Fruit disease monitoring method and system
By identifying the canopy and ground areas in the orchard image, detecting the lesion status of fruits and leaves, and combining historical environmental parameters to calculate the risk of fruit diseases, the problems of low efficiency and subjectivity of fruit tree disease monitoring in the existing technology are solved, and the problem of low efficiency and subjectivity of fruit tree disease monitoring in the existing technology is achieved. Accurate and automated monitoring of fruit tree diseases.
Patent Information
- Application Number
- CN202411229021.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-12-27
AI Technical Summary
The prior art is inefficient and subjective in fruit tree disease monitoring, making it difficult to achieve accurate and automated fruit disease monitoring.
By identifying the canopy and ground areas in the orchard images, detecting the lesions of fruits and leaves, and combining historical environmental parameters, the entropy weight method is used to calculate the risk of fruit disease, so as to achieve comprehensive, objective, accurate and automated monitoring of fruit trees.
Comprehensive, objective, accurate and automated monitoring of the risk of fruit tree disease disease has been achieved, which improves monitoring efficiency and accuracy, and reduces the impact of subjective judgment.
Smart Images
Figure CN119206170A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of fruit disease monitoring, and in particular to a fruit disease monitoring method and system. Background Art
[0002] Diseases can seriously affect the yield and fruit quality of fruit trees. For example, walnut diseases mainly harm fruits or leaves, tender shoots and branches, which may affect the growth rate and quality of walnut kernels, or cause the entire leaf to turn yellow and fall off early, or cause the roots of walnut trees to rot and fail to grow normally. If not handled in time, this will cause various damages to the walnut tree itself, the walnut kernels, and the environment.
[0003] At present, fruit tree disease monitoring is mainly based on manual judgment, which is inefficient and subjective. It is also difficult to carry out targeted prevention and control, and accurate and automated fruit disease monitoring cannot be achieved. Summary of the invention
[0004] The embodiments of the present invention provide a fruit disease monitoring method and system to solve the problem of accurate and automated fruit disease monitoring.
[0005] In a first aspect, an embodiment of the present invention provides a fruit disease monitoring method, comprising: Determine a crown area and a ground area corresponding to a first fruit tree in the orchard image; wherein the first fruit tree is any fruit tree; Determine the fruit area and leaf area of the first fruit tree in the crown area; Determine the number of fallen diseased fruits on the first fruit trees in the ground area; Performing disease spot detection on the fruit area and the leaf area respectively to obtain the fruit disease spot status and the leaf disease spot status of the first fruit tree; The fruit disease risk of the first fruit tree was determined based on the fruit lesion status, leaf lesion status, number of fallen diseased fruits and historical environmental parameters.
[0006] In a possible implementation manner, determining a crown area and a ground area corresponding to a first fruit tree in an orchard image includes: Based on the region growing algorithm, the branches of the first fruit tree are identified in the orchard image, and the branch with the largest area among the branches is taken as the main trunk of the first fruit tree; Determine the orchard area corresponding to the first fruit tree based on the trunk position and trunk size of the first fruit tree; The orchard area is divided into crown area and ground area according to the average RGB value.
[0007] In a possible implementation, determining a fruit area and a leaf area of a first fruit tree in a tree crown area includes: A fruit detection model is used to perform fruit detection in the crown area, and the fruit area of the first fruit tree is determined; wherein the fruit detection model is a target detection model trained with fruit images.
[0008] In a possible implementation, determining the fruit area and the leaf area of the first fruit tree in the crown area further includes: Determine the branch area in the crown area based on the region growing algorithm; The area of the crown area excluding the fruit area and branch area is regarded as the leaf area.
[0009] In a possible implementation, determining the number of fallen diseased fruits of the first fruit tree in the ground area includes: A diseased fruit detection model is used to detect diseased fruits in the ground area to obtain the number of fallen diseased fruits of the first fruit tree; wherein the diseased fruit detection model is a target detection model trained with diseased fruit images.
[0010] In a possible implementation, the lesion detection is performed on the fruit area and the leaf area respectively to obtain the fruit lesion status and the leaf lesion status of the first fruit tree, including: Based on a preset RGB value range, diseased spot pixels are selected from each pixel point in the fruit area, the fruit diseased spot area of the first fruit tree is calculated based on the number of diseased spot pixels in the fruit area, and the contour coefficient is calculated based on the coordinates of the diseased spot pixels in the fruit area, and is used as the fruit diseased spot density index of the first fruit tree; Based on a preset RGB value range, diseased spot pixels are selected from each pixel point in the leaf area, the leaf diseased spot area of the first fruit tree is calculated based on the number of diseased spot pixels in the leaf area, and the contour coefficient is calculated based on the coordinates of the diseased spot pixels in the leaf area, and used as the leaf diseased spot density indicator of the first fruit tree.
[0011] In a possible implementation, the fruit disease risk of the first fruit tree is determined based on the fruit lesion status, the leaf lesion status, the number of fallen diseased fruits, and historical environmental parameters, including: Based on the entropy weight method, the weights corresponding to the fruit lesion area, fruit lesion density index, leaf lesion area, leaf lesion density index, number of fallen diseased fruits and historical environmental parameters of the first fruit tree were determined; The fruit disease risk score of the first fruit tree is obtained by multiplying the fruit disease area, fruit disease density index, leaf disease area, leaf disease density index, number of fallen diseased fruits and historical environmental parameters of the first fruit tree with their corresponding weights; The fruit disease incidence risk of the first fruit tree is determined based on the fruit disease incidence risk score of the first fruit tree.
[0012] In a second aspect, an embodiment of the present invention provides a fruit disease monitoring system, comprising: A first partitioning module is used to determine a crown area and a ground area corresponding to a first fruit tree in the orchard image; wherein the first fruit tree is any fruit tree; A second partitioning module is used to determine a fruit area and a leaf area of the first fruit tree in the crown area; A quantity detection module, used to determine the number of fallen diseased fruits of the first fruit tree in the ground area; A disease spot detection module is used to perform disease spot detection on the fruit area and the leaf area respectively to obtain the fruit disease spot status and the leaf disease spot status of the first fruit tree; The risk determination module is used to determine the risk of fruit disease occurrence of the first fruit tree based on the fruit lesion status, leaf lesion status, the number of fallen diseased fruits and historical environmental parameters.
[0013] In a third aspect, an embodiment of the present invention provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in the first aspect or any possible implementation manner of the first aspect are implemented.
[0014] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation method of the first aspect are implemented.
[0015] The embodiment of the present invention provides a fruit disease monitoring method and system, which divides the area of a first fruit tree from an orchard image containing multiple fruit trees, and distinguishes between the crown and the ground part, so as to accurately identify the fruits and leaves growing on the tree, as well as the diseased fruits that have fallen from the first fruit tree, and then detects the lesion status of the fruits and leaves. Finally, the lesion status, the number of diseased fruits and environmental parameters are combined to determine the fruit disease risk of the first fruit tree, so as to perform comprehensive, objective, accurate and automatic monitoring of the fruit disease risk of fruit trees. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0017] Figure 1 is a flow chart of the implementation of the fruit disease monitoring method provided by an embodiment of the present invention; Figure 2 is a structural schematic diagram of a fruit disease monitoring system provided by an embodiment of the present invention; Figure 3 is a schematic diagram of a terminal provided by an embodiment of the present invention. 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 invention. However, it should be clear to those skilled in the art that the present invention may 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 invention.
[0019] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.
[0020] See also Figure 1 , which shows a flow chart of the implementation of the fruit disease monitoring method provided by an embodiment of the present invention, and is described in detail as follows: Step 101, determining a crown area and a ground area corresponding to a first fruit tree in an orchard image; wherein the first fruit tree is any fruit tree.
[0021] In this embodiment, in order to ensure that the appearance information of the fruits and leaves of the fruit trees is collected comprehensively from multiple angles, the orchard image may be a panoramic image. For example, multiple cameras may be set in the orchard, and the photographs taken may be spliced according to the positions of the cameras.
[0022] The crown area of a fruit tree is mainly composed of leaves and fruits, while the ground area is mostly soil. The two areas can be divided by color.
[0023] Step 102: determine the fruit area and leaf area of the first fruit tree in the crown area.
[0024] In this embodiment, in order to accurately determine the risk of fruit disease of fruit trees, it is necessary to distinguish between fruits and leaves and determine their status separately.
[0025] Specifically, the differences in color, texture or shape between fruits and leaves can be used to divide the areas.
[0026] Step 103, determining the number of fallen diseased fruits of the first fruit tree in the ground area.
[0027] In this embodiment, the number of fallen diseased fruits can reflect the disease state of the fruit tree. By counting the number of fallen diseased fruits according to the correspondence between the fruit tree and the ground area, it is possible to avoid counting the fallen diseased fruits of other fruit trees into the fallen diseased fruits of the first fruit tree, thereby ensuring the accuracy of the number of fallen diseased fruits.
[0028] Step 104, performing disease spot detection on the fruit area and the leaf area respectively to obtain the fruit disease spot status and the leaf disease spot status of the first fruit tree.
[0029] In this embodiment, walnut trees are taken as an example. The main diseases of walnut trees include walnut black spot disease and walnut rot disease. When these two types of diseases occur, lesions will appear on the surface of fruits and leaves. Fruit lesions usually appear as small, round black spots on the surface of the fruit. As the disease progresses, these black spots may expand and connect into pieces, causing the fruit to rot. The lesions on the leaves are small black spots at the beginning, and then expand into irregular shapes. In severe cases, they will cause yellowing of the leaves and premature leaf fall.
[0030] Since the degree of development of the lesions on the fruit and leaves varies with the severity of the disease, the lesion detection can be carried out separately according to the fruit area and the leaf area to judge the status of the fruit lesions and the status of the leaf lesions respectively, which facilitates the subsequent accurate judgment of the disease status of the fruit tree.
[0031] Step 105, determining the fruit disease risk of the first fruit tree based on the fruit spot status, the leaf spot status, the number of fallen diseased fruits and historical environmental parameters.
[0032] In this embodiment, the fruit spot state, leaf spot state, and number of fallen diseased fruits are direct information on the disease state of the fruit tree, and the historical environmental parameters are factors affecting the disease state of the fruit tree. All of this information can reflect the disease state of the fruit tree. The historical environmental parameters may include parameters such as temperature, humidity, and rainfall in the fruit tree growth environment.
[0033] The present invention divides the area of the first fruit tree from an orchard image containing multiple fruit trees, and distinguishes between the crown and the ground part, so as to accurately identify the fruits and leaves growing on the tree, as well as the diseased fruits that have fallen from the first fruit tree, and then detects the lesion status of the fruits and leaves. Finally, the lesion status, the number of diseased fruits and environmental parameters are combined to determine the fruit disease risk of the first fruit tree, so as to conduct comprehensive, objective, accurate and automatic monitoring of the fruit disease risk of fruit trees.
[0034] In a possible implementation manner, determining a crown area and a ground area corresponding to a first fruit tree in an orchard image includes: Based on the region growing algorithm, the branches of the first fruit tree are identified in the orchard image, and the branch with the largest area among the branches is taken as the main trunk of the first fruit tree; Determine the orchard area corresponding to the first fruit tree based on the trunk position and trunk size of the first fruit tree; The orchard area is divided into crown area and ground area according to the average RGB value.
[0035] In this embodiment, the characteristics of the branches of the fruit trees mainly include: the color is mainly black-brown, the edges are mostly straight lines, the shape is slender, and the area in the orchard image accounts for a small proportion. Based on the above characteristics, the pixel points with black-brown color and at the intersection of the straight line segments can be selected as seed points, and the pixel points with similar colors can be merged into the same area using the region growing algorithm. The disconnected branches can also be connected by the expansion operation, and the small interference objects can be eliminated by the corrosion operation. Finally, the branches in the orchard image are segmented, and the intersection of the straight line segments can be regarded as the endpoints of the branches.
[0036] The trunk of a fruit tree is much larger in volume than other branches, and is reflected in the image as the branch with the largest area. For orchards with densely populated fruit trees, the leaves between the fruit trees may be partially crossed. In order to reduce the amount of data processing for image detection, this embodiment proposes to determine the orchard area of the fruit tree based on the position and size of the trunk. Specifically, since there is a certain proportional relationship between the height and width of the fruit tree and the size of the trunk, the height of the fruit tree can be calculated based on the product of the trunk length and the preset height ratio coefficient, and the width of the fruit tree can be calculated based on the product of the trunk width and the preset width ratio coefficient to form a rectangle. Finally, the orchard area corresponding to the first fruit tree is determined in the orchard image according to the position of the trunk, and an appropriate angle transformation is performed so that the orchard area covers the land under the tree crown.
[0037] In a possible implementation, determining a fruit area and a leaf area of a first fruit tree in a tree crown area includes: A fruit detection model is used to perform fruit detection in the crown area, and the fruit area of the first fruit tree is determined; wherein the fruit detection model is a target detection model trained with fruit images.
[0038] In this embodiment, the target detection model is trained using fruit images, so that the target detection model can learn the characteristics of the fruit images, accurately detect the fruit in the crown area, and segment the fruit area, which facilitates the analysis of the diseased state of the fruit.
[0039] In a possible implementation, determining the fruit area and the leaf area of the first fruit tree in the crown area further includes: Determine the branch area in the crown area based on the region growing algorithm; The area of the crown area excluding the fruit area and branch area is regarded as the leaf area.
[0040] In this embodiment, since the leaf morphology of fruit trees is relatively complex, and this embodiment only needs to analyze the diseased state of the leaves, it is only necessary to determine the approximate area of the leaf region without identifying each leaf. Specifically, the method in the above embodiment can be used to segment the branch region based on the region growing algorithm, and then use the fruit region that has been determined in the above steps, and use the remaining area as the leaf region.
[0041] In a possible implementation, determining the number of fallen diseased fruits of the first fruit tree in the ground area includes: A diseased fruit detection model is used to detect diseased fruits in the ground area to obtain the number of fallen diseased fruits of the first fruit tree; wherein the diseased fruit detection model is a target detection model trained with diseased fruit images.
[0042] In this embodiment, taking walnut trees as an example, the fallen diseased fruits usually have the following characteristics in appearance: Color change: Diseased fruit may change color, becoming brown, black, or another unusual color. Healthy fruit is usually green, turning yellow-brown as it matures.
[0043] Spots or streaks: Small, round lesions, brown spots or streaks may appear on the surface of the fruit. These spots may enlarge and connect into patches as the disease progresses.
[0044] Rot: Infected fruit may appear soft and rotten, feel slimy, and sometimes have a foul odor.
[0045] Abnormal shape: The fruit may be deformed due to the disease, such as appearing sunken, swollen or twisted.
[0046] Texture changes: The texture of diseased fruit may become soft and juicy, unlike the firm texture of healthy fruit.
[0047] Early fruit drop: Diseased fruit may drop from the tree earlier than normal fruit.
[0048] Mycelium or mildew: In some cases, a white or gray mycelium or mildew layer may appear on the surface of the diseased fruit.
[0049] Based on the above characteristics, the target detection model can be trained based on the object category of fruit trees for disease monitoring and the corresponding diseased fruit images can be collected. After the target detection model learns the characteristics of the diseased fruit images, it can accurately detect the diseased fruits in the ground area and determine the number of fallen diseased fruits.
[0050] In a possible implementation, the lesion detection is performed on the fruit area and the leaf area respectively to obtain the fruit lesion status and the leaf lesion status of the first fruit tree, including: Based on a preset RGB value range, diseased spot pixels are selected from each pixel point in the fruit area, the fruit diseased spot area of the first fruit tree is calculated based on the number of diseased spot pixels in the fruit area, and the contour coefficient is calculated based on the coordinates of the diseased spot pixels in the fruit area, and is used as the fruit diseased spot density index of the first fruit tree; Based on a preset RGB value range, diseased spot pixels are selected from each pixel point in the leaf area, the leaf diseased spot area of the first fruit tree is calculated based on the number of diseased spot pixels in the leaf area, and the contour coefficient is calculated based on the coordinates of the diseased spot pixels in the leaf area, and used as the leaf diseased spot density indicator of the first fruit tree.
[0051] In this embodiment, the closer the RGB value of a pixel is to (0, 0, 0), that is, the closer the color of the pixel is to black, the RGB value range for selecting the pixel of the diseased spot can be determined according to the color range of the diseased spot of the walnut fruit tree. For other types of fruit trees, the color range of the diseased spot can be determined according to the specific characteristics of the diseased spot to select the pixel.
[0052] The fruit lesion area or the leaf lesion area can be calculated based on the product of the number of lesion pixels and the area of a single pixel. To simplify the calculation process, the number of lesion pixels can also be used directly to represent the lesion area.
[0053] The silhouette coefficient is an indicator used to evaluate the effectiveness of clustering. It is measured by calculating the difference between the similarity of each sample point to other points in its cluster and the similarity to other cluster points. The value range of the silhouette coefficient is between -1 and 1. The closer the value is to 1, the more similar the sample point is to the points in its cluster and the less similar it is to the points in other clusters, that is, the better the clustering effect. In clustering algorithms, distance is usually used as the similarity of sample points. In this embodiment, the silhouette coefficient is used to represent the density of lesions, so the coordinates of the pixel points are directly used to calculate the distance between the pixel points. The specific calculation formula is as follows:
[0054] in, It is the pixel of the diseased spot The silhouette coefficient, It is the pixel of the diseased spot The average distance to other diseased pixels, It is the pixel of the diseased spot The minimum value of the distance to other non-lesion pixels. It should be noted that the fruit lesion density index and leaf lesion density index are calculated based on the pixels within their respective areas, and do not involve pixels in other areas.
[0055] In a possible implementation, the fruit disease risk of the first fruit tree is determined based on the fruit lesion status, the leaf lesion status, the number of fallen diseased fruits, and historical environmental parameters, including: Based on the entropy weight method, the weights corresponding to the fruit lesion area, fruit lesion density index, leaf lesion area, leaf lesion density index, number of fallen diseased fruits and historical environmental parameters of the first fruit tree were determined; The fruit disease risk score of the first fruit tree is obtained by multiplying the fruit disease area, fruit disease density index, leaf disease area, leaf disease density index, number of fallen diseased fruits and historical environmental parameters of the first fruit tree with their corresponding weights; The fruit disease incidence risk of the first fruit tree is determined based on the fruit disease incidence risk score of the first fruit tree.
[0056] In this embodiment, the entropy weight method is an objective weighting method, which calculates the weight based on the discrete degree of the data itself, avoiding the influence of subjective judgment on the weight distribution. The greater the deviation between the historical environmental parameters and the ideal environment for fruit tree growth, the more unfavorable it is for the health of the fruit. Therefore, the difference between the historical environmental parameters and the ideal environmental parameters can be used as the historical environmental parameters multiplied by the corresponding weight.
[0057] Correspondingly, it can be seen that the larger the values of fruit lesion area, fruit lesion density index, leaf lesion area, leaf lesion density index, number of fallen diseased fruits and historical environmental parameters, the higher the fruit disease risk score of the first fruit tree, and the higher the fruit disease risk of the first fruit tree.
[0058] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0059] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.
[0060] Figure 2 The structure diagram of the fruit disease monitoring system provided by the embodiment of the present invention is shown. For the convenience of description, only the part related to the embodiment of the present invention is shown, which is described in detail as follows: like Figure 2 As shown, the fruit disease monitoring system 2 comprises: A first partitioning module 21 is used to determine a crown area and a ground area corresponding to a first fruit tree in the orchard image; wherein the first fruit tree is any fruit tree; A second partitioning module 22, for determining a fruit area and a leaf area of the first fruit tree in the crown area; A quantity detection module 23 is used to determine the number of fallen diseased fruits of the first fruit tree in the ground area; The disease spot detection module 24 is used to perform disease spot detection on the fruit area and the leaf area respectively to obtain the fruit disease spot status and the leaf disease spot status of the first fruit tree; The risk determination module 25 is used to determine the risk of fruit disease of the first fruit tree based on the fruit spot status, the leaf spot status, the number of fallen diseased fruits and historical environmental parameters.
[0061] In a possible implementation, the first partitioning module 21 is specifically configured to: Based on the region growing algorithm, the branches of the first fruit tree are identified in the orchard image, and the branch with the largest area among the branches is taken as the main trunk of the first fruit tree; Determine the orchard area corresponding to the first fruit tree based on the trunk position and trunk size of the first fruit tree; The orchard area is divided into crown area and ground area according to the average RGB value.
[0062] In a possible implementation, the second partitioning module 22 is specifically configured to: A fruit detection model is used to perform fruit detection in the crown area, and the fruit area of the first fruit tree is determined; wherein the fruit detection model is a target detection model trained with fruit images.
[0063] In a possible implementation, the second partitioning module 22 is further configured to: Determine the branch area in the crown area based on the region growing algorithm; The area of the crown area excluding the fruit area and branch area is regarded as the leaf area.
[0064] In a possible implementation, the quantity detection module 23 is specifically used to: A diseased fruit detection model is used to detect diseased fruits in the ground area to obtain the number of fallen diseased fruits of the first fruit tree; wherein the diseased fruit detection model is a target detection model trained with diseased fruit images.
[0065] In a possible implementation, the lesion detection module 24 is specifically used for: Based on a preset RGB value range, diseased spot pixels are selected from each pixel point in the fruit area, the fruit diseased spot area of the first fruit tree is calculated based on the number of diseased spot pixels in the fruit area, and the contour coefficient is calculated based on the coordinates of the diseased spot pixels in the fruit area, and is used as the fruit diseased spot density index of the first fruit tree; Based on a preset RGB value range, diseased spot pixels are selected from each pixel point in the leaf area, the leaf diseased spot area of the first fruit tree is calculated based on the number of diseased spot pixels in the leaf area, and the contour coefficient is calculated based on the coordinates of the diseased spot pixels in the leaf area, and used as the leaf diseased spot density indicator of the first fruit tree.
[0066] In a possible implementation, the risk determination module 25 is specifically configured to: Based on the entropy weight method, the weights corresponding to the fruit lesion area, fruit lesion density index, leaf lesion area, leaf lesion density index, number of fallen diseased fruits and historical environmental parameters of the first fruit tree were determined; The fruit disease risk score of the first fruit tree is obtained by multiplying the fruit disease area, fruit disease density index, leaf disease area, leaf disease density index, number of fallen diseased fruits and historical environmental parameters of the first fruit tree with their corresponding weights; The fruit disease incidence risk of the first fruit tree is determined based on the fruit disease incidence risk score of the first fruit tree.
[0067] The embodiment of the present invention divides the area of the first fruit tree from the orchard image containing multiple fruit trees, and distinguishes between the crown and the ground part to accurately identify the fruits and leaves growing on the tree, as well as the diseased fruits that have fallen from the first fruit tree, and then detects the lesion status of the fruits and leaves. Finally, the lesion status, the number of diseased fruits and environmental parameters are combined to determine the fruit disease risk of the first fruit tree, thereby enabling comprehensive, objective, accurate and automated monitoring of the fruit disease risk of fruit trees.
[0068] Figure 3 is a schematic diagram of a terminal provided by an embodiment of the present invention. Figure 3 As shown, the terminal 3 of this embodiment includes: a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the processor 30. When the processor 30 executes the computer program 32, the steps in the above-mentioned fruit disease monitoring method embodiments are implemented. Alternatively, when the processor 30 executes the computer program 32, the functions of each module / unit in the above-mentioned device embodiments are implemented.
[0069] Exemplarily, the computer program 32 may be divided into one or more modules / units, which are stored in the memory 31 and executed by the processor 30 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 32 in the terminal 3.
[0070] The terminal 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 3 may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will appreciate that Figure 3 It is only an example of terminal 3 and does not constitute a limitation on terminal 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.
[0071] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0072] The memory 31 may be an internal storage unit of the terminal 3, such as a hard disk or memory of the terminal 3. The memory 31 may also be an external storage device of the terminal 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 3. Further, the memory 31 may also include both an internal storage unit and an external storage device of the terminal 3. The memory 31 is used to store the computer program and other programs and data required by the terminal. The memory 31 may also be used to temporarily store data that has been output or is to be output.
[0073] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0074] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0075] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0076] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0077] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0078] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0079] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various fruit disease monitoring method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.
[0080] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A fruit disease monitoring method, characterized in that: include: Determine a crown area and a ground area corresponding to a first fruit tree in the orchard image; wherein the first fruit tree is any fruit tree; Determining a fruit area and a leaf area of the first fruit tree in the crown area; determining the number of fallen diseased fruits of the first fruit tree in the ground area; Performing disease spot detection on the fruit area and the leaf area respectively to obtain the fruit disease spot status and the leaf disease spot status of the first fruit tree; The fruit disease risk of the first fruit tree is determined based on the fruit spot status, the leaf spot status, the number of fallen diseased fruits and historical environmental parameters.
2. The fruit disease monitoring method according to claim 1, characterized in that: The step of determining the crown area and the ground area corresponding to the first fruit tree in the orchard image includes: Identify branches of the first fruit tree in the orchard image based on a region growing algorithm, and use the branch with the largest area among the branches as the main trunk of the first fruit tree; Determine the orchard area corresponding to the first fruit tree based on the trunk position and trunk size of the first fruit tree; The orchard area is divided into a crown area and a ground area according to the average RGB value.
3. The fruit disease monitoring method according to claim 1, characterized in that: Determining the fruit area and the leaf area of the first fruit tree in the crown area includes: A fruit detection model is used to perform fruit detection in the crown area, and the fruit area of the first fruit tree is determined; wherein the fruit detection model is a target detection model trained with fruit images.
4. The fruit disease monitoring method according to claim 3, characterized in that: Determining the fruit area and leaf area of the first fruit tree in the tree crown area also includes: Determining a branch region in the crown region based on a region growing algorithm; The area of the crown area excluding the fruit area and the branch area is taken as the leaf area.
5. The fruit disease monitoring method according to claim 1, characterized in that: Determining the number of fallen diseased fruits of the first fruit tree in the ground area includes: A diseased fruit detection model is used to detect diseased fruits in the ground area to obtain the number of fallen diseased fruits of the first fruit tree; wherein the diseased fruit detection model is a target detection model trained with diseased fruit images.
6. The fruit disease monitoring method according to claim 1, characterized in that: The step of performing disease spot detection on the fruit area and the leaf area respectively to obtain the fruit disease spot status and the leaf disease spot status of the first fruit tree comprises: Based on a preset RGB value range, diseased spot pixels are selected from each pixel point in the fruit area, the fruit diseased spot area of the first fruit tree is calculated based on the number of diseased spot pixels in the fruit area, and the contour coefficient is calculated based on the coordinates of the diseased spot pixels in the fruit area, and used as the fruit diseased spot density index of the first fruit tree; Based on a preset RGB value range, diseased spot pixels are selected from each pixel point in the leaf area, the leaf diseased spot area of the first fruit tree is calculated based on the number of diseased spot pixels in the leaf area, and the contour coefficient is calculated based on the coordinates of the diseased spot pixels in the leaf area, and used as an indicator of the density of leaf diseased spots of the first fruit tree.
7. The fruit disease monitoring method according to claim 6, characterized in that: The determining the fruit disease risk of the first fruit tree based on the fruit spot status, the leaf spot status, the number of fallen diseased fruits and historical environmental parameters includes: Determine the weights corresponding to the fruit lesion area, fruit lesion density index, leaf lesion area, leaf lesion density index, number of fallen diseased fruits and historical environmental parameters of the first fruit tree based on the entropy weight method; The fruit disease spot area, fruit disease spot density index, leaf disease spot area, leaf disease spot density index, number of fallen diseased fruits and historical environmental parameters of the first fruit tree are multiplied by their respective corresponding weights to obtain a fruit disease incidence risk score of the first fruit tree; The fruit disease incidence risk of the first fruit tree is determined based on the fruit disease incidence risk score of the first fruit tree.
8. A fruit disease monitoring system, characterized in that: include: A first partitioning module is used to determine a crown area and a ground area corresponding to a first fruit tree in the orchard image; wherein the first fruit tree is any fruit tree; A second partitioning module is used to determine the fruit area and leaf area of the first fruit tree in the crown area; A quantity detection module, used to determine the number of fallen diseased fruits of the first fruit tree in the ground area; a disease spot detection module, used to perform disease spot detection on the fruit area and the leaf area respectively, to obtain the fruit disease spot status and the leaf disease spot status of the first fruit tree; The risk determination module is used to determine the risk of fruit disease of the first fruit tree based on the fruit spot status, the leaf spot status, the number of fallen diseased fruits and historical environmental parameters.
9. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method as claimed in any one of claims 1 to 7 are implemented.