment and key structural point identification module has successfully constructed the accurate associated data relationships among the equipment, key structural points, and pole tower in the same image, the image and recognition result clustering module makes full use of the GNSS (Global Navigation Satellite System) coordinate information contained in the EXIF file of the collected image and conducts a detailed spatial density clustering analysis of the spatial position of the image to provide data preparation for improving the efficiency and accuracy of subsequent processing.

[0114] Spatial density clustering analysis uses the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm. The neighborhood radius (eps, the recommended value in this patent is 10 meters) and the minimum number of points (MinPts, the recommended value in this patent is 20) are used to define how many points at least are required in the neighborhood of a point to form a high-density area. That is, if the density of points in a region is greater than a certain threshold, the points in this region belong to the same cluster. The algorithm usually starts from any unvisited point and searches for regions with a density greater than the threshold in the neighborhood of this point. If such regions are found, the points in these regions are grouped into a cluster, and the search for new high-density regions continues in the neighborhoods of these points until no more high-density regions can be found. Then, the algorithm continues to search for the next unvisited point and repeats the above process until all points have been visited. The schematic diagram of the algorithm principle is shown in Figure 8.

[0115] During the clustering process, images that do not contain complete poles, on-pole equipment, and key structure points are mainly cleaned. The images that do not meet the requirements are automatically excluded through filtering and screening algorithms, so as to ensure that the dataset for subsequent analysis is of high quality and complete. This data cleaning step is crucial for reducing noise and improving the analysis accuracy. In addition, to more comprehensively understand and utilize the image data, the attitude information of the drone and the pan-tilt attitude data at the corresponding moment are associated with the inspection images to prepare data for the multi-view solution and fast spatial reconstruction module.

[0116] (5) Multi-view solution and fast spatial reconstruction module

[0117] The dataset processed by the equipment and key structure point recognition module and the image and recognition result clustering module is calculated according to the inventive principle of step 1. The analysis and solution are carried out on a certain equipment or structure point in the images collected by the drone at any two moments. Taking the insulator as an example. Given the insulator identification frames in two images and the initial values of the direction vectors of the initial pointing directions of the drone and the pan-tilt, first, the attitude information of the drone and the pan-tilt in the two images is subjected to coordinate transformation and converted into a vector mode in the rectangular coordinate system. According to the attitude angle and direction vector conversion calculation formulas (1), (2), (3), and (4), the rotation matrix corresponding to the pan-tilt direction vector is calculated, and then the initial value of the direction vector is subjected to rotation calculation using formula (5).

[0118] For the imaging deflection caused by the insulator identification frame in the figure, equations (7) and (8) are used to calculate the offset between the insulator identification frame and the pixel center point, and then converted into deflection in physical size through (9) and (10). The results of the superimposed gimbal deflection and imaging deflection are used to calculate the direction vector of the ray corresponding to the imaging identification frame using (11), and then the ray equations (12) and (13) are obtained. The simultaneous equations can obtain the intersection coordinates (14) corresponding to the insulator identification frame of the image collected by the drone at two moments. Calculate the intersection points of the rays corresponding to any two identification frames in the collected image to obtain the set of intersection points of the device in the mapping space, such as Figure 9 shown.

[0119] For the obtained intersection point set with equipment structural attributes, the processed discrete points are density clustered to accurately define the spatial scale of each component, realize modeling and rapid mapping of key components and structural points such as insulators, lightning arresters, tower tops and tower bottoms in three-dimensional space, and provide a data basis for material identification, deduplication statistics and typical distance measurement.

[0120] (6) Process and typical electrical distance calibration module

[0121] During routine inspection of overhead distribution lines, the key measurement points of the towers and substations shown in the figure are measured according to the distribution characteristics of the defect types on the towers and combined with key electrical distance parameters, such as conductor spacing, cross arm spacing, tower height, cross arm length, height of the transformer on the pole and the ground, etc. The statistical items to be measured are as follows: Figure 10 shown.

[0122] By analyzing the mapping space, the number of various equipment such as insulators, drop-out fuses, lightning arresters, pole-mounted transformers, etc. in the mapping space is accurately counted according to the point clustering labels, thereby realizing the precise construction of line homologous data.

[0123] In addition, on-site verification was carried out on the simulated lines of the State Grid UHV AC test base, such as Figure 11 As shown, the target tower to be accepted has a total of 18 insulators, among which the tower height from the ground is 11.697m measured by the present invention, and the value measured by manual climbing is 12.02m, with an absolute error of 0.32m; the conductor spacing is 1.138m measured by the present invention, and the value measured by manual climbing is 1.03m, with an error of 0.253m; the upper cross arm height from the ground is 11.264, and the value measured by manual climbing is 11.59m, with an error of 0.326m; the middle cross arm height from the ground is 10.083m, and the value measured by manual climbing is 10.4m, with an error of 0.317m; the lower cross arm height from the ground is 8.924, and the value measured by manual climbing is 9.24, with an error of 0.316m, the insulator material consumption statistics are accurate, and the distance measurement deviation does not exceed 0.5m.

[0124] The aerial distribution line unmanned aerial vehicle acceptance method proposed by the present invention has the following effects:

[0125] 1) Effectively avoids the safety risks brought by manual tower climbing, significantly improves the operation efficiency, and ensures the safe and efficient progress of the acceptance work;

[0126] 2) While realizing the accurate settlement of the project quantity, accurately and autonomously reconstructs the line topology homologous data, significantly improving the digital-physical consistency of the line;

[0127] 3) Accurately measures the typical construction electrical distances, effectively eliminates the possible technical blind spots in the line acceptance process, further improves the project quality, and provides a strong guarantee for the long-term stable operation of the line.

[0128] Exemplary Apparatus

[0129] Figure 12 It is a schematic structural diagram of an overhead distribution line acceptance device based on multi-view solution and rapid spatial reconstruction provided by an exemplary embodiment of the present invention. As Figure 12 shown, the device 1200 includes:

[0130] An acquisition module 1210, configured to acquire visible light images and image information of each pole tower of the overhead distribution line to be accepted;

[0131] An identification module 1220, configured to quickly identify and mark the pole towers, each power equipment, and key structure points in the visible light image by using a target detection algorithm, and determine an identification image, where the identification image includes identification frames of the pole towers, each power equipment, and key structure points;

[0132] An analysis module 1230, configured to perform spatial density clustering analysis on the spatial positions of the identification images to obtain the clustering results of each pole tower;

[0133] A obtaining module 1240, configured to perform multi-view solution and rapid spatial reconstruction on the clustering results of each pole tower based on the image information to obtain the spatial coordinate information of each pole tower;

[0134] A determination module 1250, configured to determine the size information of the power equipment and key structure points on the pole tower according to the spatial coordinate information of each pole tower, and determine whether there are defects in the power equipment according to the size information.

[0135] Optionally, the acquisition of the visible light images of each pole tower of the overhead distribution line to be accepted in the acquisition module 1210 includes:

[0136] A first acquisition sub-module, configured to acquire a full-view image of each pole tower of the overhead distribution line to be accepted;

[0137] The second acquisition sub-module is used to acquire multi-view power equipment images of each pole tower of the overhead distribution line to be accepted;

[0138] The first determination sub-module is used to determine visible light images based on the panoramic image and multi-view power equipment images.

[0139] Optionally, the power equipment on the pole tower includes: insulators, lightning arresters, primary-secondary integrated switches, circuit breakers, earthing switches, transformers, and integrated terminals;

[0140] The key structural points include: the top of the pole tower, the bottom of the pole tower, and the cross arms installed on the pole tower.

[0141] Optionally, the analysis module 1230 includes:

[0142] The clustering sub-module is used to perform clustering on the coordinate information of the pole towers, each power equipment, and key structural points in the recognition image by using the spatial density clustering analysis algorithm to determine the clustering result of each pole tower.

[0143] Optionally, the image information includes the drone trajectory information, the drone direction information, and the attitude information of the drone pan-tilt, and the obtaining module 1240 includes:

[0144] The conversion sub-module is used to convert the coordinates of multiple images in the clustering result of each pole tower based on the image information to determine the direction vector in the rectangular coordinate system;

[0145] The construction sub-module is used to construct a rotation matrix based on the direction vector and calculate the pan-tilt deflection vector according to the rotation matrix and the initial direction vector of the pan-tilt;

[0146] The first calculation sub-module is used to calculate the offset of the identification frame of each power equipment of the pole tower in multiple images from the pixel center respectively, and convert the offset into the imaging deflection vector in the physical dimension;

[0147] The second determination sub-module is used to determine the imaging curve deflection vector formed by the pan-tilt and the imaging according to the pan-tilt deflection vector and the imaging deflection vector;

[0148] The second calculation sub-module is used to calculate the intersection coordinates of the identification frames of the same power equipment in multiple images based on the curve deflection vector;

[0149] The third determination sub-module is used to determine the spatial coordinate information of each pole tower according to the set of intersection coordinates.

[0150] Optionally, the direction vector includes the pitch angle θ, the azimuth angle and the roll angle ψ, where

[0151]

[0152] The rotation matrix R is

[0153]

[0154] wherein, V0 = (x0, y0, z0) is the initial direction vector of the pan-tilt head; E a is the shooting point; x, y, and z are spatial coordinates.

[0155] Optionally, the calculation formula for the offset is:

[0156]

[0157] wherein, are image imaging parameters, P mid = (x Amid , y Amid ) is the image pixel center point of the phase plane A; is the distance in the x direction, is the distance in the y direction;

[0158] The imaging deflection vector has an expression of wherein

[0159]

[0160] wherein, a is the pixel size; is the offset in the x direction; is the offset in the y direction.

[0161] Exemplary Electronic Device

[0162] Figure 13 is the structure of the electronic device provided by an exemplary embodiment of the present invention. As Figure 13 shown, the electronic device 130 includes one or more processors 131 and a memory 132.

[0163] The processor 131 may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0164] The memory 132 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage media, and the processor 131 may run the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above and / or other desired functions. In one example, the electronic device may further include: an input device 133 and an output device 134, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0165] In addition, the input device 133 may further include, for example, a keyboard, a mouse, and so on.

[0166] The output device 134 may output various information to the outside. The output device 134 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, and so on.

[0167] Of course, for the sake of simplicity, Figure 13 only some of the components related to the present invention in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device may further include any other appropriate components.

[0168] Exemplary Computer Program Product and Computer Readable Storage Medium

[0169] In addition to the above methods and devices, embodiments of the present invention may also be computer program products, which include computer program instructions that, when run by a processor, cause the processor to execute the steps in the methods according to various embodiments of the present invention described in the "Exemplary Methods" section above of this specification.

[0170] The computer program products may be written in any combination of one or more programming languages for programming code to perform the operations of the embodiments of the present invention. The programming languages include object-oriented programming languages, such as Java, C++, etc., and also include conventional procedural programming languages, such as the "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, executed as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0171] In addition, an embodiment of the present invention may also be a computer-readable storage medium storing computer program instructions, which, when run by a processor, cause the processor to execute the steps in the methods according to various embodiments of the present invention described in the above "Exemplary Methods" section of this specification.

[0172] The computer-readable storage medium may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, include but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0173] The basic principles of the present invention have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present invention. In addition, the above-disclosed specific details are only for illustrative and facilitating understanding purposes and are not limitations. The above details do not limit the present invention to necessarily adopt the above specific details for implementation.

[0174] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. For the same or similar parts among the embodiments, reference may be made to each other. For system embodiments, since they basically correspond to method embodiments, the description is relatively simple, and reference may be made to the relevant parts of the method embodiments for the relevant content.

[0175] The block diagrams of the devices, systems, equipment, and systems involved in the present invention are only illustrative examples and do not intend to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, systems, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open-ended terms, meaning "including but not limited to", and can be used interchangeably with each other. The words "or" and "and" used herein refer to the word "and / or" and can be used interchangeably with each other, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to" and can be used interchangeably with each other.

[0176] The methods and systems of the present invention can be implemented in many ways. For example, the methods and systems of the present invention can be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of the steps for the method is for illustrative purposes only, and the steps of the method of the present invention are not limited to the specific order described above, unless otherwise specifically stated. In addition, in some embodiments, the present invention can also be implemented as a program recorded in a recording medium, and these programs include machine-readable instructions for implementing the method according to the present invention. Therefore, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0177] It should also be noted that in the systems, devices, and methods of the present invention, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present invention. The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

[0178] The above description has been given for purposes of illustration and description. In addition, this description is not intended to limit the embodiments of the present invention to the forms disclosed herein. Although several example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.

Claims

1. A method for completion acceptance of overhead distribution lines based on multi-view solution and rapid spatial reconstruction, characterized in that: include: Collect visible light images and image information of each tower of the overhead distribution line to be accepted; Using a target detection algorithm to quickly identify and mark the poles, power equipment and key structural points in the visible light image, and determine a recognition image, wherein the recognition image includes identification frames of the poles, power equipment and key structural points; Performing spatial density cluster analysis on the spatial position of the recognition image to obtain a clustering result for each tower; Based on the image information, multi-view solving and fast spatial reconstruction are performed on the clustering results of each tower to obtain spatial coordinate information of each tower; According to the spatial coordinate information of each pole tower, the size information of the power equipment and key structural points on the pole tower is determined, and according to the size information, it is determined whether the power equipment has defects.

2. The method according to claim 1, characterized in that Collect visible light images of each tower of the overhead distribution line to be accepted, including: Collecting a full-view image of each pole tower of the overhead distribution line to be accepted; Collecting multi-view images of power equipment on each pole tower of the overhead distribution line to be inspected and accepted; The visible light image is determined according to the overall image and the multi-view images of the electric power equipment.

3. The method according to claim 1, characterized in that The power equipment on the tower includes: insulators, lightning arresters, primary and secondary fusion switches, circuit breakers, grounding switches, transformers and fusion terminals; The key structural points include: the top of the tower, the bottom of the tower and the cross arms installed on the tower.

4. The method according to claim 1, characterized in that: Performing spatial density cluster analysis on the spatial position of the recognition image to obtain a clustering result for each tower includes: According to the coordinate information of the pole tower, each power equipment and key structural points in the recognition image, a spatial density clustering analysis algorithm is used to perform clustering to determine the clustering result of each pole tower.

5. The method according to claim 1, characterized in that The image information includes the drone trajectory information, the drone direction information and the drone gimbal attitude information, and based on the image information, the clustering results of each tower are multi-view solved and quickly reconstructed to obtain the spatial coordinate information of each tower, including: Based on the image information, coordinates of multiple images in the clustering result of each tower are transformed to determine a direction vector in a rectangular coordinate system; Constructing a rotation matrix according to the direction vector, and calculating the gimbal deflection vector according to the rotation matrix and the gimbal initial direction vector; Calculate the offset of the identification frame of each power equipment on the tower in the multiple images from the pixel center respectively, and convert the offset into the imaging deflection vector in physical size; Determining the deflection vector of the phase curve formed by the pan-tilt and the imaging according to the pan-tilt deflection vector and the imaging deflection vector; Calculating the intersection coordinates of the same electric power equipment identification frame in multiple images based on the curve deflection vector; The spatial coordinate information of each tower is determined according to the collection of the intersection coordinates.

6. The method according to claim 5, characterized in that The direction vector includes pitch The rotation matrix R is 7. The method according to claim 6, characterized in that The expression of the gimbal deflection vector is: Right now Where V0 = (x0, y0, z0) is the initial direction vector of the gimbal; E a is the shooting point; x, y, z are the spatial coordinates.

8. The method according to claim 5, characterized in that The calculation formula of the offset is: In the formula, is the imaging parameter, P mid =(x Amid ,y Amid ) is the center point of the image pixel of face A; is the distance in the x direction, is the distance in the y direction; The imaging deflection vector The expression is in Where a is the pixel size; is the offset in the x direction; is the offset in the y direction.

9. A device for completing and accepting overhead distribution lines based on multi-view solution and rapid spatial reconstruction, characterized in that: include: A collection module, used to collect visible light images and image information of each tower of the overhead distribution line to be accepted; A recognition module, used to use a target detection algorithm to quickly identify and mark the poles, power equipment and key structural points in the visible light image, and determine a recognition image, wherein the recognition image includes identification frames of the poles, power equipment and key structural points; An analysis module, used to perform spatial density cluster analysis on the spatial position of the recognition image to obtain a clustering result for each tower; An obtaining module is used to perform multi-viewing solution and fast spatial reconstruction on the clustering result of each tower based on the image information to obtain the spatial coordinate information of each tower; The determination module is used to determine the size information of the power equipment and key structural points on each tower according to the spatial coordinate information of the tower, and determine whether the power equipment has defects according to the size information.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 8.

11. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1-8.

Images