Fruit tree pruning intelligent recommendation method based on point cloud skeleton analysis

Abstract

The invention relates to a fruit tree pruning intelligent recommendation method based on point cloud skeleton analysis, and belongs to the technical field of agricultural information. The method comprises the following steps: S1, point cloud preprocessing: removing noise and reducing a data sampling rate through statistical filtering and uniform down-sampling technologies, and converting into a triangular mesh model; s2, point cloud skeleton extraction: skeleton processing is performed on the point cloud by using a skeleton extraction algorithm SEMC, and a skeleton structure of the fruit tree is extracted; s3, skeleton topological structure analysis: decomposing the extracted skeleton into a plurality of non-bifurcation segments, and generating a segmented chain table structure; each segment in the linked list represents an independent branch, and nodes and branch information of the linked list are used for describing the topological relation of the skeleton; s4, intelligent pruning recommendation: according to the classified branch information, in combination with pruning rules, identifying and marking the branches needing to be pruned, and generating a pruning scheme according to geometric features of the branches; meanwhile, through visual display of the pruning scheme, orchard managers are assisted to make decisions.

Description

Technical Field

[0001] The present invention belongs to the field of agricultural information technology and relates to an intelligent pruning recommendation method for fruit trees based on point cloud skeleton analysis. Background Art

[0002] With the rapid development of modern agriculture, fruit tree pruning, as a key link in orchard management, is of great significance for optimizing the tree structure and improving the fruit yield and quality. However, the traditional fruit tree pruning method mainly relies on manual experience, which has problems such as low efficiency, high labor intensity, and unstable pruning quality, and it is difficult to meet the refined management requirements of modern orchards.

[0003] In recent years, the rise of three-dimensional point cloud technology has provided a new technical means for the refined analysis of fruit tree structures. Through point cloud modeling and skeleton extraction technology, the spatial structure of fruit trees can be clearly presented and gradually applied to the field of fruit tree management. Existing research attempts to use point cloud data to extract fruit tree skeletons and conduct topological structure analysis for the automatic recognition and geometric feature analysis of tree trunks and branches. Some research has proposed pruning strategies based on classification results to assist manual decision-making. However, these studies usually focus on basic geometric analysis, ignoring the accurate recognition requirements of various branches in complex tree structures and failing to achieve efficient and automated pruning recommendations.

[0004] The existing technology mainly has the following problems in the analysis of fruit tree point cloud skeletons and pruning applications:

[0005] 1) High error rate in branch classification: It is difficult to accurately distinguish the main trunk and different types of branches in complex tree structures, especially there are large errors in the recognition of drooping branches, upright branches, and competing branches.

[0006] 2) Imperfect pruning rules: The existing methods lack a unified branch determination standard, resulting in poor applicability of pruning strategies among different fruit trees and being difficult to promote and apply.

[0007] 3) Low level of pruning intelligence: The geometric characteristics (such as length, angle, etc.) and growth status of branches are not fully combined, and the accuracy and automation of pruning decisions are insufficient. Summary of the Invention

[0008] In view of this, the purpose of the present invention is to provide an intelligent pruning recommendation method for fruit trees based on point cloud skeleton analysis to achieve accurate recognition and intelligent pruning recommendation for upright branches, competing branches, and drooping branches of fruit trees. Through the method of the present invention, the topological structure analysis of the point cloud skeleton can be effectively combined with geometric characteristics such as branch length and angle to formulate scientific pruning rules and generate a visual pruning plan, solving the problems of large branch classification errors, inconsistent pruning rules, and insufficient intelligence in the existing technology, thereby improving the efficiency and accuracy of fruit tree pruning and promoting the development of fruit tree pruning towards automation and intelligence.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] An intelligent recommendation method for fruit tree pruning based on point cloud skeleton analysis, specifically including the following steps:

[0011] S1: Point cloud preprocessing:

[0012] Denoise the input fruit tree point cloud data, specifically including: using a statistical filtering method to remove isolated points, error points and noise points; reducing the point cloud density by a uniform sampling method while retaining the overall geometric features of the fruit tree; converting the point cloud data into a triangular mesh model according to needs;

[0013] S2: Point cloud skeleton extraction:

[0014] Use the skeleton extraction algorithm SEMC to skeletonize the fruit tree point cloud after point cloud preprocessing and extract the skeleton structure of the fruit tree;

[0015] S3: Skeleton topological structure analysis:

[0016] Decompose the extracted skeleton into several non-branching segments and generate a segmented linked list structure; each segment in the linked list represents an independent branch, and the node and branch information in the linked list are used to describe the topological relationship of the skeleton, facilitating the classification and hierarchical processing of the branches;

[0017] S4: Intelligent pruning recommendation:

[0018] According to the classified branch information, combined with pruning rules (such as removing vertical branches, dense branches, competing branches and drooping branches), identify and mark the branches to be pruned, and generate a pruning plan according to the geometric features of the branches (such as length, diameter, bifurcation angle and spatial distribution); the pruning rules are set in combination with the characteristics of branch length, diameter, bifurcation angle and spatial distribution, and can be adapted to different fruit tree species and pruning requirements; at the same time, through the visual display of the pruning plan, assist orchard managers in making decisions.

[0019] Further, in step S2, the skeleton extraction algorithm SEMC is a skeleton extraction algorithm based on mesh contraction, specifically including: first, use the Meshlab tool to preprocess the fruit tree point cloud, including normal smoothing and spherical rotation surface reconstruction, to convert the point cloud into a triangular mesh model that meets the requirements; then, calculate the mesh curvature and contract the mesh according to the curvature information to extract the skeleton structure.

[0020] Other alternative skeleton extraction algorithms are the VOXEL-based contraction algorithm or L 1-medial algorithm. Further, in step S3, the analysis of the skeleton topology specifically includes: describing the topology of the point cloud data using a directed acyclic graph (DAG); organizing the paths between key nodes into a linked list structure through feature extraction and a path tracing algorithm based on depth-first search (DFS); subsequently, using KDTree radius search to filter out potential broken branch connection points and using angle measurement to filter out the only correctly connected nodes; finally, completing the skeleton repair by calculating the growth direction of the branch linked list.

[0021] Further, in step S3, in the analysis of the skeleton topology, the geometric features of the skeleton are extracted through the local geometric shape of the tree point cloud, including the direction, curvature of the branches, and the connection relationship between nodes;

[0022]

[0023]

[0024] Among them, represents the direction vector of branch i, and x i+1 , y i+1 , z i+1 respectively represent the three-dimensional space coordinates of the next node position p i+1 ; κ i is the curvature of the branch; through curvature analysis, the bending degree of the branch can be identified, which helps to further conduct topological analysis.

[0025] The skeleton repair specifically includes: First, divide the skeleton into two parts: the correct skeleton and the broken branches; the correct skeleton refers to all the skeleton nodes on the path from any leaf node, traversing along the direction of the parent node until the root node; the remaining nodes that do not belong to the correct skeleton are regarded as broken branches; the task of skeleton repair is to reconnect and correct the broken branches, and it is necessary to calculate the distance and angle differences between the broken branch nodes and the correct skeleton nodes, filter out potential broken branch connection points through KDTree radius search, and use angle measurement to determine the only correct connection node;

[0026] KDTree radius search: Through KDTree radius search, filter out all candidate connection points pj within the radius r from the broken branch node pi:

[0027] d(p i , p d ) ≤ r (3)

[0028] Among them, p i is the broken branch node, p j is the candidate connection point, and d(p i , p j ) is the distance between p i and pj Distance between;

[0029] Angle measurement: For all candidate connection points p j , calculate the angle θ(p i between it and the broken branch node p i , p j ), and select the connection point with the smallest angle as the correct connection node p connect :

[0030]

[0031] Among them, is the direction vector from p i to the previous node; is the direction vector from p j to p i 's direction vector.

[0032] Furthermore, in step S4, the branches to be pruned are identified, specifically including: formulating scientific pruning rules by combining the years of experience and judgment of experts; extracting the geometric features (such as angles, lengths, etc.) of the branches by analyzing the topological structure of the fruit tree, and initially realizing the automatic identification of upright branches, drooping branches, competing branches, and dense branches; then, to improve the identification accuracy, according to the growth characteristics of different fruit trees, dynamically adjust the angle threshold and other relevant parameters, so as to optimize the identification effect of the pruning target; among them, the priority display order of the branches is drooping branches > upright branches > competing branches > dense branches (that is, some branches may be both drooping branches and dense branches, and in this case, they are preferentially displayed as drooping branches).

[0033] Furthermore, in step S4, the identification of upright branches is specifically to judge whether it is an upright branch by calculating the included angle between two tree branches, so as to decide whether to prune;

[0034] The calculation formula for the included angle between branches is:

[0035]

[0036] Among them, θ ij represents the included angle between two branches i and j, p i , p j are the starting points of the two branches respectively, p' i , p' j are their end points; x i , y i , z i respectively represent the three-dimensional space coordinates of the starting point p i of branch i, x' i , y' i , z' i respectively represent the three-dimensional space coordinates of the end point p' of branch ii The three-dimensional spatial coordinates, x' j , y' j , z' j respectively represent the three-dimensional spatial coordinates of the end point p' of branch j j ; if the included angle is within the range of [80°, 100°], the branch with a higher level is identified as an upright branch.

[0037] Furthermore, in step S4, a drooping branch generally refers to a branch whose growth direction is towards the ground, showing a drooping phenomenon; the drooping branch can be identified by calculating the included angle between each branch and the Y-axis;

[0038] Growth direction vector is defined as:

[0039]

[0040] where and are the coordinates of two adjacent points on the branch, and n is the total number of points in the branch point cloud;

[0041] The Y-axis vector is defined as:

[0042] The included angle θ is calculated as:

[0043]

[0044] If θ > 90°, then the branch is a drooping branch.

[0045] Furthermore, in step S4, a competing branch is an upright and vigorous branch germinated from the second and third buds below the pruning cut, which affects the development of the main trunk or main branch due to competing for growth space with the extension branch and needs to be pruned, generally occurring at the end of the branch; all the end branches can be traversed first, and then the competing branch can be judged and identified according to the branch length and growth direction;

[0046] (1) Judging by branch length: If then select the branch with a shorter length as the competing branch; otherwise, further judge using the growth direction; where L 1 and L 2 are the lengths of two end branches, and D min is the length of the shortest branch among the branches;

[0047] The calculation formula for the branch length D:

[0048]

[0049] where n is the total number of points in the branch point cloud, x i , y i , z irespectively represent the three-dimensional spatial coordinates of the i-th point cloud on the branch, x j , y j , z j respectively represent the three-dimensional spatial coordinates of the j-th point cloud;

[0050] (2) Growth direction judgment: Call formula (6) to calculate the angles between these two terminal branches and their parent branch respectively. The smaller the angle, the more similar the growth direction of the terminal branch is to that of the main trunk, that is, the more it should be retained; Therefore, the branch with a larger angle value is identified as a competing branch.

[0051] Furthermore, in step S4, dense branches refer to branches that are too dense in the same area, resulting in mutual occlusion or cross-growth between branches, usually making the crown irregular and crowded. These branches usually grow from the trunk or main branches at very close angles, forming narrow angles, making the branches almost parallel or overlapping, resulting in affecting light and ventilation. To identify these branches, the angle between the branches and the branch density in the area can be combined for judgment.

[0052] The identification of dense branches specifically includes: First, conduct a preliminary screening through density analysis to identify possible dense areas; then, further screen out the dense branches that need to be pruned by analyzing the angle between the branches and the matching degree of the growth direction of the branches with their parent branches; This method combines the geometric features of spatial distribution density and branch growth direction and can accurately identify and mark dense branches.

[0053] (1) Analysis of branch density in the area

[0054] In a specific area of the tree, overly dense branches will cause mutual occlusion or overlap. By calculating the number of branches in this area, the density of the branches can be evaluated and used as a preliminary screening criterion.

[0055] Divide the point cloud space into grid cells: First, use a three-dimensional space partitioning method to divide the tree point cloud data into several smaller grid cells; the number of branches in each grid cell can reflect the branch density in this area; the specific steps are as follows:

[0056] 1) Define the grid size: According to the scale of the tree and the density of the point cloud, set an appropriate grid size; assume that the space is divided into cubic grids with each side length of δ;

[0057] 2) Grid division: For each point p i =(x i , y i , z i ), calculate the grid cell it belongs to; set the coordinates of the grid cell as:

[0058]

[0059] Among them, represents the floor operation;

[0060] 3) Count the number of branches in each grid: Calculate the number of point clouds N belonging to different branches in each grid grid , that is, the number of point clouds of different types represents the number of branches. If the number of branches N grid in a certain grid exceeds the set threshold N thresh = 3, it is considered that there are dense branches in this area;

[0061]

[0062] Among them, I(p i ∈ grid k ) is an indicator function, and m represents the total number of branches; when the point p i falls within the grid k, its value is 1, otherwise it is 0;

[0063] (2) Branch angle analysis

[0064] After initially screening out possible dense branch areas through density analysis, dense branches can be finally identified by further analyzing the angles between branches. In a dense area, if the angles between branches are too small and the growth directions of these branches are inconsistent with the direction of the parent branch, they may be dense branches that need to be pruned.

[0065] 1) Parent branch: If branch b grows on branch a, then branch a is the parent branch of branch b;

[0066] 2) Calculate the angle between branches: For each pair of branches i and j, the angle θ ij between them can be calculated:

[0067]

[0068] If the angle θ ij between branches is less than the set threshold θ thresh = 30°, it is considered that the growth directions between these branches are too close and they may be dense branches;

[0069] 3) For each branch i, calculate the angle between its growth direction and that of the parent branch; if the angle is small, it indicates that its growth direction is relatively consistent with that of the parent branch and should be retained; if the angle is large, it indicates that its growth direction is inconsistent with that of the parent branch and should be regarded as a dense branch;

[0070]

[0071] Among them, is the growth direction vector of branch i, is the growth direction vector of the parent branch; if θ parent > θ thresh , then this branch is considered a dense branch.

[0072] The beneficial effects of the present invention are as follows: Through the intelligent pruning recommendation method for fruit trees based on point cloud skeleton analysis, the present invention significantly improves the intelligent level of fruit tree pruning management. Compared with the prior art, it has the following remarkable effects:

[0073] (1) Performance and efficiency improvement: The present invention uses an improved SEMC algorithm to extract the point cloud skeleton of fruit trees, and both the extraction efficiency and accuracy are significantly improved, which can better adapt to the topological structure of complex fruit trees. At the same time, by analyzing the geometric characteristics of branches (such as length, angle, spatial distribution) and combining scientific pruning rules, the present invention realizes the accurate identification of unfavorable branches such as vertical branches, competing branches, and drooping branches, and the accuracy rate of pruning recommendation reaches more than 90%, greatly improving the scientificity of pruning decisions.

[0074] (2) Labor and cost reduction: The present invention can automatically generate pruning suggestion schemes through point cloud data, reducing the dependence on manual participation and lowering the labor cost of orchard management, especially in large-scale orchard management, the effect is more significant.

[0075] (3) The present invention effectively solves the problems existing in the prior art, such as high error rate in branch classification, difficulty in popularizing and adapting pruning rules, and insufficient intelligence in pruning decisions. Through a unified branch grading standard and intelligent recommendation scheme, the efficiency and accuracy of fruit tree pruning are comprehensively improved, making up for the deficiencies of the prior art.

[0076] (4) The present invention realizes the goals of accurate branch classification and intelligent pruning recommendation, not only optimizing the fruit tree pruning process, but also ensuring the scientificity and universality of the pruning scheme. Compared with traditional methods, the pruning efficiency is significantly improved, and the growth quality of fruit trees and the fruit yield after pruning are significantly improved, providing strong technical support for intelligent orchard management.

[0077] (5) Ecological and economic benefits: By reducing the input costs of labor and materials during pruning, the present invention realizes the maximization of the economic benefits of orchard management. At the same time, this method can effectively improve the growth environment of fruit trees, increase the fruit yield and quality, and help modern agriculture develop towards high efficiency and intelligence.

[0078] In summary, the present invention is significantly superior to the prior art in terms of performance, efficiency, cost, intelligent level, etc., and has important application value and broad promotion prospects.

[0079] Other advantages, objects, and features of the present invention will be set forth in part in the following description, and in part will be obvious to those skilled in the art upon examination of the following, or may be learned from the practice of the present invention. The objects and other advantages of the present invention may be realized and attained by the means of the instrumentalities and combinations particularly pointed out hereinafter. Brief Description of the Drawings

[0080] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be described in detail preferably with reference to the accompanying drawings, where:

[0081] Figure 1 is the road map for tree branch classification based on skeleton extraction and topological structure analysis of the present invention;

[0082] Figure 2 are the effect diagrams of pruning recognition in fruit tree pruning with different topological structures. Detailed Embodiments

[0083] The following specific examples illustrate the embodiments of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the drawings provided in the following embodiments only illustrate the basic concept of the present invention schematically. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0084] Among them, the drawings are only for illustrative purposes, showing only schematic diagrams, not physical diagrams, and should not be construed as limiting the present invention; in order to better illustrate the embodiments of the present invention, some components in the drawings will be omitted, enlarged, or reduced, which do not represent the dimensions of the actual products; for those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0085] In the drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components; in the description of the present invention, it should be understood that if there are terms such as "upper", "lower", "left", "right", "front", "rear", etc. indicating the orientation or positional relationship, they are based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, the terms describing the positional relationship in the drawings are only for illustrative purposes and should not be construed as limiting the present invention. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to specific circumstances.

[0086] Please refer toFigures 1 to 2 , the present invention provides an intelligent recommendation method for fruit tree pruning based on point cloud skeleton analysis, which specifically includes the following steps:

[0087] (1) Point cloud preprocessing:

[0088] Denoise the input fruit tree point cloud data, and use statistical filtering methods to remove isolated points, error points, and noise points, thereby improving the data quality. To optimize the calculation efficiency, based on retaining the overall geometric features of the fruit tree, reduce the point cloud density through uniform sampling. In addition, the point cloud data can be converted into a triangular mesh model according to needs, thereby providing a smoother geometric representation for subsequent skeleton extraction.

[0089] (2) Point cloud skeleton extraction:

[0090] Use the SEMC algorithm to skeletonize the fruit tree point cloud and extract the skeleton structure of the fruit tree. The SEMC algorithm can retain the main topological information of the fruit tree and provide a basis for subsequent branch classification and pruning recommendation.

[0091] (3) Skeleton topology analysis:

[0092] Conduct topological analysis on the extracted skeleton, decompose the skeleton into several non-branching segments, and generate a segmented linked list structure. Each segment in the linked list represents an independent branch, and the node and branch information in the linked list are used to describe the topological relationship of the skeleton, facilitating the classification and hierarchical processing of branches.

[0093] (4) Intelligent pruning recommendation:

[0094] According to the classified branch information, combined with pruning rules (such as removing vertical branches, competing branches, and drooping branches), mark the branches to be pruned and generate a pruning recommendation plan. The pruning rules are set in combination with branch length, diameter, bifurcation angle, and spatial distribution characteristics, and can be adapted to different fruit tree species and pruning requirements. At the same time, through the visual display of the pruning plan, assist orchard managers in making decisions.

[0095] The system structure corresponding to the method of the present invention is:

[0096] (1) Point cloud preprocessing module: The input is the original fruit tree point cloud data. After denoising and density reduction processing, the quality and calculation efficiency of the point cloud data are optimized, and it is converted into a triangular mesh model according to needs. The processed point cloud data will be used as the input for the subsequent point cloud skeleton extraction module.

[0097] (2) Point cloud skeleton extraction module: Based on the processed point cloud data, use the SEMC algorithm to extract the skeleton and obtain the skeleton structure of the fruit tree. The extraction result will be used as the input for the skeleton topology analysis module, providing the main topological information and geometric shape for further analysis.

[0098] (3) Skeleton Topology Analysis Module: Using the skeleton data obtained from the point cloud skeleton extraction module, it performs topology analysis and decomposes the skeleton into several non-branching segments, storing the topological relationship of the skeleton through a segmented linked list structure. This structure will be used as the input for the pruning intelligent recommendation module to help classify and accurately identify the pruned branches.

[0099] (4) Pruning Intelligent Recommendation Module: Based on the pruning recognition experience of experts in reality and the set pruning rules (such as removing vertical branches, competing branches, and drooping branches), it marks the branches that need to be pruned and generates a pruning plan according to the geometric characteristics of the branches (such as length, diameter, bifurcation angle, and spatial distribution). The finally output pruning plan helps orchard managers make decisions through visualization.

[0100] Replacement Scheme: The skeleton extraction module can be replaced with other skeletonization algorithms suitable for point cloud data (such as the VOXEL-based shrinking algorithm or the L1-medial algorithm), and the branch classification algorithm can also optimize the geometric feature extraction method according to the specific fruit tree structure. The pruning rules can be flexibly adjusted to adapt to the pruning requirements of different fruit trees.

[0101] Figure 1 For the branch classification roadmap based on skeleton extraction and topological structure analysis, as Figure 1 shown, the present invention provides a branch classification method based on skeleton extraction and topological analysis, mainly including three stages: point cloud preprocessing, skeleton topology analysis, and pruning recognition. In the point cloud preprocessing stage, noise is removed and the data sampling rate is reduced through statistical filtering and uniform downsampling techniques to improve the quality and consistency of the point cloud data. The processed point cloud data is converted into a triangular mesh through Meshlab for subsequent analysis. In the skeleton topology analysis stage, a directed acyclic graph (DAG) is used to describe the topological structure of the point cloud data. Through feature extraction and a path tracing algorithm based on depth-first search (DFS), the paths between key nodes are organized into a linked list structure. Subsequently, KDTree is used for radius search to screen out potential broken branch connection points, and angle measurement is used to screen out the uniquely correctly connected nodes. Finally, the skeleton is repaired by calculating the growth direction of the branch linked list. In the pruning recognition stage, scientific pruning rules are formulated by combining the experience and judgment of experts over the years. By analyzing the topological structure of the fruit tree, geometric features of the branches (such as angle, length, etc.) are extracted to initially realize the automatic recognition of upright branches, drooping branches, and competing branches. To improve the recognition accuracy, the angle threshold and other related parameters are dynamically adjusted according to the growth characteristics of different fruit trees, thereby optimizing the recognition effect of the pruning target.

[0102] Figure 2For the pruning recognition effects of fruit trees with different topologies, where blue represents drooping branches, green represents upright branches, purple represents competing branches, and red represents dense branches. The specific rules for identifying fruit tree pruning branches are as follows: In fruit tree pruning, drooping branches (blue) are branches with an angle exceeding 90° with the vertical plane in the middle and lower parts of the crown, which need to be pruned due to affecting fruit picking or light; upright branches (green) are upright branches growing vigorously in the middle of the crown, with an angle between 80° and 100° and a diameter greater than 1 cm, which need to be pruned because they compete for nutrients and affect fruit quality; competing branches (purple) are upright and vigorous branches sprouted from the second and third buds below the pruning cut, which need to be pruned because they compete with the extension branch for growth space and affect the development of the main trunk or main branch. Dense branches (red) refer to branches that are too dense in the same area, resulting in mutual shading or cross-growth between branches, usually causing the crown to appear irregular and crowded. These branches usually grow from the trunk or main branch at very close angles, forming narrow angles, making the branches almost parallel or overlapping, resulting in affecting light and ventilation. To identify these branches, the angle between the branches and the branch density within the area can be combined for judgment.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not restrictive. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the purpose and scope of the present technical solution, and they should all be covered by the scope of the claims of the present invention.

Claims

1. An intelligent recommendation method for fruit tree pruning based on point cloud skeleton analysis, characterized in that: The method specifically comprises the following steps: S1: Point cloud preprocessing: The input point cloud data of fruit trees is de-noised, specifically including: using statistical filtering methods to remove isolated points, error points and noise points; reducing the point cloud density through uniform sampling methods on the basis of retaining the overall geometric characteristics of the fruit trees; converting the point cloud data into a triangular mesh model as needed; S2: Point cloud skeleton extraction: The skeleton extraction algorithm SEMC is used to skeletonize the fruit tree point cloud after point cloud preprocessing to extract the skeleton structure of the fruit tree; S3: Skeleton topology analysis: Decompose the extracted skeleton into several non-branched segments and generate a segmented linked list structure; each segment in the linked list represents an independent branch, and the node and branch information of the linked list is used to describe the topological relationship of the skeleton; S4: Intelligent pruning recommendation: Based on the classified branch information and combined with pruning rules, the branches to be pruned are identified and marked, and a pruning plan is generated based on the geometric characteristics of the branches. The pruning rules are set in combination with branch length, diameter, bifurcation angle and spatial distribution characteristics to adapt to different fruit tree types and pruning needs. At the same time, the visual display of the pruning plan assists orchard managers in making decisions.

2. The fruit tree pruning intelligent recommendation method according to claim 1, characterized in that: In step S2, the skeleton extraction algorithm SEMC is a skeleton extraction algorithm based on mesh shrinkage, which specifically includes: first, using the Meshlab tool to preprocess the fruit tree point cloud, including normal smoothing and spherical rotation surface reconstruction, so as to convert the point cloud into a triangular mesh model that meets the requirements; then, by calculating the mesh curvature and shrinking the mesh according to the curvature information, the skeleton structure is extracted.

3. The fruit tree pruning intelligent recommendation method according to claim 1, characterized in that: In step S3, the skeleton topology analysis specifically includes: using a directed acyclic graph to describe the topological structure of the point cloud data; organizing the paths between key nodes into a linked list structure through feature extraction and a path tracing algorithm based on depth-first search; then, using KDTree radius search to screen out potential broken branch connection points, and using angle measurement to screen out the only correctly connected nodes; finally, completing the skeleton repair by calculating the growth direction of the branch linked list.

4. The fruit tree pruning intelligent recommendation method according to claim 3, characterized in that: In step S3, in the skeleton topology analysis, the geometric features of the skeleton are extracted through the local geometric shapes of the tree point cloud, including the direction and curvature of the branches and the connection relationship between the nodes; in, represents the direction vector of branch i, x i ,y i 、z i Respectively represent the current node position p i The three-dimensional space coordinates, x i+1 ,y i+1 、z i+1 Respectively represent the next node position p i+1 The three-dimensional space coordinates of i is the curvature of the branch; through curvature analysis, the degree of bending of the branch can be identified.

5. The fruit tree pruning intelligent recommendation method according to claim 3, characterized in that: In step S3, skeleton repair specifically includes: first, the skeleton is divided into two parts: the correct skeleton and the broken branches; the correct skeleton refers to all skeleton nodes on the path starting from any leaf node and traversing along the parent node to the root node; the remaining nodes that do not belong to the correct skeleton are regarded as broken branches; the task of skeleton repair is to reconnect and correct the broken branches, which requires calculating the distance and angle difference between the broken branch node and the correct skeleton node, screening out potential broken branch connection points through KDTree radius search, and using angle measurement to determine the only correct connection node; KDTree radius search: Through KDTree radius search, filter out all candidate connection points pj within the radius r from the broken branch node pi: d(p i ,p j )≤r (3)where p i is a broken branch node, p j is a candidate connection point, d(p i ,p j ) is p i and p j The distance between Angle measure: For all candidate connection points p j , calculate its relationship with the broken branch node p i The angle θ(p i ,p j ), select the connection point with the smallest angle as the correct connection node p connect : in, Yes i The direction vector to the previous node; Yes j to p i The direction vector of .

6. The fruit tree pruning intelligent recommendation method according to claim 1, characterized in that: In step S4, the branches to be pruned are identified, specifically including: formulating pruning rules based on the experts' years of experience and judgment; extracting the geometric features of the branches by analyzing the topological structure of the fruit trees, and preliminarily realizing the automatic identification of upright branches, drooping branches, competing branches and dense branches; then dynamically adjusting the angle threshold and other related parameters according to the growth characteristics of different fruit trees, so as to optimize the identification effect of pruning targets; wherein, the priority display order of branches is drooping branches> upright branches> competing branches> dense branches.

7. The method for intelligently recommending fruit tree pruning according to claim 6, characterized in that: In step S4, the identification of upright branches is specifically to determine whether it is an upright branch by calculating the angle between two tree branches, thereby deciding whether to prune; The angle between branches is calculated as: Among them, θ ij represents the angle between two branches i and j, p i 、p j are the starting points of the two branches, p′ i , p′ j is their end point; x i ,y i 、z i They represent the starting point p of branch i respectively i The three-dimensional space coordinates, x′ i , y′ i , z′ i They represent the end point p′ of branch i respectively. i The three-dimensional space coordinates, x′ j , y′ j , z′ j They represent the end point p′ of branch j respectively. j ; if the angle is in the interval [80°, 100°], the higher-level branches are identified as upright branches.

8. The method for intelligent recommendation of fruit tree pruning according to claim 6, characterized in that: In step S4, the drooping branches refer to branches that grow toward the ground and show a drooping phenomenon; the drooping branches are identified by calculating the angle between each branch and the Y axis; Growth direction vector Defined as: in, and are the coordinates of two adjacent points on the branch, and n is the total number of branch point clouds; The Y axis vector is defined as: The angle θ is calculated as: If θ>90°, the branch is a drooping branch.

9. The method for intelligently recommending fruit tree pruning according to claim 7, characterized in that: In step S4, the competing branches are upright and vigorous branches that sprout from the second and third buds below the cut, which occur at the end of the branches; first traverse all the end branches, and then identify the competing branches based on the length and growth direction of the branches; (1) Determination of branch length: If Then the shorter branch is selected as the competing branch; otherwise, the growth direction is used for further judgment; where L1 and L2 are the lengths of the two terminal branches, and D min is the length of the shortest branch among the branches; The calculation formula of branch length D is: Where n is the total number of branch point clouds, x i ,y i 、z i Respectively represent the three-dimensional space coordinates of the i-th point cloud on the branch, x j ,y j 、z j Respectively represent the three-dimensional space coordinates of the j-th point cloud; (2) Growth direction judgment: Formula (6) is used to calculate the angles between the two terminal branches and their parent branches. The smaller the angle, the more similar the growth direction of the terminal branch is to the trunk, and the more it should be retained. Therefore, the branch with a larger angle value is identified as a competing branch.

10. The method for intelligent recommendation of fruit tree pruning according to claim 7, characterized in that: In step S4, the identification of dense branches specifically includes: firstly, preliminary screening is performed through density analysis to identify dense areas; then, dense branches that need to be pruned are further screened out by analyzing the angles between branches and the matching degree between the growth directions of branches and parent branches; (1) Analysis of branch density in the region Divide the point cloud space into grid cells: First, use a three-dimensional space division method to divide the tree point cloud data into several small grid cells; the number of branches in each grid cell reflects the branch density in the area; the specific steps are as follows: 1) Define the grid size: According to the scale of the trees and the density of the point cloud, set the grid size; assume that the space is divided into cubic grids with each side length of δ; 2) Grid division: For each point p i =(x i ,y i ,z i ), calculate the grid unit where it is located; set the coordinates of the grid unit to: in, Indicates a round-down operation; 3) Count the number of branches in each grid: Calculate the number of point clouds N belonging to different branches in each grid grid , that is, the number of different types of point clouds represents the number of branches. If the number of branches in a grid is N grid Exceeds the set threshold N thresh =3, it is considered that there are dense branches in the area; Among them, I(p i ∈grid k ) is the indicator function, m represents the total number of branches; when point p i The value is 1 if it falls within the grid k, otherwise it is 0; (2) Branch angle analysis 1) Parent branch: If branch b grows on branch a, then branch a is the parent branch of branch b; 2) Calculate the angle between branches: For each pair of branches i and j, calculate the angle θ between them ij : If the angle θ between the branches ij Less than the set threshold value θ thresh =30°, it is considered that the growth directions of these branches are too close and may be dense branches; 3) For each branch i, calculate the angle between its growth direction and that of the parent branch; if the angle is small, it indicates that its growth direction is relatively consistent with that of the parent branch and should be retained; if the angle is large, it indicates that its growth direction is inconsistent with that of the parent branch and should be regarded as a dense branch; in, is the growth direction vector of branch i, is the growth direction vector of the parent branch; if θ parent >θ thresh , then the branch is considered to be a dense branch.

Images