Satellite-based power transmission line monitoring method and device and storage medium

Abstract

The invention discloses a satellite-based power transmission line monitoring method and device and a storage medium. Relates to the technical field of satellites. The method comprises the following steps: a satellite obtains a satellite remote sensing image of a predetermined area, and determines a plurality of pixels corresponding to a power transmission line; the satellite determines abundance values of end members corresponding to various preset surface feature types in the pixels according to the frequency domain features corresponding to the pixels, and the preset surface feature types comprise forest surface feature types, water body surface feature types and building surface feature types; the satellite determines whether the ground corresponding to the corresponding pixel has potential safety hazards or not according to the abundance value through the monitoring model; the satellite sends early warning information corresponding to the ground with the potential safety hazard to a gateway station; and the gateway station uses the unmanned aerial vehicle to inspect the ground with the potential safety hazard according to the early warning information. Therefore, the technical problems of relatively small monitoring area, relatively long monitoring time and relatively high limitation caused by only using the unmanned aerial vehicle to monitor the power transmission line are solved.

Description

Technical Field

[0001] The present application relates to the field of satellite technology, and in particular to a satellite-based power transmission line monitoring method, device and storage medium. Background Art

[0002] As an important part of the power system, transmission lines play a vital role in the transmission of electric energy. The safety of transmission lines is the premise for ensuring the safe and stable transmission of electric energy. Transmission lines often cross mountains and trees, and the continuous growth of trees threatens the safety of transmission lines. The damage caused by trees to transmission lines is mainly manifested in branches touching the lines, causing short circuits and tripping, which in turn causes power outages or even fires; trees break and break power lines, causing power outages and threatening the stable operation of the power system. This is the tree flash problem. In addition, floods are also one of the major threats to transmission lines. Floods will wash away the foundations of poles and towers, causing tower collapses and line breaks, seriously damaging transmission facilities, causing large-scale power outages, and huge economic losses. Building obstructions should not be ignored either. Illegal buildings may endanger the operation of the power grid and personal safety.

[0003] At present, most of the research on transmission line hidden danger monitoring is based on drones. With the continuous expansion of the scale of transmission lines, the use of drones alone to monitor transmission lines can no longer meet the needs of large-scale and large-area monitoring of transmission line hidden dangers, and has high limitations.

[0004] The publication number is CN119273169A, and the name is a transmission line risk prediction method based on multimodal fusion, which includes the following steps: collecting static images and dynamic videos of the transmission line, extracting the geographic location information embedded in the image and video file names, comparing the extracted geographic location information with the geographic coordinates in the geographic information, and matching the images and videos to the corresponding geographic coordinates.

[0005] The publication number is CN119268573A, and the name is a method and device for monitoring the thickness of ice on a line based on machine vision, which includes the following steps: Step 1: The drone takes off with a camera and a short-wave light; Step 2: The drone flies toward the target transmission line, and the short-wave light has at least two light signals of different wavelengths; Step 3: After the reference object has a length and a pointing reference object enters the camera's field of view, the camera acquires an image of ice; Step 4: The images of ice under light signals of different wavelengths in the same context are fused to obtain a fused image; Step 5: The thickness of ice is calculated based on the ratio of the reference object to ice. The present invention also discloses a device for monitoring the thickness of ice on a line based on machine vision.

[0006] Currently, no effective solution has been proposed for the technical problems of small monitoring area, long monitoring time and high limitations caused by using only drones to monitor transmission lines in the above-mentioned prior art. Summary of the invention

[0007] The embodiments of the present application provide a satellite-based transmission line monitoring method, device and storage medium to at least solve the technical problems existing in the prior art of using only drones to monitor transmission lines, such as small monitoring area, long monitoring time and high limitations.

[0008] According to one aspect of an embodiment of the present application, a satellite-based transmission line monitoring method is provided, including: the satellite acquires a satellite remote sensing image of a predetermined area to determine a plurality of pixels corresponding to the transmission line; the satellite determines the abundance value of the end element corresponding to each preset land feature type in the pixel based on the frequency domain characteristics corresponding to the plurality of pixels, wherein the preset land feature types include forest land feature type, water body land feature type and building land feature type; the satellite determines whether there is a safety hazard in the ground corresponding to the corresponding pixel based on the abundance value through a monitoring model; the satellite sends warning information corresponding to the ground with safety hazards to a gateway station; and the gateway station uses a drone to patrol the ground with safety hazards based on the warning information.

[0009] According to another aspect of an embodiment of the present application, a satellite-based power transmission line monitoring device is also provided, including: a pixel determination module, used for the satellite to acquire satellite remote sensing images of a predetermined area and determine multiple pixels corresponding to the power transmission line; an abundance value determination module, used for the satellite to determine the abundance value of the end element corresponding to each preset land feature type in the pixel according to the frequency domain characteristics corresponding to the multiple pixels, wherein the preset land feature types include forest land feature type, water body land feature type and building land feature type; a hidden danger determination module, used for the satellite to determine whether there is a safety hazard on the ground corresponding to the corresponding pixel according to the abundance value through a monitoring model; an information sending module, used for the satellite to send early warning information corresponding to the ground with safety hazards to a signal gateway station; and an inspection module, used for the signal gateway station to use a drone to inspect the ground with safety hazards according to the early warning information.

[0010] According to another aspect of an embodiment of the present application, a satellite-based power transmission line monitoring device is also provided, including: a processor; and a memory connected to the processor, for providing the processor with instructions for processing the following processing steps: the satellite acquires a satellite remote sensing image of a predetermined area, and determines a plurality of pixels corresponding to the power transmission line; the satellite determines the abundance value of the end element corresponding to each preset land feature type in the pixel based on the frequency domain characteristics corresponding to the plurality of pixels, wherein the preset land feature types include forest land feature type, water body land feature type and building land feature type; the satellite determines whether there is a safety hazard on the ground corresponding to the corresponding pixel based on the abundance value through a monitoring model; the satellite sends warning information corresponding to the ground with safety hazards to a gateway station; and the gateway station uses a drone to patrol the ground with safety hazards based on the warning information.

[0011] According to another aspect of an embodiment of the present application, there is also provided an integrated electronic system, including a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.

[0012] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0013] According to another aspect of the embodiments of the present application, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0014] In the embodiment of the present application, the satellite uses satellite remote sensing images combined with abundance value analysis to conduct preliminary screening, quickly cover large areas, and identify potential safety hazards. Compared with monitoring using only drones, satellite monitoring is not restricted by terrain and can effectively cope with complex environments such as power transmission lines crossing mountains and forests. After the satellite preliminarily screens out pixels with safety hazards, the signal gateway station uses drones for precise inspections, which can accurately determine the specific location and type of safety hazards (such as tree flash hazards, flood hazards, or building obstructions). Therefore, when determining whether there are safety hazards in a predetermined area, the satellite first roughly determines the pixels with safety hazards based on the satellite remote sensing images of the predetermined area, and then the signal gateway station uses drones to inspect the ground corresponding to the pixels with safety hazards, thereby accurately determining whether there are safety hazards on the ground and the specific location of the safety hazards. Therefore, the coarse-to-fine monitoring method of the technical solution not only improves the monitoring efficiency, but also ensures the monitoring accuracy, and reduces the limitations of determining safety hazards only by drones. In addition, this technical solution can not only cover a large area, but also conduct detailed inspections on specific areas through the collaborative work of satellites and drones, which not only improves the efficiency and accuracy of monitoring safety hazards of power transmission lines, but also enhances the safety and stability of the power grid system. This solves the technical problems existing in the prior art of using only drones to monitor power transmission lines, such as small monitoring area, long monitoring time and high limitations. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 is a hardware structure block diagram for implementing the satellite according to Embodiment 1 of the present application; Figure 2 is a schematic diagram of a power transmission line monitoring system according to Example 1 of the present application; Figure 3 is a schematic flow chart of a satellite-based power transmission line monitoring method according to the first aspect of Example 1 of the present application; Figure 4 is a schematic diagram of a satellite remote sensing image according to Example 1 of the present application; Figure 5 is a module schematic diagram of the monitoring model according to Example 1 of the present application; Figure 6 is a sequential flow chart of the satellite-based power transmission line monitoring method according to the first aspect of Example 1 of the present application; Figure 7 is a schematic diagram of a satellite-based power transmission line monitoring device according to Example 2 of the present application; and Figure 8 It is a schematic diagram of a satellite-based power transmission line monitoring device according to Example 3 of the present application. DETAILED DESCRIPTION

[0016] In order to enable those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0017] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. Example 1

[0018] According to this embodiment, a method embodiment of satellite-based transmission line monitoring is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0019] Figure 1 A schematic diagram showing the hardware architecture of the satellite. Figure 1 As shown, the satellite 100 includes an integrated electronic system, which includes: a processor, a memory, a bus management module and a communication interface. The memory is connected to the processor, so that the processor can access the memory, read the program instructions stored in the memory, read data from the memory or write data to the memory. The bus management module is connected to the processor and is also connected to a bus such as a CAN bus. Therefore, the processor can communicate with the satellite-borne peripherals connected to the bus through the bus managed by the bus management module. In addition, the processor is also connected to communication devices such as cameras, star sensors, measurement and control transponders, and data transmission equipment via the communication interface. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0020] It should be noted that Figure 1 The one or more processors and / or other data processing circuits shown in the figure may generally be referred to as "data processing circuits" herein. The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computing device. As involved in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0021] Figure 1 The memory shown in the figure can be used to store software programs and modules of application software, such as the program instruction / data storage device corresponding to the satellite-based power transmission line monitoring in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the satellite-based power transmission line monitoring of the above-mentioned application. The memory may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.

[0022] It should be noted that, in some optional embodiments, the above Figure 1 The devices shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware elements and software elements. Figure 1This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the above described apparatus.

[0023] Figure 2 Schematic diagram of the power transmission line monitoring system according to this embodiment. Figure 2 As shown, the system includes: a satellite 100, a gateway station 200 and a drone 300.

[0024] The satellite 100 is used to collect satellite remote sensing images of the predetermined area 400, and analyze the satellite remote sensing images to determine whether there are safety hazards in the power transmission lines in the predetermined area 400. Therefore, if there are safety hazards in the power transmission lines, early warning information is sent to the gateway station 200.

[0025] The gateway station 200 is used to receive the warning information sent by the satellite 100, and use the drone 300 to inspect the corresponding position of the predetermined area 400 according to the warning information to determine whether there is a safety hazard in the power transmission line.

[0026] Under the above operating environment, according to the first aspect of this embodiment, a satellite-based power transmission line monitoring method is provided. The method comprises: Figure 2 The satellite 100 shown in FIG. Figure 3 A schematic diagram showing the process of the method is shown in FIG. Figure 3 As shown, the method includes: S302: The satellite acquires a satellite remote sensing image of a predetermined area and determines a plurality of pixels corresponding to the power transmission line; S304: The satellite determines the abundance value of the endmember corresponding to each preset ground feature type in the pixel according to the frequency domain characteristics corresponding to the multiple pixels, wherein the preset ground feature types include forest ground feature type, water ground feature type and building ground feature type; S306: The satellite determines whether there is a safety hazard on the ground corresponding to the corresponding pixel according to the abundance value through the monitoring model; S308: The satellite sends the warning information corresponding to the ground where there is a potential safety hazard to the gateway station; and S310: The gateway station uses drones to conduct inspections on the ground where there are safety hazards based on early warning information.

[0027] Specifically, the satellite 100 acquires a satellite remote sensing image 500 corresponding to the predetermined area 400. The satellite remote sensing image is composed of individual pixels. The satellite remote sensing image is pre-marked with the location of the power transmission line, so that according to the location of the power transmission line in the satellite remote sensing image, a plurality of pixels in the satellite remote sensing image where the power transmission line exists are determined. Figure 4A partial schematic diagram of a satellite remote sensing image 500 composed of a plurality of pixels is shown. For example, a plurality of pixels in the satellite remote sensing image 500 where there are power transmission lines include pixels 501 to 50n.

[0028] Further, the satellite remote sensing image 500 can be obtained, for example, by a surface reflectance sensor on a satellite. For example, a Landsat 8 OLI sensor can be set on the satellite, so that the satellite remote sensing image 500 of the predetermined area 400 can be obtained by the Landsat 8 OLI sensor. Thus, the satellite 100 can obtain surface reflectance data of multiple different frequency bands for each pixel. For example, the Landsat 8 OLI sensor can provide surface reflectance data of 9 different bands, so that the computing device can obtain surface reflectance data of 9 different bands for each pixel.

[0029] Furthermore, the satellite 100 calculates the abundance values ​​of the end members of each type of land feature in each pixel 501-50n according to the frequency domain features corresponding to different frequency bands for the pixels 501-50n. The preset land feature types include forest land feature types, water body land feature types, and building land feature types. And the frequency domain features may be, for example, reflectivity data of different frequency bands corresponding to the pixel obtained by a surface reflectivity sensor, or reflectivity data of several frequency domains corresponding to the pixel obtained after principal component analysis.

[0030] Furthermore, the satellite 100 is pre-set with a monitoring model. The monitoring model is used to determine whether there is a safety hazard in the power transmission line set on the ground corresponding to a certain pixel according to the abundance value. The safety hazard is, for example, a tree flash hazard, a flood hazard, and a building obstruction. The satellite 100 inputs the abundance value of the end element corresponding to each ground object type in each pixel 501~50n into the preset monitoring model. After that, the satellite 100 analyzes and processes the abundance value of each pixel 501~50n through the monitoring model to determine whether the area occupied by the forest, water body, and building in the ground area corresponding to the pixel exceeds the preset value and encroaches on the area of ​​the power transmission line, so as to determine whether there is a safety hazard on the ground corresponding to each pixel 501~50n. That is, when the satellite 100 determines that the area occupied by the forest, water body, and building in the ground area corresponding to the pixel exceeds the preset value, it is determined that there is a safety hazard on the ground corresponding to the pixel.

[0031] Furthermore, when the satellite 100 determines that there is a safety hazard on the ground corresponding to a certain pixel, it will generate warning information corresponding to the ground and send the warning information to the gateway station 200.

[0032] Furthermore, after receiving the warning information sent by the satellite 100, the gateway station 200 determines the location of the ground where the safety hazard exists according to the warning information, and then uses a drone to inspect the ground according to the location, takes on-site video images of the ground, and returns the video images to the gateway station 200, so as to determine whether there is a safety hazard.

[0033] As described in the background technology, as an important part of the power system, the transmission line plays a vital role in the transmission of electric energy. The safety of the transmission line is the premise for ensuring the safe and stable transmission of electric energy. Transmission lines often cross mountains and trees, and the continuous growth of trees threatens the safety of transmission lines. The damage of trees to transmission lines is mainly manifested in branches touching the wires, causing short circuit tripping, which in turn causes power outages or even fires; trees break and break the power lines, causing power outages and threatening the stable operation of the power system. This is the tree flash problem. In addition, floods are also one of the major threats to transmission lines. Floods will wash away the foundation of poles and towers, causing tower collapse and line breakage, seriously damaging transmission facilities, causing large-scale power outages and huge economic losses. Building obstructions should not be ignored. Illegal buildings may endanger the operation of the power grid and personal safety. At present, most of the research on the hidden danger monitoring of transmission lines is based on drones or images. With the continuous expansion of the scale of transmission lines, the use of drones or images to monitor transmission lines alone can no longer meet the needs of large-scale and large-area monitoring of transmission line hidden dangers, and the limitations are high.

[0034] In view of the technical problems described above, through the technical solution of the embodiment of the present application, the satellite uses satellite remote sensing images combined with abundance value analysis to conduct preliminary screening, quickly cover large areas, and identify potential safety hazards. Compared with monitoring using only drones, satellite monitoring is not restricted by terrain and can effectively cope with complex environments such as power transmission lines crossing mountains and forests. After the satellite preliminarily screens out pixels with safety hazards, the signal gateway station uses drones for precise inspections, which can accurately determine the specific location and type of safety hazards (such as tree flash hazards, flood hazards, or building obstructions). Therefore, when determining whether there are safety hazards in a predetermined area, the satellite first roughly determines the pixels with safety hazards based on the satellite remote sensing images of the predetermined area, and then the signal gateway station uses drones to inspect the ground corresponding to the pixels with safety hazards, thereby accurately determining whether there are safety hazards on the ground and the specific location of the safety hazards. Therefore, the coarse-to-fine monitoring method of the technical solution not only improves the monitoring efficiency, but also ensures the monitoring accuracy, and reduces the limitations of determining safety hazards only by drones. Moreover, this technical solution can cover a large area and conduct detailed inspections on specific areas through the collaborative work of satellites and drones, which not only improves the efficiency and accuracy of monitoring safety hazards of power transmission lines, but also enhances the safety and stability of the power grid system. This solves the technical problems existing in the prior art of using only drones or only images to monitor power transmission lines, such as small monitoring area, long monitoring time and high limitations.

[0035] Optionally, the operation of the satellite determining the abundance value of the end-member corresponding to each preset land object type in the pixel based on the frequency domain characteristics corresponding to multiple pixels includes: the satellite obtains the first frequency domain characteristics corresponding to the end-member of each preset land object type; and the satellite determines the abundance value of the end-member corresponding to each preset land object type in the pixel based on the first frequency domain characteristics and the second frequency domain characteristics corresponding to the pixel.

[0036] Specifically, the satellite 100 determines the second frequency domain features corresponding to the pixels 501 to 50n based on the reflectivity data of the pixels 501 to 50n. More specifically, the satellite 100 determines the second frequency domain features corresponding to the pixels 501 to 50n. A j (j=1~n): A j =[ a 1,j , a 2,j ,..., a m,j ] T .

[0037] in, ai,j ( i =1~ m ) is the reflectance data of different frequency bands (i-th frequency band) corresponding to the j-th pixel. The different frequency bands may be, for example, reflectance data of different frequency bands generated by a surface reflectance sensor, or reflectance data of several frequency bands obtained after principal component analysis.

[0038] In this embodiment, the variables to be determined include the abundance values ​​corresponding to the end members of three different types of land objects, and an error term. Therefore, m≥4, that is, the number of parameters in the frequency domain characteristics is at least 1 more than the number of end members of different land object types. In addition, in the following text, the frequency bands corresponding to the frequency domain characteristics corresponding to the end members of different land object types are the same as the frequency bands in the frequency domain characteristics of pixels 501~50n. For example, the frequency domain characteristics corresponding to the end members of different land object types also include m frequency bands, and are the same as the frequency bands of the frequency domain characteristics of pixels 501~50n. No further details will be given here.

[0039] Furthermore, the satellite 100 determines the frequency domain features (ie, first frequency domain features) corresponding to the end elements of each feature type according to the reflectivity data for the pixels 501 to 50n, wherein the preset feature types include forest feature type, water feature type and building feature type.

[0040] More specifically, the satellite 100 determines the frequency domain features (i.e., the first frequency domain features) corresponding to the end elements of different ground object types for the pixels 501-50n respectively. The frequency domain features may be predetermined by measurement, for example. In this embodiment, the frequency domain features corresponding to the end elements of different ground object types include, for example: For pixels 501~50n, the frequency domain characteristics of forest end members corresponding to forest feature types B 1,j (j=1~n): B 1,j =[ b 1,1,j , b 1,2,j ,..., b 1,m,j ] T ,in b 1,i,j ( i =1~ m ) is the reflectance data of different frequency bands (i-th frequency band) corresponding to the forest endmember of the j-th pixel.

[0041] For pixels 501~50n, the frequency domain characteristics of the water end-members corresponding to the water feature types are B 2,j : B 2,j =[ b 2,1,j , b 2,2,j ,..., b 2,m,j ] T ,in b 2,i,j ( i =1~ m ) is the reflectance data of different frequency bands (i-th frequency band) corresponding to the water end member of the j-th pixel.

[0042] For pixels 501~50n, the frequency domain characteristics of the building end element corresponding to the building feature type B 3,j : B 3,j =[ b 3,1,j , b 3,2,j ,..., b 3,m,j ] T ,in b 3,i,j ( i =1~ m ) is the reflectance data of different frequency bands (i-th frequency band) corresponding to the building end element of the j-th pixel.

[0043] Furthermore, the satellite 100 calculates the abundance value of the endmember of each ground feature type in each pixel 501 - 50n according to the first frequency domain feature.

[0044] Therefore, this technical solution can more accurately calculate the abundance values ​​of different types of ground objects in pixels by obtaining the first frequency domain features corresponding to the end members of each preset ground object type and combining them with the second frequency domain features corresponding to the pixel. This method based on frequency domain features makes full use of the differences in reflectivity data of different ground object types in different frequency bands, and improves the accuracy of ground object type recognition.

[0045] Optionally, the satellite determines the abundance value of the end member corresponding to each preset land object type in the pixel based on the first frequency domain feature and the second frequency domain feature corresponding to the pixel, including: the satellite calculates the abundance value of the end member corresponding to each preset land object type in the pixel by using a calculation formula pre-constructed based on the frequency domain characteristics and forest abundance value of the end member of the forest land object type, the frequency domain characteristics and water abundance value of the end member of the water body land object type, the frequency domain characteristics and building abundance value of the building land object type, and the second frequency domain feature.

[0046] Specifically, the satellite 100 detects the frequency domain characteristics of the end elements of the forest feature type. B 1,j and forest abundance value k 1,j , frequency domain characteristics of end members of water feature types B 2,j and water abundance value k 2,j , Frequency domain characteristics of building feature types B 2,j and the building abundance value k 3,j And the second frequency domain feature A j Construct the following equation: (1) in, k 1,j is the abundance value of the forest end member in the jth pixel; k 2,j is the abundance value of the water body end member in the jth pixel; k 3,j is the abundance value of the building end member in the jth pixel; K0=[k 0,1 ,k 0,2 ,...,k 0,m ] T is the error term to be determined.

[0047] Therefore, the satellite will take the second frequency domain features of pixels 501~50n A j , frequency domain characteristics of forest endmembers B 1,j , frequency domain characteristics of water end members B 2,j , frequency domain characteristics of building end elements B 3,j Substitute into the above formula (1) to obtain K0 and k 1,j ~ k 3,j Then, the satellite 100 obtains the abundance value of the end member corresponding to the forest feature type in the pixels 501 to 50n. k 1,j , the abundance value of the end member corresponding to the water feature type in pixels 501~50n k 2,j , the abundance value of the end member corresponding to the building feature type in pixels 501~50n k 3,j .

[0048] Therefore, by constructing a calculation formula containing the frequency domain characteristics of forest, water body and building object type end elements and their corresponding abundance values, this technical solution can more accurately solve the abundance value of each preset object type in the pixel, thereby fully considering the mutual influence between different object types and improving the accuracy of abundance value calculation.

[0049] Optionally, the operation of the satellite determining whether there is a safety hazard on the ground corresponding to the corresponding pixel based on the abundance value through the monitoring model includes: the satellite determining the corresponding first feature information based on the abundance value through the fully connected layer of the monitoring model; and the satellite determining whether there is a safety hazard on the ground corresponding to the corresponding pixel based on the first feature information through the binary classifier of the monitoring model.

[0050] Specifically, the monitoring model includes a fully connected layer and a binary classifier, which is used to determine whether there is a safety hazard in the power transmission line set on the ground corresponding to a certain pixel according to the abundance value. The safety hazard includes tree flash hazard, flood hazard and building obstruction.

[0051] refer to Figure 5 As shown, the satellite 100 calculates the abundance value of each end member of each ground feature type in each pixel 501~50n [ k 1,j , k 2,j , k 3,j ] T Input to the monitoring model, and the abundance value [ k 1,j , k 2,j , k 3,j ] T Feature extraction is performed to generate corresponding first feature information. Then, the satellite 100 inputs the first feature information into the binary classifier of the monitoring model, processes the first feature information through the binary classifier, and outputs a safety hazard probability value, so that when the safety hazard probability value is greater than or equal to 50%, it is determined that there is a safety hazard on the ground corresponding to the corresponding pixel.

[0052] Therefore, this technical solution extracts features of the abundance value through the fully connected layer in the monitoring model and combines it with the binary classifier for processing, so as to more accurately determine whether there are safety hazards on the ground corresponding to the pixel. Therefore, this technical solution makes full use of the land feature type information contained in the abundance value and improves the accuracy of safety hazard identification.

[0053] Optionally, the steps for training the monitoring model are as follows: collecting sample input information and corresponding sample output information, wherein the sample input information is the sample abundance value, and the sample output information is the sample safety hazard probability value; and training the monitoring model according to the sample input information and the corresponding sample output information through a gradient descent algorithm.

[0054] Specifically, before the monitoring model is put into use, the satellite 100 will train the monitoring model. First, the satellite 100 collects sample input information and corresponding output information for training the monitoring model. The sample input information is the sample abundance value, and the sample output information is the sample safety hazard probability value. Then, the satellite 100 trains the monitoring model according to the sample input information and the corresponding sample output information through the gradient descent algorithm, thereby generating a monitoring model that can be put into use.

[0055] Therefore, this technical solution uses a gradient descent algorithm to train the monitoring model, and iteratively adjusts the model parameters to minimize the difference between the predicted results and the actual output, thereby continuously improving the generalization ability and prediction accuracy of the model.

[0056] In summary, reference Figure 6 As shown, the sequential steps of the satellite-based transmission line monitoring method are as follows: S601: The satellite acquires a satellite remote sensing image of a predetermined area and determines a plurality of pixels corresponding to the power transmission line; S602: The satellite acquires a first frequency domain feature corresponding to an end member of each preset ground feature type; S603: The satellite calculates the abundance value of the endmember corresponding to each preset land feature type in the pixel by using a calculation formula pre-constructed according to the frequency domain characteristics and forest abundance value of the endmember of the forest land feature type, the frequency domain characteristics and water abundance value of the endmember of the water land feature type, the frequency domain characteristics and building abundance value of the building land feature type, and the second frequency domain characteristics; S604: The satellite determines corresponding first feature information according to the abundance value through the fully connected layer of the monitoring model; S605: The satellite determines whether there is a safety hazard on the ground corresponding to the corresponding pixel according to the first feature information through a binary classifier of the monitoring model; S606: The satellite sends the warning information corresponding to the ground with potential safety hazards to the gateway station; S607: The gateway station uses drones to conduct inspections on the ground where there are safety hazards.

[0057] In addition, according to a second aspect of this embodiment, an integrated electronic system is provided, including a memory, a processor, and a computer program stored in the memory, and the processor executes the computer program to implement the steps of the above method.

[0058] In addition, according to a third aspect of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0059] In addition, according to a fourth aspect of this embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0060] Thus, according to this embodiment, the satellite uses satellite remote sensing images combined with abundance value analysis to conduct preliminary screening, quickly cover large areas, and identify potential safety hazards. Compared with monitoring using only drones, satellite monitoring is not restricted by terrain and can effectively cope with complex environments such as power transmission lines crossing mountains and forests. After the satellite preliminarily screens out pixels with safety hazards, the signal gateway station uses drones for precise inspections, and can accurately determine the specific location and type of safety hazards (such as tree flash hazards, flood hazards, or building obstructions). Therefore, when determining whether there are safety hazards in a predetermined area, the satellite first roughly determines the pixels with safety hazards based on the satellite remote sensing images of the predetermined area, and then the signal gateway station uses drones to inspect the ground corresponding to the pixels with safety hazards, thereby accurately determining whether there are safety hazards on the ground and the specific location of the safety hazards. Therefore, the coarse-to-fine monitoring method of the technical solution not only improves the monitoring efficiency, but also ensures the monitoring accuracy, and reduces the limitations of determining safety hazards only by drones. In addition, this technical solution can not only cover a large area, but also conduct detailed inspections on specific areas through the collaborative work of satellites and drones, which not only improves the efficiency and accuracy of monitoring safety hazards of power transmission lines, but also enhances the safety and stability of the power grid system. This solves the technical problems existing in the prior art of using only drones to monitor power transmission lines, such as small monitoring area, long monitoring time and high limitations.

[0061] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0062] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention. Example 2

[0063] Figure 7 FIG. 7 shows a satellite-based power transmission line monitoring device 700 according to this embodiment, which corresponds to the method according to the first aspect of embodiment 1. Figure 7 As shown, the device 700 includes: a pixel determination module 710, which is used for the satellite to obtain a satellite remote sensing image of a predetermined area and determine a plurality of pixels corresponding to the transmission line; an abundance value determination module 720, which is used for the satellite to determine the abundance value of the end element corresponding to each preset ground feature type in the pixel according to the frequency domain characteristics corresponding to the plurality of pixels, wherein the preset ground feature types include forest feature type, water feature type and building feature type; a hidden danger determination module 730, which is used for the satellite to determine whether there is a safety hazard on the ground corresponding to the corresponding pixel according to the abundance value through a monitoring model; an information sending module 740, which is used for the satellite to send the warning information corresponding to the ground with safety hazards to the signal gateway station; and an inspection module 750, which is used for the signal gateway station to use a drone to inspect the ground with safety hazards according to the warning information.

[0064] Optionally, the abundance value determination module 720 includes: a feature acquisition submodule, which is used by the satellite to acquire the first frequency domain features corresponding to the end elements of each preset land object type; and a first determination submodule, which is used by the satellite to determine the abundance value of the end element corresponding to each preset land object type in the pixel based on the first frequency domain features and the second frequency domain features corresponding to the pixel.

[0065] Optionally, the first determination submodule includes: an abundance value calculation unit, which is used for the satellite to calculate the abundance value of the end member corresponding to each preset land feature type in the pixel through a calculation formula pre-constructed according to the frequency domain characteristics and forest abundance value of the end member of the forest feature type, the frequency domain characteristics and water abundance value of the end member of the water feature type, the frequency domain characteristics and building abundance value of the building feature type, and the second frequency domain characteristics.

[0066] Optionally, the hidden danger determination module 730 includes: a second determination module, which is used for the satellite to pass through the fully connected layer of the monitoring model to determine the corresponding first feature information according to the abundance value; and a third determination module, which is used for the satellite to pass through the binary classifier of the monitoring model to determine whether there is a safety hazard on the ground corresponding to the corresponding pixel according to the first feature information.

[0067] Optionally, the training module is used to train the monitoring model in the following steps: a collection submodule is used to collect sample input information and corresponding sample output information, wherein the sample input information is the sample abundance value, and the sample output information is the sample safety hazard probability value; and a training submodule is used to train the monitoring model according to the sample input information and the corresponding sample output information through a gradient descent algorithm.

[0068] Thus, according to this embodiment, the satellite uses satellite remote sensing images combined with abundance value analysis to conduct preliminary screening, quickly cover large areas, and identify potential safety hazards. Compared with monitoring using only drones, satellite monitoring is not restricted by terrain and can effectively cope with complex environments such as power transmission lines crossing mountains and forests. After the satellite preliminarily screens out pixels with safety hazards, the signal gateway station uses drones for precise inspections, and can accurately determine the specific location and type of safety hazards (such as tree flash hazards, flood hazards, or building obstructions). Therefore, when determining whether there are safety hazards in a predetermined area, the satellite first roughly determines the pixels with safety hazards based on the satellite remote sensing images of the predetermined area, and then the signal gateway station uses drones to inspect the ground corresponding to the pixels with safety hazards, thereby accurately determining whether there are safety hazards on the ground and the specific location of the safety hazards. Therefore, the coarse-to-fine monitoring method of the technical solution not only improves the monitoring efficiency, but also ensures the monitoring accuracy, and reduces the limitations of determining safety hazards only by drones. In addition, this technical solution can not only cover a large area, but also conduct detailed inspections on specific areas through the collaborative work of satellites and drones, which not only improves the efficiency and accuracy of monitoring safety hazards of power transmission lines, but also enhances the safety and stability of the power grid system. This solves the technical problems existing in the prior art of using only drones to monitor power transmission lines, such as small monitoring area, long monitoring time and high limitations. Example 3

[0069] Figure 8 FIG. 8 shows a satellite-based power transmission line monitoring device 800 according to this embodiment, which corresponds to the method according to the first aspect of embodiment 1. Figure 8As shown, the device 800 includes: a processor 810; and a memory 820, which is connected to the processor 810 and is used to provide the processor 810 with instructions for processing the following processing steps: the satellite acquires a satellite remote sensing image of a predetermined area and determines a plurality of pixels corresponding to the transmission line; the satellite determines the abundance value of the end element corresponding to each preset land feature type in the pixel according to the frequency domain characteristics corresponding to the plurality of pixels, wherein the preset land feature types include forest land feature type, water body land feature type and building land feature type; the satellite determines whether there is a safety hazard on the ground corresponding to the corresponding pixel according to the abundance value through a monitoring model; the satellite sends the warning information corresponding to the ground with the safety hazard to the signal gateway station; and the signal gateway station uses a drone to inspect the ground with the safety hazard according to the warning information.

[0070] Optionally, the operation of the satellite determining the abundance value of the end-member corresponding to each preset land object type in the pixel based on the frequency domain characteristics corresponding to multiple pixels includes: the satellite obtains the first frequency domain characteristics corresponding to the end-member of each preset land object type; and the satellite determines the abundance value of the end-member corresponding to each preset land object type in the pixel based on the first frequency domain characteristics and the second frequency domain characteristics corresponding to the pixel.

[0071] Optionally, the satellite determines the abundance value of the end member corresponding to each preset land object type in the pixel based on the first frequency domain feature and the second frequency domain feature corresponding to the pixel, including: the satellite calculates the abundance value of the end member corresponding to each preset land object type in the pixel by using a calculation formula pre-constructed based on the frequency domain characteristics and forest abundance value of the end member of the forest land object type, the frequency domain characteristics and water abundance value of the end member of the water body land object type, the frequency domain characteristics and building abundance value of the building land object type, and the second frequency domain feature.

[0072] Optionally, the operation of the satellite determining whether there is a safety hazard on the ground corresponding to the corresponding pixel based on the abundance value through the monitoring model includes: the satellite determining the corresponding first feature information based on the abundance value through the fully connected layer of the monitoring model; and the satellite determining whether there is a safety hazard on the ground corresponding to the corresponding pixel based on the first feature information through the binary classifier of the monitoring model.

[0073] Optionally, the steps for training the monitoring model are as follows: collecting sample input information and corresponding sample output information, wherein the sample input information is the sample abundance value, and the sample output information is the sample safety hazard probability value; and training the monitoring model according to the sample input information and the corresponding sample output information through a gradient descent algorithm.

[0074] Thus, according to this embodiment, the satellite uses satellite remote sensing images combined with abundance value analysis to conduct preliminary screening, quickly cover large areas, and identify potential safety hazards. Compared with monitoring using only drones, satellite monitoring is not restricted by terrain and can effectively cope with complex environments such as power transmission lines crossing mountains and forests. After the satellite preliminarily screens out pixels with safety hazards, the signal gateway station uses drones for precise inspections, and can accurately determine the specific location and type of safety hazards (such as tree flash hazards, flood hazards, or building obstructions). Therefore, when determining whether there are safety hazards in a predetermined area, the satellite first roughly determines the pixels with safety hazards based on the satellite remote sensing images of the predetermined area, and then the signal gateway station uses drones to inspect the ground corresponding to the pixels with safety hazards, thereby accurately determining whether there are safety hazards on the ground and the specific location of the safety hazards. Therefore, the coarse-to-fine monitoring method of the technical solution not only improves the monitoring efficiency, but also ensures the monitoring accuracy, and reduces the limitations of determining safety hazards only by drones. In addition, this technical solution can not only cover a large area, but also conduct detailed inspections on specific areas through the collaborative work of satellites and drones, which not only improves the efficiency and accuracy of monitoring safety hazards of power transmission lines, but also enhances the safety and stability of the power grid system. This solves the technical problems existing in the prior art of using only drones to monitor power transmission lines, such as small monitoring area, long monitoring time and high limitations.

[0075] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0076] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0077] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0078] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0079] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0080] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0081] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A satellite-based power transmission line monitoring method, characterized in that: include: The satellite acquires a satellite remote sensing image of a predetermined area and determines a plurality of pixels corresponding to the transmission line; The satellite determines the abundance value of the end member corresponding to each preset ground object type in the pixel according to the frequency domain characteristics corresponding to the multiple pixels, wherein the preset ground object type includes a forest ground object type, a water ground object type and a building ground object type; The satellite determines whether there is a safety hazard on the ground corresponding to the corresponding pixel according to the abundance value through a monitoring model; The satellite sends warning information corresponding to the ground where there are potential safety hazards to the gateway station; as well as The gateway station uses a drone to conduct inspections on the ground where potential safety hazards exist according to the warning information, wherein The operation of the satellite determining the abundance value of the endmember corresponding to each preset ground object type in the pixel according to the frequency domain characteristics corresponding to the multiple pixels includes: The satellite acquires a first frequency domain feature corresponding to an end member of each preset ground feature type; as well as The satellite determines the abundance value of the endmember corresponding to each preset ground object type in the pixel according to the first frequency domain feature and the second frequency domain feature corresponding to the pixel.

2. The method according to claim 1, characterized in that The operation of determining, by the satellite, the abundance value of the endmember corresponding to each preset ground object type in the pixel according to the first frequency domain feature and the second frequency domain feature corresponding to the pixel, comprises: The satellite calculates the abundance value of the end member corresponding to each preset land feature type in the pixel by using a calculation formula pre-constructed based on the frequency domain characteristics and forest abundance value of the end member of the forest land feature type, the frequency domain characteristics and water abundance value of the end member of the water land feature type, the frequency domain characteristics and building abundance value of the building land feature type, and the second frequency domain characteristics.

3. The method according to claim 1, characterized in that The satellite determines whether there is a potential safety hazard on the ground corresponding to the corresponding pixel according to the abundance value through the monitoring model, including: The satellite determines corresponding first feature information according to the abundance value through the fully connected layer of the monitoring model; and The satellite determines whether there is a safety hazard on the ground corresponding to the corresponding pixel based on the first feature information through the binary classifier of the monitoring model.

4. The method according to claim 1, characterized in that The steps for training the monitoring model are as follows: Collecting sample input information and corresponding sample output information, wherein the sample input information is a sample abundance value, and the sample output information is a sample safety hazard probability value; as well as The monitoring model is trained according to the sample input information and the corresponding sample output information through a gradient descent algorithm.

5. A satellite-based power transmission line monitoring device, characterized in that: include: A pixel determination module, used for obtaining a satellite remote sensing image of a predetermined area by a satellite, and determining a plurality of pixels corresponding to a transmission line; An abundance value determination module, used for the satellite to determine the abundance value of the end member corresponding to each preset ground feature type in the pixel according to the frequency domain characteristics corresponding to the multiple pixels, wherein the preset ground feature types include forest ground feature type, water body ground feature type and building ground feature type; A hidden danger determination module, used for the satellite to determine whether there is a safety hazard on the ground corresponding to the corresponding pixel according to the abundance value through a monitoring model; An information sending module, used for the satellite to send early warning information corresponding to the ground with potential safety hazards to the information gateway station; as well as The inspection module is used for the gateway station to use a drone to inspect the ground where there are safety hazards according to the warning information, wherein The abundance value determination module comprises: A feature acquisition submodule, used for the satellite to acquire first frequency domain features corresponding to end members of each preset ground feature type; as well as The first determination submodule is used for the satellite to determine the abundance value of the end members corresponding to the respective preset ground object types in the pixel according to the first frequency domain feature and the second frequency domain feature corresponding to the pixel.

6. A satellite-based power transmission line monitoring device, characterized in that: include: processor; as well as A memory, connected to the processor, configured to provide the processor with instructions for processing the following processing steps: The satellite acquires a satellite remote sensing image of a predetermined area and determines a plurality of pixels corresponding to the transmission line; The satellite determines the abundance value of the end member corresponding to each preset ground object type in the pixel according to the frequency domain characteristics corresponding to the multiple pixels, wherein the preset ground object type includes a forest ground object type, a water ground object type and a building ground object type; The satellite determines whether there is a safety hazard on the ground corresponding to the corresponding pixel according to the abundance value through a monitoring model; The satellite sends warning information corresponding to the ground where there are potential safety hazards to the gateway station; as well as The gateway station uses a drone to conduct inspections on the ground where potential safety hazards exist according to the warning information, wherein The operation of the satellite determining the abundance value of the endmember corresponding to each preset ground object type in the pixel according to the frequency domain characteristics corresponding to the multiple pixels includes: The satellite acquires a first frequency domain feature corresponding to an end member of each preset ground feature type; as well as The satellite determines the abundance value of the endmember corresponding to each preset ground object type in the pixel according to the first frequency domain feature and the second frequency domain feature corresponding to the pixel.

7. An integrated electronic system comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method of claim 1.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to claim 1 are implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to claim 1 are implemented.

Images