Power transmission line reconstruction method and device, electronic equipment and storage medium

Abstract

The application discloses a power transmission line reconstruction method and device, electronic equipment and a storage medium, and the method comprises the steps of: identifying a target image based on a pre-trained deep learning model to obtain pixel position information of power transmission line pixels in the target image; determining actual coordinate information corresponding to the power transmission line pixels according to the pixel position information and pose information of at least two power transmission line pixels; obtaining parameters of the power transmission line according to the actual coordinate information, and performing line reconstruction based on the parameters of the power transmission line. Based on the above technical scheme, the line point position is accurately matched in the power transmission line reconstruction process, and the technical effect of improving the accuracy of power transmission line reconstruction is achieved.

Description

Technical Field

[0001] This invention relates to the field of power technology, and in particular to a method, apparatus, electronic device, and storage medium for reconstructing power transmission lines. Background Technology

[0002] With the development and advancement of power technology, corresponding digital models are constructed to facilitate the maintenance of transmission lines, thereby improving the convenience of maintenance.

[0003] However, existing model building methods are based on directly reconstructing transmission lines using acquired image information, or can only reconstruct lines for scenes with limited image information. This results in low accuracy of the reconstructed transmission line models, and the transmission line reconstruction methods cannot meet user needs. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for reconstructing power transmission lines, which achieves precise matching of line locations during the reconstruction process, thereby improving the accuracy of power transmission line reconstruction.

[0005] In a first aspect, the present invention provides a method for reconstructing transmission lines, comprising:

[0006] The target image is identified based on a pre-trained deep learning model to obtain the pixel location information of the transmission line pixels in the target image.

[0007] The actual coordinate information corresponding to the transmission line pixel is determined based on the pixel position information and pose information of at least two transmission line pixels, wherein the pose information is the angle information when the image is captured by the UAV;

[0008] The parameters of the transmission line are obtained based on the actual coordinate information, and the line is reconstructed based on the parameters of the transmission line.

[0009] Secondly, embodiments of the present invention also provide a transmission line reconstruction device, the device comprising:

[0010] The location information acquisition module is used to identify the target image based on a pre-trained deep learning model in order to obtain the pixel location information of the transmission line pixels in the target image.

[0011] The coordinate information acquisition module is used to determine the actual coordinate information corresponding to the transmission line pixel based on the pixel position information and pose information of at least two transmission line pixels, wherein the pose information is the angle information when the UAV captures the image;

[0012] The line reconstruction module is used to obtain relevant parameters of the transmission line based on the actual coordinate information, and to reconstruct the line based on the relevant parameters of the transmission line.

[0013] Thirdly, embodiments of the present invention also provide an electronic device, the device comprising:

[0014] One or more processors;

[0015] Storage device for storing one or more programs;

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the transmission line reconstruction method as described in any embodiment of the present invention.

[0017] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the transmission line reconstruction method as described in any embodiment of the present invention.

[0018] The technical solution of this invention identifies target images based on a pre-trained deep learning model to obtain pixel position information of transmission line pixels in the target image. Then, based on the pixel position information and pose information of at least two transmission line pixels, the actual coordinate information corresponding to the transmission line pixels is determined. Finally, the relevant parameters of the transmission line are obtained based on the actual coordinate information, and the line is reconstructed based on the relevant parameters of the transmission line. Based on the above technical solution, the accurate matching of line points in the transmission line reconstruction process achieves the technical effect of improving the accuracy of transmission line reconstruction.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments are briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic flowchart of a power transmission line reconstruction method provided in an embodiment of the present invention;

[0022] Figure 2 This is a flowchart of a power transmission line reconstruction method provided in an embodiment of the present invention;

[0023] Figure 3 This is a flowchart of a power transmission line reconstruction method provided in an embodiment of the present invention;

[0024] Figure 4 This is a structural block diagram of a power transmission line reconstruction device provided in an embodiment of the present invention;

[0025] Figure 5 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Example 1

[0029] Figure 1 This is a flowchart illustrating a transmission line reconstruction method provided in an embodiment of the present invention. This embodiment is applicable to situations where collected transmission line image information is analyzed and the location of the transmission line is reconstructed based on the analysis results. This method can be integrated into an electronic device, such as a PC or a server.

[0030] like Figure 1 As shown, the method includes:

[0031] S110. Based on a pre-trained deep learning model, the target image is identified to obtain the pixel position information of the transmission line pixels in the target image.

[0032] Deep learning models can be built based on artificial neural networks. It's important to understand that different models serve different purposes; therefore, deep learning models can be image recognition models, semantic segmentation models, etc. The target image can be understood as an image containing power transmission lines and towers. Pixel location information can be the location information of pixels on the power transmission lines.

[0033] Specifically, after obtaining the target image, a pre-defined deep learning model is used to identify the target image, thereby obtaining the pixel location information of all transmission line pixels in the target image. For example, the acquired image can first be input into an image recognition model to identify images containing transmission lines, and then the images containing transmission lines can be input into the model to identify the pixel location information of the transmission line pixels.

[0034] Based on the above technical solution, before recognizing the target image based on the pre-trained deep learning model, the method further includes: determining the target area according to the tower span and the coordinate information of the target tower, obtaining all images within the target area, and using them as the target image.

[0035] The target area is a circular region centered on the target tower and with the tower span as its radius. The tower span can be the horizontal distance between two suspension points of an overhead line in a plane parallel to the specific load on the conductor between adjacent towers. The target tower can be understood as the tower that needs to be addressed. It should be noted that towers are the supports used to support transmission lines in overhead power lines. Towers are mostly made of steel or reinforced concrete and are the main supporting structure of overhead power lines. The coordinate information of the target tower can be its coordinates in WGS84 coordinates, a coordinate system established for use with the GPS global positioning system.

[0036] Specifically, using the target tower as the center and the tower span as the radius, the drone's position information when taking the image determines all images within the target area and uses them as the target images. For example, the target area can be determined based on the tower span and the target tower's coordinate information, and then all images taken within the target area can be obtained based on the drone's coordinate information when taking the image and used as the target images.

[0037] Based on the above technical solution, after obtaining the target image, the method further includes: dividing the target image into at least one sub-image based on the current direction in the transmission line, the coordinate information of the preset identification object and the target tower.

[0038] At least one sub-image corresponds to a tower of a preset model. The current direction can be the direction of current flow in the transmission line. The preset identified object can be an object installed on the transmission line, such as an insulator string.

[0039] Specifically, the target image can be categorized based on the current flow direction in the transmission line and the coordinate information of the preset identified objects and towers. For example, the transmission line can be divided into three sub-images based on the coordinate information: a large tower end image, a middle target image, and a small tower end image. It should be noted that the preset tower type can be divided into large and small towers. For instance, based on the current flow direction, towers where current flows in can be designated as large towers, and towers where current flows out can be designated as small towers. Furthermore, the target image can be divided into at least one sub-image based on the tower type and the coordinate information of the preset identified objects and target towers. These sub-images can include large tower end images, middle target images, and small tower end images.

[0040] In practical applications, a corresponding image recognition model can be set up. After the preset object is identified by the image recognition model, the target image is classified to obtain at least one sub-image.

[0041] Based on the above technical solution, the step of using a pre-trained deep learning model to identify the target image and obtain the pixel location information of the transmission line pixels in the target image includes: performing semantic segmentation on the pixels in the at least one sub-image based on a pre-trained semantic segmentation model, and obtaining the pixel location information of the transmission line pixels corresponding to each sub-image.

[0042] The semantic segmentation model can be a pre-trained model for semantic segmentation of images. It's important to note that semantic segmentation is the process of identifying and labeling targets of interest in an image. In other words, after at least one sub-image has undergone speech segmentation, the pixels representing power transmission lines can be labeled within the image. Pixel location information can be the location information of the pixels corresponding to the power transmission lines in the sub-image.

[0043] Specifically, after performing semantic segmentation on each sub-image based on a pre-trained semantic segmentation model, the pixel location information of the transmission lines in each sub-image is obtained. For example, a sub-image can be input into the semantic segmentation model, and the corresponding semantically labeled image can be output, along with the corresponding pixel location information.

[0044] It should be noted that the deep learning models mentioned in the embodiments of this invention, such as image recognition models and semantic segmentation models, are not limited in their training methods. Those skilled in the art can pre-train the required models according to their needs.

[0045] S120. Determine the actual coordinate information corresponding to the transmission line pixel based on the pixel position information and pose information of at least two transmission line pixels.

[0046] The pose information refers to the angle information when the drone captures the image. The actual coordinate information can be understood as the coordinate information of a pixel in WGS84 coordinates. It should be noted that the drone's pose information may include its yaw angle, pitch angle, and roll angle information during the capture process.

[0047] Specifically, the actual coordinates of the transmission line pixels are determined by combining the pixel position information of at least two transmission line pixels with the yaw angle, pitch angle and roll angle information of the UAV when capturing the corresponding image.

[0048] Based on the above technical solution, the step of determining the actual coordinate information corresponding to the transmission line pixel based on the pixel position information of at least two pixels in the point set and the spatial pose information of the target image includes: processing the pixel position information of the at least two pixels and the pose information based on the spatial forward intersection method to obtain the actual coordinate information corresponding to the transmission line pixel.

[0049] Among them, spatial forward intersection can be a method to determine the spatial position of model points by using the intersection of rays of the same name after recovering the beams and establishing the geometric model during stereo image pair photography.

[0050] Specifically, the actual coordinates of a pixel can be obtained by processing the pixel position and pose information of at least two pixels using the spatial forward intersection method.

[0051] S130. Obtain the parameters of the transmission line based on the actual coordinate information, and reconstruct the line based on the parameters of the transmission line.

[0052] Among them, the parameters can be parameter information used to reconstruct the transmission line.

[0053] Specifically, after obtaining the actual coordinate information, the parameters of the transmission line can be obtained based on the actual coordinate information, and then the reconstruction of the transmission line on the coordinate system can be completed based on the parameter information, thus constructing the corresponding three-dimensional model. For example, the actual coordinates of all pixels can be directly displayed on the coordinate system, and then the power line can be reconstructed based on the points in the coordinate system.

[0054] Based on the above technical solution, before obtaining the relevant parameters of the transmission line according to the actual coordinate information and reconstructing the line based on the relevant parameters of the transmission line, the method further includes: classifying the actual coordinate information corresponding to the pixels of the transmission line based on the coordinate information of the target tower, and sorting them according to the height information in the actual coordinate information corresponding to the pixels of the transmission line.

[0055] Among them, height information can be understood as the z-axis coordinate information in the actual coordinate information.

[0056] Specifically, based on the coordinates of the large and small towers within a single tower span, the actual coordinate information corresponding to the transmission line pixels is divided into large tower coordinate information and small tower coordinate information. For example, the distance averaging point between two towers can be found based on the tower span information. Then, the position information of the transmission line pixels is classified based on the position of the averaging point, and the pixels are sorted according to their height information. It should be noted that since multiple lines may be mounted on a single tower, it is necessary to sort the lines at different heights according to their height information to avoid duplicate selection of points.

[0057] Based on the above technical solution, the step of obtaining the parameters of the transmission line according to the actual coordinate information and reconstructing the line based on the parameters of the transmission line includes: substituting the actual coordinate information of at least three points in the actual coordinate information into the catenary equation to obtain the relevant parameters of the catenary equation, and completing the reconstruction of the transmission line based on the relevant parameters.

[0058] The catenary equation can be represented by the curve shape of a uniformly shaped, flexible (inextensible) chain (of uniform thickness and mass distribution) fixed at both ends, under the influence of gravity. Specifically, the actual coordinates of three points can be selected from real-world coordinate data and substituted into the catenary equation to solve for its parameters. These parameters can then be used to rebuild the transmission line. It should be noted that, with a suitable coordinate system, the catenary equation is a hyperbolic cosine function, with the standard equation: y = a cosh(x / a), where a is the distance from the vertex of the curve to the horizontal axis.

[0059] Based on the above technical solution, the method further includes: projecting all reconstructed transmission lines onto a horizontal plane and calculating the slope of the corresponding horizontal plane projection; if the slopes are not equal, recalculating the parameters of the transmission lines; if the slopes are equal, continuing to divide all reconstructed transmission lines into equal parts and projecting them onto a vertical plane, calculating the vertical coordinate difference between each part; if the vertical coordinate difference meets a preset condition, retaining the reconstruction result; if the vertical coordinate difference does not meet the preset condition, recalculating the parameters of the transmission lines.

[0060] In this context, the horizontal plane can be understood as the xoy plane. The slope can be the degree of inclination of the transmission line's projection onto the horizontal plane. The vertical plane can be the xoz plane, and the corresponding vertical coordinate difference can be understood as the height value of each segment of the vertical plane projection. The preset conditions can be that the height values ​​of each segment of the vertical plane projection are equal, or that the error is within a preset range, such as an error within 0.1 meters.

[0061] Specifically, to ensure the accuracy of transmission line reconstruction, multiple sets of coordinates can be selected and substituted into the catenary equations to obtain the corresponding parameters and complete the reconstruction. The reconstructed transmission line is then projected onto the xoy plane, and the slopes on the xoy plane are calculated and compared. When the slopes are the same, the reconstructed line is projected onto the xoz plane and bisected along the X-axis. It is thus divided into four equal parts along the X-axis. The height values ​​between each part are compared. If the height values ​​meet preset conditions, the current reconstruction result is retained, thereby ensuring the accuracy of the reconstruction result. For example, a Z-value is taken from each part, and after sorting each Z-value by size, the difference between adjacent Z-values ​​is calculated. If the differences in each part are substantially equal and no difference is negative, the catenary equations are retained. If the conditions of substantially equal differences in each part and no difference being negative are not met, the process returns to the catenary equation calculation point.

[0062] The technical solution of this invention identifies target images based on a pre-trained deep learning model to obtain pixel position information of transmission line pixels in the target image. Then, based on the pixel position information and pose information of at least two transmission line pixels, the actual coordinate information corresponding to the transmission line pixels is determined. Finally, the relevant parameters of the transmission line are obtained based on the actual coordinate information, and the line is reconstructed based on the relevant parameters of the transmission line. Based on the above technical solution, the accurate matching of line points in the transmission line reconstruction process achieves the technical effect of improving the accuracy of transmission line reconstruction.

[0063] Example 2

[0064] Figure 2This is a flowchart illustrating a transmission line reconstruction method according to an embodiment of the present invention. This embodiment further refines the implementation process of the transmission line reconstruction method based on the above examples. Specific implementation details can be found in the technical solution of this embodiment. Technical terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0065] It should be noted that after receiving image data collected by the drone, this invention filters out relevant images within the span of the tower based on the tower coordinates. These images are then subjected to aerial triangulation to calculate the image pose and camera interior and exterior elements. Deep learning is used to perform semantic segmentation of the electric field lines in the images. After matching the segmented pixels, the electric field lines are finally fitted into the catenary equation.

[0066] like Figure 2 As shown, taking the line calculation between single spans as an example, the specific implementation process of this method is as follows:

[0067] First, image data I0 from a single UAV flight needs to be acquired. Then, the spatial attitude information (yaw, pitch, and roll) of the image data from a single UAV flight is analyzed using aerial triangulation techniques. Aerial triangulation is a measurement method in stereo photogrammetry that uses a small number of field control points to densify the control points indoors, and then determines the elevation and planar position of the densified points.

[0068] Furthermore, using the WGS84 coordinate information of the tower, image data In within a single span is filtered out from I0. Simultaneously, using the tower's WGS84 coordinates, relevant image data Imid at the midpoint of a single span is filtered out from I0. It should be noted that the relevant image data Imid at the midpoint of a single span can refer to image information at the midpoint of the transmission line.

[0069] Then, deep learning is used to identify the position Ix (x = 1, 2, 3…n) of the insulator string from In. Specifically, a corresponding image recognition model can be pre-trained, and the position of the insulator string can be marked after the image is recognized by the image recognition model. Using the WGS84 coordinate information of the tower, the position Ix of the insulator string is divided into Iminx at the small tower end and Imaxx at the large tower end. It should be noted that the towers can be divided into large and small towers based on the current flow direction, and the current flows from the small tower to the large tower.

[0070] In image data containing Iminx and Imaxx, deep learning is used to segment the corresponding pixel positions IPminxn (n = 1, 2, 3…n) and IPmaxxn (n = 1, 2, 3…n) of the power line pixel by pixel. Similarly, deep learning is used to segment the pixel position IPmidn (n = 1, 2, 3…n) of the power line in the image data Imid. Specifically, a semantic segmentation model can be used to process the image to achieve pixel-by-pixel segmentation.

[0071] For the image dataset containing pixels IPminxn, IPmaxxn, and IPImidn, image feature point matching is performed to find pairwise corresponding point groups IPZminxn (n = 1, 2, 3…n), IPZmaxxn (n = 1, 2, 3…n), and IPZmidn (n = 1, 2, 3…n) within each point set of IPminxn, IPmaxxn, and IPmidn. For each pair of points in each point group IPZminxn, IPZmaxxn, and IPZmidn, spatial forward intersection is performed using the spatial pose information of the image to obtain the corresponding WGS84 coordinates IPZWminxn, IPZWmaxxn, and IPZWmidn.

[0072] Using the coordinates of single-span towers of varying sizes, the coordinates IPZWminxn, IPZWmaxxn, and IPZWmidn are divided into left and right IPZWLminxn, IPZWLmaxxn, IPZWLmidn, IPZWRminxn, IPZWRmaxxn, and IPZWRmidn. The resulting point information IPZWLminxn, IPZWLmaxxn, IPZWLmidn, IPZWRminxn, IPZWRmaxxn, and IPZWRmidn are then arranged in ascending order of altitude for their respective point sets.

[0073] First, randomly select the first, second, and third points from IPZWLminxn, IPZWLmaxxn, and IPZWLmidn to form a group of three points. Then, substitute the first group, the second group, and the third group into the catenary equation to solve for the relevant parameters of the catenary equation.

[0074] In practical applications, after calculating the parameters and reconstructing the transmission line, it is necessary to verify the reconstructed transmission line to ensure the accuracy of the reconstruction. The verification method is as follows: Figure 3As shown, firstly, the catenary equations obtained from the first, second, and third groups are projected onto the XOY plane. The slopes of the catenary equations projected onto the XOY plane are calculated to determine if they are equal. If the slopes are equal, the point sets for each group are retained; otherwise, the process returns to the previous step to continue point set calculation. Next, based on retaining the corresponding points with equal slopes, the X-axis of each group's catenary equation is divided into four equal parts. A Z-value is taken from each part, and after sorting each Z-value by size, the difference between adjacent Z-values ​​is calculated. If the differences in each part are substantially equal, and no difference is negative, the catenary equations for each group are retained. If the conditions of substantially equal differences in each part and no difference being negative are not met, the process returns to the point where the catenary equation is calculated.

[0075] The technical solution of this invention identifies target images based on a pre-trained deep learning model to obtain pixel position information of transmission line pixels in the target image. Then, based on the pixel position information and pose information of at least two transmission line pixels, the actual coordinate information corresponding to the transmission line pixels is determined. Finally, the relevant parameters of the transmission line are obtained based on the actual coordinate information, and the line is reconstructed based on the relevant parameters of the transmission line. Based on the above technical solution, the accurate matching of line points in the transmission line reconstruction process achieves the technical effect of improving the accuracy of transmission line reconstruction.

[0076] Example 3

[0077] Figure 4 This invention provides a power transmission line reconstruction device. The device includes: a location information acquisition module 410, a coordinate information acquisition module 420, and a line reconstruction module 430.

[0078] The location information acquisition module 410 is used to identify the target image based on a pre-trained deep learning model in order to obtain the pixel location information of the transmission line pixels in the target image.

[0079] The coordinate information acquisition module 420 is used to determine the actual coordinate information corresponding to the transmission line pixel based on the pixel position information and pose information of at least two transmission line pixel points, wherein the pose information is the angle information when the UAV captures the image;

[0080] The line reconstruction module 430 is used to obtain the parameters of the transmission line based on the actual coordinate information, and to reconstruct the line based on the parameters of the transmission line.

[0081] Based on the above technical solution, the device further includes:

[0082] The target image acquisition module is used to determine the target area based on the tower span and the coordinate information of the target tower, obtain all images within the target area, and use them as the target image. The target area is a circular area with the target tower as the center and the tower span as the radius.

[0083] Based on the above technical solution, the target image acquisition module includes:

[0084] An image segmentation unit is used to divide the target image into at least one sub-image based on the current direction in the transmission line, the coordinate information of a preset identification object and the target tower; wherein the at least one sub-image corresponds to a tower of a preset model.

[0085] Based on the above technical solution, the coordinate information acquisition module is used to: perform semantic segmentation on the pixels in the at least one sub-image based on a pre-set semantic segmentation model, and obtain the pixel position information of the transmission line pixels corresponding to each image.

[0086] Based on the above technical solution, the coordinate information acquisition module is further used to: process the pixel position information and pose information of the at least two pixels based on the spatial forward intersection method to obtain the actual coordinate information corresponding to the transmission line pixel.

[0087] Based on the above technical solution, the coordinate information acquisition module further includes:

[0088] The classification unit is used to classify the actual coordinate information corresponding to the pixels of the transmission line based on the coordinate information of the target tower, and to sort them according to the height information in the actual coordinate information corresponding to the pixels of the transmission line.

[0089] Based on the above technical solution, the line reconstruction module is specifically used to: input the actual coordinate information of at least three points in the actual coordinate information into the catenary equation to obtain the relevant parameters of the catenary equation, and complete the reconstruction of the transmission line based on the relevant parameters.

[0090] Based on the above technical solution, the line reconstruction module further includes:

[0091] The verification unit is used to project all reconstructed transmission lines onto a horizontal plane and calculate the slope of the corresponding horizontal plane projection. If the slopes are not equal, the relevant parameters of the transmission lines are recalculated. If the slopes are equal, all reconstructed transmission lines are divided into equal parts and projected onto a vertical plane. The vertical coordinate difference between each part is calculated. If the vertical coordinate difference meets a preset condition, the reconstruction result is retained. If the vertical coordinate difference does not meet the preset condition, the relevant parameters of the transmission lines are recalculated.

[0092] The technical solution of this invention identifies target images based on a pre-trained deep learning model to obtain pixel position information of transmission line pixels in the target image. Then, based on the pixel position information and pose information of at least two transmission line pixels, the actual coordinate information corresponding to the transmission line pixels is determined. Finally, the relevant parameters of the transmission line are obtained based on the actual coordinate information, and the line is reconstructed based on the relevant parameters of the transmission line. Based on the above technical solution, the accurate matching of line points in the transmission line reconstruction process achieves the technical effect of improving the accuracy of transmission line reconstruction.

[0093] The transmission line reconstruction device provided in this embodiment of the invention can execute the transmission line reconstruction method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0094] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of the present invention.

[0095] Example 4

[0096] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0097] like Figure 5As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0098] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0099] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as transmission line reconstruction methods.

[0100] In some embodiments, the transmission line reconstruction method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the transmission line reconstruction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the transmission line reconstruction method by any other suitable means (e.g., by means of firmware).

[0101] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0102] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0103] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0104] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0105] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0106] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0107] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0108] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for reconstructing a power transmission line, characterized in that, include: The target area is determined based on the tower span and the coordinate information of the target tower. All images within the target area are obtained and used as the target image. The target area is a circular area with the target tower as the center and the tower span as the radius. The tower span is the horizontal distance between two suspension points of an overhead line in a plane parallel to the specific load on the conductor between two adjacent towers. Based on the current direction in the transmission line, the coordinate information of the preset identification object and the target tower, the target image is divided into at least one sub-image; wherein, the at least one sub-image corresponds to a tower of a preset model; Based on a pre-set semantic segmentation model, the pixels in the at least one sub-image are semantically segmented, and the pixel position information of the transmission line pixels corresponding to each sub-image is obtained. The actual coordinate information corresponding to the transmission line pixel is determined based on the pixel position information and pose information of at least two transmission line pixels, wherein the pose information is the angle information when the image is captured by the UAV; The parameters of the transmission line are obtained based on the actual coordinate information, and the line is reconstructed based on the parameters of the transmission line.

2. The method according to claim 1, wherein determining the actual coordinate information corresponding to the transmission line pixel based on the pixel position information and pose information of at least two transmission line pixels includes: The actual coordinate information corresponding to the pixel point of the transmission line is obtained by processing the pixel position information and pose information of the at least two pixels using the spatial forward intersection method.

3. The method according to claim 1, further comprising, before obtaining the parameters of the transmission line based on the actual coordinate information and reconstructing the line based on the parameters of the transmission line: Based on the coordinate information of the target tower, the actual coordinate information corresponding to the pixels of the transmission line is classified, and sorted according to the height information in the actual coordinate information corresponding to the pixels of the transmission line.

4. The method according to claim 1, wherein obtaining the parameters of the transmission line based on the actual coordinate information and reconstructing the line based on the parameters of the transmission line comprises: The actual coordinates of at least three points in the actual coordinate information are substituted into the catenary equation to obtain the relevant parameters of the catenary equation, and the reconstruction of the transmission line is completed based on the relevant parameters.

5. The method according to claim 1, characterized in that, Also includes: Project all reconstructed transmission lines onto a horizontal plane and calculate the slope of the corresponding horizontal plane projection. If the slopes are not equal, recalculate the relevant parameters of the transmission lines. If the slopes are equal, then continue to divide all the reconstructed transmission lines into equal parts and project them onto the vertical plane, and calculate the vertical coordinate difference between each part. If the vertical coordinate difference meets the preset conditions, then retain the reconstruction result. If the vertical coordinate difference does not meet the preset conditions, the relevant parameters of the transmission line are recalculated.

6. A transmission line reconstruction device, characterized in that, include: The location information acquisition module is used to identify the target image based on a pre-trained deep learning model in order to obtain the pixel location information of the transmission line pixels in the target image. The coordinate information acquisition module is used to determine the actual coordinate information corresponding to the transmission line pixel based on the pixel position information and pose information of at least two transmission line pixels, wherein the pose information is the angle information when the UAV captures the image; The line reconstruction module is used to obtain relevant parameters of the transmission line based on the actual coordinate information, and to reconstruct the line based on the relevant parameters of the transmission line. The device further includes: The target image acquisition module is used to determine the target area based on the tower span and the coordinate information of the target tower, obtain all images within the target area, and use them as the target image. The target area is a circular area with the target tower as the center and the tower span as the radius. The tower span is the horizontal distance between two suspension points of an overhead line in a plane parallel to the specific load on the conductor between two adjacent towers. The target image acquisition module includes: An image segmentation unit is used to divide the target image into at least one sub-image based on the current direction in the transmission line, the coordinate information of a preset identification object and the target tower; wherein the at least one sub-image corresponds to a tower of a preset model. Specifically, the coordinate information acquisition module is used to perform semantic segmentation on the pixels in the at least one sub-image based on a pre-set semantic segmentation model, and obtain the pixel position information of the transmission line pixels corresponding to each sub-image.

7. An electronic device, characterized in that, The electronic device includes: One or more processors; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the transmission line reconstruction method according to any one of claims 1-5.

Images