A method and system for monitoring and early warning of the spread of pine wilt disease

Abstract

This invention belongs to the field of disease monitoring and detection technology, specifically disclosing a method and system for monitoring and early warning of pine wilt disease spread. It obtains cropped multispectral images of the target vegetation area at different time points through two rounds of UAV multispectral remote sensing image acquisition and corresponding image processing. Then, it identifies pine trees with discolored wood in the two cropped multispectral images, determining and marking the pixel regions of these trees. Next, it calculates the diffusion coefficient based on the image area ratio of the corresponding pine tree pixel regions in the two cropped multispectral images. Finally, it determines whether a spread warning is needed and the warning level based on the diffusion coefficient, thus issuing an appropriate pine wilt disease spread warning. This invention enables rapid and accurate identification and location of pine trees with discolored wood, and can accurately assess the spread of pine wilt disease, improving the efficiency of pine wilt disease spread monitoring and early warning.

Description

Technical Field

[0001] This invention belongs to the field of disease monitoring technology, specifically relating to a method and system for monitoring and early warning of the spread of pine wilt disease. Background Technology

[0002] Pine wilt disease is characterized by its rapid spread and high mortality rate, making it one of the most threatening forestry diseases in the world. Its control is a key focus of forest protection efforts. Pine wilt disease spreads rapidly and is extremely difficult to control, causing widespread death of pine forests; it is known as "pine cancer" and "smokeless forest fires." Therefore, early detection and control of pine wilt disease before it establishes a spreading trend in vegetated areas can effectively prevent its expansion and significantly reduce its damage to forest areas. Traditional methods for monitoring the spread of pine wilt disease include manual surveys and satellite remote sensing. Manual surveys are inefficient, difficult, and resource-intensive, while satellite remote sensing is limited by temporal and spatial resolution issues and cannot fully meet monitoring needs, failing to efficiently and accurately monitor the development of pine wilt disease or provide comprehensive monitoring and early warning during its outbreak phase. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for monitoring and early warning of the spread of pine wilt disease, in order to solve the above-mentioned problems existing in the prior art.

[0004] To achieve the above objectives, the present invention adopts the following technical solution:

[0005] Firstly, a method for monitoring and early warning of the spread of pine wilt disease is provided, including:

[0006] The first UAV multispectral image set and the second UAV multispectral image set were obtained by two separate multispectral remote sensing image acquisitions of the target vegetation area by a UAV equipped with a multispectral camera.

[0007] Preprocessing is performed on the first UAV multispectral image set and the second UAV multispectral image set to obtain the first multispectral image and the second multispectral image;

[0008] The target vegetation area is cropped from the first multispectral image and the second multispectral image respectively to obtain the first cropped multispectral image and the second cropped multispectral image. The image area and resolution of the first cropped multispectral image and the second cropped multispectral image are the same.

[0009] The first cropped multispectral image was used to identify pine trees with discoloration, and the identification results of the first discoloration-representing trees were obtained. The second cropped multispectral image was used to identify pine trees with discoloration, and the identification results of the second discoloration-representing trees were obtained.

[0010] Based on the first discoloration standing tree identification result, the pixel regions of each first discoloration standing tree in the first cropped multispectral image are marked, and based on the second discoloration standing tree identification result, the pixel regions of each second discoloration standing tree in the second cropped multispectral image are marked.

[0011] The image area ratio of all marked first pine discoloration standing tree pixel regions in the first cropped multispectral image is determined to obtain the first area ratio value. The image area ratio of all marked second pine discoloration standing tree pixel regions in the second cropped multispectral image is determined to obtain the second area ratio value.

[0012] The diffusion coefficient is calculated based on the first area ratio and the second area ratio, and the diffusion coefficient is compared with a set threshold. The comparison result is used to determine whether it is necessary to issue an early warning for the spread of pine wilt disease.

[0013] When it is determined that an early warning of pine wilt disease spread is needed based on the comparison results, an early warning message for the spread of pine wilt disease is generated, and the spread level of pine wilt disease is determined based on the diffusion coefficient.

[0014] The early warning information and spread level of pine wilt disease are transmitted to the monitoring terminal so that the monitoring terminal can visually display the early warning information and spread level of pine wilt disease.

[0015] In one possible design, the preprocessing of the first UAV multispectral image set and the second UAV multispectral image set to obtain the first multispectral image and the second multispectral image includes:

[0016] Image registration, image stitching, and reflectance correction were performed on the first UAV multispectral image set and the second UAV multispectral image set respectively to obtain the stitched first multispectral image and the second multispectral image.

[0017] In one possible design, the process of identifying pine trees with discoloration from a first cropped multispectral image to obtain a first discoloration identification result, and identifying pine trees with discoloration from a second cropped multispectral image to obtain a second discoloration identification result, includes:

[0018] The first cropped multispectral image is imported into the preset multispectral data inversion software Yusense Map Plus for pine wood discoloration identification, and the first discoloration identification result is obtained. The first discoloration identification result includes several first pine wood discoloration pixel regions and their image coordinate information.

[0019] The second cropped multispectral image is imported into the preset multispectral data inversion software Yusense Map Plus for the identification of pine trees with discoloration, and the identification result of the second discoloration tree is obtained. The identification result of the second discoloration tree includes several pixel regions of the second pine trees with discoloration and their image coordinate information.

[0020] In one possible design, before marking the pixel regions of each first pine tree with discoloration in the first cropped multispectral image based on the first discoloration standing tree identification result, and marking the pixel regions of each second pine tree with discoloration in the second cropped multispectral image based on the second discoloration standing tree identification result, the method further includes:

[0021] Based on the image coordinate information of each first pine tree discoloration pixel area and each second pine tree discoloration pixel area, the first discoloration standing tree identification results are cleaned, and the first pine tree discoloration standing tree pixel areas and their image coordinate information that are not included in the image coordinate areas of each second pine tree discoloration standing tree pixel area are removed.

[0022] In one possible design, determining the image area percentage of all marked first-stage pine discoloration standing tree pixel regions in the first cropped multispectral image to obtain a first area percentage value, and determining the image area percentage of all marked second-stage pine discoloration standing tree pixel regions in the second cropped multispectral image to obtain a second area percentage value, includes:

[0023] Calculate the first image area of ​​the first cropped multispectral image and the second image area occupied by the total pixel area of ​​all the first pine discoloration standing trees. Divide the second total image area by the first image area to obtain the first area ratio value.

[0024] Calculate the third image area of ​​the second cropped multispectral image and the fourth image area occupied by all second pine discoloration standing tree pixel areas. Divide the fourth total image area by the third image area to obtain the second area ratio value.

[0025] In one possible design, the step of calculating the diffusion coefficient based on the first area proportion value and the second area proportion value, comparing the diffusion coefficient with a set threshold, and determining whether to issue an early warning for the spread of pine wilt disease based on the comparison result includes:

[0026] The diffusion coefficient is obtained by dividing the second area proportion by the first area proportion.

[0027] The diffusion coefficient is compared with a set threshold. If the diffusion coefficient is greater than the set threshold, it is determined that an early warning of pine wilt disease spread is required; otherwise, it is determined that an early warning of pine wilt disease spread is not required.

[0028] In one possible design, determining the spread level of pine wilt disease based on the diffusion coefficient includes:

[0029] The diffusion coefficient is substituted into a preset spread level table for matching to determine the spread level of pine wilt disease corresponding to the diffusion coefficient. The spread level table contains several spread levels of pine wilt disease, and each spread level of pine wilt disease is associated with a corresponding spread coefficient range.

[0030] Secondly, a monitoring and early warning system for the spread of pine wilt disease is provided, comprising an acquisition unit, a processing unit, a trimming unit, an identification unit, a marking unit, a determination unit, a calculation unit, a judgment unit, and a transmission unit, wherein:

[0031] The acquisition unit is used to acquire a first UAV multispectral image set and a second UAV multispectral image set obtained by two consecutive multispectral remote sensing image acquisitions of the target vegetation area by a UAV equipped with a multispectral camera.

[0032] The processing unit is used to preprocess the first UAV multispectral image set and the second UAV multispectral image set respectively to obtain the first multispectral image and the second multispectral image.

[0033] The cropping unit is used to crop the target vegetation area of ​​the first multispectral image and the second multispectral image respectively to obtain the first cropped multispectral image and the second cropped multispectral image. The image area and resolution of the first cropped multispectral image and the second cropped multispectral image are the same.

[0034] The identification unit is used to identify pine trees with color change in the first cropped multispectral image to obtain the identification result of the first color-change standing tree, and to identify pine trees with color change in the second cropped multispectral image to obtain the identification result of the second color-change standing tree.

[0035] The marking unit is used to mark the pixel regions of each first pine tree with color change in the first cropped multispectral image according to the first color change standing tree identification result, and to mark the pixel regions of each second pine tree with color change in the second cropped multispectral image according to the second color change standing tree identification result.

[0036] The determining unit is used to determine the image area ratio of all marked first pine discoloration standing tree pixel regions in the first cropped multispectral image to obtain a first area ratio value, and to determine the image area ratio of all marked second pine discoloration standing tree pixel regions in the second cropped multispectral image to obtain a second area ratio value.

[0037] The calculation unit is used to calculate the diffusion coefficient based on the first area ratio and the second area ratio, compare the diffusion coefficient with a set threshold, and determine whether it is necessary to issue an early warning for the spread of pine wilt disease based on the comparison result.

[0038] The judgment unit is used to generate pine wilt disease spread warning information when it is determined that a pine wilt disease spread warning is needed based on the comparison results, and to determine the pine wilt disease spread level based on the diffusion coefficient.

[0039] The transmitting unit is used to transmit the early warning information and the spread level of pine wilt disease to the monitoring terminal so that the monitoring terminal can visually display the early warning information and the spread level of pine wilt disease.

[0040] Thirdly, a monitoring and early warning system for the spread of pine wilt disease is provided, including:

[0041] Memory, used to store instructions;

[0042] The processor is configured to read instructions stored in the memory and execute any one of the methods for monitoring and early warning of pine wilt disease spread described in the first aspect above, according to the instructions.

[0043] Fourthly, a computer-readable storage medium is provided, on which instructions are stored, which, when executed on a computer, cause the computer to perform any of the methods described in the first aspect. Simultaneously, a computer program product containing instructions is also provided, which, when executed on a computer, cause the computer to perform any of the pine wilt disease spread monitoring and early warning methods described in the first aspect.

[0044] Beneficial Effects: This invention obtains cropped multispectral images of the target vegetation area at different time points through two rounds of UAV multispectral remote sensing image acquisition and corresponding image processing. Then, it identifies pine trees with discoloration in the two cropped multispectral images, determining and marking the pixel areas of these trees. Based on the area ratio of the corresponding pine tree pixel areas in the two cropped multispectral images, it calculates the diffusion coefficient. Finally, it determines whether a spread warning is needed and the warning level based on the diffusion coefficient, enabling efficient and accurate monitoring and early warning of pine wilt disease spread. This invention facilitates rapid and accurate identification and location of pine trees with discoloration through UAV multispectral remote sensing image acquisition and processing. Furthermore, by comparing the area ratio of pine tree discoloration regions within the target vegetation area at different time points, it can accurately assess the spread of pine wilt disease, greatly improving the efficiency of pine wilt disease monitoring and early warning. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a schematic diagram of the steps in the method of Embodiment 1 of the present invention;

[0047] Figure 2 This is a schematic diagram of the system configuration in Embodiment 2 of the present invention;

[0048] Figure 3 This is a schematic diagram of the system configuration in Embodiment 3 of the present invention. Detailed Implementation

[0049] It should be noted that the descriptions of these embodiments are intended to aid in understanding the invention and do not constitute a limitation thereof. The specific structural and functional details disclosed herein are merely for describing exemplary embodiments of the invention. However, the invention may be embodied in many alternative forms and should not be construed as being limited to the embodiments described herein.

[0050] It should be understood that, unless otherwise explicitly specified and limited, the term "connection" should be interpreted broadly. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in the embodiments according to the specific circumstances.

[0051] Specific details are provided in the following description to provide a complete understanding of the exemplary embodiments. However, those skilled in the art will understand that the exemplary embodiments can be implemented without these specific details. For example, the system may be shown in block diagrams to avoid obscuring the example with unnecessary details. In other embodiments, well-known processes, structures, and techniques may be shown without non-essential details to avoid obscuring the embodiments.

[0052] Example 1:

[0053] This embodiment provides a method for monitoring and early warning of the spread of pine wilt disease, which can be applied to relevant computer terminals, such as... Figure 1 As shown, the method includes the following steps:

[0054] S1. Obtain the first UAV multispectral image set and the second UAV multispectral image set obtained by the UAV equipped with a multispectral camera acquiring multispectral remote sensing images of the target vegetation area in two separate instances.

[0055] In practice, a drone equipped with a multispectral camera can be used to collect multispectral remote sensing orthophotos of the target vegetation area twice at different times, resulting in a first drone multispectral image set and a second drone multispectral image set. The first drone multispectral image set is derived from the first drone multispectral remote sensing orthophoto acquisition, and the second drone multispectral image set is derived from the second drone multispectral remote sensing orthophoto acquisition. The time interval between the two acquisitions can be set, such as one week, half a month, or one month.

[0056] In the field of monitoring pine wilt diseased trees, the canopy spectral characteristics of pine wilt diseased trees can be analyzed and identified. Low-altitude multispectral remote sensing orthophotos can be acquired using drones equipped with multispectral cameras. This approach combines the advantages of rich spectral remote sensing information with the high efficiency of drone operations, enabling low-cost, high-resolution, and high-frequency dynamic monitoring. With specific multispectral inversion processing, refined detection of abnormal conditions such as pine tree death and pine needle discoloration can be achieved.

[0057] S2. Preprocess the first UAV multispectral image set and the second UAV multispectral image set respectively to obtain the first multispectral image and the second multispectral image.

[0058] In practice, after acquiring the first UAV multispectral image set and the second UAV multispectral image set, the first UAV multispectral image set and the second UAV multispectral image set can be preprocessed accordingly, including image registration, image stitching and reflectance correction processing in sequence, to obtain the stitched first multispectral image and the second multispectral image.

[0059] S3. Crop the target vegetation area from the first multispectral image and the second multispectral image respectively to obtain the first cropped multispectral image and the second cropped multispectral image. The image area and resolution of the first cropped multispectral image and the second cropped multispectral image are the same.

[0060] In practice, after obtaining the first and second multispectral images, cropping can be performed by manually labeling and configuring the cropping, or by using edge detection or other ROI extraction methods to crop and extract the first and second multispectral images containing only the target vegetation area, so that the image area and resolution of the first and second multispectral images are consistent.

[0061] S4. Perform pine wood discoloration identification on the first cropped multispectral image to obtain the first discoloration identification result. Perform pine wood discoloration identification on the second cropped multispectral image to obtain the second discoloration identification result.

[0062] In practice, after obtaining the first and second cropped multispectral images, the first cropped multispectral image can be imported into third-party multispectral data inversion software (such as Yusense Map Plus) for pine wood discoloration identification, yielding the first discoloration identification result, which includes several first discoloration pixel regions and their image coordinate information. Similarly, the second cropped multispectral image can be imported into third-party multispectral data inversion software (such as Yusense Map Plus) for pine wood discoloration identification, yielding the second discoloration identification result, which includes several second discoloration pixel regions and their image coordinate information. Alternatively, the first and second cropped multispectral images can be imported into a neural network model trained with deep learning, such as a support vector machine model or a decision tree model, to identify and classify the pine wood discoloration pixel regions, obtaining the corresponding discoloration identification result.

[0063] After obtaining the initial identification results of the first and second discolored standing trees, the identification results of the first discolored standing trees can be cleaned based on the image coordinate information of the pixel areas of each first discolored pine standing tree and the pixel areas of each second discolored pine standing tree. This process removes the first discolored pine standing tree pixel areas and their image coordinate information that are not included in the image coordinate areas of each second discolored pine standing tree pixel area. This prevents situations where there are pine discolored standing tree pixel areas in the previous multispectral image but no corresponding pine discolored standing tree pixel areas in the subsequent multispectral image, thus reducing monitoring and judgment errors.

[0064] S5. Based on the first discoloration standing tree identification result, mark the pixel area of ​​each first discoloration standing tree in the first cropped multispectral image, and based on the second discoloration standing tree identification result, mark the pixel area of ​​each second discoloration standing tree in the second cropped multispectral image.

[0065] In practice, after determining the final identification results of the first and second discolored standing trees, the pixel regions of each first discolored pine standing tree can be marked in the first cropped multispectral image based on the pixel regions of the first discolored pine standing trees and their image coordinates in the identification results of the first discolored standing trees. Similarly, the pixel regions of each second discolored pine standing tree can be marked in the second cropped multispectral image based on the pixel regions of the second discolored pine standing trees and their image coordinates in the identification results of the second discolored standing trees.

[0066] S6. Determine the image area ratio of all marked first pine discoloration standing tree pixel regions in the first cropped multispectral image to obtain a first area ratio value. Determine the image area ratio of all marked second pine discoloration standing tree pixel regions in the second cropped multispectral image to obtain a second area ratio value.

[0067] In specific implementation, the first image area of ​​the first cropped multispectral image and the second image area occupied by the total pixel area of ​​all first pine discoloration standing trees are calculated. The second total image area is divided by the first image area to obtain the first area ratio value. The third image area of ​​the second cropped multispectral image and the fourth image area occupied by the total pixel area of ​​all second pine discoloration standing trees are calculated. The fourth total image area is divided by the third image area to obtain the second area ratio value.

[0068] S7. Calculate the diffusion coefficient based on the first area ratio and the second area ratio, and compare the diffusion coefficient with the set threshold. Based on the comparison result, determine whether it is necessary to issue an early warning for the spread of pine wilt disease.

[0069] In practice, the diffusion coefficient can be obtained by dividing the second area ratio by the first area ratio. Then, the diffusion coefficient is compared with a set threshold. If the diffusion coefficient is greater than the set threshold, it is determined that a pine wilt disease spread warning needs to be issued. Otherwise, it is determined that a pine wilt disease spread warning does not need to be issued. For example, the set threshold is 1.

[0070] S8. When it is determined that an early warning of pine wilt disease spread is needed based on the comparison results, generate early warning information for pine wilt disease spread and determine the spread level of pine wilt disease based on the diffusion coefficient.

[0071] In practice, when it is determined that an early warning of pine wilt disease spread is needed based on the comparison results, the corresponding early warning information of pine wilt disease spread can be generated, and the diffusion coefficient can be substituted into a preset spread level table for matching to determine the pine wilt disease spread level corresponding to the diffusion coefficient. The spread level table contains several pine wilt disease spread levels, and each pine wilt disease spread level is associated with a corresponding diffusion coefficient range.

[0072] S9. Transmit the early warning information and spread level of pine wilt disease to the monitoring terminal so that the monitoring terminal can visually display the early warning information and spread level of pine wilt disease.

[0073] In practice, after generating the corresponding pine wilt disease spread warning information and determining the pine wilt disease spread level corresponding to the spread coefficient, the pine wilt disease spread warning information and pine wilt disease spread level can be transmitted to the monitoring terminal so that the monitoring terminal can visually display the pine wilt disease spread warning information and pine wilt disease spread level.

[0074] The method in this embodiment facilitates rapid and accurate identification and location of pine trees with discolored wood by acquiring and processing multispectral remote sensing images from UAVs. Furthermore, by comparing the area of ​​discolored pine trees within the target vegetation area at different time points, the spread of pine wilt disease can be accurately assessed, greatly improving the efficiency of monitoring and early warning of pine wilt disease spread.

[0075] Example 2:

[0076] This embodiment provides a monitoring and early warning system for the spread of pine wilt disease, such as... Figure 2 As shown, it includes an acquisition unit, a processing unit, a cropping unit, an identification unit, a marking unit, a determination unit, a calculation unit, a judgment unit, and a sending unit, wherein:

[0077] The acquisition unit is used to acquire a first UAV multispectral image set and a second UAV multispectral image set obtained by two consecutive multispectral remote sensing image acquisitions of the target vegetation area by a UAV equipped with a multispectral camera.

[0078] The processing unit is used to preprocess the first UAV multispectral image set and the second UAV multispectral image set respectively to obtain the first multispectral image and the second multispectral image.

[0079] The cropping unit is used to crop the target vegetation area of ​​the first multispectral image and the second multispectral image respectively to obtain the first cropped multispectral image and the second cropped multispectral image. The image area and resolution of the first cropped multispectral image and the second cropped multispectral image are the same.

[0080] The identification unit is used to identify pine trees with color change in the first cropped multispectral image to obtain the identification result of the first color-change standing tree, and to identify pine trees with color change in the second cropped multispectral image to obtain the identification result of the second color-change standing tree.

[0081] The marking unit is used to mark the pixel regions of each first pine tree with color change in the first cropped multispectral image according to the first color change standing tree identification result, and to mark the pixel regions of each second pine tree with color change in the second cropped multispectral image according to the second color change standing tree identification result.

[0082] The determining unit is used to determine the image area ratio of all marked first pine discoloration standing tree pixel regions in the first cropped multispectral image to obtain a first area ratio value, and to determine the image area ratio of all marked second pine discoloration standing tree pixel regions in the second cropped multispectral image to obtain a second area ratio value.

[0083] The calculation unit is used to calculate the diffusion coefficient based on the first area ratio and the second area ratio, compare the diffusion coefficient with a set threshold, and determine whether it is necessary to issue an early warning for the spread of pine wilt disease based on the comparison result.

[0084] The judgment unit is used to generate pine wilt disease spread warning information when it is determined that a pine wilt disease spread warning is needed based on the comparison results, and to determine the pine wilt disease spread level based on the diffusion coefficient.

[0085] The transmitting unit is used to transmit the early warning information and the spread level of pine wilt disease to the monitoring terminal so that the monitoring terminal can visually display the early warning information and the spread level of pine wilt disease.

[0086] Example 3:

[0087] This embodiment provides a monitoring and early warning system for the spread of pine wilt disease, such as... Figure 3 As shown, at the hardware level, it includes:

[0088] The data interface is used to establish data communication between the processor, the drone, and the monitoring terminal;

[0089] Memory, used to store instructions;

[0090] The processor is used to read the instructions stored in the memory and execute the pine wilt disease spread monitoring and early warning method in Embodiment 1 according to the instructions.

[0091] Optionally, the device also includes an internal bus. The processor, memory, and data interface can be interconnected via the internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0092] The memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory. The processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0093] Example 4:

[0094] This embodiment provides a computer-readable storage medium storing instructions. When these instructions are executed on a computer, the computer performs the pine wilt disease spread monitoring and early warning method described in Embodiment 1. The computer-readable storage medium refers to a data storage medium, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems.

[0095] This embodiment also provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the pine wilt disease spread monitoring and early warning method described in Embodiment 1. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system.

[0096] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for monitoring and early warning of the spread of pine wilt disease, characterized in that, include: The first UAV multispectral image set and the second UAV multispectral image set were obtained by acquiring multispectral remote sensing images of the target vegetation area in two separate UAVs equipped with multispectral cameras. Preprocessing is performed on the first UAV multispectral image set and the second UAV multispectral image set to obtain the first multispectral image and the second multispectral image; The target vegetation area is cropped from the first multispectral image and the second multispectral image respectively to obtain the first cropped multispectral image and the second cropped multispectral image. The image area and resolution of the first cropped multispectral image and the second cropped multispectral image are the same. The first cropped multispectral image was used to identify pine trees with discoloration, and the identification results of the first discoloration-representing trees were obtained. The second cropped multispectral image was used to identify pine trees with discoloration, and the identification results of the second discoloration-representing trees were obtained. Based on the first discoloration standing tree identification result, the pixel regions of each first discoloration standing tree in the first cropped multispectral image are marked, and based on the second discoloration standing tree identification result, the pixel regions of each second discoloration standing tree in the second cropped multispectral image are marked. The image area ratio of all marked first pine discoloration standing tree pixel regions in the first cropped multispectral image is determined to obtain the first area ratio value. The image area ratio of all marked second pine discoloration standing tree pixel regions in the second cropped multispectral image is determined to obtain the second area ratio value. The diffusion coefficient is calculated based on the first area ratio and the second area ratio, and the diffusion coefficient is compared with a set threshold. The comparison result is used to determine whether it is necessary to issue an early warning for the spread of pine wilt disease. When it is determined that an early warning of pine wilt disease spread is needed based on the comparison results, an early warning message for the spread of pine wilt disease is generated, and the spread level of pine wilt disease is determined based on the diffusion coefficient. The early warning information and spread level of pine wilt disease are transmitted to the monitoring terminal so that the monitoring terminal can visually display the early warning information and spread level of pine wilt disease.

2. The method for monitoring and early warning of the spread of pine wilt disease according to claim 1, characterized in that, The preprocessing of the first UAV multispectral image set and the second UAV multispectral image set to obtain the first multispectral image and the second multispectral image includes: Image registration, image stitching, and reflectance correction were performed on the first UAV multispectral image set and the second UAV multispectral image set respectively to obtain the stitched first multispectral image and the second multispectral image.

3. The method for monitoring and early warning of the spread of pine wilt disease according to claim 1, characterized in that, The process of identifying pine trees with discoloration from the first cropped multispectral image to obtain the first discoloration identification result, and identifying pine trees with discoloration from the second cropped multispectral image to obtain the second discoloration identification result, includes: The first cropped multispectral image is imported into a third-party multispectral data inversion software for pine wood discoloration identification, and the first discoloration identification result is obtained. The first discoloration identification result includes several first pine wood discoloration pixel regions and their image coordinate information. The second cropped multispectral image is imported into a third-party multispectral data inversion software for the identification of pine trees with discoloration, and the identification result of the second discoloration tree is obtained. The identification result of the second discoloration tree includes several pixel regions of the second pine trees with discoloration and their image coordinate information.

4. The method for monitoring and early warning of the spread of pine wilt disease according to claim 3, characterized in that, Before marking the pixel regions of each first pine tree with discoloration in the first cropped multispectral image based on the first discoloration standing tree identification result, and marking the pixel regions of each second pine tree with discoloration in the second cropped multispectral image based on the second discoloration standing tree identification result, the method further includes: Based on the image coordinate information of each first pine tree discoloration pixel area and each second pine tree discoloration pixel area, the first discoloration standing tree identification results are cleaned, and the first pine tree discoloration standing tree pixel areas and their image coordinate information that are not included in the image coordinate areas of each second pine tree discoloration standing tree pixel area are removed.

5. The method for monitoring and early warning of the spread of pine wilt disease according to claim 1, characterized in that, The process of determining the percentage of image area of ​​all marked first-stage pine discoloration standing tree pixel regions in the first cropped multispectral image to obtain a first area percentage value, and determining the percentage of image area of ​​all marked second-stage pine discoloration standing tree pixel regions in the second cropped multispectral image to obtain a second area percentage value, includes: Calculate the first image area of ​​the first cropped multispectral image and the second image area occupied by the total pixel area of ​​all the first pine discoloration standing trees. Divide the second total image area by the first image area to obtain the first area ratio value. Calculate the third image area of ​​the second cropped multispectral image and the fourth image area occupied by all second pine discoloration standing tree pixel areas. Divide the fourth total image area by the third image area to obtain the second area ratio value.

6. The method for monitoring and early warning of the spread of pine wilt disease according to claim 1, characterized in that, The process of calculating the diffusion coefficient based on the first area proportion value and the second area proportion value, comparing the diffusion coefficient with a set threshold, and determining whether an early warning for the spread of pine wilt disease is needed based on the comparison result includes: The diffusion coefficient is obtained by dividing the second area proportion by the first area proportion. The diffusion coefficient is compared with a set threshold. If the diffusion coefficient is greater than the set threshold, it is determined that an early warning of pine wilt disease spread is required; otherwise, it is determined that an early warning of pine wilt disease spread is not required.

7. The method for monitoring and early warning of the spread of pine wilt disease according to claim 1, characterized in that, The determination of the spread level of pine wilt disease based on the diffusion coefficient includes: The diffusion coefficient is substituted into a preset spread level table for matching to determine the spread level of pine wilt disease corresponding to the diffusion coefficient. The spread level table contains several spread levels of pine wilt disease, and each spread level of pine wilt disease is associated with a corresponding spread coefficient range.

8. A monitoring and early warning system for the spread of pine wilt disease, characterized in that, It includes an acquisition unit, a processing unit, a cropping unit, an identification unit, a marking unit, a determination unit, a calculation unit, a judgment unit, and a transmission unit, wherein: The acquisition unit is used to acquire a first UAV multispectral image set and a second UAV multispectral image set obtained by two consecutive multispectral remote sensing image acquisitions of the target vegetation area by a UAV equipped with a multispectral camera. The processing unit is used to preprocess the first UAV multispectral image set and the second UAV multispectral image set respectively to obtain the first multispectral image and the second multispectral image. The cropping unit is used to crop the target vegetation area of ​​the first multispectral image and the second multispectral image respectively to obtain the first cropped multispectral image and the second cropped multispectral image. The image area and resolution of the first cropped multispectral image and the second cropped multispectral image are the same. The identification unit is used to identify pine trees with color change in the first cropped multispectral image to obtain the identification result of the first color-change standing tree, and to identify pine trees with color change in the second cropped multispectral image to obtain the identification result of the second color-change standing tree. The marking unit is used to mark the pixel regions of each first pine tree with color change in the first cropped multispectral image according to the first color change standing tree identification result, and to mark the pixel regions of each second pine tree with color change in the second cropped multispectral image according to the second color change standing tree identification result. The determining unit is used to determine the image area ratio of all marked first pine discoloration standing tree pixel regions in the first cropped multispectral image to obtain a first area ratio value, and to determine the image area ratio of all marked second pine discoloration standing tree pixel regions in the second cropped multispectral image to obtain a second area ratio value. The calculation unit is used to calculate the diffusion coefficient based on the first area ratio and the second area ratio, compare the diffusion coefficient with a set threshold, and determine whether it is necessary to issue an early warning for the spread of pine wilt disease based on the comparison result. The judgment unit is used to generate pine wilt disease spread warning information when it is determined that a pine wilt disease spread warning is needed based on the comparison results, and to determine the pine wilt disease spread level based on the diffusion coefficient. The transmitting unit is used to transmit the early warning information and the spread level of pine wilt disease to the monitoring terminal so that the monitoring terminal can visually display the early warning information and the spread level of pine wilt disease.

9. A monitoring and early warning system for the spread of pine wilt disease, characterized in that, include: Memory, used to store instructions; A processor is configured to read instructions stored in the memory and execute the pine wilt disease spread monitoring and early warning method according to any one of claims 1-7.

Images