A method and system for updating power tower database using image map service

Abstract

A method and system for updating a power pole tower database using an image map service. The method includes determining a power pole tower update range in an image map service, automatically identifying power pole towers in the image map service based on the power pole tower update range; automatically superimposing and analyzing the identified power pole tower data with the existing power pole tower data in the database to determine newly added power pole towers and removed power pole towers; displaying the newly added power pole towers and removed power pole towers in the image map service for user verification, and updating the verified newly added power pole towers and removed power pole towers into the power pole tower database. The solution of the present invention improves the efficiency of updating the power pole tower database.

Description

Technical Field

[0001] The present invention belongs to the field of power data management, and in particular relates to a method and system for updating a power tower database using an image map service. Background Art

[0002] Power towers are the main supports for overhead transmission lines. The relevant data of power towers are an important part of the basic data of transmission lines. With the addition, removal and movement of power towers, the relevant data in the database needs to be updated synchronously. The maintenance methods of power tower databases in the prior art mainly include manual field survey methods and manual interpretation methods based on remote sensing images. Among them, manual field surveys are to send technicians to the area of ​​concern for field surveys, and check whether there are any new, removed and moved power towers by comparing with the existing line single-line diagram. If so, the position coordinates of the power towers are measured and recorded using the GPS / Beidou positioning terminal. This method has a large manual workload, low efficiency, and some areas cannot be reached. The manual interpretation based on remote sensing images is mainly to perform manual interpretation on offline remote sensing images, and then compare the interpretation results with the existing power tower positions in the database to find the newly added, removed and moved power towers and complete the database update. However, this method still has the disadvantages of large workload and low efficiency, and requires manual interpretation in professional remote sensing software, which increases the skill requirements of operators. Summary of the invention

[0003] In order to solve the deficiencies in the prior art, the present invention provides a method and system for updating a power pole tower database using an image map service, so as to solve the technical problem that the power pole tower database update is too dependent on manual operation, resulting in low efficiency.

[0004] In order to solve the above technical problems, the present invention adopts the following technical solutions.

[0005] The present invention first discloses a method for updating a power tower database using an image map service, the method comprising the following steps:

[0006] Step 1, determining an update range of a power pole tower in an image map service, and automatically identifying the power pole tower in the image map service by using a tile inference algorithm based on the update range of the power pole tower;

[0007] Step 2: Automatically superimpose and analyze the identified power pole tower data with the existing power pole tower data in the database to determine the newly added power pole towers and the removed power pole towers;

[0008] Step 3: Display the newly added power poles and removed power poles in the image map service for verification by the user, and update the verified newly added power poles and removed power poles into the power pole database.

[0009] The present invention further includes the following preferred embodiments:

[0010] In step 1, determining the update range of the power tower in the image map service specifically includes:

[0011] The update range of the power poles and towers in the image map service is determined by selecting an administrative division in the image map service interface, or by drawing a rectangle or an irregular polygon on the image map service interface.

[0012] Based on the update range of the power pole tower, automatically identifying the power pole tower by using a tile inference algorithm in the image map service specifically includes:

[0013] Step 1.1: Calculate the bounding rectangle of the power tower update area area ;

[0014] Step 1.2: Calculate the bounding rectangle Rect area The map tile number within the range, the upper left corner tile is marked as tile tl , whose row and column numbers are Row tl and Col tl , the lower right corner tile is marked as tile br , whose row and column numbers are denoted by Row br and Col br , the length and width of each tile is 256;

[0015] Step 1.3: Traverse all tiles from left to right and from top to bottom. (i,j) , and the corresponding spatial range is recorded as Rect tile , where i is the tile row number and j is the tile column number, the following judgment is made:

[0016] If Rect area ∩Rect tile If it is empty, skip the tile and traverse the next tile;

[0017] If Rect area ∩Rect tile If it is not empty, download and read the tile to the right of this tile (i,j+1) , bottom tile (i+1,j) , bottom right tile (i+1,j+1) , and combine these three tiles with tile (i,j) Aggregate into a picture of size 512×512, denoted as TILE (i,j) ;

[0018] Perform inference prediction on the tile image to obtain the tile (i,j) Result of power tower prediction box set (i,j) ;

[0019] Step 1.4: After obtaining the predicted frame set of all tiles, complete the inference prediction of all tiles, convert the predicted frame into geographic coordinates, and obtain the predicted frame set Result All ;

[0020] Step 1.5: Use NMS algorithm to analyze the result All The results are deduplicated to obtain the final prediction box set Result;

[0021] Step 1.6: Generate a vector layer for automatically identifying power towers based on the final prediction box set Result predict .

[0022] In step 2, the identified power tower data is automatically superimposed and analyzed with the existing power tower data in the database, specifically including:

[0023] Step 2.1: Automatically load the power tower vector layer predict to the image map service;

[0024] Step 2.2: Using the range Area as the query condition, retrieve the existing power poles and towers within the range from the database, and generate a temporary layer and load it into the image map service, denoted as layer store ;

[0025] Step 2.3: Layer predict Layers and layers store Automatic overlay analysis of layers. predict In but not in layer store The power tower prediction box in the layer is recorded as the newly added power tower. store In but not in layer predict The power tower prediction box in the image is recorded as removing the power tower; the overlay analysis results are used to generate the power tower change layer layer change , loaded into the image map service.

[0026] The step 3 specifically includes:

[0027] The user changes the layer in the power tower layer change The newly added power poles and removed power poles are checked and verified one by one to eliminate false detections, and the information of the changed power poles that are detected correctly is updated to the system database.

[0028] The present invention also discloses a system for updating a power tower database using an image map service using the aforementioned method for updating a power tower database using an image map service, comprising a power tower automatic identification module, a power tower change analysis module and a power tower data update module.

[0029] The power pole automatic identification module is used to determine the power pole update range in the image map service, and based on the power pole update range, automatically identify the power pole in the image map service through a tile inference algorithm;

[0030] The power pole tower change analysis module is used to automatically overlay and analyze the identified power pole tower data with the existing power pole tower data in the database to determine the addition of new power pole towers and the removal of power pole towers;

[0031] The power pole data updating module is used to display the newly added power poles and removed power poles in the image map service for user verification, and update the verified newly added power poles and removed power poles into the power pole database.

[0032] Accordingly, the present application also discloses a terminal, including a processor and a storage medium;

[0033] The storage medium is used to store instructions;

[0034] The processor is used to operate according to the instructions to execute the steps of the method for updating the power pole tower database using the image map service.

[0035] Correspondingly, the present application also discloses a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the aforementioned method for updating a power pole tower database using an image map service are implemented.

[0036] The beneficial effect of the present invention is that, compared with the prior art, the present invention provides a method and system for updating the power tower database using image map services, and uses a machine interpretation and manual assisted inspection mode to complete the update of the power tower database, saving the time for internal interpretation, and no manual field investigation is required, which significantly improves the work efficiency. In addition, the method of the present invention reduces the skill requirements of remote sensing interpretation personnel. The entire update process is completed in the web-side system without the need for professional remote sensing software. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flow chart of the method for updating the power tower database using the image map service in the present invention.

[0038] Figure 2It is a module diagram of the method for updating the power tower database in the present invention.

[0039] Figure 3 It is the method for obtaining the bounding rectangle Rect in the present invention. area And obtain the schematic diagram of the corresponding upper left corner and lower right corner tile numbers.

[0040] Figure 4 It is a schematic diagram of obtaining a set of tile numbers to be calculated in the present invention.

[0041] Figure 5 It is a schematic diagram of the process of determining whether the current tile needs to be processed in the present invention.

[0042] Figure 6 This is the current tile tile in the present invention (i,j) With the right tile (i,j+1) , bottom tile (i+1,j) and the lower right tile (i+1,j+1) Aggregate picture TILE (i,j) Schematic diagram of the process used for inference prediction.

[0043] Figure 7 It is the picture TILE of four tiles aggregated in the present invention (i,j) Perform inference prediction and obtain the power tower prediction frame set Result (i,j) Schematic diagram of the process.

[0044] Figure 8 It is a local example diagram of the prediction frame set Result of the final automatic power pole tower recognition result generated in the present invention.

[0045] Fig. 9 It is a structural schematic diagram of a system for updating a power pole tower database using an image map service in the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present invention more clear, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0047] The embodiments described in this application are only some embodiments of the present invention, not all embodiments. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the protection scope of the present invention.

[0048] In view of the deficiencies of the prior art, the present invention proposes a method and system for updating a power tower database using an image map service, and the database update process is completed in the image map service system on the web side. An image map refers to a map with ground remote sensing images. It is a map that directly reflects the geographical characteristics and spatial distribution of the mapping object by using aerial photographs or satellite remote sensing images, through geometric correction, projection transformation and scale naturalization, and using certain map symbols and annotations. The image map service is a service mode in which the image map is published to a specified network segment through the network, and users can directly use the image map in the browser. The system releases a satellite remote sensing image service with a resolution better than 0.5 meters every year, and completes the annual update of the power tower data based on the newly released remote sensing image service and the existing power tower data in the database, so as to reduce the workload of field surveys and internal interpretation, reduce the skill requirements for technical personnel, and efficiently, normalize and standardize the annual update of power tower data.

[0049] See also Figure 1 As shown, the method for updating the power tower database using the image map service disclosed in the present invention includes the following steps:

[0050] Step 1: Determine the update range of the power pole tower in the image map service, and based on the update range of the power pole tower, automatically identify the power pole tower in the image map service through a tile inference algorithm.

[0051] See also Figure 2 First, specify the area where the power poles and towers need to be updated in the image map service. Specifically, you can select an administrative division, such as a city or a county in the image map service interface; you can also use the polygon drawing function provided by the system to select, such as drawing a rectangle or irregular polygon on the image map service interface. Specify the area (Area) of the power pole database to be updated in the image map service.

[0052] After specifying the area, you can click the "Automatic Identification" button on the page to start the automatic power pole tower identification function. Based on the current image service, the system's integrated automatic target detection algorithm is called to complete the automatic identification of power pole towers in the selected area.

[0053] Since the original image map is very large and difficult to load on the web page, before publishing the image map service, the image map needs to be cut into multiple smaller slice files according to certain rules. The size of each slice file is generally 256×256, and one slice file is one tile. When users browse, they only load the slice files of the browsing area to improve the browsing experience. Therefore, after receiving the automatic power pole tower recognition command, the background computing server starts the tile image inference process.

[0054] In a preferred embodiment, the specific inference steps of the tile image include:

[0055] Step 1.1: Calculate the bounding rectangle of the area area ,like Figure 3 As shown;

[0056] Step 1.2: Calculate the bounding rectangle Rect area The map tile number within the range, the upper left corner tile is marked as tile tl , whose row and column numbers are Row tl and Col tl , the lower right corner tile is marked as tile br , whose row and column numbers are denoted by Row br and Col br , the length and width of each tile are 256; obtain the set of tile numbers that will participate in the calculation, such as Figure 4 as stated;

[0057] Step 1.3: Traverse all tiles from left to right and from top to bottom. (i,j) (i is the tile row number, j is the tile column number), and the corresponding spatial range is recorded as Rect tile , make the following judgment:

[0058] See also Figure 5 , if Rect area ∩Rect tile If it is empty, that is, the two do not intersect, then skip the tile and traverse the next tile.

[0059] If Rect area ∩Rect tile If it is not empty, that is, the two tiles intersect, then download and read the tile to the right of the tile. (i,j+1) , bottom tile (i+1,j) , bottom right tile (i+1,j+1) , and combine these three tiles with tile (i,j) Aggregate into a picture of size 512×512, denoted as TILE (i,j) ,like Figure 6 Through tile synthesis, the towers are displayed completely in the tiles as much as possible, and more background information is introduced to improve the accuracy of subsequent reasoning and prediction. The subsequent steps only require the NMS algorithm to perform deduplication processing.

[0060] Perform inference prediction on the tile image. The inference prediction algorithm may include Faster RCNN or YOLO series, and obtain tile (i,j) Result of power tower prediction box set (i,j)(Result (i,j) It consists of one or more rectangular boxes, each of which is a tower prediction box, that is, a tower target detected by reasoning. Each rectangular box is used in TILE (i,j) The upper left corner coordinates and lower right corner coordinates in the tile represent that the geographic coordinates of the rectangular box are calculated according to the tile number (i, j) and the position of the rectangular box in the tile, so that a layer with geographic coordinates can be formed in the subsequent steps, such as Figure 7 shown.

[0061] Step 1.4: After obtaining the predicted frame set of all tiles, complete the inference prediction of all tiles, convert the predicted frame into geographic coordinates, and obtain the predicted frame set Result All ,like Figure 8 shown.

[0062] The prediction box set Result of a single tile inference prediction (i,j) The coordinates are described as row and column numbers relative to the upper left corner of the tile. When merging multiple tile prediction boxes, they need to be converted into geographic coordinates. (i,j) The latitude and longitude coordinates of the upper left corner are (lng (i,j) ,lat (i,j) ), where lng (i,j) is longitude, lat (i,j) is the latitude, the tile resolution is res, Result (i,j) A rectangular box in Result (i,j,k) The coordinates are described as (col_s (i,j,k) ,row_s (i,j,k) ,col_e (i,j,k) ,row_e (i,j,k) ), where col_s (i,j,k) is the upper left column number, row_s (i,j,k) is the row number in the upper left corner, col_e (i,j,k) is the lower right column number, row_e (i,j),k The row number in the lower right corner. (i,j,k) The geographic coordinates are expressed as (lng_s (i,j,k) ,lat_s (i,j,k) ,lng_e (i,j,k) ,lat_e (i,j,k) ),in:

[0063] lng_s (i,j,k) =lng (i,j) +res×col_s (i,j,k)

[0064] lat_s (i,j,k) =lat(i,j) +res×row_s (i,j,k)

[0065] lng_e (i,j,k) =lng (i,j) +res×col_e (i,j,k)

[0066] lat_e (i,j,k) =lat (i,j) +res×row_e (i,j,k)

[0067] After all prediction boxes are converted into geographic coordinates, the prediction box set Result is obtained. All , where each box represents a detected tower, and the coordinates of each box are the longitude and latitude geographic coordinates.

[0068] Step 1.5: Use NMS algorithm to analyze the result All The results are deduplicated to obtain the final prediction box set Result. The NMS algorithm refers to the non-maximum suppression algorithm. When detecting a target, there may be multiple detection boxes for the same target. The NMS algorithm is used for calculation, and only one box is retained for one target.

[0069] Step 1.6: Generate a vector layer for automatically identifying power towers based on the final prediction box set Result predict .

[0070] Step 2: Automatically overlay and analyze the identified power pole tower data with the existing power pole tower data in the database to determine the newly added power pole towers and the removed power pole towers.

[0071] In step 2, the newly generated power tower vector layer layer predict Load it into the image map service and perform overlay analysis with the existing power tower data in the area in the database system. The specific steps include:

[0072] Step 2.1: Automatically load the power tower vector layer predict to the image map service.

[0073] Step 2.2: Using the range Area as the query condition, retrieve the existing power poles and towers within the range from the database system, generate a temporary layer and load it into the image map service, recorded as layer store .

[0074] Step 2.3: Layer predict Layers and layers store Automatic overlay analysis of layers.predict In but not in layer store The power tower prediction box in the layer is recorded as the newly added power tower. store In but not in layer predict The power tower prediction box in the image is recorded as removing the power tower. The overlay analysis results are used to generate the power tower change layer layer change , loaded into the image map service.

[0075] The moved power poles cannot be directly identified through the above process, and they appear in the map as a pair of a newly added pole and a removed pole.

[0076] Step 3: Display the newly added power poles and removed power poles in the image map service for user verification, and update the verified newly added power poles and removed power poles into the power pole database.

[0077] For the newly added or removed power poles, the user can manually add the power pole change layer on the image map service page. change Check and verify each one by one to eliminate false detections, and update the changed power tower information that is detected correctly into the system database.

[0078] The beneficial effect of the present invention is that, compared with the prior art, the present invention provides a method and system for updating the power tower database using image map services, and uses a machine interpretation and manual assisted inspection mode to complete the update of the power tower database, saving the time for internal interpretation, and no manual field investigation is required, which significantly improves the work efficiency. In addition, the method of the present invention reduces the skill requirements of remote sensing interpretation personnel. The entire update process is completed in the web-side system without the need for professional remote sensing software.

[0079] The present invention may be a system, method and / or computer program product. Fig. 9 The present invention also discloses a system for updating a power pole tower database using an image map service based on the aforementioned method for updating a power pole tower database using an image map service, comprising a power pole tower automatic identification module 1, a power pole tower change analysis module 2 and a power pole tower data update module 3.

[0080] The power pole automatic identification module 1 is used to determine the power pole update range in the image map service, and based on the power pole update range, automatically identify the power pole in the image map service through a tile inference algorithm;

[0081] The power pole tower change analysis module 2 is used to automatically overlay and analyze the identified power pole tower data with the existing power pole tower data in the database to determine the newly added power pole towers and the removed power pole towers;

[0082] The power pole data updating module 3 is used to display the newly added power poles and removed power poles in the image map service for user verification, and update the verified newly added power poles and removed power poles into the power pole database.

[0083] Based on the spirit of the present invention, those skilled in the art can easily think that a computer program product can be obtained based on the aforementioned method of updating the power pole tower database using the image map service. The computer program product may include a computer-readable storage medium, which carries computer-readable program instructions for enabling the processor to implement various aspects of the present disclosure. That is, the present application also includes a terminal, including a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to perform the steps of the aforementioned method of updating the power pole tower database using the image map service.

[0084] Computer readable storage medium can be a tangible device that can keep and store the instructions used by the instruction execution device. Computer readable storage medium can be, for example, - but not limited to - electrical storage device, magnetic storage device, optical storage device, electromagnetic storage device, semiconductor storage device or any suitable combination of the above. More specific examples (non-exhaustive list) of computer readable storage medium include: portable computer disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device, for example, punch card or groove protrusion structure with instructions stored thereon and any suitable combination of the above. Computer readable storage medium used here is not interpreted as instantaneous signal itself, such as radio wave or other free propagating electromagnetic wave, electromagnetic wave propagated by waveguide or other transmission medium (for example, light pulse by optical fiber cable) or electrical signal transmitted by wire.

[0085] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0086] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages-such as Smalltalk, C++, etc., and conventional procedural programming languages-such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network-including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA) may be personalized by utilizing the state information of a computer-readable program instruction, and the electronic circuit may execute a computer-readable program instruction, thereby realizing various aspects of the present disclosure.

[0087] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for updating a power tower database using an image map service, characterized in that: The following steps are involved: Step 1: determining an update range of a power pole tower in an image map service, and automatically identifying the power pole tower in the image map service by using a tile inference algorithm based on the update range of the power pole tower; Step 2: Automatically superimpose and analyze the identified power pole tower data with the existing power pole tower data in the database to determine the newly added power pole towers and the removed power pole towers; Step 3: Display the newly added power poles and removed power poles in the image map service for verification by the user, and update the verified newly added power poles and removed power poles into the power pole database; In step 1, determining the update range of the power tower in the image map service specifically includes: Determine the update range of the power poles and towers in the image map service by selecting an administrative division in the image map service interface, or by drawing a rectangle or an irregular polygon on the image map service interface; Based on the update range of the power pole tower, automatically identifying the power pole tower by using a tile inference algorithm in the image map service specifically includes: Step 1.1: Calculate the bounding rectangle of the power tower update area area ; Step 1.2: Calculate the bounding rectangle Rect area The map tile number within the range, the upper left corner tile is marked as tile tl , whose row and column numbers are Row tl and Col tl , the lower right corner tile is marked as tile br , whose row and column numbers are denoted by Row br and Col br , the length and width of each tile is 256; Step 1.3: Traverse all tiles from left to right and from top to bottom. (i,j) , and the corresponding spatial range is recorded as Rect tile , where i is the tile row number and j is the tile column number, the following judgment is made: If Rect area ∩Rect tile If it is empty, skip the tile and traverse the next tile; If Rect area ∩Rect tile If it is not empty, download and read the tile to the right of this tile (i,j+1) , bottom tile (i+1,j) , bottom right tile (i+1,j+1) , and combine these three tiles with tile (i,j) Aggregate into a picture of size 512×512, denoted as TILE (i,j) ; Perform inference prediction on the tile image to obtain the tile (i,j) Result of power tower prediction box set (i,j) ; Step 1.4: After obtaining the predicted frame set of all tiles, complete the inference prediction of all tiles, convert the predicted frame into geographic coordinates, and obtain the predicted frame set Result All ; Step 1.5: Use NMS algorithm to analyze the result All The results are deduplicated to obtain the final prediction box set Result; Step 1.6: Generate a vector layer for automatically identifying power towers based on the final prediction box set Result predict .

2. The method for updating the power tower database using the image map service according to claim 1, characterized in that: In step 2, the identified power tower data is automatically superimposed and analyzed with the existing power tower data in the database, specifically including: Step 2.1: Automatically load the power tower vector layer predict to the image map service; Step 2.2: Using the range Area as the query condition, retrieve the existing power poles and towers within the range from the database, and generate a temporary layer and load it into the image map service, denoted as layer store ; Step 2.3: Layer predict Layers and layers store Automatic overlay analysis of layers. predict In but not in layer store The power tower prediction box in the layer is recorded as the newly added power tower. store In but not in layer predict The power tower prediction box in the image is recorded as removing the power tower; the overlay analysis results are used to generate the power tower change layer layer change , loaded into the image map service.

3. The method for updating the power tower database using the image map service according to claim 2, characterized in that: The step 3 specifically includes: The user changes the layer in the power tower layer change The newly added power poles and removed power poles are checked and verified one by one to eliminate false detections, and the information of the changed power poles that are detected correctly is updated to the system database.

4. A system for updating a power tower database using an image map service, comprising a power tower automatic identification module, a power tower change analysis module and a power tower data update module, characterized in that: The power pole automatic identification module is used to determine the power pole update range in the image map service, and based on the power pole update range, automatically identify the power pole in the image map service through a tile inference algorithm; The power pole tower change analysis module is used to automatically overlay and analyze the identified power pole tower data with the existing power pole tower data in the database to determine the addition of new power pole towers and the removal of power pole towers; The power pole tower data update module is used to display the newly added power pole towers and removed power pole towers in the image map service for verification by the user, and update the verified newly added power pole towers and removed power pole towers into the power pole tower database; The power tower automatic identification module is further used for: Determine the update range of the power poles and towers in the image map service by selecting an administrative division in the image map service interface, or by drawing a rectangle or an irregular polygon on the image map service interface; The power tower automatic identification module is further used for: Step 1.1: Calculate the bounding rectangle of the power tower update area area ; Step 1.2: Calculate the bounding rectangle Rect area The map tile number within the range, the upper left corner tile is marked as tile tl , whose row and column numbers are Row tl and Col tl , the lower right corner tile is marked as tile br , whose row and column numbers are denoted by Row br and Col br , the length and width of each tile is 256; Step 1.3: Traverse all tiles from left to right and from top to bottom. (i,j) , and the corresponding spatial range is recorded as Rect tile , where i is the tile row number and j is the tile column number, the following judgment is made: If Rect area ∩Rect tile If it is empty, skip the tile and traverse the next tile; If Rect area ∩Rect tile If it is not empty, download and read the tile to the right of this tile (i,j+1) , bottom tile (i+1,j) , bottom right tile (i+1,j+1) , and combine these three tiles with tile (i,j) Aggregate into a picture of size 512×512, denoted as TILE (i,j) ; Perform inference prediction on the tile image to obtain the tile (i,j) Result of power tower prediction box set (i,j) ; Step 1.4: After obtaining the predicted frame set of all tiles, complete the inference prediction of all tiles, convert the predicted frame into geographic coordinates, and obtain the predicted frame set Result All ; Step 1.5: Use NMS algorithm to analyze the result All The results are deduplicated to obtain the final prediction box set Result; Step 1.6: Generate a vector layer for automatically identifying power towers based on the final prediction box set Result predict .

5. The system for updating a power tower database using an image map service according to claim 4, characterized in that: The power tower change analysis module is further used for: Step 2.1: Automatically load the power tower vector layer predict to the image map service; Step 2.2: Using the range Area as the query condition, retrieve the existing power poles and towers within the range from the database, and generate a temporary layer and load it into the image map service, denoted as layer store ; Step 2.3: Layer predict Layers and layers store Automatic overlay analysis of layers. predict In but not in layer store The power tower prediction box in the layer is recorded as the newly added power tower. store In but not in layer predict The power tower prediction box in the image is recorded as removing the power tower; the overlay analysis results are used to generate the power tower change layer layer change , loaded into the image map service.

6. The system for updating a power tower database using an image map service according to claim 5, characterized in that: The power tower data updating module is further used for: The user changes the layer in the power tower layer change The newly added power poles and removed power poles are checked and verified one by one to eliminate false detections, and the information of the changed power poles that are detected correctly is updated to the system database.

7. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the method for updating the power pole tower database using the image map service according to any one of claims 1 to 3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method for updating the power tower database using image map services described in any one of claims 1 to 3 are implemented.

Images