A tree vertex multi-scale iterative extraction method, device, medium and equipment

Abstract

The present application relates to the field of remote sensing information extraction, and discloses a tree top point multi-scale iterative extraction method, device, medium and equipment, the method comprising: using at least two windows of different scales to extract the local maximum of the gradient direction map or the canopy height model of the target forest respectively, and determining the repeated points as real tree top points and the remaining points as candidate points, then according to the geometric characteristics between the target forest canopies and combining the gradient direction map, digital terrain model and the like, iteratively screening the real tree top points from the candidate points until a preset iteration end condition is reached. The present application iteratively finds the remaining tree top points from the real tree top points according to the geometric characteristics between the canopies, and deletes the wrong tree top points, thereby effectively suppressing the over-segmentation and under-segmentation phenomenon, and significantly improving the single tree segmentation accuracy.

Description

Technical Field

[0001] This invention relates to the field of remote sensing information extraction, and more particularly to a multi-scale iterative extraction method, apparatus, medium, and device for tree vertices. Background Technology

[0002] Timely and effective acquisition of forest growth information is crucial for protecting forest resources and developing reasonable forest management plans. Individual trees are the basic units constituting a forest, and their spatial structure, biophysical, and chemical composition are key factors required for forest resource surveys and ecological environment modeling research. Existing methods for individual tree segmentation typically rely on the canopy height model (CHM) of the vegetation canopy. This involves first subtracting the difference between the digital surface model (DSM) and digital elevation model (DEM) corresponding to the forest point cloud data, then using a local maximum tree vertex detection algorithm to extract tree vertices and identify the crown width of individual trees within a certain range. However, due to the characteristics of broad-leaved trees, such as numerous prominent branches, irregular crown shapes, and high overlap between adjacent crowns, existing methods easily lead to the incorrect extraction of these prominent branches as tree vertices, while tree vertices in densely populated canopy areas are easily missed, resulting in low accuracy in individual tree segmentation. Summary of the Invention

[0003] This invention provides a method, apparatus, medium, and device for multi-scale iterative extraction of tree vertices, which solves the technical problems mentioned above.

[0004] A first aspect of this invention provides a multi-scale iterative extraction method for tree vertices, comprising the following steps:

[0005] Step 1: Obtain the gradient pointing map or canopy height model of the target forest;

[0006] Step 2: Extract the local maxima of the gradient pointing map or the canopy height model using at least two windows of different scales to generate multiple sets of local maxima;

[0007] Step 3: Compare the multiple sets of local maximum values, determine the duplicate points as real tree vertices and the remaining points as candidate points, and establish a set of real tree vertices and a set of candidate points;

[0008] Step 4: Identify the geometric features between the tree canopies of the target forest, and iteratively filter out the real tree vertices from the candidate point set based on the geometric features between the tree canopies. Update the set of real tree vertices and the candidate point set according to the filtering results until the preset iteration end condition is reached.

[0009] A second aspect of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the multi-scale iterative extraction method for tree vertices described above.

[0010] A third aspect of the present invention provides a multi-scale iterative extraction device for tree vertices, including a computer-readable storage medium and a processor, wherein the processor executes a computer program on the computer-readable storage medium to implement the steps of the multi-scale iterative extraction method for tree vertices described above.

[0011] A fourth aspect of this invention provides a multi-scale iterative extraction device for tree vertices, including an acquisition module, an extraction module, a classification module, and an iteration module.

[0012] The acquisition module is used to acquire the gradient pointing map or canopy height model of the target forest;

[0013] The extraction module is used to extract the local maxima of the gradient pointing map or the canopy height model using at least two windows of different scales, and generate multiple sets of local maxima.

[0014] The classification module is used to compare the multiple sets of local maximum values, determine the duplicate points as real tree vertices and the remaining points as candidate points, and establish a set of real tree vertices and a set of candidate points.

[0015] The iterative module is used to identify the geometric features between the tree canopies of the target forest, and iteratively filter out the real tree vertices from the candidate point set based on the geometric features between the tree canopies, and update the set of real tree vertices and the candidate point set according to the filtering results until the preset iteration end condition is reached.

[0016] The beneficial effects of the present invention are as follows: The present invention provides a multi-scale iterative extraction method, apparatus, medium and device for tree vertices, which extracts tree vertices from the gradient pointing graph using windows of different scale sizes, and iteratively searches for the remaining tree vertices starting from the real tree vertices based on the geometric features between the tree crowns, and deletes erroneous tree vertices, thereby effectively suppressing over-segmentation and under-segmentation phenomena and significantly improving the segmentation accuracy of single trees.

[0017] To make the above-mentioned objects, features and advantages of the invention more apparent and understandable, preferred embodiments of the invention are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating the multi-scale iterative extraction method for tree vertices provided in Example 1;

[0020] Figure 2 This is a schematic diagram of the multi-scale iterative extraction device for tree vertices provided in Example 2;

[0021] Figure 3 This is a schematic diagram of the structure of the multi-scale iterative extraction device for tree vertices provided in Example 3. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0023] It should be noted that, unless otherwise specified, the various features in the embodiments of this invention can be combined with each other, all of which are within the protection scope of this invention. Furthermore, although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than the module division in the device or the order in the flowchart. Moreover, the terms "first," "second," and "third" used in this invention do not limit the data or execution order, but only distinguish identical or similar items with essentially the same function and effect.

[0024] Figure 1 This is a flowchart illustrating a multi-scale iterative extraction method for tree vertices provided in Example 1. Figure 1 As shown, it includes the following steps:

[0025] Step 1: Obtain the gradient pointing map or canopy height model of the target forest;

[0026] Step 2: Extract the local maxima of the gradient pointing map or the canopy height model using at least two windows of different scales to generate multiple sets of local maxima;

[0027] Step 3: Compare the multiple sets of local maximum values, determine the duplicate points as real tree vertices and the remaining points as candidate points, and establish a set of real tree vertices and a set of candidate points;

[0028] Step 4: Identify the geometric features between the tree canopies of the target forest, and iteratively filter out the real tree vertices from the candidate point set based on the geometric features between the tree canopies. Update the set of real tree vertices and the candidate point set according to the filtering results until the preset iteration end condition is reached.

[0029] The above embodiments provide a multi-scale iterative extraction method for tree vertices. It uses windows of different scales to extract tree vertices from gradient pointing graphs or canopy height models (CHMs), and iteratively searches for other tree vertices starting from the real tree vertices based on the geometric features between the tree canopies. In addition, it deletes erroneous tree vertices, thereby effectively suppressing over-segmentation and under-segmentation phenomena and significantly improving the segmentation accuracy of single trees.

[0030] The following specific embodiments will be used to describe each step of the above method in detail.

[0031] In one embodiment, a canopy height model (CHM) of the target forest can be obtained first. Specifically, the UAV can be controlled to fly in terrain-following mode in areas with large undulations, and airborne LiDAR can be used to acquire high-density point cloud data of the target forest to fully depict the three-dimensional structure of the forest canopy. Then, the point cloud data is preprocessed, such as denoising, point cloud classification, and point cloud normalization, to separate ground points and non-ground points. Finally, the normalized point cloud data is divided into regular grids of a certain resolution, and the highest point is searched within each grid. The height of the highest point above the ground is used as the value of that grid, thus obtaining the canopy height model of the target forest, i.e., the CHM model. Subsequently, a multi-scale iterative method is used based on the CHM model to accurately extract tree vertices.

[0032] In another preferred embodiment, a gradient convergence map (GCM) of the target forest can also be obtained, and tree vertices can be extracted based on this gradient convergence map. This preferred embodiment replaces the CHM with a gradient convergence map, which is unaffected by terrain and provides more accurate canopy segmentation. Specifically, firstly, point cloud data of the target forest is collected, and the point cloud data is preprocessed to classify ground points and non-ground points. Then, a digital surface model (DSM) of the target forest is established based on the classified complete point cloud data. The DSM is then used to statistically analyze the directional properties of local gradient vectors in the neighboring point cloud, i.e., the degree of convergence between the local gradient vectors of neighboring pixels and the corresponding pixels, thereby generating a gradient convergence map. In one preferred embodiment, establishing a gradient convergence map of the target forest specifically includes the following steps:

[0033] Convolution kernels are constructed, and the data of the digital surface model of the target forest are convolved in two vertical directions using the convolution kernels to generate local gradient vectors for each cell and its neighborhood.

[0034] Construct a direction vector from the center pixel to the neighboring pixels, and calculate the angle difference between the gradient vector of the neighboring pixels and the direction vector from the center pixel to the neighboring pixels;

[0035] Weights are assigned to pixels with different angle differences based on a two-dimensional Gaussian kernel function, and the pixel value of each pixel is calculated. The gradient pointing map of the target forest is then generated based on the pixel values.

[0036] In the gradient pointing map established using the above method, a higher pixel value indicates that the local gradient vectors of neighboring pixels are more concentrated in pointing towards that pixel. Based on the geometric characteristics of the tree canopy, this value is highest at the tree apex and lowest at the canopy boundary. In the preferred embodiment described above, since the gradient pointing map is unaffected by terrain, it can replace the CHM model for canopy segmentation, further improving the accuracy of canopy segmentation.

[0037] Then, tree vertices are extracted based on the gradient pointing map or canopy height model of the target forest. Existing techniques typically use a fixed-size square window that moves across each grid cell, identifying whether the CHM value of the grid cell at the window's center is the maximum value within the window. If it is the maximum value, the grid cell is considered to potentially contain a tree vertex, and the grid center is extracted as the possible tree vertex location. Embodiments of this invention employ at least two windows of different scales to extract the local maxima of the gradient pointing map or canopy height model, establishing multiple sets of local maxima. Duplicate points are identified as true tree vertices, and the remaining points are identified as candidate points. Finally, an accurate set of true tree vertices is obtained through iteration.

[0038] Specifically, two windows can be used to extract the local maximum values ​​of the gradient pointing map or the canopy height model, with the window values ​​of the two windows being the minimum and maximum canopy diameters within the region, thus balancing the extraction efficiency and accuracy of the real tree vertices.

[0039] In a preferred embodiment, step 4 can identify the inter-canopy geometric features of the target forest through the gradient pointing map, canopy height model, and / or digital land surface model, and iteratively filter out the real tree vertices from the candidate points based on the inter-canopy geometric features, specifically including the following steps:

[0040] S401, Construct a Delaunay triangulation using all points in the set of real tree vertices and the set of candidate points;

[0041] S402, traverse each edge of each triangle, obtain the target candidate point connected by the real tree vertex, and determine the corresponding edge, that is, determine whether the edge connecting the real point and the candidate point meets the preset condition. If so, add the target candidate point to the real tree vertex set; otherwise, remove the target candidate point from the candidate point set.

[0042] S403, repeat steps S401-S402 until the preset iteration end condition is met, and obtain the complete tree vertex result of the region corresponding to the target forest point cloud data. The preset iteration end condition includes that all points in the candidate point set have been processed.

[0043] Step 402 includes a first preset condition, a second preset condition, and a third preset condition. If the corresponding edge meets any one of the first preset condition, the second preset condition, and the third preset condition, then the target candidate point is added to the set of real tree vertices.

[0044] Specifically, in one embodiment, the first preset condition is: obtaining the ratio of the minimum value to the endpoint value of the connecting line based on the gradient pointing graph, and the ratio is less than a preset ratio. This condition uses the gradient pointing graph to check the ratio of the minimum value to the endpoint value of the connecting line. In other words, the edges connecting real points and candidate points selected after constructing the Delaunay triangulation are processed by checking the minimum value of the pixels in the gradient pointing graph that the edge passes through, as well as the endpoint values ​​at both ends of the edge. If the ratio of the minimum value to the endpoint value is less than the preset ratio, the connection is considered to meet the condition. This condition considers that the neighborhood gradient vectors of two tree canopy boundary points have opposite directions, thus there is a local low value. It also considers the size of the two tree canopies, with the smaller tree canopy having a smaller endpoint value and the larger tree canopy having a larger endpoint value. Meeting this condition means that the connecting line may have passed through a boundary (pixel), indicating that the path is a valid connection of real tree vertices.

[0045] In another embodiment, the second preset condition is: the angle difference between the lowest point of the connecting line and the two endpoint vectors of the line segment is obtained based on the digital surface model of the target forest, and the angle difference is less than a preset angle threshold. This condition uses the digital surface model (DSM) to check whether the angle difference between the lowest point of the connecting line and the two endpoint vectors of the line segment is less than the preset angle threshold. It also considers the distance between two tree vertices and the possible low points at the boundary. If the angle difference of the connecting line is less than the threshold, it indicates that the connection conforms to the geometric relationship between real tree vertices.

[0046] In another embodiment, the third preset condition is: obtaining the length of the connecting line, and the length of the connecting line is greater than a first preset length threshold. This condition checks whether the length of the connecting line is greater than the first preset length threshold, which is generally set to the maximum crown diameter. If the length of the connecting line exceeds this threshold, it indicates that the two endpoints of the connection are real tree vertices.

[0047] In another preferred embodiment of the present invention, during the construction of Delaunay triangulation in step S401, edges exceeding a second preset length threshold are acquired and removed to prevent any triangle in the Delaunay triangulation result from having edges spanning multiple tree canopies, thereby further improving the accuracy of tree vertex extraction. Specifically, the first preset length threshold and the second preset length threshold may be inconsistent. The first preset length threshold is used to determine whether the candidate points connected by the lines are real points, while the second preset length threshold is used to remove long, thin lines that may span multiple tree canopies from the study boundary or other locations.

[0048] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0049] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the multi-scale iterative extraction method for tree vertices described above.

[0050] Figure 2 This is a schematic diagram of the multi-scale iterative extraction device for tree vertices provided in Embodiment 2, as shown below. Figure 2 As shown, it includes an acquisition module 100, an extraction module 200, a classification module 300, and an iteration module 400.

[0051] The acquisition module 100 is used to acquire the gradient pointing map or canopy height model of the target forest;

[0052] The extraction module 200 is used to extract the local maxima of the gradient pointing map or the canopy height model using at least two windows of different scales, and generate multiple sets of local maxima.

[0053] The classification module 300 is used to compare the multiple sets of local maximum values, determine the duplicate points as real tree vertices and the remaining points as candidate points, and establish a set of real tree vertices and a set of candidate points.

[0054] The iteration module 400 is used to identify the geometric features between the tree canopies of the target forest, and iteratively filter out the real tree vertices from the candidate point set based on the geometric features between the tree canopies, and update the set of real tree vertices and the candidate point set according to the filtering results until the preset iteration end condition is reached.

[0055] The above embodiments provide a multi-scale iterative extraction device for tree vertices. Based on the geometric features between tree canopies, iteratively searches for other tree vertices starting from the real tree vertices and deletes erroneous tree vertices, thereby effectively suppressing over-segmentation and under-segmentation phenomena and significantly improving the segmentation accuracy of single trees.

[0056] In a preferred embodiment, the iteration module 400 specifically includes:

[0057] Construction unit, used to construct Delaunay triangulation using all points in the real tree vertex set and the candidate point set;

[0058] The determination unit is used to traverse each edge of each triangle, obtain the target candidate point connected to the real tree vertex, and determine whether the corresponding edge meets the preset conditions. If so, the target candidate point is added to the real tree vertex set; otherwise, the target candidate point is removed from the candidate point set.

[0059] An iteration unit is used to repeatedly drive the construction unit and the determination unit until a preset iteration end condition is reached, wherein the preset iteration end condition includes that all points in the candidate point set have been processed.

[0060] In a preferred embodiment, the iteration module 400 further includes a removal unit, which is used to acquire and remove edges whose length exceeds a second preset length threshold when constructing the Delaunay triangulation, so as to prevent any triangle in the Delaunay triangulation result from having an edge that crosses multiple tree canopies.

[0061] It should be noted that the explanation of the above-described embodiments of the multi-scale iterative extraction method for tree vertices also applies to the multi-scale iterative extraction device for tree vertices in the above embodiments, and will not be repeated here.

[0062] This invention also provides a multi-scale iterative extraction device for tree vertices, including a computer-readable storage medium and a processor. When the processor executes a computer program on the computer-readable storage medium, it implements the steps of the multi-scale iterative extraction method for tree vertices described above.

[0063] Figure 3 This is a schematic diagram of the structure of the multi-scale iterative extraction device for tree vertices provided in Embodiment 3 of the present invention, as shown below. Figure 3As shown, the multi-scale iterative extraction device 8 for tree vertices in this embodiment includes: a processor 80, a readable storage medium 81, and a computer program 82 stored in the readable storage medium 81 and executable on the processor 80. When the processor 80 executes the computer program 82, it implements the steps in the various method embodiments described above, for example... Figure 1 The steps shown. Alternatively, when the processor 80 executes the computer program 82, it implements the functions of each module in the above-described device embodiments, for example... Figure 2 The functions of the module shown.

[0064] For example, the computer program 82 may be divided into one or more modules, which are stored in the readable storage medium 81 and executed by the processor 80 to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 82 in the multi-scale iterative extraction device 8 for tree vertices.

[0065] The multi-scale iterative extraction device 8 for tree vertices may include, but is not limited to, a processor 80 and a readable storage medium 81. Those skilled in the art will understand that... Figure 3 This is merely an example of the multi-scale iterative extraction device 8 for tree vertices and does not constitute a limitation on the multi-scale iterative extraction device 8 for tree vertices. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the multi-scale iterative extraction device for tree vertices may also include a power management module, an arithmetic processing module, input / output devices, network access devices, buses, etc.

[0066] The processor 80 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. A general-purpose processor may be a microprocessor or any conventional processor.

[0067] The readable storage medium 81 can be an internal storage unit of the multi-scale iterative extraction device 8 for tree vertices, such as a hard disk or memory of the multi-scale iterative extraction device 8 for tree vertices. The readable storage medium 81 can also be an external storage device of the multi-scale iterative extraction device 8 for tree vertices, such as a plug-in hard disk, SmartMediaCard (SMC), SecureDigital (SD) card, or FlashCard equipped on the multi-scale iterative extraction device 8 for tree vertices. Furthermore, the readable storage medium 81 can include both internal storage units and external storage devices of the multi-scale iterative extraction device 8 for tree vertices. The readable storage medium 81 is used to store the computer program and other programs and data required by the multi-scale iterative extraction device for tree vertices. The readable storage medium 81 can also be used to temporarily store data that has been output or will be output.

[0068] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0069] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0070] Those skilled in the art will recognize that the units and method steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0071] In the embodiments provided by this invention, it should be understood that the disclosed apparatus / terminal devices and methods can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0072] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0073] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0074] The present invention is not limited to the description in the specification and embodiments, and thus other advantages and modifications can be readily realized by those skilled in the art. Therefore, the present invention is not limited to the specific details, representative devices and illustrated examples shown and described herein without departing from the spirit and scope of the general concept as defined by the claims and their equivalents.

Claims

1. A multi-scale iterative extraction method for tree vertices, characterized in that, Includes the following steps: Step 1: Obtain the gradient pointing map or canopy height model of the target forest; Step 2: Extract the local maxima of the gradient pointing map or the canopy height model using at least two windows of different scales to generate multiple sets of local maxima; Step 3: Compare the multiple sets of local maximum values, determine the duplicate points as real tree vertices and the remaining points as candidate points, and establish a set of real tree vertices and a set of candidate points; Step 4: Identify the inter-canopy geometric features of the target forest, and iteratively filter out real tree vertices from the candidate point set based on these features. Update the set of real tree vertices and the candidate point set according to the filtering results until a preset iteration termination condition is met. Specifically: S401, Construct a Delaunay triangulation using all points in the set of real tree vertices and the set of candidate points; S402, traverse each edge of each triangle, obtain the target candidate point connected to the real tree vertex, and determine whether the corresponding edge meets the preset conditions. If so, add the target candidate point to the real tree vertex set; otherwise, remove the target candidate point from the candidate point set. S403, Repeat steps S401-S402 until the preset iteration end condition is met. The preset iteration end condition includes that all points in the candidate point set have been processed.

2. The multi-scale iterative extraction method for tree vertices according to claim 1, characterized in that, Step 402 includes a first preset condition, a second preset condition, and a third preset condition. If the corresponding edge meets any one of the first preset condition, the second preset condition, and the third preset condition, then the target candidate point is added to the set of real tree vertices. The first preset condition is: based on the gradient pointing graph, the ratio of the minimum value of the connecting line to the endpoint value is obtained, and the ratio is less than a preset ratio; The second preset condition is: the angle difference between the lowest point in the connecting line and the two endpoint vectors of the line segment is obtained based on the digital surface model of the target forest, and the angle difference is less than a preset angle threshold. The third preset condition is: the length of the connecting line is obtained, and the length of the connecting line is greater than the first preset length threshold.

3. The multi-scale iterative extraction method for tree vertices according to claim 1, characterized in that, When constructing Delaunay triangulation, edges with lengths exceeding a second preset length threshold are obtained and removed to prevent any triangle in the Delaunay triangulation result from having an edge that spans multiple tree canopies.

4. The multi-scale iterative extraction method for tree vertices according to any one of claims 1-3, characterized in that, In step 2, two windows are used to extract the local maximum values ​​of the gradient pointing map or the canopy height model, respectively. The window values ​​of the two windows are the minimum canopy diameter and the maximum canopy diameter in the region.

5. The multi-scale iterative extraction method for tree vertices according to claim 4, characterized in that, The acquisition of the gradient pointing map of the target forest specifically involves: Collect forest point cloud data of the target forest; After preprocessing the forest point cloud data, ground points and non-ground points are classified, and a digital surface model of the target forest is generated based on the classified complete point cloud data. Obtain the neighboring pixels corresponding to each pixel, calculate the local gradient vector of the neighboring pixels and the pointing concentration of the corresponding pixels based on the digital land surface model, and generate the gradient pointing map of the target forest.

6. A multi-scale iterative extraction device for tree vertices, based on the multi-scale iterative extraction method for tree vertices according to any one of claims 1-5, characterized in that, It includes an acquisition module, an extraction module, a classification module, and an iteration module. The acquisition module is used to acquire the gradient pointing map or canopy height model of the target forest; The extraction module is used to extract the local maxima of the gradient pointing map or the canopy height model using at least two windows of different scales, and generate multiple sets of local maxima. The classification module is used to compare the multiple sets of local maximum values, determine the duplicate points as real tree vertices and the remaining points as candidate points, and establish a set of real tree vertices and a set of candidate points. The iterative module is used to identify the geometric features between the tree canopies of the target forest, and iteratively filter out the real tree vertices from the candidate point set based on the geometric features between the tree canopies, and update the set of real tree vertices and the candidate point set according to the filtering results until the preset iteration end condition is reached. The iteration module specifically includes: Construction unit, used to construct Delaunay triangulation using all points in the real tree vertex set and the candidate point set; The determination unit is used to traverse each edge of each triangle, obtain the target candidate point connected to the real tree vertex, and determine whether the corresponding edge meets the preset conditions. If so, the target candidate point is added to the real tree vertex set; otherwise, the target candidate point is removed from the candidate point set. An iteration unit is used to repeatedly drive the construction unit and the determination unit until a preset iteration end condition is reached, wherein the preset iteration end condition includes that all points in the candidate point set have been processed.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the multi-scale iterative extraction method for tree vertices as described in any one of claims 1-5.

8. A multi-scale iterative extraction device for tree vertices, comprising a computer-readable storage medium and a processor, characterized in that, When the processor executes the computer program on the computer-readable storage medium, it implements the steps of the multi-scale iterative extraction method for tree vertices according to any one of claims 1-5.

Images