Forest cultivation ecosystem health evaluation method and system
By using drone remote sensing technology to divide forests into equal areas and process images, combined with vegetation coverage and fragmentation index, the accuracy problem of forest health assessment was solved, and precise health level assessment was achieved, thus assisting forest management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- 古浪县林业技术服务中心
- Filing Date
- 2023-11-20
- Publication Date
- 2026-04-17
AI Technical Summary
Existing methods for assessing the health of forest-cultivated ecosystems are insufficient in terms of accuracy, especially when considering the actual conditions of different regions, as the weighting of assessment indicators varies greatly, resulting in low assessment accuracy.
Using drones equipped with aerial remote sensing cameras, forest areas were divided into equal areas and remote sensing images were captured. Vegetation coverage and forest community structure index were estimated through a pixel binary model. The forest fragmentation index was then combined with a weighted summation to generate a forest cultivation ecosystem health assessment level.
It enables precise calculation of forest health assessment, improves the accuracy of assessment and its support for management, and can better reflect the health status of forest ecosystems.
Smart Images
Figure CN121884103A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of forest cultivation ecosystem health assessment technology, and in particular to a method and system for assessing the health of forest cultivation ecosystems. Background Technology
[0002] Forests, as an important renewable resource for human survival, possess multiple ecological service functions such as water conservation, atmospheric purification, carbon sequestration and oxygen release, and wind and sand prevention. They play an irreplaceable role in maintaining the resource balance and material cycle of the entire ecosystem. Therefore, a method and system for evaluating the health of forest ecosystems are needed. Chinese patent CN116029616A discloses a method for evaluating the health of forest ecosystems. First, an evaluation index set is established; the evaluation level of each evaluation index in the evaluation index set is determined; a comment set is established; a multi-level fuzzy comprehensive evaluation method is used to determine the membership degree of each evaluation index to each evaluation level in the comment set, resulting in a single-factor evaluation matrix model; the weight vector of each evaluation index is determined; fuzzy comprehensive evaluation is performed; and the evaluation level with the largest weight vector of the evaluation index is obtained, thus obtaining the health evaluation level of the forest ecosystem.
[0003] However, existing methods for assessing the health of forest-cultivated ecosystems have some drawbacks, such as:
[0004] Due to the significant spatial heterogeneity in the quality and functional characteristics of forest ecosystems, determining the factor layer indicators corresponding to the criterion layer requires consideration of the actual conditions of each region. The weights assigned to each evaluation indicator also vary considerably, resulting in low evaluation accuracy. Therefore, we propose a method and system for evaluating the health of forest cultivation ecosystems. Summary of the Invention
[0005] In view of this, the purpose of this invention is to propose a method and system for evaluating the health of forest-cultivated ecosystems, so as to solve the problem of low accuracy in existing methods for evaluating the health of forest-cultivated ecosystems.
[0006] To achieve the above objectives, the present invention provides a method for evaluating the health of a forest cultivation ecosystem, comprising the following steps:
[0007] S1: First, the entire forest area is divided into several sub-regions with equal area, and the boundary points of each sub-region are located to obtain the coordinates of the boundary points;
[0008] S2: Use a drone equipped with an aerial remote sensing camera to capture remote sensing images of each sub-region at the center point of each sub-region; thus obtaining the first group of remote sensing images.
[0009] S3: Use a drone equipped with an aerial remote sensing camera to capture remote sensing images of each sub-region at the boundary points of each sub-region; thus obtaining the second set of remote sensing images.
[0010] S4: Perform image boundary stitching on the first remote sensing image group to obtain the entire Senlian remote sensing image;
[0011] S6: Using the second set of remote sensing images as a comparison, determine whether the forest remote sensing image is accurate. If it is accurate, output the forest remote sensing image. If it is not accurate, repeat step S3.
[0012] S5: Process the forest remote sensing images to complete the forest ecosystem health assessment results. The specific steps are as follows:
[0013] S501: First, vegetation cover is estimated using a pixel-based binary model; then, the forest community structure index is calculated.
[0014] S502: Use forest fragmentation index obtained from forest remote sensing images to measure the degree of forest landscape fragmentation;
[0015] S503: The vegetation coverage, the community structure index, and the degree of fragmentation of the forest landscape are weighted and summed to obtain the forest cultivation ecosystem health evaluation level.
[0016] Further, in step S3, the two images at the initial position in the first set of images are cross-correlation similarity measured to extract the features of pixel blocks. Matching is performed on the overlapping part of the two images, with one image as a template and the other image as a matching block. The similarity value between the template and the matching block is given by the cross-correlation evaluation function. The positions of the two images are compared and the compared images are overlapped. Each pixel position in the overlapping part has two pixel values, generating overlapping pixels. The pixels at the overlapping position of the two images are subjected to initial averaging and secondary averaging, and the stitched image is output.
[0017] Furthermore, in step S4, the remote sensing images at corresponding locations in the second set of remote sensing images are compared with the images at the corresponding point stitching locations. If the image similarity exceeds a set threshold, an accurate forest remote sensing image is output.
[0018] Further, in step S501, a pixel-based binary model is used to estimate vegetation cover; the specific process is as follows: assuming that the vegetation index value ND of each pixel in the forest remote sensing image is composed of vegetation and soil components, then its calculation formula is: ND = ND v C i +ND s (1-C i In the formula, ND vIt is the vegetation index value of the vegetation cover area, ND. s C represents the vegetation index value of the soil portion. i Let C be the vegetation cover; according to the above formula, then C... i The calculation formula is as follows: The maximum and minimum values of the forest vegetation index (ND) were used to replace ND, respectively. v and ND s ,but The vegetation cover of the forest area to be evaluated is normalized and calculated: S Ci =10×C m In the formula, C m This refers to the average vegetation cover of the forest area to be evaluated.
[0019] Furthermore, in step S5, the forest community structure index corresponds to the score S. f Calculate using the following formula: In the formula, Aa represents the area of a multi-layered forest community of trees, shrubs, and grasses; Ab represents the area of a single-layered forest community of trees, shrubs, and grasses; Ac represents the area of a community of trees and shrubs; Ad represents the area of a community of only trees and herbs; Ae represents the area of a community of only trees; Af represents the area of a community of only shrubs and grasses; Ag represents the area of a community of only shrubs; and Ah represents the area of a community of only herbs. All units are in km². 2 Specifically, the community area within the corresponding area is calculated by segmenting the image.
[0020] Furthermore, the process of measuring the degree of forest landscape fragmentation using the forest fragmentation index obtained from forest remote sensing images is as follows; the expression for the degree of fragmentation is as follows: In the formula, A represents the forest landscape area, Ni represents the number of the i-th type of landscape patch, which at the landscape level refers to the total number of different types of forest patches such as finger-leaved forest and broad-leaved forest; m represents the number of patch types in the landscape; and the normalized score of the forest fragmentation index for this region. In the formula, I f The landscape fragmentation index for the year in which the forest to be evaluated is located; I fr The forest landscape fragmentation index represents the reference year for the forest to be evaluated.
[0021] Further, the feature is that: in step S503, the forest cultivation ecosystem health assessment level FHI = ∑Q1S ci +Q2S f +Q3S if Based on the scores of the forest cultivation ecosystem health evaluation level, forest health can be divided into four levels: excellent, healthy, sub-healthy, and unhealthy.
[0022] A forest cultivation ecosystem health assessment system includes a regional division module, a remote sensing image acquisition module, a remote sensing image processing module, and a forest cultivation ecosystem health assessment module.
[0023] The region division module is used to divide the entire forest area into several equally sized square sub-regions. At the same time, each square sub-region is marked with nine boundary points to obtain the region division result, and the region division result is fed back to the remote sensing image acquisition module.
[0024] The remote sensing image acquisition module is used to take aerial photos of the boundaries of each square sub-region by using a drone equipped with an aerial remote sensing camera according to the region division results. The shooting range of each remote sensing image is centered on the center point of the sub-region, and the shooting range is larger than the sub-region range; thus obtaining a first remote sensing image group and a second remote sensing image group.
[0025] The remote sensing image processing module processes the first remote sensing image group and the second remote sensing image group, and obtains the entire forest remote sensing image through remote sensing image stitching and verification. The remote sensing image processing module also performs image segmentation and area calculation on the entire forest remote sensing image, and feeds back the segmentation results and area calculation results to the forest cultivation ecosystem health evaluation module.
[0026] The forest cultivation ecosystem health assessment module is used to process the segmentation results and area calculation results to obtain the forest cultivation ecosystem health assessment level.
[0027] Compared with the prior art, the present invention has the following beneficial effects:
[0028] In this invention, the entire forest area is first divided into several sub-regions with equal areas, and the boundary points of each sub-region are located to obtain the coordinates of the boundary points. A drone equipped with an aerial remote sensing camera is used to capture remote sensing images of each sub-region from its center point, resulting in a first set of remote sensing images. The drone is then used to capture remote sensing images of each sub-region from its boundary point, resulting in a second set of remote sensing images. The first set of remote sensing images is then stitched together to obtain a remote sensing image of the entire forest. The accuracy of the forest remote sensing image is judged using the second set of images as a comparison. If the image is accurate, a more precise forest remote sensing image can be obtained.
[0029] In this invention, forest health assessment is completed by processing forest remote sensing images. This allows for the accurate calculation of the score for the forest cultivation ecosystem health assessment level, which is more conducive to assisting in the management of forest health. Attached Figure Description
[0030] Figure 1 This is a flowchart of a method for evaluating the health of a forest cultivation ecosystem according to the present invention;
[0031] Figure 2 This is a flowchart of remote sensing image stitching in a forest cultivation ecosystem health assessment method of the present invention;
[0032] Figure 3 This is a flowchart of the forest health assessment method in the forest cultivation ecosystem health assessment method of the present invention;
[0033] Figure 4 This is a schematic diagram of the regional division in the forest cultivation ecosystem health assessment method and system of the present invention;
[0034] Figure 5 This is a schematic diagram of the first remote sensing image group in the forest cultivation ecosystem health assessment method and system of the present invention;
[0035] Figure 6 This is a schematic diagram of the second remote sensing image group in the forest cultivation ecosystem health assessment method and system of the present invention;
[0036] Figure 7 This is a system block diagram of a forest cultivation ecosystem health assessment system according to the present invention. Detailed Implementation
[0037] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.
[0038] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0039] Please refer to the following: Figures 1-7 ,in, Figure 1 This is a flowchart of a method for evaluating the health of a forest cultivation ecosystem according to the present invention; Figure 2This is a flowchart of remote sensing image stitching in a forest cultivation ecosystem health assessment method of the present invention; Figure 3 This is a flowchart of the forest health assessment method in the forest cultivation ecosystem health assessment method of the present invention; Figure 4 This is a schematic diagram of the regional division in the forest cultivation ecosystem health assessment method and system of the present invention; Figure 5 This is a schematic diagram of the first remote sensing image group in the forest cultivation ecosystem health assessment method and system of the present invention; Figure 6 This is a schematic diagram of the second remote sensing image group in the forest cultivation ecosystem health assessment method and system of the present invention; Figure 7 This is a system block diagram of a forest cultivation ecosystem health assessment system according to the present invention.
[0040] A method for assessing the health of a forest cultivation ecosystem includes the following steps:
[0041] S1: First, the entire forest area is divided into several sub-regions with equal area, and the boundary points of each sub-region are located to obtain the coordinates of the boundary points;
[0042] S2: Use a drone equipped with an aerial remote sensing camera to capture remote sensing images of each sub-region at the center point of each sub-region; thus obtaining the first group of remote sensing images.
[0043] S3: Use a drone equipped with an aerial remote sensing camera to capture remote sensing images of each sub-region at the boundary points of each sub-region; thus obtaining the second set of remote sensing images.
[0044] S4: Perform image boundary stitching on the first remote sensing image group to obtain the entire Senlian remote sensing image;
[0045] S6: Using the second set of remote sensing images as a comparison, determine whether the forest remote sensing image is accurate. If it is accurate, output the forest remote sensing image. If it is not accurate, repeat step S3.
[0046] S5: Process the forest remote sensing images to complete the forest ecosystem health assessment results. The specific steps are as follows:
[0047] S501: First, vegetation cover is estimated using a pixel-based binary model; then, the forest community structure index is calculated.
[0048] S502: Use forest fragmentation index obtained from forest remote sensing images to measure the degree of forest landscape fragmentation;
[0049] S503: The vegetation coverage, the community structure index, and the degree of fragmentation of the forest landscape are weighted and summed to obtain the forest cultivation ecosystem health evaluation level.
[0050] In actual use, in step S1, as shown in the figure, during the process of dividing the region, the vertices, midpoints of the edges, and center points of the region are marked. At the same time, blank cells are added to the boundary of the forest where the area is not a whole region, so that all sub-regions are square regions of equal size.
[0051] In step S2, the drone, equipped with an aerial remote sensing camera, captures remote sensing images of each sub-region at its center point (P1, P2, P3, P4, P5); resulting in the first set of remote sensing images as shown in the figure (a1, a2, a3, a4), where the capture area of each image is larger than the size of the sub-region.
[0052] In step S3, the UAV is equipped with an aerial remote sensing camera to capture remote sensing images of each sub-region at the midpoint of the boundary of each sub-region, i.e. (Q1, Q2, Q3); the second remote sensing image group is shown in the figure, (b1, b2, b3);
[0053] Further, in step S3, the two images (a1 and a2) at the initial position in the first set of images are subjected to cross-correlation similarity measurement to extract the features of pixel blocks. Matching is performed on the overlapping part of the two images, with one image as the template and the other image as the matching block. The similarity value between the template and the matching block is given by the cross-correlation evaluation function. The expression of the cross-correlation function is: In the formula above, T represents the template as an image, S represents the matching block as an image, i and j represent the positions of the matching block S, and m and n represent the pixel positions in the image. When the relation coefficient R(i, j) is the largest, the two images have the highest positional overlap and matching. Then, the positions of the two images are compared, and the compared images are overlapped. Each pixel position in the overlapped part has two pixel values, generating overlapping pixels. Finally, the pixels at the overlapped positions of the two images are subjected to initial averaging and secondary averaging, and the stitched image is output. This makes the stitched remote sensing image more accurate, which is conducive to improving the accuracy of forest cultivation ecosystem health assessment.
[0054] Furthermore, in step S4, the remote sensing images at corresponding locations in the second group of remote sensing images are compared with the images at the corresponding point stitches. If the image similarity exceeds a set threshold, an accurate forest remote sensing image is output.
[0055] Specifically, the method is to determine whether the pixel values at corresponding positions are the same. Specifically, the difference between the pixel values at two identical positions is calculated, and the difference is checked against a set range, such as (-5 to +5). The probability of the difference being within the set range is then determined. If the probability is greater than 0.9, it means that the pixels at the stitched image are more accurate.
[0056] Further, in step S501, a pixel-based binary model is used to estimate vegetation cover; the specific process is as follows: assuming that the vegetation index value ND of each pixel in the forest remote sensing image is composed of vegetation and soil components, then its calculation formula is: ND = ND v C i +ND s (1-C i In the formula, ND v It is the vegetation index value of the vegetation cover area, ND. s C represents the vegetation index value of the soil portion. i Let C be the vegetation cover; according to the above formula, then C... i The calculation formula is as follows: The maximum and minimum values of the forest vegetation index (ND) were used to replace ND, respectively. v and ND s ,but The vegetation cover of the forest area to be evaluated is normalized and calculated: S Ci =10×C m In the formula, C m This refers to the average vegetation cover of the forest area to be evaluated.
[0057] Furthermore, in step S5, the forest community structure index corresponds to the score S. f Calculate using the following formula: In the formula, Aa represents the area of a multi-layered forest community of trees, shrubs, and grasses; Ab represents the area of a single-layered forest community of trees, shrubs, and grasses; Ac represents the area of a community of trees and shrubs; Ad represents the area of a community of only trees and herbs; Ae represents the area of a community of only trees; Af represents the area of a community of only shrubs and grasses; Ag represents the area of a community of only shrubs; and Ah represents the area of a community of only herbs. All units are in km². 2 Specifically, the community area within the corresponding area is calculated by segmenting the image.
[0058] In practical applications, the area of each community is calculated by segmenting the remote sensing image of the entire forest.
[0059] Furthermore, the process of measuring the degree of forest landscape fragmentation using the forest fragmentation index obtained from forest remote sensing images is as follows; the expression for the degree of fragmentation is as follows: In the formula, A represents the forest landscape area, Ni represents the number of the i-th type of landscape patch, which at the landscape level refers to the total number of different types of forest patches such as finger-leaved forest and broad-leaved forest; m represents the number of patch types in the landscape; and the normalized score of the forest fragmentation index for this region. In the formula, I f The landscape fragmentation index for the year in which the forest to be evaluated is located; I fr The forest landscape fragmentation index represents the reference year for the forest to be evaluated.
[0060] Further, the feature is that: in step S503, the forest cultivation ecosystem health assessment level FHI = ∑Q1S ci +Q2S f +Q3S if Based on the scores of the forest cultivation ecosystem health evaluation level, forest health can be divided into four levels: excellent, healthy, sub-healthy and unhealthy. Specifically, (9-10) is excellent, (7-9) is healthy, (4-7) is sub-healthy and (0-4) is unhealthy.
[0061] In summary, this invention processes forest remote sensing images to determine and calculate forest health assessments, accurately calculating the scores for the forest ecosystem health assessment levels, which is more conducive to assisting in the management of forest health.
[0062] A forest cultivation ecosystem health assessment system includes a regional division module, a remote sensing image acquisition module, a remote sensing image processing module, and a forest cultivation ecosystem health assessment module.
[0063] The region division module is used to divide the entire forest area into several equally sized square sub-regions. At the same time, each square sub-region is marked with nine boundary points to obtain the region division result, and the region division result is fed back to the remote sensing image acquisition module.
[0064] The remote sensing image acquisition module is used to take aerial photos of the boundaries of each square sub-region by using a drone equipped with an aerial remote sensing camera according to the region division results. The shooting range of each remote sensing image is centered on the center point of the sub-region, and the shooting range is larger than the sub-region range; thus obtaining a first remote sensing image group and a second remote sensing image group.
[0065] The remote sensing image processing module processes the first remote sensing image group and the second remote sensing image group, and obtains the entire forest remote sensing image through remote sensing image stitching and verification. The remote sensing image processing module also performs image segmentation and area calculation on the entire forest remote sensing image, and feeds back the segmentation results and area calculation results to the forest cultivation ecosystem health evaluation module.
[0066] The forest cultivation ecosystem health assessment module is used to process the segmentation results and area calculation results to obtain the forest cultivation ecosystem health assessment level.
[0067] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the invention (including the claims) is limited to these examples; within the framework of the invention, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in the details for the sake of brevity.
[0068] This invention is intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A method for evaluating the health of a forest cultivation ecosystem, characterized by: Includes the following steps: S1: First, the entire forest area is divided into several sub-regions with equal area, and the boundary points of each sub-region are located to obtain the coordinates of the boundary points; S2: Use a drone equipped with an aerial remote sensing camera to capture remote sensing images of each sub-region at the center point of each sub-region; thus obtaining the first group of remote sensing images. S3: Use a drone equipped with an aerial remote sensing camera to capture remote sensing images of each sub-region at the boundary points of each sub-region; The second set of remote sensing images was obtained; S4: Perform image boundary stitching on the first remote sensing image group to obtain the entire Senlian remote sensing image; S6: Using the second set of remote sensing images as a comparison, determine whether the forest remote sensing image is accurate. If it is accurate, output the forest remote sensing image. If it is not accurate, repeat step S3. S5: Process the forest remote sensing images to complete the forest ecosystem health assessment results. The specific steps are as follows: S501: First, vegetation cover is estimated using a pixel-based binary model; then, the forest community structure index is calculated. S502: Use forest fragmentation index obtained from forest remote sensing images to measure the degree of forest landscape fragmentation; S503: The vegetation coverage, the community structure index, and the degree of fragmentation of the forest landscape are weighted and summed to obtain the forest cultivation ecosystem health evaluation level.
2. The method for evaluating the health of a forest cultivation ecosystem according to claim 1, characterized in that: In step S3, the cross-correlation similarity measure is performed on the two images at the initial position in the first set of images to extract the features of the pixel blocks. Matching is performed on the overlapping part of the two images, with one image as the template and the other image as the matching block. The similarity value between the template and the matching block is given by the cross-correlation evaluation function. The positions of the two images are compared and the compared images are overlapped. Each pixel position in the overlapping part has two pixel values, generating overlapping pixels. The pixels at the overlapping position of the two images are subjected to initial averaging and secondary averaging, and the stitched image is output.
3. The method for evaluating the health of a forest cultivation ecosystem according to claim 2, characterized in that: In step S4, the remote sensing images at corresponding locations in the second set of remote sensing images are compared with the images at the corresponding points. If the image similarity exceeds a set threshold, an accurate forest remote sensing image is output.
4. The method for evaluating the health of a forest cultivation ecosystem according to claim 3, characterized in that: In step S501, a pixel-based binary model is used to estimate vegetation cover. The specific process is as follows: Assume that the vegetation index value ND of each pixel in a forest remote sensing image is composed of both vegetation and soil components. Then, the calculation formula is: ND = ND v C i +ND s (1-C i In the formula, ND v It is the vegetation index value of the vegetation cover area, ND. s C represents the vegetation index value of the soil portion. i Let C be the vegetation cover; according to the above formula, then C... i The calculation formula is as follows: The maximum and minimum values of the forest vegetation index (ND) were used to replace ND, respectively. v and ND s ,but The vegetation cover of the forest area to be evaluated is normalized and calculated: S Ci =10×C m In the formula, C m This refers to the average vegetation cover of the forest area to be evaluated.
5. The method for evaluating the health of a forest cultivation ecosystem according to claim 4, characterized in that: In step S5, the forest community structure index corresponds to the score S. f Calculate using the following formula: In the formula, Aa represents the area of a multi-layered forest community of trees, shrubs, and grasses; Ab represents the area of a single-layered forest community of trees, shrubs, and grasses; Ac represents the area of a community of trees and shrubs; Ad represents the area of a community of only trees and herbs; Ae represents the area of a community of only trees; Af represents the area of a community of only shrubs and grasses; Ag represents the area of a community of only shrubs; and Ah represents the area of a community of only herbs. All units are in km². 2 Specifically, the community area within the corresponding area is calculated by segmenting the image.
6. The method for evaluating the health of a forest cultivation ecosystem according to claim 5, characterized in that: The process of measuring the degree of forest landscape fragmentation using the forest fragmentation index obtained from forest remote sensing images is as follows; the expression for the degree of fragmentation is as follows. In the formula, A represents the forest landscape area, Ni represents the number of the i-th type of landscape patch, which at the landscape level refers to the total number of different types of forest patches such as finger-leaved forest and broad-leaved forest; m represents the number of patch types in the landscape; and the normalized score of the forest fragmentation index for this region. In the formula, I f The landscape fragmentation index for the year in which the forest to be evaluated is located. I fr The forest landscape fragmentation index for the reference year of the forest to be evaluated.
7. The method for evaluating the health of a forest cultivation ecosystem according to claim 6, characterized in that: In step S503, the forest cultivation ecosystem health assessment level FHI = ∑Q1S ci +Q2S f +Q3S if Based on the scores of the forest cultivation ecosystem health evaluation level, forest health can be divided into four levels: excellent, healthy, sub-healthy, and unhealthy.
8. A forest cultivation ecosystem health evaluation system characterized by comprising: It includes a regional division module, a remote sensing image acquisition module, a remote sensing image processing module, and a forest cultivation ecosystem health assessment module; The region division module is used to divide the entire forest area into several equally sized square sub-regions. At the same time, each square sub-region is marked with nine boundary points to obtain the region division result, and the region division result is fed back to the remote sensing image acquisition module. The remote sensing image acquisition module is used to take aerial photos of the boundaries of each square sub-region by using a drone equipped with an aerial remote sensing camera according to the region division results. The shooting range of each remote sensing image is centered on the center point of the sub-region, and the shooting range is larger than the sub-region range; thus obtaining a first remote sensing image group and a second remote sensing image group. The remote sensing image processing module processes the first remote sensing image group and the second remote sensing image group, and obtains the entire forest remote sensing image through remote sensing image stitching and verification. The remote sensing image processing module also performs image segmentation and area calculation on the entire forest remote sensing image, and feeds back the segmentation results and area calculation results to the forest cultivation ecosystem health evaluation module. The forest cultivation ecosystem health assessment module is used to process the segmentation results and area calculation results to obtain the forest cultivation ecosystem health assessment level.
Citation Information
Patent Citations
Forest ecosystem health evaluation method and device and electronic equipment
CN116029616A