Method and device for deduplication of vaccine wood and computer equipment

Abstract

The application discloses a method and device for removing repeated epidemic trees and a computer device. The method comprises the following steps: obtaining epidemic tree point data in an original image; forming a grid area corresponding to the epidemic tree according to the epidemic tree point data; dividing the grid area into a plurality of subareas, and associating a subarea with epidemic tree points with a subimage area in the original image where the epidemic tree points are located, the size of the subimage area being smaller than that of the original image; and comparing the difference values between the subimage areas where the epidemic tree points are located, and taking the epidemic tree corresponding to the epidemic tree points in the subimage area with a difference value smaller than a preset value as a repeated epidemic tree, which can effectively solve the problem of low efficiency caused by the need to calculate a large amount of data in the original method.

Description

Technical Field

[0001] This invention relates to the field of image recognition and positioning technology, and in particular to a method, apparatus, and computer equipment for deduplication of infected wood. Background Technology

[0002] Pine wilt disease, also known as pine wilt, is a devastating forest disease caused by the pine wilt nematode. Infected pine trees have yellowish-brown or reddish-brown needles that wilt and droop, resin secretion stops, and the trees gradually dry out and die, eventually rotting. Because the pine wilt nematode is highly virulent, the host dies quickly, and the disease spreads rapidly, it is difficult to detect in time due to the large area of ​​forests, making it very difficult to control.

[0003] Because infected pine wood nematode trees are yellowish-brown or reddish-brown and their needles gradually wither, they differ in appearance from normal pine trees and other tree species in the forest. Therefore, there are currently solutions that use remote sensing aerial photography to obtain images of the forest and intelligently identify infected trees based on deep learning technology.

[0004] Existing solutions identify and locate infected trees on aerial photographs. This approach first uses remote sensing aerial photography to acquire aerial images of the forest. Adjacent aerial images often overlap significantly, and phase control points are set up at intervals on the ground. During the remote sensing aerial photography process, different batches of drones are deployed in the same survey to acquire drone aerial images under uncontrollable factors such as weather, survey area, and lighting conditions. After acquiring the original drone aerial images, image stitching software or algorithms are used to match and stitch them together. However, due to differences in shooting positions, survey areas, perspective distortion, inaccurate matching, and external factors such as wind-induced leaf movement and changes in weather and lighting, the stitched image accumulates duplicate infected tree data. This requires extensive Cartesian processing of the large amount of data in the original images, resulting in high computational cost and low efficiency. Summary of the Invention

[0005] This invention provides a method for deduplicating infected wood, which can effectively solve the problem of low efficiency caused by the need to calculate a large amount of data in the current original method.

[0006] According to one aspect of the present invention, a method for deduplicating infected trees is provided, comprising: acquiring infected tree point data in an original image; forming a grid region corresponding to the infected tree based on the infected tree point data; dividing the grid region into multiple sub-regions, and associating the sub-regions containing the infected tree points with the sub-image regions in the original image where the infected tree points are located, wherein the size of the sub-image regions is smaller than the size of the original image; comparing the discriminant values ​​between the sub-image regions where the infected tree points are located, and identifying the infected trees corresponding to the infected tree points in the sub-image regions where the discriminant values ​​are less than a preset value as duplicate infected trees.

[0007] Furthermore, the step of acquiring the infected tree spot data in the original image includes: acquiring the original image through an imaging device; and storing the infected tree spot data obtained by data processing of the original image into a database.

[0008] Furthermore, the step of obtaining the infected tree spot data in the original image also includes: cleaning the infected tree spot data in the database and removing the infected tree spot data that does not meet the preset conditions from the database.

[0009] Furthermore, the step of forming a grid region corresponding to the infected tree based on the infected tree data includes: taking one of the infected trees as a target infected tree point; and forming a region centered on the target infected tree point as the grid region.

[0010] Furthermore, the step of dividing the grid region into multiple sub-regions and associating the sub-region containing the infected tree spot with the sub-image region where the infected tree spot is located in the original image, wherein the size of the sub-image region is smaller than the size of the original image, includes: dividing the grid region into division regions of the same shape, using the division regions as the sub-regions, using the sub-region where the target infected tree spot is located as the standard sub-region, and the target infected tree spot is located at the center of the sub-region.

[0011] Further, the step of comparing the difference values ​​between the sub-image regions where the infected tree point is located, and classifying the infected tree corresponding to the infected tree point in the sub-image region whose difference value is less than a preset value as a duplicate infected tree, includes: obtaining the image parameters of the infected tree corresponding to the infected tree point in the sub-image; obtaining the image parameters of the infected tree corresponding to the target infected tree point in the standard sub-region; comparing the difference value between the image parameters of the infected tree corresponding to the infected tree point and the image parameters of the infected tree corresponding to the target infected tree point, and using the difference value as the difference value; and marking the infected tree whose difference value is less than the preset value compared to the target infected tree as a duplicate infected tree.

[0012] Furthermore, when the sub-region includes the target infected tree point and at least one infected tree point, the deduplication method further includes: obtaining the sub-image region associated with the sub-region; determining the number and location of infected trees corresponding to the infected tree point based on the sub-image region; and updating the number and location of infected trees corresponding to the infected tree point in the sub-region based on the number and location of infected trees determined by the sub-image region.

[0013] Furthermore, the deduplication method also includes: removing the data of the diseased tree points corresponding to the duplicated diseased trees from the database.

[0014] According to another aspect of the present invention, a deduplication device for infected wood is provided, comprising: a data acquisition unit for acquiring infected wood point data in an original image; a grid forming unit for forming a grid region corresponding to the infected wood based on the infected wood point data; a region association unit for dividing the grid region into multiple sub-regions and associating the sub-regions containing infected wood points with the sub-image regions in the original image where the infected wood points are located, wherein the size of the sub-image regions is smaller than the size of the original image; and a region comparison unit for comparing the difference values ​​between the sub-image regions where the infected wood points are located, and identifying the infected wood corresponding to the infected wood points in the sub-image regions where the difference value is less than a preset value as duplicate infected wood.

[0015] According to another aspect of the present invention, a computer device is provided, comprising a processor and a memory, the processor being electrically connected to the memory, the memory being used to store instructions and data, and the processor being used to perform steps in the deduplication method for deduplication of wood as described in any of the preceding claims.

[0016] The beneficial effects of this invention are as follows: This invention forms a grid region corresponding to the infected trees by acquiring infected tree point data from the original image. By limiting the grid region and filtering it, the filtering range is narrowed, reducing the processing bandwidth required. The sub-image region is divided into multiple sub-regions. By comparing the discriminant values ​​between the sub-image regions where the infected tree points are located, the infected trees corresponding to the infected tree points in the sub-regions with discriminant values ​​less than a preset value are identified as duplicate infected trees. By comparing the discriminant values ​​of the infected tree points in the sub-region images, duplicate infected trees can be determined through the attribute information of the sub-region images themselves. This avoids the computational pressure caused by using other algorithms and avoids the inefficiency problem caused by the Cartesian product of a large amount of data required by the original method. Attached Figure Description

[0017] The technical solution and other beneficial effects of the present invention will become apparent from the following detailed description of specific embodiments of the invention, in conjunction with the accompanying drawings.

[0018] Figure 1 This is a flowchart illustrating the steps of the deduplication method for infected wood provided in Embodiment 1 of the present invention.

[0019] Figure 2 This is a flowchart illustrating step S110 in an embodiment of the present invention.

[0020] Figure 3 This is a flowchart illustrating step S120 in an embodiment of the present invention.

[0021] Figure 4 This is a flowchart illustrating step S140 in an embodiment of the present invention.

[0022] Figure 5 This is a schematic diagram of the structure of the de-weighting device for epidemic wood provided in an embodiment of the present invention.

[0023] Figure 6 This is a schematic diagram of a computer device structure provided for an embodiment of the present invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0025] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection, an electrical connection, or a connection that allows for communication; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0026] Now refer to Figure 1 , Figure 1 This is a flowchart illustrating the steps of a method for removing excess wood from diseased trees according to Embodiment 1 of the present invention. The method includes the following steps.

[0027] Step S110: Obtain the data of infected tree points in the original image.

[0028] For example, in the original image, the infected trees have corresponding image features due to their different appearances. Therefore, if there is a point in the original image that matches the image features of an infected tree, then that point is an infected tree point, and the infected tree point in the original image necessarily corresponds to an infected tree. That is, there is a one-to-one correspondence between the infected tree point with the image feature in the original image and the infected tree. After obtaining the image features of the infected trees, the original image is filtered according to the one-to-one correspondence between the infected trees and the infected tree points in the original image, and the image features of the infected trees are used to determine the location and image information of the infected tree points, thereby obtaining the infected tree point data in the original image.

[0029] For example, see Figure 2 , Figure 2 This is a flowchart illustrating step S110 in an embodiment of the present invention. Step S110 includes the following steps:

[0030] Step S111: Acquire the original image using an imaging device.

[0031] For example, an imaging device carried by a drone or other remote sensing flight equipment can be used to photograph a pine forest and obtain an image of the pine trees as the original image.

[0032] Step S112: The original image is processed to obtain a database including the data of the infected tree spots.

[0033] For example, the original image is subjected to diseased tree detection and identification to obtain diseased tree spot information in the original image. This diseased tree spot information constitutes the database information of diseased tree spot data, and the diseased tree spot data obtained after data processing is stored in the database.

[0034] Step S113: Clean the infected tree data in the database and remove the infected tree data that does not meet the preset conditions from the database.

[0035] For example, after importing the diseased tree data obtained by processing images captured by drones into the database using a data migration tool, erroneous data such as all field values ​​being exactly the same, missing diseased tree data attributes, or all fields of the diseased tree data being empty are cleaned to remove the diseased tree data that does not meet the preset conditions from the database.

[0036] Step S120: Based on the infected tree data, form a grid area corresponding to the infected tree.

[0037] For example, the infected tree spot data is divided into grid areas, and the infected tree spots corresponding to the infected tree spot data are located within the grid areas. The size of the grid can be set according to industry rules, such as the actual area of ​​the pine forest, the accuracy of the aerial images, and the processing efficiency of the processor.

[0038] For example, see Figure 3 , Figure 3 This is a flowchart illustrating step S120 in an embodiment of the present invention. Step S120 includes the following steps.

[0039] Step S121: Select one of the infected trees as the target infected tree point.

[0040] For example, any infected tree in the list is selected and designated as the target infected tree point.

[0041] Step S122: A region centered on the target infected point is formed as the grid region.

[0042] For example, with the target infected tree as the center, the preset orientation within the extended range is defined as the grid area. Specifically, the grid area where the target infected tree is located can be linked to the URL location of the orthophoto image of the original image corresponding to the grid area, facilitating the acquisition of image information corresponding to the grid area range for subsequent operations.

[0043] Step S130: Divide the grid area into multiple sub-regions, and associate the sub-regions containing the infected wood spots with the sub-image regions where the infected wood spots are located in the original image, wherein the size of the sub-image regions is smaller than the size of the original image.

[0044] For example, after dividing the grid area into multiple sub-regions according to a preset query area size, the multiple sub-regions are associated one by one with the corresponding sub-image regions in the original image, and the size of the sub-image region is smaller than the size of the original image.

[0045] For example, step 130 includes the following steps.

[0046] The grid area is divided into sub-regions of the same shape, and the sub-regions are used as sub-regions. The sub-region where the target infected point is located is used as the standard sub-region, and the target infected point is located at the center of the sub-region.

[0047] For example, a 10m × 10m square grid area is drawn outward from the point of infection to be treated, and this grid area is further subdivided into 2m × 2m sub-regions. The data of the infected tree point is bound to the URL of the orthophoto image information corresponding to the grid it belongs to. When determining spatial relationships, it is only necessary to use the sub-region centered on the infected tree point to be treated as the standard sub-region and query all grids containing infected trees within the grid area. This significantly improves query efficiency compared to directly querying all objects in the spatial data.

[0048] Step S140: Compare the difference values ​​between the sub-image regions where the infected tree point is located, and identify the infected tree points in the sub-image regions where the difference value is less than a preset value as duplicate infected trees.

[0049] For example, the similarity between the image corresponding to the standard sub-region and the sub-image region described in the epidemic case is compared. Specifically, the difference value can be obtained by comparing the image corresponding to the standard sub-region with the URL of the orthophoto image information of the sub-image region described in the epidemic case. If the difference value is less than a preset value, the epidemic case in the sub-image region with a difference value less than the preset value is regarded as a duplicate epidemic case.

[0050] For example, see Figure 4 , Figure 4This is a flowchart illustrating step S140 in an embodiment of the present invention. Step S140 includes the following steps.

[0051] Step S141: Obtain the image parameters of the infected tree corresponding to the infected tree point in the sub-image;

[0052] For example, by performing image analysis on the sub-image, the image parameters of the infected tree corresponding to the infected tree point in the sub-image are obtained.

[0053] Step S142: Obtain the image parameters of the infected tree corresponding to the target infected tree point in the standard sub-region.

[0054] For example, by performing image analysis on the image corresponding to the standard sub-region, the image parameters of the infected tree corresponding to the target infected tree point are obtained.

[0055] Step S143: Compare the image parameters of the infected tree corresponding to the infected tree point with the image parameters of the infected tree corresponding to the target infected tree point, and use the difference value as the distinguishability value.

[0056] For example, the image parameters of the infected tree spot are compared with the image parameters of the target infected tree spot to obtain a difference value, and the difference value is used as the distinguishability value. Specifically, the distinguishability value and the difference value can be positively correlated. The larger the difference value, the larger the distinguishability value, and the smaller the difference value, the smaller the distinguishability value.

[0057] Step S144: Mark the infected wood whose difference from the target infected wood is less than a preset value as a duplicate infected wood.

[0058] For example, when the difference between the infected tree and the target infected tree is less than a preset value, the infected tree is marked as a duplicate infected tree. If there are multiple infected trees in the same sub-image area, each of the multiple infected trees is compared with the target infected tree to obtain difference data. It is then determined whether the difference data is less than a preset value. If it is less than the preset value, the infected tree is marked as a duplicate infected tree. If an infected tree is marked as a duplicate infected tree, it will not be compared with the target infected tree a second time.

[0059] Step S145: Remove the data of the infected tree points corresponding to the duplicate infected trees from the database.

[0060] For example, delete the data of the diseased tree corresponding to the duplicate diseased tree in the database.

[0061] When the sub-region includes the target infected tree and at least one infected tree, the deduplication method further includes the following steps.

[0062] Obtain the sub-image region associated with the sub-region.

[0063] For example, the sub-image region corresponding to the sub-region is obtained.

[0064] The number and location of the infected trees corresponding to the infected tree points are determined based on the sub-image regions.

[0065] For example, image analysis is performed on the sub-image region to determine the number and location of the infected trees corresponding to the infected tree point.

[0066] Based on the sub-image region, determine the number and location of infected trees, and update the number and location of infected trees corresponding to the infected tree points in the sub-region.

[0067] For example, the number of infected trees in the sub-image region is taken as the number of infected tree points in the sub-image region, and the position of the infected trees in the sub-image region is respectively matched with the position of the infected tree points in the sub-image region.

[0068] This invention uses the data of infected tree points in the acquired original image to form a grid region corresponding to the infected tree. Utilizing the characteristic that images obtained from different batches of UAVs overlap at the edge of the aerial shooting range, it limits the grid region to match the overlapping area and filters this grid region, narrowing the filtering range and reducing the processing bandwidth required. The sub-image region is divided into multiple sub-regions. By comparing the discriminant values ​​between the sub-image regions containing the infected tree point, infected trees corresponding to infected tree points in sub-regions with discriminant values ​​less than a preset value are identified as duplicate infected trees. By comparing the discriminant values ​​of the infected trees in the sub-region images, duplicate infected trees can be determined through the attribute information of the sub-region images themselves. Once a duplicate infected tree is identified, its data is removed from the database. This avoids the computational pressure of other algorithms and the inefficiency caused by the Cartesian product of large amounts of data required by the original method, improving the accuracy of data processing and providing a more accurate and realistic result for determining duplicate infected trees.

[0069] See Figure 5 , Figure 5This is a schematic diagram of the deduplication device for infected trees provided in an embodiment of the present invention. It includes a data acquisition unit 210, used to acquire infected tree point data from the original image. By obtaining the image features of the infected trees and filtering the original image based on these features, the location and image information of the infected tree points are determined, thereby obtaining the infected tree point data in the original image. A grid forming unit 220 is used to form a grid region corresponding to the infected tree based on the infected tree point data. By dividing the infected tree point data into grid regions, the infected tree points corresponding to the infected tree point data are located within the grid regions. The size of the grid can be set according to industry rules, such as the actual range of the pine forest, the accuracy of the aerial photograph, and the processing efficiency of the processor. A region association unit 230 is used to divide the grid region into multiple sub-regions and associate the sub-regions containing the infected tree points with the sub-image regions where the infected tree points are located in the original image. The size of the sub-image regions is smaller than the size of the original image. After dividing the grid region into multiple sub-regions according to a preset query region size, the multiple sub-regions are associated one-to-one with the corresponding sub-image regions in the original image. The region comparison unit 240 is used to compare the difference values ​​between the sub-image regions where the infected tree point is located. Trees in sub-image regions with difference values ​​less than a preset value corresponding to the infected tree point are identified as duplicate infected trees. The unit also compares the similarity between the image corresponding to the standard sub-region and the sub-image region containing the infected tree. For example, the difference value is obtained by comparing the image corresponding to the standard sub-region with the URL of the orthophoto image information of the sub-image region containing the infected tree. If the difference value is less than a preset value, the infected tree in the sub-image region with the difference value less than the preset value is identified as a duplicate infected tree. The device is used to perform any of the above-described methods for deduplicating infected trees. The advantages of this device are as described above and will not be repeated here.

[0070] This invention also provides a computer device, including a processor and a memory, wherein the processor is electrically connected to the memory, the memory is used to store instructions and data, and the processor is used to execute the steps in the deduplication method for deduplication of infected wood as described in any of the above embodiments.

[0071] This invention discloses a method, apparatus, and computer device for deduplicating infected trees. It uses infected tree point data from acquired original images to form grid regions corresponding to the infected trees. Leveraging the overlap of image features from different batches of UAVs at the edge of the aerial shooting range, it defines and filters grid regions matching the overlapping area, thus narrowing the filtering range and reducing the processing bandwidth required. The sub-image regions are divided into multiple sub-regions. By comparing the discriminancy values ​​between the sub-image regions containing the infected tree points, infected trees in sub-regions with discriminancy values ​​less than a preset value are identified as duplicate infected trees. By comparing the discriminancy of infected trees in the sub-region images, duplicate infected trees can be determined using the attribute information of the sub-region images themselves. Once identified as duplicate infected trees, the data is removed from the database. This avoids the computational pressure of other algorithms and the inefficiency caused by the Cartesian product of large amounts of data required by the original method, improving the accuracy of data processing and providing more accurate and realistic results for determining duplicate infected trees.

[0072] The computer device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more storage media, a power supply 403, and an input unit 404. Those skilled in the art will understand that... Figure 6 The computer device structure shown does not constitute a limitation on the device. The computer device may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0073] Processor 401 is the control center of the device, connecting various parts of the device through various interfaces and lines. It executes various functions and processes data by running or executing software programs and / or unit modules stored in memory 402, and by calling data stored in memory 402. Optionally, processor 401 may include one or more processing cores; processor 401 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. Preferably, processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the aforementioned modem processor may not be integrated into processor 401.

[0074] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0075] The computer device may also include a power supply 403 that supplies power to the various components. Preferably, the power supply 403 is logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0076] The computer device may also include an input unit 404 and an output unit 405. The input unit 404 can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0077] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in this application, the processor 401 in the computer device loads the executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 401 runs the application programs stored in the memory 402 to realize various functions, as follows:

[0078] Obtain the data of infected tree spots in the original image;

[0079] Based on the infected tree data, a grid area corresponding to the infected tree is formed;

[0080] The grid region is divided into multiple sub-regions, and the sub-regions containing the infected wood spots are associated with the sub-image regions in the original image where the infected wood spots are located. The size of the sub-image regions is smaller than the size of the original image.

[0081] By comparing the difference values ​​between the sub-image regions where the infected tree point is located, the infected trees corresponding to the infected tree point in the sub-image region whose difference value is less than a preset value are identified as duplicate infected trees.

[0082] Those skilled in the art will understand that all or part of the steps in the various methods described above can be accomplished by instructions, or by controlling related hardware with instructions. These instructions can be stored in a storage medium and loaded and executed by the processor 401.

[0083] Therefore, embodiments of this application provide a storage medium, which may include: read-only memory (ROM), random access memory (RAM), a disk, or an optical disk, etc. Computer instructions are stored thereon, and these computer instructions are loaded by a processor 401 to execute the steps in any of the deduplication methods provided in this application. For example, when the computer instructions are executed by the processor 401, they perform the following functions:

[0084] Obtain the data of infected tree spots in the original image;

[0085] Based on the infected tree data, a grid area corresponding to the infected tree is formed;

[0086] The grid region is divided into multiple sub-regions, and the sub-regions containing the infected wood spots are associated with the sub-image regions in the original image where the infected wood spots are located. The size of the sub-image regions is smaller than the size of the original image.

[0087] By comparing the difference values ​​between the sub-image regions where the infected tree point is located, the infected tree corresponding to the infected tree point in the sub-image region where the difference value is less than a preset value is identified as a duplicate infected tree.

[0088] The computer instructions stored in the storage medium can execute the steps in the deduplication method for infected wood in any embodiment of this application. Therefore, the beneficial effects that the deduplication method for infected wood in any embodiment of this application can achieve can be realized. For details, please refer to the foregoing description, which will not be repeated here.

[0089] In summary, although the present invention has been disclosed above with reference to preferred embodiments, the above preferred embodiments are not intended to limit the present invention. Those skilled in the art can make various modifications and refinements without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the scope defined in the claims.

Claims

1. A method for removing excess material from infected wood, characterized in that, include: Obtain the data of infected tree spots in the original image; One of the infected trees corresponding to the infected tree data is taken as the target infected tree. A region is formed with the target infected tree as the center as the grid region corresponding to the infected tree. The grid region is bound to the URL location of the orthophoto image of the original image in order to obtain the image information corresponding to the grid region range. The grid region is divided into multiple sub-regions. The sub-region where the target infected tree point is located is taken as the standard sub-region. The sub-region with the infected tree point is associated with the sub-image region where the infected tree point is located in the original image. The size of the sub-image region is smaller than the size of the original image. By comparing the discriminant values ​​between the sub-image regions where the infected tree point is located, the infected trees corresponding to the infected tree points in the sub-image regions where the discriminant value is less than a preset value are identified as duplicate infected trees; wherein, the discriminant value is obtained by comparing the difference between the image parameters of the infected tree corresponding to the infected tree point in the sub-image region and the image parameters of the infected tree corresponding to the target infected tree point in the standard sub-region, and the discriminant value is positively correlated with the difference value; When the sub-region includes the target infected tree point and at least one infected tree point, the deduplication method further includes: Obtain the sub-image region associated with the sub-region; The number and location of infected trees corresponding to the infected tree points are determined based on the sub-image region, and the number and location of infected trees corresponding to the infected tree points in the sub-region are updated based on the number and location.

2. The method for removing excess material from infected wood according to claim 1, characterized in that, The process of obtaining the infected tree spot data in the original image includes: The original image is acquired using an imaging device; The infected wood spot data obtained by data processing the original image is stored in the database.

3. The method for removing excess material from infected wood according to claim 2, characterized in that, The process of obtaining the infected tree spot data in the original image also includes: The infected tree data in the database is cleaned, and the infected tree data that does not meet the preset conditions is removed from the database.

4. The method for removing excess material from infected wood according to claim 1, characterized in that, The step of dividing the grid region into multiple sub-regions includes: The grid area is divided into sub-regions of the same shape, and each sub-region is used as a sub-region. The target point is located at the center of its respective sub-region.

5. The method for removing excess material from infected wood according to claim 4, characterized in that, The step of comparing the difference values ​​between the sub-image regions where the infected tree spot is located, and classifying the infected tree spot corresponding to the infected tree spot in the sub-image region where the difference value is less than a preset value as a duplicate infected tree, includes: Obtain the image parameters of the infected tree corresponding to the infected tree point in the sub-image; Obtain the image parameters of the infected tree corresponding to the target infected tree point in the standard sub-region; The difference between the image parameters of the infected tree corresponding to the infected tree point and the image parameters of the infected tree corresponding to the target infected tree point is used as the discriminant value. Trees with a difference value less than a preset value from the target infected tree are marked as duplicate infected trees.

6. The method for removing excess material from infected wood according to claim 4, characterized in that, The deduplication method further includes: Remove the data of the infected tree points corresponding to the duplicate infected trees from the database.

7. A device for removing weight from infected wood, characterized in that, include: The data acquisition unit is used to acquire the data of infected tree spots in the original image; A grid forming unit is used to take one of the infected trees corresponding to the infected tree point data as the target infected tree point, form an area centered on the target infected tree point as a grid area corresponding to the infected tree, and bind the grid area with the URL location of the orthophoto image of the original image in order to obtain the image information corresponding to the grid area range; A region association unit is used to divide the grid region into multiple sub-regions, take the sub-region where the target infected tree point is located as the standard sub-region, and associate the sub-region with the infected tree point with the sub-image region where the infected tree point is located in the original image. The size of the sub-image region is smaller than the size of the original image. A region comparison unit is used to compare the difference values ​​between the sub-image regions where the infected tree point is located, and to identify the infected tree corresponding to the infected tree point in the sub-image region whose difference value is less than a preset value as a duplicate infected tree; wherein, the difference value is obtained by comparing the difference value between the image parameters of the infected tree corresponding to the infected tree point in the sub-image region and the image parameters of the infected tree corresponding to the target infected tree point in the standard sub-region, and the difference value is positively correlated with the difference value; When the sub-region includes the target infected timber point and at least one infected timber point, the deduplication device is further used for: Obtain the sub-image region associated with the sub-region; The number and location of infected trees corresponding to the infected tree points are determined based on the sub-image region, and the number and location of infected trees corresponding to the infected tree points in the sub-region are updated based on the number and location.

8. A computer device, characterized in that it comprises a processor and a memory, the processor being electrically connected to the memory, the memory being used to store instructions and data, and the processor being used to perform the steps in the deduplication method for consuming wood according to any one of claims 1-6.

Images