Multi-scale iterative extraction method and device for tree vertexes, medium and equipment

Abstract

The invention relates to the field of remote sensing information extraction, and discloses a multi-scale iterative extraction method and device for tree vertexes, a medium and equipment, and the method comprises the steps: employing at least two windows of different scales to extract a gradient directivity map of a target forest or a local maximum value of a canopy height model, and determining the repeated points as real tree vertexes and the remaining points as candidate points, and iteratively screening the real tree vertexes from the candidate points according to the inter-crown geometric features of the target forest in combination with a gradient directivity map, a digital earth surface model and the like until a preset iteration ending condition is met. According to the method, the rest tree vertexes are searched gradually and iteratively from the real tree vertexes according to the geometric features between the tree crowns, and the wrong tree vertexes are deleted, so that the over-segmentation and under-segmentation phenomena are effectively inhibited, and the individual tree segmentation precision is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of remote sensing information extraction, and particularly to a multi-scale iterative extraction method, device, medium and equipment for tree vertices. Background Art

[0002] Timely and effectively obtaining forest growth information is of great significance for protecting forest resources and formulating reasonable forest management plans. And single trees are the basic units that make up a forest, and their spatial structure, biophysical and chemical components are key factors required for forest resource surveys, ecological environment modeling research, etc. The existing single-tree segmentation methods usually perform segmentation based on the Canopy Height Model (CHM) of the vegetation canopy. First, the difference between the Digital Surface Model (DSM) corresponding to the forest point cloud data and the Digital Elevation Model (DEM) is calculated, and then the local maximum tree vertex detection algorithm is used to extract the tree vertices and identify the crown width of a single tree within a certain range based on this, so as to extract the tree. Due to the characteristics of broad-leaved trees such as many prominent branches, irregular crown shapes, and high overlap degrees of adjacent crowns, it is easy to misextract these prominent branches as tree vertices using the methods of the existing technology, while the tree vertices in the crown-dense areas are easily missed, resulting in a low accuracy of single-tree segmentation. Summary of the Invention

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

[0004] The first aspect of the embodiments of the present invention provides a multi-scale iterative extraction method for tree vertices, including the following steps:

[0005] Step 1, obtaining a gradient direction map or a canopy height model of the target forest;

[0006] Step 2, respectively extracting local maxima of the gradient direction map or the canopy height model using at least two windows of different scales to generate a plurality of local maximum sets;

[0007] Step 3, comparing the plurality of local maximum sets, determining the repeated points among them as real tree vertices and the remaining points as candidate points, and establishing a real tree vertex set and a candidate point set;

[0008] Step 4, identifying the geometric features between the crowns of the target forest, and iteratively screening out real tree vertices from the candidate point set based on the geometric features between the crowns, and updating the real tree vertex set and the candidate point set according to the screening results until a preset iteration end condition is reached.

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

[0010] The third aspect of the embodiments of the present invention provides a multi-scale iterative extraction device for tree vertices, including a computer-readable storage medium and a processor. When the processor executes the computer program on the computer-readable storage medium, the steps of the above-mentioned multi-scale iterative extraction method of tree vertices are implemented.

[0011] The fourth aspect of the embodiments of the present 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 orientation map or the canopy height model of the target forest.

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

[0014] The classification module is used to compare the plurality of local maxima sets, determine the repeated points as real tree vertices and the remaining points as candidate points, and establish a real tree vertex set and a candidate point set.

[0015] The iteration module is used to identify the geometric features between the tree crowns of the target forest, iteratively screen out real tree vertices from the candidate point set based on the geometric features between the tree crowns, and update the real tree vertex set and the candidate point set according to the screening results until a 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, device, medium, and equipment for tree vertices. Windows of different scale sizes are used to extract tree vertices from the gradient orientation map, and the remaining tree vertices are gradually iteratively searched starting from the real tree vertices according to the geometric features between the tree crowns, and the wrong tree vertices are deleted, thereby effectively suppressing the over-segmentation and under-segmentation phenomena and significantly improving the single-tree segmentation accuracy.

[0017] To make the above objects, features, and advantages of the invention more obvious and understandable, the following specifically lists the preferred embodiments of the present invention and, in conjunction with the accompanying drawings, provides a detailed description as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0019] Figure 1 It is a schematic flowchart of the multi-scale iterative extraction method of tree vertices provided in Embodiment 1;

[0020] Figure 2 It is a schematic structural diagram of the multi-scale iterative extraction device of tree vertices provided in Embodiment 2;

[0021] Figure 3 It is a schematic structural diagram of the multi-scale iterative extraction device of tree vertices provided in Embodiment 3. Specific embodiments

[0022] In order to make the purpose, technical solutions and advantages of the present invention clearer, the following further details the present invention in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0023] It should be noted that if there is no conflict, the various features in the embodiments of the present invention can be combined with each other, and all are within the protection scope of the present invention. In addition, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the device or the flowchart. Furthermore, the terms "first", "second", "third", etc. used in the present invention do not limit the data and execution order, but only distinguish the same items or similar items with basically the same functions and effects.

[0024] Figure 1 It is a schematic flowchart of a multi-scale iterative extraction method of tree vertices provided in Embodiment 1. As Figure 1 shown, it includes the following steps:

[0025] Step 1, obtain the gradient direction map or canopy height model of the target forest;

[0026] Step 2, respectively extract the local maxima of the gradient direction map or the canopy height model by using at least two windows of different scales to generate a plurality of local maxima sets;

[0027] Step 3: Compare the multiple sets of local maxima, determine the repeated points among them 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 canopies of the target forest, iteratively screen out real tree vertices from the set of candidate points based on the geometric features between the canopies, and update the set of real tree vertices and the set of candidate points according to the screening results until a preset iteration end condition is reached.

[0029] The above embodiments provide a multi-scale iterative extraction method for tree vertices, which extracts tree vertices from a gradient direction map or a canopy height model CHM using windows of different scale sizes, gradually iteratively searches for the remaining tree vertices starting from real tree vertices according to the geometric features between the canopies, and deletes incorrect tree vertices, thereby effectively suppressing the over-segmentation and under-segmentation phenomena and significantly improving the single-tree segmentation accuracy.

[0030] The following uses specific embodiments to elaborate on each step of the above method in detail.

[0031] In one embodiment, the canopy height model CHM of the target forest can be obtained first. Specifically, first, the drone can be controlled to adopt a terrain-following flight mode in areas with large terrain undulations, and high-density point cloud data of the target forest can be obtained using an airborne lidar to fully depict the three-dimensional structure information of the forest canopy. Then, preprocess the point cloud data, such as denoising, point cloud classification, and point cloud normalization, etc., to separate ground points and non-ground points. Finally, divide the normalized point cloud data into regular grids with a certain resolution, then search for the highest point in each grid, and use the height from the ground of the highest point as the value of the grid, and finally obtain the canopy height model of the target forest, that is, the CHM model. Subsequently, a multi-scale iterative method is used based on this CHM model to accurately extract tree vertices.

[0032] In another preferred embodiment, the gradient convergence map (GCM) of the target forest can also be obtained, and tree vertices can be extracted based on this gradient convergence map. In this preferred embodiment, the CHM is replaced by the gradient convergence map, which is not affected by the terrain and the canopy segmentation is more accurate. Specifically, first, collect the point cloud data of the target forest, and classify the ground points and non-ground points for preprocessing of the point cloud data. Then, based on the complete classified point cloud data, establish the digital surface model (DSM) of the target forest, and statistically analyze the directivity of the local gradient vectors of the neighborhood point cloud through the digital surface model (DSM), that is, the concentration degree of the local gradient vectors of the neighborhood pixels and the corresponding pixels, so as to generate the gradient convergence map. In one preferred embodiment, establishing the gradient convergence map of the target forest specifically includes the following steps:

[0033] Construct a convolution kernel, and perform convolution processing on the data of the digital surface model of the target forest in two perpendicular directions using the convolution kernel to generate local gradient vectors of each pixel and its neighborhood;

[0034] Construct a direction vector from the central pixel to the neighborhood pixels, and calculate the angular difference between the neighborhood pixel gradient vector and the direction vector from the central pixel to the neighborhood pixels;

[0035] Set weights for pixels with different angular differences based on a two-dimensional Gaussian kernel function, calculate the pixel value of each pixel, and generate a gradient orientation map of the target forest according to the pixel values.

[0036] In the gradient orientation map established by the above method, the higher the pixel value, the more concentrated the local gradient vectors of the pixels in the neighborhood point to the pixel. According to the geometric characteristics of the tree crown, this value is the highest at the tree vertex and the lowest at the crown boundary. In the above preferred embodiment, since the gradient orientation map is not affected by the terrain, it can replace the CHM model for crown segmentation, further improving the accuracy of crown segmentation.

[0037] Then extract tree vertices based on the gradient orientation map or canopy height model of the target forest. The prior art usually moves a square window of a fixed size on each grid, and identifies whether the CHM value of the grid at the center of the window is the maximum value within the window. If it is the maximum value, it is considered that the grid may contain a tree vertex, and the center of the grid is extracted as the possible tree vertex position. The embodiments of the present invention use at least two windows of different scales to respectively extract the local maximum values of the gradient orientation map or the canopy height model, establish multiple local maximum value sets, determine the repeated points as real tree vertices, determine the remaining points as candidate points, and finally obtain an accurate set of real tree vertices through an iterative method.

[0038] Specifically, two windows can be used to respectively extract the local maximum values of the gradient orientation map or the canopy height model. The window values of the two windows are respectively the minimum tree crown diameter and the maximum tree crown diameter in the area, so as to take into account both the extraction efficiency and extraction accuracy of real tree vertices.

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

[0040] S401, use all the points in the real tree vertex set and the candidate point set to construct a Delaunay triangulation;

[0041] S402. Traverse each edge of each triangle, obtain the target candidate points connected by the real tree vertices, and determine the corresponding edge, that is, determine whether the edge connecting the real point - candidate point 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.

[0042] S403. Repeat steps S401 - S402 until the preset iteration end condition is reached, and obtain the complete tree vertex result of the area 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, add the target candidate point to the real tree vertex set.

[0044] Specifically, in one embodiment, the first preset condition is: obtain the ratio of the minimum value to the endpoint value of the connection line based on the gradient direction map, and the ratio is less than the preset ratio. This condition uses the gradient direction map to check the ratio of the minimum value to the endpoint value of the connection line. In other words, for the edge connecting the real point - candidate point screened out after constructing the Delaunay triangulation above, process the minimum value in the pixels of the gradient direction map passed by the edge and 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, it is considered that this connection meets the condition. This condition takes into account that the directionalities of the neighborhood gradient vectors of two canopy boundary points are opposite, so there is a local low value. At the same time, considering the sizes of the two canopies, the endpoint value of the small canopy is smaller, while the endpoint value of the large canopy is larger. Meeting this condition means that the connection line may pass through a boundary (pixel), indicating that this path is an effective connection of real tree vertices.

[0045] In another embodiment, the second preset condition is: obtain the angle difference between the vectors from the lowest point of the connection line to the two endpoints of the line segment based on the digital surface model of the target forest, and the angle difference is less than the preset angle threshold. This condition uses the digital surface model DSM to check whether the angle difference between the vectors from the lowest point of the connection line to the two endpoints of the line segment is less than the preset angle threshold, and at the same time takes into account the distance between the two tree vertices and the possible low points at the boundary. If the angle difference of the connection line is less than this threshold, it indicates that this connection meets the geometric relationship between real tree vertices.

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

[0047] In another preferred embodiment provided by the present invention, that is, when constructing the Delaunay triangulation in step S401, the edges with lengths exceeding the second preset length threshold are obtained and removed to avoid any edge of the Delaunay triangulation result from crossing multiple tree crowns, further improving the accuracy of tree vertex extraction. In a specific embodiment, 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 connection line are real points, and the second preset length threshold is used to remove the slender connection lines that may appear at the research boundary or other places and cross multiple tree crowns.

[0048] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0049] The embodiment of the present invention also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the multi-scale iterative extraction method of the above-mentioned tree vertices is implemented.

[0050] Figure 2 It is a schematic structural diagram of the multi-scale iterative extraction device for tree vertices provided in Embodiment 2, as Figure 2 shown, including 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 direction map or the canopy height model of the target forest.

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

[0053] The classification module 300 is used to compare the plurality of local maxima sets, determine the repeated points as real tree vertices and the remaining points as candidate points, and establish a real tree vertex set and a candidate point set.

[0054] The iterative module 400 is used to identify the geometric features among the tree crowns of the target forest, iteratively screen out the true tree vertices from the set of candidate points based on the geometric features among the tree crowns, and update the set of true tree vertices and the set of candidate points according to the screening results until a preset iterative end condition is reached.

[0055] The above embodiments provide a multi-scale iterative extraction device for tree vertices, which gradually iteratively searches for the remaining tree vertices starting from the true tree vertices according to the geometric features among the tree crowns, and deletes the incorrect tree vertices, thereby effectively suppressing the over-segmentation and under-segmentation phenomena and significantly improving the single-tree segmentation accuracy.

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

[0057] A construction unit for constructing a Delaunay triangulation using all the points in the set of true tree vertices and the set of candidate points;

[0058] A determination unit for traversing each edge of each triangle, obtaining the target candidate points connected to the true tree vertices, and determining whether the corresponding edge meets the preset conditions. If so, adding the target candidate points to the set of true tree vertices; otherwise, removing the target candidate points from the set of candidate points;

[0059] An iteration unit for repeatedly driving the construction unit and the determination unit until a preset iterative end condition is reached. The preset iterative end condition includes that all the points in the set of candidate points have been processed.

[0060] In a preferred embodiment, the iterative module 400 further includes a removal unit, which is used to obtain and remove the edges whose lengths exceed the second preset length threshold when constructing the Delaunay triangulation, so as to prevent the edges of any triangle in the Delaunay triangulation result from spanning multiple tree crowns.

[0061] It should be noted that the foregoing explanation of the 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 elaborated here.

[0062] The embodiments of the present invention also provide a multi-scale iterative extraction device for tree vertices, including a computer-readable storage medium and a processor. When the processor executes the computer program on the computer-readable storage medium, the steps of the above-mentioned multi-scale iterative extraction method for tree vertices are implemented.

[0063] Figure 3 is a schematic structural diagram of the multi-scale iterative extraction device for tree vertices provided in Embodiment 3 of the present invention, as Figure 3As shown, the multi-scale iterative extraction device 8 of the tree vertex 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 each of the above method embodiments, such as Figure 1 the steps shown. Alternatively, when the processor 80 executes the computer program 82, it implements the functions of each module in each of the above device embodiments, such as Figure 2 the functions of the module shown.

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

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

[0066] The so-called processor 80 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0067] The readable storage medium 81 may be an internal storage unit of the multi-scale iterative extraction device 8 of the tree vertices, such as a hard disk or memory of the multi-scale iterative extraction device 8 of the tree vertices. The readable storage medium 81 may also be an external storage device of the multi-scale iterative extraction device 8 of the tree vertices, such as a plug-in hard disk equipped on the multi-scale iterative extraction device 8 of the tree vertices, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the readable storage medium 81 may also include both an internal storage unit and an external storage device of the multi-scale iterative extraction device 8 of the 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 of the tree vertices. The readable storage medium 81 may also be used to temporarily store the data that has been output or will be output.

[0068] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated herein.

[0069] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0070] Those of ordinary skill in the art can realize that the units and method steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner 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 implementation should not be considered to exceed the scope of the present invention.

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

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

[0073] In addition, each functional unit in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0074] The present invention is not limited only to what is described in the specification and embodiments. Therefore, for those skilled in the art, additional advantages and modifications can be easily achieved. Therefore, without departing from the spirit and scope of the general concept defined by the claims and their equivalents, the present invention is not limited to specific details, representative devices and the illustrated examples shown and described here.

Claims

1. A multi-scale iterative extraction method for tree vertices, characterized in that: The following steps are involved: Step 1, obtaining a gradient pointing map or canopy height model of the target forest; Step 2, using at least two windows of different scales to respectively extract the local maximum of the gradient directivity map or the canopy height model, and generating multiple local maximum sets; Step 3, comparing the multiple local maximum value sets, determining the repeated points therein as real tree vertices and the remaining points as candidate points, and establishing a real tree vertex set and a candidate point set; Step 4, identifying the geometric features between tree crowns of the target forest, and iteratively screening out real tree vertices from the candidate point set based on the geometric features between tree crowns, and updating the real tree vertex set and the candidate point set according to the screening results until a preset iteration end condition is reached.

2. The multi-scale iterative extraction method of tree vertices according to claim 1, characterized in that: In step 4, the geometric features between tree crowns of the target forest are identified, and the real tree vertices are iteratively selected from the candidate point set based on the geometric features between tree crowns, specifically: S401, constructing a Delaunay triangulation using the real tree vertex set and all points in the candidate point set; S402, traversing each edge of each triangle, obtaining a target candidate point connected to a vertex of the real tree, and determining whether the corresponding edge meets a preset condition, if so, adding the target candidate point to the real tree vertex set, otherwise removing the target candidate point from the candidate point set; S403, repeating steps S401-S402 until a preset iteration end condition is reached, wherein the preset iteration end condition includes that all points in the candidate point set are processed.

3. The multi-scale iterative extraction method of tree vertices according to claim 2, characterized in that: The 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, the target candidate point is added to the real tree vertex set; The first preset condition is: based on the gradient directivity graph, a ratio of a minimum value to an endpoint value of a connecting line is obtained, and the ratio is less than a preset ratio; The second preset condition is: based on the digital surface model of the target forest, the angle difference between the lowest point in the connecting line and the two endpoints of the line segment is obtained, and the angle difference is less than a preset angle threshold; The third preset condition is: obtaining the length of the connection line, and the length of the connection line is greater than a first preset length threshold.

4. The multi-scale iterative extraction method of tree vertices according to claim 2, characterized in that: When constructing the Delaunay triangulation, edges whose lengths exceed a second preset length threshold are obtained and removed to prevent the edge of any triangle in the Delaunay triangulation result from crossing multiple tree crowns.

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

6. The multi-scale iterative extraction method of tree vertices according to claim 5, characterized in that: The step of obtaining the gradient pointing graph of the target forest is specifically as follows: Collect forest point cloud data of the target forest; Classifying the ground points and non-ground points after preprocessing the forest point cloud data, and generating a digital surface model of the target forest based on the classified complete point cloud data; The neighboring pixels corresponding to each pixel are obtained, the local gradient vectors of the neighboring pixels and the degree of directional concentration of the corresponding pixels are calculated based on the digital surface model, and a gradient directional map of the target forest is generated.

7. 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 to 6, characterized in that: Including acquisition module, extraction module, classification module and 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 respectively extract the local maximum of the gradient directivity map or the canopy height model using at least two windows of different scales to generate multiple local maximum sets; The classification module is used to compare the multiple local maximum value sets, determine the repeated points therein as real tree vertices and the remaining points as candidate points, and establish a real tree vertex set and a candidate point set; The iterative module is used to identify the geometric features between tree crowns of the target forest, and iteratively screen out real tree vertices from the candidate point set based on the geometric features between tree crowns, and update the real tree vertex set and the candidate point set according to the screening results until a preset iteration end condition is reached.

8. The multi-scale iterative extraction device for tree vertices according to claim 7, characterized in that: The iteration module specifically includes: A construction unit, configured to construct a Delaunay triangulation using the real tree vertex set and all points in the candidate point set; A determination unit, used to traverse each edge of each triangle, obtain a target candidate point connected to a vertex of the real tree, and determine whether the corresponding edge meets a preset condition, and if so, add the target candidate point to the real tree vertex set, otherwise remove the target candidate point from the candidate point set; The 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 are processed.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the multi-scale iterative extraction method of tree vertices described in any one of claims 1 to 6 is implemented.

10. 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, the processor implements the steps of the multi-scale iterative extraction method for tree vertices according to any one of claims 1 to 6.

Images