Plant pruning method and system based on three-dimensional modeling

Abstract

The invention discloses a plant pruning method and system based on three-dimensional modeling. The method comprises the steps that three-dimensional point cloud data and multi-view image data of a target plant are collected; monitoring the target plant by using sensing equipment, and collecting environment sensing data; generating a three-dimensional model of the target plant by using a three-dimensional reconstruction technology; extracting morphological features, physiological features and environmental features of the target plant from the three-dimensional model and the environmental sensing data through a pre-constructed polymorphic recognition model; identifying spatial distribution of branches and buds on the basis of the three-dimensional model; predicting the growth trend of the target plant in combination with time sequence data; generating pruning suggestions of branches and trunks of the target plant based on the growth prediction result; and displaying the growth prediction result and / or the pruning suggestion through a visual interface to assist manual pruning.

Description

Technical Field

[0001] The present application relates to the field of agricultural technology, and in particular to a plant pruning method and system based on three-dimensional modeling. Background Art

[0002] At present, in agricultural production, the management and pruning of fruit trees still rely heavily on manual experience. Traditional pruning methods are not only inefficient, but also prone to inconsistent pruning or incorrect operations due to the lack of scientific data support, making it difficult to achieve large-scale and standardized operations. In addition, with the advancement of agricultural science and technology, some automated tools and technologies have begun to be applied to this field, but these technologies and tools still have certain limitations, especially in complex and changeable natural environments, making it difficult to achieve accurate and effective pruning operations. These problems limit fruit farmers' effective control over fruit yield and quality, and also affect the overall benefits and development speed of modern agricultural production. Summary of the invention

[0003] In order to solve the above technical problems, the present application discloses a plant pruning method and system based on three-dimensional modeling, which uses a polymorphic recognition model to predict the growth trend of the target plant; and generates pruning suggestions for the branches and trunks of the target plant based on the growth prediction results. The accuracy of the model is improved by integrating multi-dimensional feature data, and a three-dimensional visualization display is achieved, so that users can intuitively see the comparison effect before and after pruning and its predicted effect on future growth trends, assisting manual plant pruning. Specifically, the technical solution of this application is as follows: In a first aspect, the present application discloses a plant pruning method based on three-dimensional modeling, comprising the following steps: Collecting three-dimensional point cloud data and multi-view image data of the target plant; using a sensor device to monitor the target plant and collect environmental sensor data; Generating a three-dimensional model of the target plant using three-dimensional reconstruction technology; The morphological characteristics, physiological characteristics and environmental characteristics of the target plant are extracted from the three-dimensional model and the environmental sensor data through a pre-constructed polymorphic recognition model; the spatial distribution of branches and buds is identified based on the three-dimensional model; the growth trend of the target plant is predicted in combination with the time series data; and pruning suggestions for the branches of the target plant are generated based on the growth prediction results; The growth prediction result and / or the pruning suggestion are displayed through a visual interface to assist manual pruning work.

[0004] In some embodiments, the plant pruning method based on three-dimensional modeling further includes: The polymorphic recognition model is constructed by combining a Transformer structure with a three-dimensional convolutional neural network (3D CNN); According to specific rules, historical growth records of several types of plants are selected and collected as training sets to train the polymorphic recognition model; An expert knowledge base is constructed so that the polymorphic recognition model utilizes a machine learning algorithm to integrate the expert knowledge base to provide dynamic feedback of pruning suggestions to the user.

[0005] In some embodiments, the three-dimensional model of the target plant is generated by using three-dimensional reconstruction technology, specifically comprising: Performing data preprocessing on the three-dimensional point cloud data and the multi-view image data, including filtering and denoising, and data normalization; Through point cloud registration technology, feature points are extracted from point cloud data and matched, and point cloud registration algorithm is used to align multi-view point cloud data to the same coordinate system; The registered point cloud data is fused through grid processing technology, and the fused point cloud data is converted into a grid model using a grid algorithm; Texture information is extracted from the multi-view image data through texture mapping technology, and the extracted texture is mapped to the grid model to generate a three-dimensional model to ensure that the generated three-dimensional model can restore the spatial distribution of the branches and trunks of the target plant and the positions of the buds.

[0006] In some embodiments, the predicting the growth trend of the target plant by combining the time series data specifically includes: The physiological characteristic data and environmental characteristic data of the target plant extracted at different periods are arranged in chronological order to form time series data of the growth of the target plant; the growth trend of the target plant is obtained by combining the time series data with the growth law analysis of the target plant using the polymorphic recognition model.

[0007] In some embodiments, generating pruning suggestions for branches and trunks of the target plant based on the growth prediction results specifically includes: Performing virtual pruning operations based on the three-dimensional model to simulate pruning effects under different pruning schemes; Pruning suggestions are generated based on the results of the virtual pruning simulation and the predicted growth trends before and after pruning, including the branch pruning position, angle, and retained branch length.

[0008] In some embodiments, presenting the growth prediction result and / or the pruning suggestion through a visual interface specifically includes: Using an augmented reality device, the pruning suggestions are superimposed in real time on the three-dimensional model, including displaying the branch pruning position, angle, and retained branch length.

[0009] In some embodiments, presenting the growth prediction result and / or the pruning suggestion through a visual interface further includes: Using augmented reality equipment, the growth prediction results of the target plant before and after pruning are displayed based on the three-dimensional model, including the predicted direction and length of branch growth and the predicted fruit yield.

[0010] In a second aspect, the present application further discloses a plant pruning system based on three-dimensional modeling, comprising: A data acquisition module is used to collect three-dimensional point cloud data and multi-view image data of the target plant; use a sensor device to monitor the target plant and collect environmental sensor data; A three-dimensional modeling module, used to generate a three-dimensional model of the target plant using three-dimensional reconstruction technology; A feature extraction module, used to extract the morphological features, physiological features and environmental features of the target plant from the three-dimensional model and the environmental sensing data through a pre-built polymorphic recognition model; An intelligent algorithm module, for identifying the spatial distribution of branches and buds based on the three-dimensional model through the polymorphic recognition model; predicting the growth trend of the target plant in combination with the time series data; and generating pruning suggestions for the branches of the target plant based on the growth prediction results; The AR display module is used to display the growth prediction results and / or the pruning suggestions through a visual interface to assist manual pruning work.

[0011] In some implementations, the intelligent algorithm module specifically includes: An identification submodule, for identifying the spatial distribution of branches and buds based on the three-dimensional model through the polymorphic identification model; A prediction submodule is used to arrange the physiological characteristic data and environmental characteristic data of the target plant extracted at different periods in chronological order to form time series data of the growth of the target plant; and to obtain the growth trend of the target plant by combining the time series data with the growth law of the target plant using the polymorphic recognition model; The simulated pruning submodule is used to perform virtual pruning operations based on the three-dimensional model to simulate the pruning effects under different pruning schemes; and generate pruning suggestions based on the results of the virtual pruning simulation and the predicted growth trends before and after pruning, including the branch pruning position, angle, and retained branch length.

[0012] In some embodiments, the AR display module is specifically used to: use an augmented reality device; superimpose the pruning suggestions in real time on the three-dimensional model, including displaying the branch pruning position, angle, and retained branch length; The AR display module is also used to use augmented reality equipment to display the growth prediction results of the target plant before and after pruning based on the three-dimensional model, including the predicted direction and length of branch growth and the predicted fruit yield.

[0013] Compared with the prior art, the present invention has at least one of the following beneficial effects: 1. This application uses a deep learning algorithm to accurately identify the structure and growth status of plants by analyzing multi-source data, predict the growth trend of target plants, and generate scientific plant pruning suggestions, thereby providing precise guidance for pruning. This method not only improves the efficiency of pruning, but also reduces the errors of manual operation. It ensures that neither excessive pruning nor neglect of necessary thinning work will be achieved. It is helpful to promote the scale and standardization of modern agricultural production.

[0014] 2. Through AR devices, users can directly see virtual pruning suggestions superimposed on actual plants in the real environment. This intuitive visualization method can help users perform pruning operations more accurately. AR technology can display the location, pruning angle and length of branches that need to be pruned in real time, reducing errors in human judgment, thereby improving the accuracy and consistency of pruning. AR devices can quickly provide pruning suggestions, and users do not need to frequently check paper guides or rely on experience, thereby significantly improving the efficiency of pruning work.

[0015] 3. The plant pruning method of the present application reduces the skill requirements for operators. Even novices can quickly get started with AR devices and complete pruning work according to virtual prompts, thereby expanding the number of people who can perform pruning work. Automatic pruning can be achieved with robot technology, thereby significantly reducing labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The preferred implementation scheme will be described below in a clear and understandable manner with reference to the accompanying drawings to further illustrate the above-mentioned characteristics, technical features, advantages and implementation methods of the present application.

[0017] Figure 1 A flowchart of the steps of an embodiment of a plant pruning method based on three-dimensional modeling of the present application; Figure 2 This is a structural block diagram of an embodiment of a plant pruning system based on three-dimensional modeling of the present application. DETAILED DESCRIPTION

[0018] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0019] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections.

[0020] In order to simplify the drawings, only the parts related to the invention are schematically shown in each figure, and they do not represent the actual structure of the product. In addition, in order to simplify the drawings and facilitate understanding, in some figures, only one of the parts with the same structure or function is schematically drawn or marked. In this article, "one" not only means "only one", but also means "more than one".

[0021] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0022] In a specific implementation, the terminal device described in the embodiments of the present application includes, but is not limited to, other portable devices such as mobile phones, laptop computers, tutoring machines, or tablet computers with touch-sensitive surfaces (e.g., touch screen displays and / or touch pads). It should also be understood that in some embodiments, the terminal device is not a portable communication device, but a desktop computer with a touch-sensitive surface (e.g., touch screen displays and / or touch pads).

[0023] In addition, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the specific implementation methods of the present application will be described below with reference to the accompanying drawings. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings and other implementation methods can be obtained based on these drawings without creative work.

[0025] The existing fruit tree pruning techniques mainly include the following: 1. Traditional manual pruning: It relies entirely on the workers’ personal experience and skills. Although this method is highly flexible, it is inefficient, labor-intensive, and the pruning quality is greatly affected by individual differences.

[0026] 2. Automatic recognition technology based on two-dimensional image processing: This type of technology attempts to determine the best pruning position by taking pictures of the tree crown. However, since it only considers planar information, it cannot accurately reflect the real spatial structure of the tree. Especially when the leaves fall, the occlusion relationship between branches becomes more complicated, and the effect of this method is even more limited.

[0027] 3. Automated pruning robots: In recent years, researchers have developed some robotic devices that can move autonomously in the field and perform pruning tasks. Although they can improve work efficiency and reduce labor requirements, their high costs make them less popular. At the same time, these robots lack adaptability and flexibility, and often seem unable to cope with different garden conditions.

[0028] Each solution has its scope of application and specific advantages, but also comes with obvious drawbacks. The various fruit tree pruning technologies currently available on the market have their own advantages, but from the perspective of practical application, there are generally the following shortcomings: For fruit trees that have already lost their leaves, traditional visual assessment methods have difficulty accurately determining which branches should be removed, because without leaf cover, the layering and density changes between branches are difficult to distinguish. Existing recognition methods based on two-dimensional images cannot capture the three-dimensional structural information of fruit trees and are difficult to meet the needs of precise pruning.

[0029] Simply using robotic arms or fixed cutters for large-scale operations may cause unnecessary damage or miss important growth nodes, thus affecting the subsequent growth and development of the plants.

[0030] Although some high-level equipment integrates multiple sensor elements and can better sense changes in the surrounding environment, it is difficult to promote because it is too specialized, and ordinary farmers often cannot afford such expensive investments.

[0031] This application provides a more efficient, low-cost and easy-to-operate method to assist farmers in correctly and effectively pruning fruit trees during winter or other seasons, ensuring that neither over-pruning nor neglecting necessary thinning work is done. The accuracy of the model is improved by integrating multi-dimensional feature data, overcoming the deviation caused by single-dimensional data, and combining fruit tree growth prediction with augmented reality technology to achieve three-dimensional visualization, allowing users to intuitively see the contrast effect before and after pruning and its impact on future growth trends.

[0032] The present application discloses a plant pruning method and system based on three-dimensional modeling, which can be used not only for fruit tree pruning, but also for pruning plants such as shrubs, lawns, potted plants, green belts, and vines, and plays a role in the fields of garden design, agriculture, and art. The present application specification takes the pruning of deciduous fruit trees in winter as an example to illustrate the present application method. Winter is the main period for fruit tree pruning, which is usually carried out after the fruit trees enter the dormant period and before the spring buds. At this time, the physiological activity of the fruit trees is weak, and the pruning causes less damage to the tree body. The main purpose is to remove diseased branches, insect branches, dead branches, cross branches, and overcrowded branches, etc., reduce the overwintering places for pests and diseases, and adjust the crown structure to increase the fruiting rate. Of course, the selection of other seasons or other plant species does not affect the implementation of the technical solution in the present application. It should be understood that although the preferred embodiments of the present application have been described, once the technicians in this field know the basic creative concept, they can make additional changes and modifications to these embodiments. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0033] Reference Manual Attached Figure 1 As shown, an embodiment of a plant pruning method based on three-dimensional modeling of the present application specifically includes the following steps: S100, collecting three-dimensional point cloud data and multi-view image data of a target plant; using a sensor device to monitor the target plant and collect environmental sensor data.

[0034] Specifically, LiDAR and multi-view cameras are used to collect three-dimensional point cloud data and multi-view image data of deciduous fruit trees, and environmental sensors are used to collect environmental data such as light, temperature and humidity, and soil conditions in the orchard.

[0035] S200, generating a three-dimensional model of the target plant using three-dimensional reconstruction technology.

[0036] Specifically, based on the collected three-dimensional point cloud data and multi-view image data, three-dimensional reconstruction technology is used to construct a high-precision three-dimensional model of the deciduous fruit tree to reflect the spatial positions of branches and buds in the model.

[0037] S300, extracting the morphological characteristics, physiological characteristics and environmental characteristics of the target plant from the three-dimensional model and the environmental sensing data through a pre-constructed polymorphic recognition model.

[0038] Specifically, based on a deep learning algorithm, the morphological characteristics, physiological characteristics and environmental characteristics of the fruit trees are integrated to extract polymorphic feature data, wherein the morphological characteristics include branch distribution and bud position, the physiological characteristics include historical growth data and nutritional status, and the environmental characteristics include sunshine time, light intensity, temperature and humidity, and soil conditions.

[0039] S400, identifying the spatial distribution of branches and buds based on the three-dimensional model; predicting the growth trend of the target plant in combination with time series data; and generating pruning suggestions for the branches of the target plant based on the growth prediction results.

[0040] Specifically, virtual pruning operations are performed based on the three-dimensional model to simulate the pruning effects under different pruning schemes, and the growth trend after pruning is predicted in combination with the growth law of fruit trees, including the growth direction and length change of branches and the estimated fruit yield. The best pruning scheme is selected from different pruning schemes as the pruning recommendation scheme. The pruning suggestions and prediction results are displayed through a visual interface to assist fruit farmers in making decisions.

[0041] S500, displaying the growth prediction result and / or the pruning suggestion through a visual interface to assist manual pruning work.

[0042] Specifically, the visualization interface is an AR device visualization interface, which uses AR devices to superimpose pruning suggestions in real time to guide fruit farmers to perform precise pruning. It is combined with the expert knowledge base to provide dynamic feedback, adjust pruning suggestions in real time, and reduce the rate of misoperation.

[0043] This application uses a deep learning algorithm to accurately identify the structure and growth status of plants by analyzing multi-source data, predict the growth trend of target plants, and generate scientific plant pruning suggestions, thereby providing precise guidance for pruning. This method not only improves the efficiency of pruning, but also reduces the errors of manual operation, ensuring that neither excessive pruning nor neglect of necessary thinning work is achieved.

[0044] The present application discloses another embodiment of a plant pruning method based on three-dimensional modeling. On the basis of the above embodiment, step S100 specifically includes the following sub-steps: S110, using a laser radar to collect the three-dimensional point cloud data of the target plant and the terrain in the target area where the target plant is located.

[0045] Specifically, a lidar scanner is used to obtain topographic information in a target area. Optionally, a depth camera may be used instead of a lidar to collect three-dimensional point cloud data.

[0046] S120: Use an image acquisition device to photograph the target plant from different angles to acquire the multi-viewing angle image data of the target plant.

[0047] Specifically, the image acquisition device includes a multi-view camera or a single-view camera. The image acquisition device is placed at a suitable height, and slowly walks around the fruit tree to be pruned to ensure that all parts can be captured.

[0048] S130, using soil sensors and meteorological sensors to collect environmental characteristic data of the target plant, including: soil moisture, temperature, pH value; air temperature and humidity, light intensity, wind speed, and rainfall.

[0049] Specifically, soil sensors are used to monitor soil moisture, temperature, pH value, conductivity and other parameters. These parameters can help understand the fertility and moisture status of the soil, thereby optimizing fertilization and irrigation strategies.

[0050] Meteorological sensors: used to monitor meteorological parameters such as air temperature and humidity, light intensity, wind speed, rainfall, etc. These data help to assess the impact of the orchard's climatic conditions on the growth of fruit trees.

[0051] S140, using plant physiological sensors to collect physiological characteristic data of the target plant, including: canopy coverage, tree height, fruit quantity, and nutritional status.

[0052] Specifically, plant physiological sensors are used to monitor growth indicators of fruit trees, such as leaf temperature, leaf humidity, fruit expansion, leaf thickness, leaf area, etc. These data can reflect the growth status and health of fruit trees.

[0053] This application uses a laser radar scanner to obtain topographic information in the target area, and cooperates with the multi-angle image data captured by the camera to jointly build a high-precision three-dimensional model of the fruit tree. The specific operations include: turning on the power of the device, starting the polymorphic recognition program, and confirming the normal operation of the sensor. When collecting data, you can combine the weather conditions to avoid the influence of light, and you can collect data for the fruit trees to be pruned separately on sunny days, cloudy days, and overcast days. After the data is collected, switch to the three-dimensional modeling interface and wait for the modeling system to load.

[0054] The process of establishing a three-dimensional model relies on three-dimensional reconstruction technology including point cloud registration, grid processing and texture mapping, etc. The present application provides another embodiment of a plant pruning method based on three-dimensional modeling. Based on any one of the embodiments of the above method, step S200 specifically includes the following sub-steps: S210, performing data preprocessing on the three-dimensional point cloud data and the multi-view image data, including filtering, denoising, and data normalization.

[0055] Specifically, the point cloud data is processed by denoising, filtering and cropping, and the image data is processed by correction and feature extraction.

[0056] S220, through point cloud registration technology, extracts feature points from point cloud data and matches them, and uses point cloud registration algorithm to align multi-view point cloud data to the same coordinate system.

[0057] Specifically, feature points (such as SIFT or SURF features) are extracted from the point cloud data and matched. The multi-view point cloud data is aligned to the same coordinate system using iterative closest point (ICP) or feature-based registration algorithms (such as RANSAC). The registration accuracy is further improved using global optimization algorithms (such as the Gauss-Newton method or the Levenberg-Marquardt method).

[0058] S230, using a grid processing technology, the registered point cloud data is fused, and a grid algorithm is used to convert the fused point cloud data into a grid model.

[0059] Specifically, the registered point cloud data is fused to generate a unified dense point cloud. The point cloud data is converted into a triangular mesh model using a meshing algorithm (such as Marching Cubes or Poisson reconstruction). The generated mesh is simplified, smoothed, and repaired to improve the quality of the model.

[0060] S240, extracting texture information from the multi-view image data through texture mapping technology, mapping the extracted texture onto the grid model, and generating a three-dimensional model to ensure that the generated three-dimensional model can restore the spatial distribution of branches and trunks of the target plant and the positions of buds.

[0061] Specifically, texture information is extracted from multi-view images, and the extracted texture is mapped onto a mesh model to generate a realistic three-dimensional model.

[0062] Optionally, it also includes further optimization of the generated 3D model, processing the texture overlap and inconsistency between multi-view images, ensuring the continuity and consistency of the texture, reducing the number of polygons, improving the texture quality, etc.

[0063] This embodiment provides another implementation method. On the basis of this embodiment, the step S300 extracts the morphological characteristics, physiological characteristics and environmental characteristics of the target plant from the three-dimensional model and the environmental sensor data through a pre-constructed polymorphic recognition model. Specifically, the polymorphic recognition model uses a deep learning model that combines a Transformer structure with a three-dimensional convolutional neural network (3D CNN) to extract the morphological, physiological (historical growth data, nutritional status, etc.) and environmental characteristics (sunshine duration, light, temperature and humidity, soil conditions, etc.) of the fruit tree.

[0064] On this basis, in another implementation of this embodiment, before using the polymorphic recognition model, the method further includes: S301, using a Transformer structure combined with a three-dimensional convolutional neural network (3D CNN) to construct the polymorphic recognition model.

[0065] Specifically, we integrate multi-dimensional information such as the morphological characteristics (branch distribution, bud location), physiological characteristics (historical growth data, nutritional status) and external environmental characteristics (sunshine duration, light, temperature and humidity, soil conditions) of fruit trees to construct a polymorphic recognition model to improve the recognition accuracy of the branch and trunk structure of fruit trees after deciduous leaves.

[0066] S302, selecting and collecting historical growth records of several types of plants according to specific rules as training sets to train the polymorphic recognition model.

[0067] S303, constructing an expert knowledge base so that the polymorphic recognition model can use a machine learning algorithm to integrate the expert knowledge base to provide dynamic feedback of pruning suggestions to the user.

[0068] Specifically, the expert system stores professional knowledge through a knowledge base, which contains factual knowledge (known information) and heuristic knowledge (rules based on experience). The polymorphic recognition model improves its problem-solving ability by learning this knowledge.

[0069] The polymorphic recognition model of this application can use machine learning algorithms to analyze user behavior, automatically update knowledge base content, mark outdated information, and generate new content based on user needs. Through user feedback and system self-learning, the knowledge base can be continuously optimized to improve the accuracy and relevance of information.

[0070] The present application provides another embodiment of a plant pruning method based on three-dimensional modeling. Based on any one of the embodiments of the above method, the step S400 specifically includes the following sub-steps: S410, identifying the spatial distribution of branches and buds of the target plant based on the three-dimensional model through the polymorphic recognition model.

[0071] Specifically, the polymorphic recognition model accurately and dynamically recognizes the morphological characteristics (branch distribution, bud location) of fruit trees after deciduous growth based on the three-dimensional model of the target plant. The spatial locations of branches and buds are marked on the three-dimensional model of the fruit tree.

[0072] S420, arranging the physiological characteristics and environmental characteristics data of the target plant collected at different periods in chronological order to form time series data of the growth of the target plant; and obtaining the growth trend of the target plant by combining the polymorphic recognition model with the time series data analysis.

[0073] Specifically, the collected multi-source data are fused and analyzed to obtain the time series data of fruit tree growth. For example, the polymorphic recognition model integrates the physiological characteristics of fruit trees (historical growth data, nutritional status) and external environmental characteristics (sunshine duration, light, temperature and humidity, soil conditions) and other multi-dimensional information to form comprehensive fruit tree growth monitoring data, which are arranged in chronological order to form time series data. Through the polymorphic recognition model data analysis tool, trend analysis and correlation analysis are performed on the time series data to evaluate the growth trend and environmental adaptability of fruit trees. Combined with growth data and historical yield data, the machine learning model is used to predict future fruit yields.

[0074] S430, performing virtual pruning operations based on the three-dimensional model to simulate pruning effects under different pruning schemes; generating pruning suggestions based on the results of the virtual pruning simulation and the predicted growth trends before and after pruning, including branch pruning positions, angles, and retained branch lengths.

[0075] Specifically, the spatial positions of branches and buds are marked in the model. Virtual pruning operations are performed on the basis of the three-dimensional model to simulate the pruning effects under different pruning schemes, and the growth trend after pruning is predicted in combination with the growth law of fruit trees, including the growth direction and length change of branches and the estimated fruit yield. The pruning effect is simulated in a virtual environment, and the future growth trend is predicted in combination with the growth law of fruit trees, providing a scientific basis for pruning decisions. Based on the results of the virtual pruning simulation, pruning suggestions are generated, including information such as the location of the branches to be pruned, the retained length, and the pruning angle.

[0076] The present application provides another embodiment of a plant pruning method based on three-dimensional modeling. Based on any one of the embodiments of the above method, step S500 specifically includes the following sub-steps: S510, using an augmented reality device; superimposing the pruning suggestions in real time on the three-dimensional model, including displaying the branch pruning position, angle, and retained branch length.

[0077] S520, using an augmented reality device to display the growth prediction results of the target plant before and after pruning based on the three-dimensional model, including the predicted direction and length of branch growth and the predicted fruit yield.

[0078] Specifically, augmented reality (AR) devices (such as smart glasses) are used to overlay pruning suggestions in real time, and the pruning suggestions are adjusted in real time by combining the expert knowledge base with the dynamic feedback mechanism. The above conclusions are presented in the form of a transparent layer in the user's field of vision to guide them to act according to the instructions. The specific operations can be reflected in: wearing an AR smart device, initially adjusting the viewing angle until you are satisfied; starting the virtual pruning mode, selecting the initial pruning path; following the arrow signs on the screen to perform each action in turn; after completing a round of pruning, return to view the pruning effect or expected effect, and if you need to adjust again, repeat some of the above steps until it is perfect.

[0079] AR devices can quickly provide pruning suggestions, without the need for users to frequently check paper guides or rely on experience, thus significantly improving the efficiency of pruning work. In addition, combined with deep learning algorithms, AR devices can also dynamically adjust pruning suggestions based on the real-time pruning results of plants, further optimizing the pruning process.

[0080] The present application provides another embodiment of a plant pruning method based on three-dimensional modeling, Figure 2 As shown, based on any one of the embodiments of the above method, it also includes: after the actual pruning is completed, the pruning effect is evaluated, including the branch removal rate, the accuracy of the retained length, and the impact on the growth of the fruit tree, so as to further optimize the pruning suggestion generation algorithm.

[0081] Based on the same concept, the present application also discloses a plant pruning system based on three-dimensional modeling. The system is used to implement the steps described in any of the above method embodiments. Specifically, an embodiment of a plant pruning system based on three-dimensional modeling in the present application includes: The data acquisition module is used to collect three-dimensional point cloud data and multi-view image data of the target plant; use sensor equipment to monitor the target plant and collect environmental sensor data.

[0082] The three-dimensional modeling module is used to generate a three-dimensional model of the target plant using three-dimensional reconstruction technology.

[0083] The feature extraction module is used to extract the morphological features, physiological features and environmental features of the target plant from the three-dimensional model and the environmental sensing data through a pre-built polymorphic recognition model.

[0084] An intelligent algorithm module is used to identify the spatial distribution of branches and buds based on the three-dimensional model through the polymorphic recognition model; predict the growth trend of the target plant in combination with time series data; and generate pruning suggestions for the branches of the target plant based on the growth prediction results.

[0085] The AR display module directly presents growth prediction results and pruning suggestions through a visual interface, providing precise guidance for manual pruning and ensuring efficient and accurate execution of pruning work.

[0086] Based on the above embodiment, the present application discloses another embodiment of a plant pruning system based on three-dimensional modeling, wherein the data acquisition module specifically includes the following submodules: A laser radar is used to collect the three-dimensional point cloud data of the target plant and the terrain in the target area where the target plant is located.

[0087] The image acquisition device is used to photograph the target plant from different angles to acquire the multi-viewing angle image data of the target plant.

[0088] Sensing equipment, including soil sensors, meteorological sensors, and plant physiological sensors.

[0089] Specifically, soil sensors are used to monitor soil moisture, temperature, pH value, conductivity and other parameters. These parameters can help understand the fertility and moisture status of the soil, thereby optimizing fertilization and irrigation strategies.

[0090] Meteorological sensors: used to monitor meteorological parameters such as air temperature and humidity, light intensity, wind speed, rainfall, etc. These data help to assess the impact of the orchard's climatic conditions on the growth of fruit trees.

[0091] Plant physiological sensors: used to monitor growth indicators of fruit trees, such as leaf temperature, leaf humidity, fruit expansion, leaf thickness, and leaf area. These data can reflect the growth status and health of fruit trees.

[0092] In another embodiment of the present application, the three-dimensional modeling module specifically includes the following submodules: The data preprocessing submodule is used to perform data preprocessing on the three-dimensional point cloud data and the multi-view image data, including filtering and denoising, and data normalization.

[0093] The point cloud registration submodule is used to extract and match feature points from point cloud data through point cloud registration technology, and align multi-view point cloud data to the same coordinate system using the point cloud registration algorithm.

[0094] The grid processing submodule is used to fuse the registered point cloud data through grid processing technology, and convert the fused point cloud data into a grid model using a grid algorithm.

[0095] The texture mapping submodule is used to extract texture information from the multi-view image data through texture mapping technology, map the extracted texture to the grid model, and generate a three-dimensional model.

[0096] Based on the above embodiment, the present application discloses another embodiment of a plant pruning system based on three-dimensional modeling, wherein the intelligent algorithm module specifically includes the following submodules: The identification submodule is used to identify the spatial distribution of branches and buds based on the three-dimensional model through the polymorphic identification model.

[0097] The prediction submodule is used to arrange the physiological characteristic data and environmental characteristic data of the target plant extracted at different periods in chronological order to form time series data of the growth of the target plant; and to obtain the growth trend of the target plant by combining the time series data with the growth law analysis of the target plant using the polymorphic recognition model.

[0098] The simulated pruning submodule is used to perform virtual pruning operations based on the three-dimensional model to simulate the pruning effects under different pruning schemes; and generate pruning suggestions based on the results of the virtual pruning simulation and the predicted growth trends before and after pruning, including the branch pruning position, angle, and retained branch length.

[0099] The present application provides another embodiment of a plant pruning system based on three-dimensional modeling, which, based on any one of the embodiments of the above system, further includes: The AR display module is specifically used to: utilize an augmented reality device; superimpose the pruning suggestions in real time on the three-dimensional model, including displaying the branch pruning position, angle, and retained branch length.

[0100] The AR display module is also used to use augmented reality equipment to display the growth prediction results of the target plant before and after pruning based on the three-dimensional model, including the predicted direction and length of branch growth and the predicted fruit yield.

[0101] More preferably, the present application discloses another embodiment of a plant pruning system based on three-dimensional modeling. Based on any of the above system embodiments, this embodiment also includes the following modules: The model building module is used to construct the polymorphic recognition model by combining the Transformer structure with a three-dimensional convolutional neural network (3D CNN); screen and collect historical growth records of several types of plants as a training set according to specific rules to train the polymorphic recognition model; and build an expert knowledge base so that the polymorphic recognition model can use a machine learning algorithm to integrate the expert knowledge base to provide users with dynamic feedback on pruning suggestions.

[0102] The model optimization module is used to continuously optimize and adjust the polymorphic recognition model according to the actual pruning effect feedback to improve the recognition accuracy and adaptability of the model.

[0103] The pruning effect evaluation module is used to evaluate the pruning effect after the actual pruning is completed, including the branch removal rate, the accuracy of the retained length, and the impact on the growth of fruit trees, so as to further optimize the pruning suggestion generation algorithm.

[0104] The plant pruning method and system based on three-dimensional modeling of the present application have the same technical concept, and the technical details of the embodiments of the two are applicable to each other. In order to reduce repetition, they will not be repeated here.

[0105] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned program modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program units or modules to complete all or part of the functions described above. The program modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into a processing unit, and the above-mentioned integrated unit can be implemented in the form of hardware or in the form of software program units. In addition, the specific names of the program modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application.

[0106] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A plant pruning method based on three-dimensional modeling, characterized in that: The steps include: Collecting three-dimensional point cloud data and multi-view image data of the target plant; using a sensor device to monitor the target plant and collect environmental sensor data; Generating a three-dimensional model of the target plant using three-dimensional reconstruction technology; Extracting the morphological characteristics, physiological characteristics and environmental characteristics of the target plant from the three-dimensional model and the environmental sensing data through a pre-constructed polymorphic recognition model; Identify the spatial distribution of branches and buds based on the three-dimensional model; predict the growth trend of the target plant in combination with the time series data; Generating pruning suggestions for branches and trunks of the target plant based on the growth prediction results; The growth prediction result and / or the pruning suggestion are displayed through a visual interface to assist manual pruning work.

2. A plant pruning method based on three-dimensional modeling as claimed in claim 1, characterized in that: Also includes: The polymorphic recognition model is constructed by combining a Transformer structure with a three-dimensional convolutional neural network (3D CNN); According to specific rules, historical growth records of several types of plants are selected and collected as training sets to train the polymorphic recognition model; An expert knowledge base is constructed so that the polymorphic recognition model utilizes a machine learning algorithm to integrate the expert knowledge base to provide dynamic feedback of pruning suggestions to the user.

3. A plant pruning method based on three-dimensional modeling as claimed in claim 1, characterized in that: The method of generating the three-dimensional model of the target plant by using the three-dimensional reconstruction technology specifically includes: Performing data preprocessing on the three-dimensional point cloud data and the multi-view image data, including filtering and denoising, and data normalization; Through point cloud registration technology, feature points are extracted from point cloud data and matched, and point cloud registration algorithm is used to align multi-view point cloud data to the same coordinate system; The registered point cloud data is fused through grid processing technology, and the fused point cloud data is converted into a grid model using a grid algorithm; Texture information is extracted from the multi-view image data through texture mapping technology, and the extracted texture is mapped to the grid model to generate a three-dimensional model to ensure that the generated three-dimensional model can restore the spatial distribution of the branches and trunks of the target plant and the positions of the buds.

4. A plant pruning method based on three-dimensional modeling as claimed in claim 1, characterized in that: The prediction of the growth trend of the target plant by combining the time series data specifically includes: The physiological characteristic data and environmental characteristic data of the target plant extracted at different periods are arranged in chronological order to form time series data of the growth of the target plant; the growth trend of the target plant is obtained by combining the time series data with the growth law analysis of the target plant using the polymorphic recognition model.

5. A plant pruning method based on three-dimensional modeling as claimed in claim 1 or 4, characterized in that: The generating of pruning suggestions for branches and trunks of the target plant based on the growth prediction result specifically includes: Performing virtual pruning operations based on the three-dimensional model to simulate pruning effects under different pruning schemes; Pruning suggestions are generated based on the results of the virtual pruning simulation and the predicted growth trends before and after pruning, including the branch pruning position, angle, and retained branch length.

6. A plant pruning method based on three-dimensional modeling as claimed in claim 1, characterized in that: The displaying of the growth prediction result and / or the pruning suggestion through a visual interface specifically includes: Using an augmented reality device, the pruning suggestions are superimposed in real time on the three-dimensional model, including displaying the branch pruning position, angle, and retained branch length.

7. A plant pruning method based on three-dimensional modeling as claimed in claim 1 or 6, characterized in that: The displaying of the growth prediction result and / or the pruning suggestion through a visual interface further includes: Using augmented reality equipment, the growth prediction results of the target plant before and after pruning are displayed based on the three-dimensional model, including the predicted direction and length of branch growth and the predicted fruit yield.

8. A plant pruning system based on three-dimensional modeling, characterized in that: include: A data acquisition module, used to collect three-dimensional point cloud data and multi-view image data of target plants; Using a sensor device to monitor the target plant and collect environmental sensor data; A three-dimensional modeling module, used to generate a three-dimensional model of the target plant using three-dimensional reconstruction technology; A feature extraction module, used to extract the morphological features, physiological features and environmental features of the target plant from the three-dimensional model and the environmental sensing data through a pre-built polymorphic recognition model; An intelligent algorithm module, for identifying the spatial distribution of branches and buds based on the three-dimensional model through the polymorphic recognition model; and predicting the growth trend of the target plant in combination with the time series data; Generating pruning suggestions for branches and trunks of the target plant based on the growth prediction results; The AR display module is used to display the growth prediction results and / or the pruning suggestions through a visual interface to assist manual pruning work.

9. A plant pruning system based on three-dimensional modeling as claimed in claim 8, characterized in that: The intelligent algorithm module specifically includes: An identification submodule, for identifying the spatial distribution of branches and buds based on the three-dimensional model through the polymorphic identification model; A prediction submodule, for arranging the physiological characteristic data and environmental characteristic data of the target plant extracted at different periods in chronological order to form time series data of the growth of the target plant; and obtaining the growth trend of the target plant by combining the time series data with the growth law of the target plant using the polymorphic recognition model; The simulated pruning submodule is used to perform virtual pruning operations based on the three-dimensional model to simulate the pruning effects under different pruning schemes; and generate pruning suggestions based on the results of the virtual pruning simulation and the predicted growth trends before and after pruning, including the branch pruning position, angle, and retained branch length.

10. A plant pruning system based on three-dimensional modeling as claimed in claim 8, characterized in that: The AR display module is specifically used to: use an augmented reality device; superimpose the pruning suggestions in real time on the three-dimensional model, including displaying the branch pruning position, angle, and retained branch length; The AR display module is also used to use augmented reality equipment to display the growth prediction results of the target plant before and after pruning based on the three-dimensional model, including the predicted direction and length of branch growth and the predicted fruit yield.

Images