Disease early warning method and early warning system for blueberries

Abstract

The invention discloses a disease early warning method and early warning system for blueberries, and the method comprises the steps: firstly setting a first standard judgment parameter, a second standard judgment parameter and a disease judgment function for disease early warning, and then obtaining an infrared temperature image and a visible light image of a to-be-detected blueberry leaf; the method comprises the following steps: acquiring a temperature abnormal region coordinate set according to an infrared temperature image, acquiring a color abnormal region coordinate set according to a visible light image, then screening the color abnormal region coordinate set by using the temperature abnormal region coordinate set to obtain a disease region coordinate set, and finally outputting early warning information according to the disease region coordinate set and a disease judgment model. When the leaf spot disease is attacked, abnormal changes of the blueberry leaf and metabolism temperature are caused, early warning of the blueberry leaf spot disease is achieved in a quantitative calculation and cross validation mode, and compared with a subjective judgment mode depending on worker experience, the judgment result of the method is more accurate and more objective.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent agriculture technology, in particular to a disease early warning method and system for blueberries. BACKGROUND

[0002] Blueberry is a plant of the genus Vaccinium in the subfamily Vaccinioideae of the family Ericaceae, also known as bilberry or blueberry. It is a perennial deciduous or evergreen shrub. Blueberries not only contain conventional sugars, proteins, fruit acids, and Vc, but also are rich in Ve, Va, Vb, SOD, arbutin, anthocyanins, dietary fiber, and abundant mineral elements such as K, Fe, Zn, and Ca. Studies have shown that regular consumption of blueberries and their products can help prevent the occurrence of colon cancer, significantly enhance vision, improve heart function, nourish the skin, delay brain aging, prevent Alzheimer's disease, and have good therapeutic effects on capillary lesions caused by diabetes. Blueberries are a special fruit with both economic and nutritional value.

[0003] Blueberry leaf spot is a common fungal or bacterial disease in blueberry cultivation, mainly harming leaves. When severe, it can affect photosynthesis, leading to weakened tree vigor, reduced yield, and even inducing other diseases, which is one of the important factors restricting the high quality and yield of blueberries.

[0004] In the prior art, the judgment of blueberry leaf spot is generally carried out by manual observation. For large-scale blueberry plantations, this method has low early warning efficiency, which is not conducive to early detection and prevention of leaf spot. Moreover, it is highly dependent on the work experience of workers, and the judgment result is subjective, which may lead to misjudgment and low accuracy. SUMMARY

[0005] The main purpose of the present application is to provide a disease early warning method and system for blueberries, aiming to solve the problem of low recognition accuracy in the prior art.

[0006] The above-mentioned purpose is achieved by the following technical solutions: A disease early warning method for blueberries, comprising the following steps: setting first standard judgment parameters, second standard judgment parameters, and a disease judgment function for blueberry disease early warning; obtaining an infrared temperature image and a visible light image of a blueberry leaf to be detected; converting the infrared temperature image into a grayscale image, and extracting a temperature abnormal region coordinate set S T from the grayscale image according to the first standard judgment parameters; extracting a color abnormal region coordinate set S C from the visible light image according to the second standard judgment parameters; According to the temperature anomaly region coordinate set S T According to the color anomaly region coordinate set S C Screening to obtain a disease region coordinate set S D ; According to the disease region coordinate set S D and the disease determination model, outputting early warning information.

[0007] Optionally, the first standard determination parameter comprises a standard determination gray scale domain, and the second standard determination parameter comprises a standard determination RGB domain.

[0008] Optionally, the infrared temperature image is converted into a gray scale image, and a temperature anomaly region coordinate set S T is extracted from the gray scale image according to the first standard determination parameter, comprising the following steps: The infrared temperature image is converted into a gray scale image, and a first standard coordinate system is constructed for the gray scale image; The gray scale image is divided into a plurality of pixel points, and gray scale parameters (x i , y i , G i ) of each pixel point are obtained respectively; wherein x i , y i represent the first coordinates of the pixel point, i represents the pixel point number, and G i represents the actual gray scale value; First reference coordinates (x ok , y ok ) of each calibration point in the first coordinate system are obtained; wherein the standard points are not less than 3, and k represents the number of calibration points; Each of the gray scale parameters is compared with the first standard determination parameter, and abnormal gray scale values are screened out; The first coordinates corresponding to each abnormal gray scale value are collected to generate a temperature anomaly region coordinate set S T .

[0009] Optionally, a color anomaly region coordinate set is extracted from the visible light image according to the second standard determination parameter, comprising the following steps: The visible light image is converted into an RGB image, and a second standard coordinate system is constructed for the RGB image; The RGB image is divided into a plurality of pixel points, and RGB parameters (x j , y j , r j , g j , b j ) of each pixel point are obtained respectively; wherein x i , y i represent the second coordinates of the pixel point, j represents the pixel point number, r j , gj , b j are actual RGB values; obtaining second reference coordinates (x' ok , y' ok ) of each calibration point in a second coordinate system; wherein the standard points are not less than 3; comparing each of the actual RGB values with the second standard determination parameter respectively, and screening to obtain abnormal RGB values; collecting the second coordinates corresponding to each abnormal RGB value to generate a color abnormal area coordinate set S C .

[0010] Optionally, according to the temperature abnormal area coordinate set S T , the color abnormal area coordinate set S C is screened to obtain a disease area coordinate set S D , including the following steps: According to the first reference coordinates (x ok , y ok ) and the second reference coordinates (x' ok , y' ok ), coordinate registration is performed to obtain a position conversion relationship between the temperature abnormal area coordinate set and the color abnormal area coordinate set; According to the position conversion relationship, the temperature abnormal area coordinate set S T is converted into a temperature determination coordinate set S' T ; According to the temperature determination coordinate set S' T , the color abnormal area coordinate set S C is screened for the first time to obtain a first disease coordinate set S D1 and a to-be-determined disease coordinate set S' D , wherein the expression of the first disease coordinate set S D1 is , and the expression of the to-be-determined disease coordinate set S' D is ; The to-be-determined disease coordinate set S' D is screened for the second time to obtain a second disease coordinate set S D2 ; The first disease coordinate set S D1 and the second disease coordinate set S D2 are combined into a disease area coordinate set.

[0011] Optionally, according to the first reference coordinates and the second reference coordinates, coordinate registration is performed to obtain a position conversion relationship between the temperature abnormal area coordinate set and the color abnormal area coordinate set, including the following steps: Constructing a standard expression of position conversion relationship; A one-to-one mapping is constructed between each of the first reference coordinates and each of the second reference coordinates, generating a plurality of fitting calculation groups {(x ok , y ok ), (x' ok , y' ok )}; Each fitting calculation group is introduced into the standard expression respectively, and the position conversion relationship is calculated by fitting, wherein the expression of the position conversion relationship is , wherein a, b, c, d, e, and f represent constants respectively.

[0012] Optionally, the to-be-determined lesion coordinate set S' D is subjected to secondary screening to obtain a second lesion coordinate set S D2 , including the following steps: Any to-be-determined lesion coordinate is extracted from the to-be-determined lesion coordinate set S' D ; The to-be-determined lesion coordinate corresponding to the pixel point is taken as the center, and the coordinates of all adjacent pixel points are collected to generate an adjacent pixel coordinate set; wherein the calculation expression of the adjacent pixel coordinate set is ; The adjacent pixel coordinate set is compared with the color anomaly region coordinate set S C , if there is an intersection, it meets the secondary screening, and the to-be-determined lesion coordinate is collected into the second lesion coordinate set; The step of extracting any to-be-determined lesion coordinate from the to-be-determined lesion coordinate set S'D is repeated to generate the second lesion coordinate set S D2 .

[0013] Optionally, according to the disease region coordinate set S D and the disease determination model, an early warning information is output, including the following steps: A gray image is obtained, and a leaf shape map of a to-be-detected blueberry leaf is extracted from the gray image according to a background gray value; The total number of pixel points Q of the detected blueberry leaf is calculated according to the leaf shape map; The total number of elements of the disease region coordinate set S D is taken as the number of lesion pixel points Q1; The lesion proportion is calculated according to the total number of pixel points and the number of lesion pixel points; The early warning information is output according to the lesion proportion and the disease determination function.

[0014] Optionally, the expression of the lesion proportion is q=100%Q1 / Q, and the expression of the disease determination function is wherein R represents the lesion proportion, k1, k2, k3 are constants.

[0015] Correspondingly, the application also discloses a warning system based on the above test method, which comprises: a parameter setting module, configured to set a first standard determination parameter, a second standard determination parameter and a disease determination function for blueberry disease warning; a data acquisition module, configured to acquire infrared temperature images and visible light images of blueberry leaves to be detected; a first identification module, configured to convert the infrared temperature images into gray images and extract a temperature abnormal area coordinate set from the gray images according to the first standard determination parameter; a second identification module, configured to extract a color abnormal area coordinate set from the visible light images according to the second standard determination parameter; a screening calculation module, configured to screen the color abnormal area coordinate set according to the temperature abnormal area coordinate set and acquire a disease area coordinate set; a warning information output module, configured to output warning information according to the disease area coordinate set and the disease determination model.

[0016] Compared with the prior art, the application has the following beneficial effects: The application firstly sets a first standard determination parameter, a second standard determination parameter and a disease determination function for disease warning, then acquires infrared temperature images and visible light images of blueberry leaves to be detected, extracts a temperature abnormal area coordinate set according to the infrared temperature images and a color abnormal area coordinate set according to the visible light images, then screens the color abnormal area coordinate set according to the temperature abnormal area coordinate set to obtain a disease area coordinate set, and finally outputs warning information according to the disease area coordinate set and the disease determination model; When the blueberry has leaf spot disease, the pathogen will destroy the cell structure and chlorophyll synthesis of the leaf, resulting in characteristic color changes in the lesion area: the initial stage may be a small yellow spot, and the disease will develop into brown, dark purple or gray-white spots, forming a clear color difference with the healthy area. This difference can be captured by an RGB image, showing that the R, G and B channel values deviate from the standard range of healthy leaves; Pathogen infection can trigger local defense responses in leaves (such as increased cell respiration and changes in enzyme activity), leading to an increase in energy metabolism rate in the lesion area, with a higher temperature than the healthy area. The cells in the severe lesion area die and lose normal physiological functions, and the transpiration effect is weakened, resulting in reduced heat dissipation, which may also show local temperature rise (the temperature difference with the surrounding healthy tissue can be detected by infrared imaging). Therefore, the temperature of the lesion area will deviate significantly from the normal temperature range of healthy leaves, and this feature can be quantitatively captured by infrared temperature images (converted into gray images); Based on the above principle, the application first searches the possible lesion area on the blueberry leaf through the change of color, and then screens the above area through the abnormal change of temperature, that is, selects the pixel points that meet the temperature and color change at the same time through the way of coordinate overlapping, so as to realize the rapid determination and positioning of leaf spot disease through cross-validation, finally determines the lesion stage through the quantitative calculation of the lesion area, and gives the early warning information. Compared with the prior art, the application realizes the early warning of leaf spot disease through quantitative calculation and cross-validation, and the determination result is more accurate and more objective compared with the subjective judgment method depending on the experience of workers. Secondly, the application no longer depends on the experience of workers, so that it effectively reduces the judgment threshold of leaf spot disease, thereby facilitating the timely discovery and treatment of leaf spot disease in the early stage, improving the prevention and treatment effect of blueberry disease, and improving the yield of blueberries.

[0017] Finally, the application realizes automatic recognition of leaf spot disease, especially for large blueberry plantations, which can effectively improve the prevention and treatment effect of leaf spot disease in the early stage. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 A flowchart of a disease early warning method for blueberries provided by the embodiment 1 of the application; Figure 2 A principle diagram for obtaining the temperature abnormal area coordinate set; Figure 3 A principle diagram for obtaining the color abnormal area coordinate set; Figure 4 A secondary screening principle diagram; Figure 5 A structure diagram of the early warning system provided by the embodiment 2 of the application; The purpose of the application, functional characteristics and advantages will be further described with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0020] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the application are only used to explain the relative positional relationship, movement condition, etc. between components in a certain posture (as shown in the drawings), and if the certain posture changes, the directional indications also change accordingly.

[0021] In the present application, unless otherwise explicitly specified and limited, the terms "connection", "fixing" and the like should be understood broadly, for example, "fixing" can be fixed connection, or detachable connection, or integral; can be mechanical connection, or electrical connection; can be directly connected, or indirectly connected through an intermediate medium, can be the internal communication of two elements or the interaction relationship of two elements, unless otherwise explicitly limited. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0022] In addition, if the present application has a description of "first", "second" and the like in the embodiments, the description of "first", "second" and the like is only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features limited by "first", "second" can explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing throughout the text includes three parallel schemes. For example, "robot coordinate system and / or m" includes robot coordinate system scheme, or m scheme, or robot coordinate system and m scheme that satisfies at the same time. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the realization of ordinary skilled in the art, when the combination of technical solutions appears contradictory or unachievable, it should be considered that the combination of technical solutions does not exist, nor within the scope of protection required by the present application.

[0023] Embodiment 1

[0024] Reference Figures 1 to 4 The present embodiment is an optional embodiment of the present application, which discloses a disease early warning method for blueberries, comprising the following steps: S1, setting a first standard judgment parameter, a second standard judgment parameter and a disease judgment function for blueberry disease early warning; Collecting normal blueberry leaf specimens, collecting infrared temperature images and visible light images of each leaf specimen respectively, and reading the temperature and RGB of normal green tissue after image conversion; When there are multiple values, ensure that all parameters are included by numerical domain method, while ensuring the accuracy of the parameters; The first standard judgment parameter includes a standard judgment gray domain, and its expression is [G min , G max ]; It should be noted that during the acquisition of the first standard judgment parameter, the equipment for shooting needs to be calibrated to obtain the temperature-gray conversion function, so as to convert the actual temperature into a gray value; The second standard judgment parameter includes a standard judgment RGB domain, and the expression of the standard judgment RGB domain is where RGB0 represents the standard RGB value of normal leaves, which is expressed as ; Due to the large color change of the lesion area, the color abnormal area can be quickly extracted by removing the normal area, which not only has high extraction accuracy, but also effectively simplifies the complexity of calculation, and is beneficial to improve the detection efficiency.

[0025] Due to the large color change of the lesion area, the color abnormal area can be quickly extracted by removing the normal area, which not only has high extraction accuracy, but also effectively simplifies the complexity of calculation, and is beneficial to improve the detection efficiency.

[0026] Secondly, it needs to be explained that, due to the setting of the background plate during shooting, the background area needs to be separated by the RGB standard value of the background area in the actual image processing process.

[0027] S2, acquiring an infrared temperature image and a visible light image of the blueberry leaf to be detected; It needs to be explained that the test device of the application includes a background plate, and a plurality of mark points with specific colors, such as red mark points, are arranged on the background plate; during measurement, the background plate is placed on the back of the blueberry leaf to be detected, and then the corresponding images are acquired by the infrared camera and the visible light camera.

[0028] S3, converting the infrared temperature image into a gray scale image, and extracting a temperature abnormal area coordinate set S from the gray scale image according to the first standard judgment parameter T ; S31, converting the infrared temperature image into a gray scale image, and constructing a first standard coordinate system for the gray scale image; S32, dividing the gray scale image into a plurality of pixel points, and acquiring the gray scale parameters (x i , y i , G i ) of each pixel point respectively; wherein x i , y i represent the first coordinates of the pixel points, i represents the pixel point number, and G i represents the actual gray scale value; After the first coordinate system is constructed, the coordinates of each pixel point are automatically generated, that is, the first coordinates, and the actual gray scale value of each pixel point is bound to the first coordinates, that is, the gray scale parameters (x i , y i , G i ); wherein x i , y i represent the first coordinates of the pixel points, i represents the pixel point number, and G i represents the actual gray scale value; S33, acquiring the first reference coordinates (xok , y ok ); wherein the standard points are not less than 3, and k represents the number of the calibration points; After the gray scale parameters are generated, the first reference coordinates of each calibration point in the first coordinate system are obtained, and it should be noted that, in order to ensure the accuracy of subsequent calculation, the calibration points are preferably 3; S34, comparing each gray scale parameter with the first standard judgment parameter respectively, and screening to obtain abnormal gray scale values; All gray scale parameters and the first standard judgment parameter are obtained; The actual gray scale value of any gray scale parameter is obtained, and if the actual gray scale value falls within the standard judgment gray scale domain, it is determined that the actual gray scale value meets the requirements, and it is an abnormal gray scale value; By repeating the above step of comparing each actual gray scale value, a plurality of abnormal gray scale values can be obtained; S35, the first coordinates corresponding to each abnormal gray scale value are collected to generate a temperature abnormal area coordinate set S T ; The first coordinates corresponding to each abnormal gray scale value are extracted respectively, and all the first coordinates are collected into the same set to generate a temperature abnormal area coordinate set S T .

[0029] S4, extracting a color abnormal area coordinate set S C from the visible light image according to the second standard judgment parameter; S41, converting the visible light image into an RGB image, and constructing a second standard coordinate system for the RGB image; S42, dividing the RGB image into a plurality of pixel points, and obtaining the RGB parameters (x j , y j , r j , g j , b j ) of each pixel point respectively, wherein x i , y i represent the second coordinates of the pixel point, j represents the pixel point number, and r j , g j , b j are actual RGB values; S43, obtaining the second reference coordinates (x' ok , y' ok ) of each calibration point in the second coordinate system; wherein the standard points are not less than 3; S44, comparing each actual RGB value with the second standard judgment parameter respectively, and screening to obtain abnormal RGB values; All RGB parameters (x j , y j , r j, g j , b j ) and standard judgment RGB domain, if r j , g j , b j in the RGB parameter meet , it indicates that the pixel point corresponding to the RGB parameter is normal leaf tissue, and it is rejected; that is, it meets ; Repeat the above steps to compare each RGB parameter, and classify all actual RGB values that do not meet the standard judgment RGB domain as abnormal RGB values; S45, the second coordinates corresponding to each abnormal RGB value are collected to generate a color abnormal area coordinate set S C .

[0030] S5, according to the temperature abnormal area coordinate set S T , the color abnormal area coordinate set S C is screened, and a disease area coordinate set S D is obtained; S51, according to the first reference coordinates (x ok , y ok ) and the second reference coordinates (x' ok , y' ok ), coordinate registration is performed to obtain the position conversion relationship between the temperature abnormal area coordinate set and the color abnormal area coordinate set; S511, a standard expression of the position conversion relationship is constructed; The standard expression is ; S512, one-to-one mapping is constructed between each first reference coordinate and each second reference coordinate to generate a plurality of fitting calculation groups {(x ok , y ok ), (x' ok , y' ok )}; Since all calibration points are the same, the first reference coordinates and the second reference coordinates are specific expressions of the same calibration point in different coordinate systems, so they are slightly different; One-to-one mapping is established between different expressions of the same calibration point through the same numbering method, so as to obtain a plurality of fitting calculation groups {(x ok , y ok ), (x' ok , y' ok )}. If there are 3 calibration points, 3 fitting calculation groups are obtained; S513, each fitting calculation group is introduced into the standard expression, and the position conversion relationship is obtained through fitting calculation, wherein the expression of the position conversion relationship is , wherein a, b, c, d, e, f respectively represent constants; By introducing each fitting calculation group into a standard expression, a number of equation groups can be obtained, and each constant can be calculated by solving the above equations by the least square method, and then the position conversion relationship is obtained.

[0031] S52, according to the position conversion relationship, the temperature anomaly area coordinate set S T is converted into a temperature judgment coordinate set S' T ; The temperature anomaly area coordinate set S T Each element is brought into the position conversion relationship to obtain the corresponding converted coordinates, that is, the temperature judgment coordinate set S' T ; Since the infrared temperature image and the visible light image are generated based on different coordinate systems in the post-processing process, the above steps can be used to normalize the coordinate system, thereby establishing an accurate conversion relationship between the temperature anomaly area coordinate set and the color anomaly area coordinate set, ensuring that the later calculation can be strictly corresponding, and improving the accuracy of the calculation.

[0032] S53, according to the temperature judgment coordinate set S' T , the color anomaly area coordinate set S C is subjected to a first screening to obtain a first lesion coordinate set S D1 and a to-be-determined lesion coordinate set S' D , wherein the expression of the first lesion coordinate set S D1 is , and the expression of the to-be-determined lesion coordinate set S' D is ; The abnormal area caused by blueberry leaf spot has dual variability of temperature and color. Based on the above characteristics, the intersection of the temperature judgment coordinate set S' T and the color anomaly area coordinate set S C must be a lesion area, so the first screening can be completed by solving the intersection, that is, the expression of the first lesion coordinate set S D1 is ; In the normalization of coordinates, limited by the existing technology, there are still errors in the conversion of some edge transition area pixels, which need to be further determined. The above area that needs to be further determined is the to-be-determined lesion area, and the to-be-determined lesion coordinate set S' D can be obtained by difference set, and the expression is ; S54, the to-be-determined lesion coordinate set S' D is subjected to a second screening to obtain a second lesion coordinate set SD2 ; S541、Extract any to-be-determined lesion coordinate from the to-be-determined lesion coordinate set S' D ; S542, with the pixel point corresponding to the to-be-determined lesion coordinate as the center, gather all the coordinates of the adjacent pixel points to generate an adjacent pixel coordinate set; wherein the calculation expression of the adjacent pixel coordinate set is ; A 3*3 neighborhood is constructed with the pixel point corresponding to the to-be-determined lesion coordinate as the center. In the above neighborhood, the pixel point corresponding to the to-be-determined lesion coordinate has a total of 8 adjacent pixel points, that is, the above adjacent pixel points satisfy , according to the above formula, all adjacent pixel point coordinates can be calculated, and then the adjacent pixel coordinate set is obtained; for details, refer to Figure 4 ; S543, compare the adjacent pixel coordinate set with the color anomaly region coordinate set S C , if there is an intersection, it meets the secondary screening, and the to-be-determined lesion coordinate is gathered into the second lesion coordinate set; If the adjacent pixel coordinate set and the color anomaly region coordinate set S C exist an intersection, it indicates that part of the adjacent pixel points have been determined as a color anomaly region, so the to-be-determined lesion coordinate can be determined as a lesion region, otherwise it indicates that the distance between it and the color anomaly region circled is large, which belongs to a normal region, and is excluded; S544, repeat the step of extracting any to-be-determined lesion coordinate from the to-be-determined lesion coordinate set S'D to generate the second lesion coordinate set S D2 .

[0033] By constructing a 3*3 neighborhood, the fault-tolerant screening range can be strictly limited within a reasonable registration error, neither missing the real diseased area due to error offset, nor including the non-diseased area with large offset, thereby further improving the accuracy of determination.

[0034] S55, merge the first lesion coordinate set S D1 and the second lesion coordinate set S D2 into a disease area coordinate set.

[0035] After the first lesion coordinate set S D1 and the second lesion coordinate set S D2 are determined, the first lesion coordinate set S D1 and the second lesion coordinate set S D2 are merged to obtain a disease area coordinate set.

[0036] S6, output warning information according to the disease area coordinate set S D and the disease determination model.

[0037] S61, obtaining a gray image, and extracting a leaf shape image of the blueberry leaf to be detected from the gray image according to a background gray value; The gray image obtained in the obtaining step S3 is separated to obtain the leaf shape image quickly and accurately through the background plate, because the background plate has a single color, good consistency of various parameters, and a significant difference from the related parameters of the leaves during the shooting process; The leaf shape image is obtained by first extracting all pixel points with the same background gray value and then subtracting the pixel points; S62, calculating a total number Q of pixel points of the blueberry leaf to be detected according to the leaf shape image; S63, taking the total number of elements of the disease area coordinate set S D as the number Q1 of diseased pixel points; S64, calculating a disease ratio according to the total number of pixel points and the number of diseased pixel points; The expression of the disease ratio is q = 100% Q1 / Q; S65, outputting a warning information according to the disease ratio and a disease determination function.

[0038] The expression of the disease determination function is wherein R represents the disease ratio, and k1, k2 and k3 are constants.

[0039] Embodiment 2

[0040] With reference to Figure 4 , the present embodiment discloses a warning system as another optional embodiment of the present application, which comprises a parameter setting module and a data acquisition module, the parameter setting module is used for setting a first standard determination parameter, a second standard determination parameter and a disease determination function; The data acquisition module is used for acquiring an infrared temperature image and a visible light image of a blueberry leaf to be detected; The output end of the data acquisition module is in communication connection with a first recognition module and a second recognition module, and the output ends of the first recognition module and the second recognition module are respectively connected with a screening calculation module, the screening calculation module obtains a disease area coordinate set through the received related parameters of the first recognition module and the second recognition module. The output end of the screening calculation module is further in communication connection with a warning information output module.

[0041] Correspondingly, the present application further discloses a warning device for blueberry diseases, which comprises a shell, an infrared camera and a visible light camera are integrally arranged on the shell; Meanwhile, the early warning device further comprises a background plate, a plurality of calibration points are marked on the background plate, preferably, the background plate is white or black, and the calibration points are red or other colors having obvious color difference with the background plate and leaves; Compared with the prior art, the early warning of the leaf spot disease is realized through the way of quantitative calculation and cross-validation, and the determination result is more accurate and objective compared with the subjective judgment way depending on the experience of workers. Secondly, the application no longer depends on the experience of workers, so that the determination threshold of the leaf spot disease is effectively reduced, the leaf spot disease can be found and treated in time in the early stage, the disease prevention and treatment effect of the blueberries is improved, and the yield of the blueberries is improved.

[0042] Finally, the automatic identification of the leaf spot disease is realized, and especially for large blueberry plantations, the early prevention and treatment effect of the leaf spot disease can be effectively improved.

[0043] The preferred embodiments of the application are described above, and the patent scope of the application is not limited in this way. Any equivalent structure or equivalent process transformation obtained by using the content of the specification and the drawings, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the application.

Claims

1. A method for early warning of diseases in blueberries, characterized in that, Includes the following steps: Define the first standard judgment parameter, the second standard judgment parameter, and the disease judgment function for blueberry disease early warning; Acquire infrared temperature and visible light images of the blueberry leaves to be tested; The infrared temperature image is converted into a grayscale image, and the coordinate set S of the temperature anomaly area is extracted from the grayscale image according to the first standard judgment parameter. T ; Based on the second standard judgment parameter, the coordinate set S of the color anomaly region is extracted from the visible light image. C ; According to the coordinate set S of the temperature anomaly zone T For the coordinate set S of the color anomaly region C Screening was performed to obtain the coordinate set S of the diseased area. D ; According to the coordinate set S of the diseased area D The disease determination model outputs early warning information.

2. The disease early warning method for blueberries according to claim 1, characterized in that, The first standard judgment parameter includes the standard judgment grayscale domain, and the second standard judgment parameter includes the standard judgment RGB domain.

3. The disease early warning method for blueberries according to claim 1, characterized in that, The infrared temperature image is converted into a grayscale image, and the coordinate set S of the temperature anomaly area is extracted from the grayscale image according to the first standard judgment parameter. T This includes the following steps: The infrared temperature image is converted into a grayscale image, and a first standard coordinate system is constructed for the grayscale image; The grayscale image is divided into several pixels, and the grayscale parameters (x) of each pixel are obtained respectively. i y i G i ); where x i y i This represents the first coordinate of a pixel, where i represents the pixel number, and G... i Indicates the actual grayscale value; Obtain the first reference coordinates (x, y) of each calibration point in the first coordinate system. ok y ok The number of standard points is no less than three, and k represents the number of the calibration point. Each of the grayscale parameters is compared with the first standard judgment parameter to screen out abnormal grayscale values. The first coordinates corresponding to each abnormal gray value are aggregated to generate the coordinate set S of the temperature anomaly zone. T .

4. The disease early warning method for blueberries according to claim 1, characterized in that, The coordinate set S of the color anomaly region is extracted from the visible light image according to the second standard judgment parameter. C This includes the following steps: The visible light image is converted into an RGB image, and a second standard coordinate system is constructed for the RGB image; The RGB image is divided into several pixels, and the RGB parameters (x, y, x) of each pixel are obtained. j y j r j g j b j ), where x i y i This represents the second coordinate of the pixel, j represents the pixel number, and r j g j b j These are the actual RGB values; Obtain the second reference coordinates (x') of each calibration point in the second coordinate system. ok y' ok The number of standard points mentioned above shall be no less than three. Each actual RGB value is compared with the second standard judgment parameter to screen out abnormal RGB values. The second coordinates corresponding to each abnormal RGB value are aggregated to generate a color anomaly region coordinate set S. C .

5. The disease early warning method for blueberries according to claim 1, characterized in that, The coordinate set S of the temperature anomaly zone T For the coordinate set S of the color anomaly region C Screening was performed to obtain the coordinate set S of the diseased area. D This includes the following steps: According to the first reference coordinate (x) ok y ok ) and the second reference coordinate (x' ok y' ok Perform coordinate registration to obtain the positional conversion relationship between the coordinate set of the temperature anomaly area and the coordinate set of the color anomaly area; Based on the aforementioned location conversion relationship, the coordinate set S of the temperature anomaly zone is... T Convert to temperature determination coordinate set S' T ; Based on the temperature determination coordinate set S' T For the coordinate set S of the color anomaly region C The first screening was performed to obtain the first lesion coordinate set S. D1 and the coordinate set S' of the lesion to be determined D The first lesion coordinate set S D1 The expression is The lesion coordinate set S' to be determined D The expression is ; To determine the coordinate set S' of the lesion D A second screening was performed to obtain the second lesion coordinate set S. D2 ; The first lesion coordinate set S D1 With the second lesion coordinate set S D2 The coordinates of the diseased area are merged into a set.

6. The method for early warning of diseases in blueberries according to claim 5, characterized in that, The step of performing coordinate registration based on the first reference coordinates and the second reference coordinates to obtain the positional conversion relationship between the coordinate set of the temperature anomaly area and the coordinate set of the color anomaly area includes the following steps: Standard expressions for constructing position conversion relationships; A one-to-one mapping is established between each of the first reference coordinates and each of the second reference coordinates, generating several fitting calculation groups {(x ok y ok ), (x' ok y' ok )}; Each fitted calculation group is imported into the standard expression, and the position conversion relationship is obtained through fitting calculation. The expression for the position conversion relationship is as follows: , where a, b, c, d, e, and f represent constants.

7. The method for early warning of diseases in blueberries according to claim 5, characterized in that, The lesion coordinate set S' to be determined D A second screening was performed to obtain the second lesion coordinate set S. D2 This includes the following steps: From the coordinate set S' of the lesion to be determined D Extract any coordinate of the lesion to be determined; Centered on the pixel corresponding to the lesion coordinates to be determined, the coordinates of all its neighboring pixels are collected to generate a set of neighboring pixel coordinates; wherein the calculation expression for the set of neighboring pixel coordinates is: ; Compare the set of adjacent pixel coordinates with the set of coordinates of the color anomaly region S C If there is an intersection, then the second screening is satisfied, and the coordinates of the lesion to be determined are collected into the second lesion coordinate set; Repeat the step of extracting any lesion coordinate from the lesion coordinate set S'D to generate a second lesion coordinate set S. D2 .

8. The method for early warning of diseases in blueberries according to claim 1, characterized in that, The coordinate set S of the diseased area D The disease assessment model outputs early warning information, including the following steps: Acquire a grayscale image, and extract the leaf shape of the blueberry leaf to be detected from the grayscale image based on the background grayscale value; The total number of pixels Q detected in the blueberry leaf is calculated based on the leaf shape diagram. Set the coordinates of the diseased area S D The total number of elements is taken as the number of diseased pixels, Q1; The lesion ratio is calculated based on the total number of pixels and the number of diseased pixels; Early warning information is output based on the lesion ratio and the disease determination function.

9. The disease early warning method for blueberries according to claim 8, characterized in that, The expression for the lesion ratio is q = 100%Q1 / Q, and the expression for the lesion determination function is... , where R represents the proportion of lesions, and k1, k2, and k3 are constants.

10. An early warning system based on the blueberry disease early warning method according to any one of claims 1-9, characterized in that, include: The parameter setting module is used to set the first standard judgment parameter, the second standard judgment parameter, and the disease judgment function for blueberry disease early warning. The data acquisition module is used to acquire infrared temperature images and visible light images of the blueberry leaves to be tested; The first identification module is used to convert the infrared temperature image into a grayscale image and extract the coordinate set of temperature anomaly areas from the grayscale image according to the first standard judgment parameters. The second identification module is used to extract the coordinate set of color anomaly areas from the visible light image according to the second standard judgment parameters; The sieving calculation module is used to sieve the coordinate set of the color anomaly area based on the coordinate set of the temperature anomaly area to obtain the coordinate set of the diseased area; The early warning information output module is used to output early warning information based on the disease area coordinate set and the disease determination model.

Images