Edible mushroom cultivation monitoring method and system based on machine vision

Abstract

The invention discloses an edible mushroom cultivation monitoring method and system based on machine vision, and relates to the technical field of machine vision detection. The method comprises the following steps: acquiring an image Pi and an environment parameter # imgabs0 # in an edible mushroom planting area to pre-process the acquired image, extracting an edible mushroom outline in the image, and acquiring growth information of edible mushrooms in the planting area, including edible mushroom quantity information ci, outline information lij and color information sij; classifying the identified edible mushrooms into a growth period, a mature period and a picking period according to the acquired contour information lij and color information sij, acquiring the proportion bci of the edible mushrooms in the mature period in the ith planting area, performing grey correlation analysis on the acquired proportion bci of the edible mushrooms in the mature period and the environmental parameter # imgabs1 #, calculating the correlation degree rm between the mth environmental parameter and the proportion of the edible mushrooms in the mature period, and calculating the correlation degree rm; and setting a threshold value bcbt of the mature-period edible fungus proportion, and optimizing the environmental parameters of the planting area with the mature-period edible fungus proportion smaller than the threshold value bcbt according to the obtained correlation degree rm.

Description

Technical Field

[0001] The present invention relates to the technical field of machine vision detection, and in particular to a machine vision-based edible fungus cultivation monitoring method and system. Background Art

[0002] With the development of science and technology, machine vision technology is being used more and more in agriculture. Compared with traditional human eye observation and measurement methods, machine vision technology based on image processing and analysis not only has a high degree of automation, but also has significant advantages such as fast speed, high precision, and large amount of information.

[0003] In the process of edible fungi cultivation, it is necessary not only to monitor the mushroom house environment, but also to observe and evaluate the growth of edible fungi. Some edible fungi with special environmental requirements, such as straw mushrooms, have a semi-closed growth environment. Managers need to actively enter the mushroom house to observe the growth of edible fungi. Manual observation is not only inefficient and inaccurate, but also unable to provide accurate quantitative indicators, and the effect of monitoring the growth status of edible fungi is poor. To this end, we propose an edible fungi cultivation monitoring method and system based on machine vision. Summary of the invention

[0004] The main purpose of the present invention is to provide a method and system for monitoring edible fungus cultivation based on machine vision, which can effectively solve the problems in the background technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] The edible fungus cultivation monitoring method based on machine vision includes:

[0007] Get the image P in the edible fungus planting area i And environmental parameters Among them, P i Represented as the image within the i-th planting area; It is represented as the mth environmental parameter in the i-th planting area; i=1,2,...n; m=1,2,...M; n is the total planting area; M is the type of environmental parameter, and the environmental parameter includes at least two of temperature, humidity, water, light, pH, oxygen, carbon dioxide content, and fertilizer application amount;

[0008] The acquired image is preprocessed to extract the outline of the edible fungi in the image and obtain the growth information of the edible fungi in the planting area, wherein the growth information includes the quantity information of the edible fungi c i , profile information ij , color information ij , c i It is represented by the number of edible fungi in the i-th planting area; l ijIt is represented as the perimeter value of the contour of the jth edible fungus in the i-th planting area; s ij It is represented as the pixel value of the jth edible fungus in the i-th planting area;

[0009] According to the obtained contour information l ij , color information ij Classify the identified edible fungi into growth period, maturity period, and picking period, and obtain the proportion of mature edible fungi in the i-th planting area bc i ,in, cc i It is expressed as the number of mature edible fungi in the i-th planting area;

[0010] The proportion of mature edible fungi obtained i and environmental parameters Grey correlation analysis was performed to calculate the correlation r between the mth environmental parameter and the proportion of mature edible fungi. m ;

[0011] Set the threshold value of the proportion of mature edible fungi bc bt , according to the obtained correlation r m , for mature edible fungi, the proportion is less than the threshold value bc bt Optimize the environmental parameters of the planting area.

[0012] The edible fungus classification process includes the following steps:

[0013] Set the pixel boundary threshold s of edible fungi during the growth period and maturity period bt ;

[0014] According to the set pixel boundary threshold s bt The growth cycle of the edible fungi to be classified is initially classified to screen out the edible fungi that are not in the growth stage. The classification principles for the initial classification are:

[0015] When the pixel value of the edible fungus to be classified is less than the pixel boundary threshold s bt When the pixel value of the edible fungus to be classified is greater than the pixel boundary threshold s bt When the classification result is not the growth period;

[0016] Get the minimum perimeter value l of the contour of the edible fungi to be classified that are not in the growth period min and the maximum value l max , respectively calculate the distance between the fth edible fungus to be classified and the one with the smallest contour perimeter The distance between the edible fungus with the largest contour perimeter The calculation formulas are:

[0017]

[0018] In the formula, l f 、s f are the contour perimeter value and pixel value of the fth edible fungus to be classified; α and β are weight coefficients, where α, β∈(0,1), α+β=1;

[0019] Calculate the maturity representation value C of the fth edible fungus to be classified f and maturity representation mean Among them, the maturity characterization value C f The calculation formula is: Maturity Characterization Mean The calculation formula is: F is the total amount of edible fungi to be classified that are not in the growth stage;

[0020] The mean value of maturity representation is obtained As the dividing threshold between the maturity period and the picking period, the edible fungi that are not in the growth period are secondary classified to screen out the edible fungi in the maturity period. The classification principles of the secondary classification are:

[0021] When the maturity representation value of the fth edible fungus to be classified When , the classification result is picking period;

[0022] When the maturity representation value of the fth edible fungus to be classified , the classification result is mature stage.

[0023] The relevance acquisition process includes the following steps:

[0024] To obtain the proportion of mature edible fungi in the same period bc i The data constructs the reference sequence E, with the corresponding environmental parameters Data construction comparison sequence F, where E = {bc i}; F = {F1, F2, ..., F m}, F m It is represented as the mth environmental parameter set;

[0025] The data points in the reference sequence E and the comparison sequence F are standardized using the formula: In the formula, e k is the kth data point in the reference sequence E; e' k is the normalized value of the kth data point in the reference sequence E; is the mean of all data points in the reference sequence E; f mk is the kth data point of the mth environmental parameter in the comparison sequence F; f' mk is the normalized value of the kth data point of the mth environmental parameter in the comparison sequence F; is the mean of all data points of the mth environmental parameter in the comparison sequence F;

[0026] Calculate the correlation coefficient r between all data points in the comparison sequence F and the reference sequence E mk , the calculation formula is:

[0027]

[0028] In the formula, ρ is a constant coefficient, generally ρ = 0.5; Δ min and Δ max They are the minimum difference between the two levels of data and the maximum difference between the two levels, and the calculation formulas are:

[0029] Δ min =min m (min k (|e' k -f' mk |));

[0030] Δ max =max m (max k (|e' k -f' mk |));

[0031] In the formula, min(min()) means first taking the minimum value of all factors in (), and then taking the minimum value of all minimum values; max(max()) means first taking the maximum value of all factors in (), and then taking the maximum value of all maximum values;

[0032] According to the obtained correlation coefficient, the grey correlation degree R between the mth environmental parameter and the proportion of mature edible fungi is calculated. m , the calculation formula is: K is the total amount of data.

[0033] The edible fungus cultivation monitoring system based on machine vision includes an image acquisition module, an environmental parameter acquisition module, an image preprocessing module, an edible fungus classification module, a data analysis module, and an environmental parameter control module;

[0034] The image acquisition module is used to acquire images within the edible fungus planting area;

[0035] The environmental parameter acquisition module is used to obtain environmental parameters in the edible fungus planting area;

[0036] The image preprocessing module is used to preprocess the acquired image, extract the outline of the edible fungus in the image, and obtain the growth information of the edible fungus in the planting area;

[0037] The edible fungus classification module is used to obtain the outline information l ij, color information ij Classify the identified edible fungi into growth period, maturity period, and picking period, and obtain the proportion of mature edible fungi in the i-th planting area bc i ;

[0038] The data analysis module is used to obtain the proportion of mature edible mushrooms bc i and environmental parameters Grey correlation analysis was performed to calculate the correlation r between the mth environmental parameter and the proportion of mature edible fungi. m ;

[0039] The environmental parameter control module is used to set the ratio threshold of mature edible fungi bc bt , and according to the obtained correlation r m , for mature edible fungi, the proportion is less than the threshold value bc bt Optimize environmental parameters of the planting area;

[0040] The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0041] The present invention has the following beneficial effects:

[0042] Compared with the existing technology, by obtaining the image P in the edible fungus planting area i And environmental parameters Preprocess the acquired image, extract the outline of the edible fungus in the image, and obtain the edible fungi in the planting area, including the number of edible fungi information c i , profile information ij , color information ij The growth information is obtained according to the contour information l ij , color information ij Classify the identified edible fungi into growth period, maturity period, and picking period, and obtain the proportion of mature edible fungi in the i-th planting area bc i , the proportion of mature edible fungi obtained bc i and environmental parameters Grey correlation analysis was performed to calculate the correlation r between the mth environmental parameter and the proportion of mature edible fungi. m , set the threshold value of the proportion of mature edible fungi bc bt , according to the obtained correlation r m , for mature edible fungi, the proportion is less than the threshold value bc bt By optimizing the environmental parameters of the planting area and using machine vision technology to monitor the growth status of edible fungi, the degree of informatization of the edible fungi production process can be improved, the labor intensity of managers can be reduced, and production efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a flow chart of the edible fungus cultivation monitoring method based on machine vision of the present invention;

[0044] Figure 2 The present invention is a structural block diagram of the edible fungus cultivation monitoring system based on machine vision. DETAILED DESCRIPTION

[0045] The present invention will be further described below in conjunction with specific implementation methods, wherein the accompanying drawings are only used for exemplary descriptions and represent only schematic diagrams rather than actual drawings, and should not be understood as limiting the present invention. In order to better illustrate the specific implementation methods of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0046] Example 1

[0047] The technical solution of the present invention can be used to guide the picking of planted edible fungi, and the specific implementation process includes the following steps:

[0048] Step 1: Obtain the image P of the mushroom planting area i , where P i It is represented as the image i=1,2,...n in the i-th planting area; n is the total number of planting areas;

[0049] Step 2: Preprocess the acquired image, extract the outline of the edible fungus in the image, and obtain the growth information of the edible fungus in the planting area, where the growth information includes the number of edible fungi information c i , profile information ij , color information ij , c i It is represented by the number of edible fungi in the i-th planting area; l ij It is represented as the perimeter value of the contour of the jth edible fungus in the i-th planting area; s ij It is represented as the pixel value of the jth edible fungus in the i-th planting area;

[0050] Step 3: Based on the obtained contour information l ij , color information ij Classify the identified edible fungi into growth period, maturity period, and picking period, and obtain the proportion of mature edible fungi in the i-th planting area bc i ,in, cc i It is represented by the number of mature edible fungi in the i-th planting area. The edible fungi classification process includes the following steps:

[0051] Set the pixel boundary threshold s of edible fungi during the growth period and maturity period bt ;

[0052] According to the set pixel boundary threshold s bt The growth cycle of the edible fungi to be classified is initially classified to screen out the edible fungi that are not in the growth stage. The classification principles for the initial classification are:

[0053] When the pixel value of the edible fungus to be classified is less than the pixel boundary threshold s bt When the pixel value of the edible fungus to be classified is greater than the pixel boundary threshold s bt When the classification result is not the growth period;

[0054] Get the minimum perimeter value l of the contour of the edible fungi to be classified that are not in the growth period min and the maximum value l max , respectively calculate the distance between the fth edible fungus to be classified and the one with the smallest contour perimeter The distance between the edible fungus with the largest contour perimeter The calculation formulas are:

[0055]

[0056] In the formula, l f 、s f are the contour perimeter value and pixel value of the fth edible fungus to be classified; α and β are weight coefficients, where α, β∈(0,1), α+β=1;

[0057] Calculate the maturity representation value C of the fth edible fungus to be classified f and maturity representation mean Among them, the maturity characterization value C f The calculation formula is: Maturity Characterization Mean The calculation formula is: F is the total amount of edible fungi to be classified that are not in the growth stage;

[0058] The mean value of maturity representation is obtained As the dividing threshold between the maturity period and the picking period, the edible fungi that are not in the growth period are secondary classified to screen out the edible fungi in the maturity period. The classification principles of the secondary classification are:

[0059] When the maturity representation value of the fth edible fungus to be classified When , the classification result is picking period;

[0060] When the maturity representation value of the fth edible fungus to be classified When , its classification result is mature stage;

[0061] Step 4: According to the above steps, the growth conditions of the edible fungi in the planting area can be obtained, so that the picking operation can be carried out in different areas according to the maturity rate monitoring results in different planting areas.

[0062] Example 2

[0063] The technical solution of the present invention can be used to monitor and control the growth environment of planted edible fungi, and the specific implementation process includes the following steps:

[0064] Step 1: Obtain the image P of the mushroom planting area i And environmental parameters Among them, P i Represented as the image within the i-th planting area; It is represented as the mth environmental parameter in the i-th planting area; i = 1, 2, ... n; m = 1, 2, ... M; n is the total planting area; M is the type of environmental parameter; environmental parameters include at least two of temperature, humidity, water, light, pH, oxygen, carbon dioxide content, and fertilizer application amount;

[0065] Step 2: Preprocess the acquired image, extract the outline of the edible fungus in the image, and obtain the growth information of the edible fungus in the planting area, where the growth information includes the number of edible fungi information c i , profile information ij , color information ij , c i It is represented by the number of edible fungi in the i-th planting area; l ij It is represented as the perimeter value of the contour of the jth edible fungus in the i-th planting area; s ij It is represented as the pixel value of the jth edible fungus in the i-th planting area;

[0066] Step 3: Based on the obtained contour information l ij , color information ij Classify the identified edible fungi into growth period, maturity period, and picking period, and obtain the proportion of mature edible fungi in the i-th planting area bc i ,in, cc i It is represented by the number of mature edible fungi in the i-th planting area. The specific process includes the following steps:

[0067] Step 31: Set the pixel boundary threshold s of edible fungi in the growth stage and mature stage bt ;

[0068] Step 32: According to the set pixel boundary threshold s bt The growth cycle of the edible fungi to be classified is initially classified to screen out the edible fungi that are not in the growth stage. The classification principles for the initial classification are:

[0069] Step 33: When the pixel value of the edible fungus to be classified is less than the pixel boundary threshold s btWhen the pixel value of the edible fungus to be classified is greater than the pixel boundary threshold s bt When the classification result is not the growth period;

[0070] Step 34: Obtain the minimum perimeter value l of the contour of the edible fungi to be classified that are not in the growth period min and the maximum value l max , respectively calculate the distance between the fth edible fungus to be classified and the one with the smallest contour perimeter The distance between the edible fungus with the largest contour perimeter The calculation formulas are:

[0071]

[0072] In the formula, l f 、s f are the contour perimeter value and pixel value of the fth edible fungus to be classified; α and β are weight coefficients, where α, β∈(0,1), α+β=1;

[0073] Step 35: Calculate the maturity representation value C of the fth edible fungus to be classified f and maturity representation mean Among them, the maturity characterization value C f The calculation formula is: Maturity Characterization Mean The calculation formula is: F is the total amount of edible fungi to be classified that are not in the growth stage;

[0074] Step 36: To obtain the mean value of maturity representation As the dividing threshold between the maturity period and the picking period, the edible fungi that are not in the growth period are secondary classified to screen out the edible fungi in the maturity period. The classification principles of the secondary classification are:

[0075] When the maturity representation value of the fth edible fungus to be classified When , the classification result is picking period;

[0076] When the maturity representation value of the fth edible fungus to be classified When the classification result is mature

[0077] Step 4: The proportion of mature edible fungi obtained i and environmental parameters Grey correlation analysis was performed to calculate the correlation r between the mth environmental parameter and the proportion of mature edible fungi. m The specific process includes the following steps:

[0078] Step 41: To obtain the proportion of mature edible fungi bc in the same period iThe data constructs the reference sequence E, with the corresponding environmental parameters Data construction comparison sequence F, where E = {bc i}; F = {F1, F2, ..., F m}, F m It is represented as the mth environmental parameter set;

[0079] Step 42: Standardize the data points in the reference sequence E and the comparison sequence F using the formula: In the formula, e k is the kth data point in the reference sequence E; e' k is the normalized value of the kth data point in the reference sequence E; is the mean of all data points in the reference sequence E; f mk is the kth data point of the mth environmental parameter in the comparison sequence F; f' mk is the normalized value of the kth data point of the mth environmental parameter in the comparison sequence F; is the mean of all data points of the mth environmental parameter in the comparison sequence F;

[0080] Step 43: Calculate the correlation coefficient r between all data points in the comparison sequence F and the reference sequence E mk , the calculation formula is:

[0081]

[0082] In the formula, ρ is a constant coefficient, generally ρ = 0.5; Δ min and Δ max They are the minimum difference between the two levels of data and the maximum difference between the two levels, and the calculation formulas are:

[0083] Δ min =min m (min k (|e' k -f' mk |));

[0084] Δ max =max m (max k (|e' k -f' mk |));

[0085] In the formula, min(min()) means first taking the minimum value of all factors in (), and then taking the minimum value of all minimum values; max(max()) means first taking the maximum value of all factors in (), and then taking the maximum value of all maximum values;

[0086] Step 44: Based on the obtained correlation coefficient, calculate the grey correlation degree R between the mth environmental parameter and the proportion of mature edible fungi m , the calculation formula is: K is the total amount of data;

[0087] Step 5: Set the threshold value of the proportion of mature edible fungi bc bt , according to the obtained correlation r m , for mature edible fungi, the proportion is less than the threshold value bc bt Optimize environmental parameters of the planting area;

[0088] In this embodiment, the environmental parameters include temperature, humidity, water, light, pH, oxygen, carbon dioxide content, and fertilizer application amount. m The order of influence on the threshold of the proportion of mature edible fungi can be calculated. The greater the correlation, the greater the influence. If the proportion of mature edible fungi in a certain planting area in the same period is less than the threshold bc bt When , it means that the growth status in the planting area is poor. The management personnel can adjust the environmental parameters in order of the degree of influence, so as to improve its growth status and increase the proportion of mature edible fungi in the planting area.

[0089] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for monitoring edible fungus cultivation based on machine vision, characterized in that: include: Get the image P in the edible fungus planting area i And environmental parameters Among them, P i Represented as the image within the i-th planting area; It is represented as the mth environmental parameter in the i-th planting area; i = 1, 2, ... n; m = 1, 2, ... M; n is the total number of planting areas; M is the type of environmental parameter; The acquired image is preprocessed to extract the outline of the edible fungi in the image and obtain the growth information of the edible fungi in the planting area, wherein the growth information includes the quantity information of the edible fungi c i , profile information ij , color information ij , c i It is represented by the number of edible fungi in the i-th planting area; l ij It is represented as the perimeter value of the contour of the jth edible fungus in the i-th planting area; s ij It is represented as the pixel value of the jth edible fungus in the i-th planting area; According to the obtained contour information l ij , color information ij Classify the identified edible fungi into growth period, maturity period, and picking period, and obtain the proportion of mature edible fungi in the i-th planting area bc i ,in, cc i It is expressed as the number of mature edible fungi in the i-th planting area; The proportion of mature edible fungi obtained i and environmental parameters Grey correlation analysis was performed to calculate the correlation r between the mth environmental parameter and the proportion of mature edible fungi. m ; Set the threshold value of the proportion of mature edible fungi bc bt , according to the obtained correlation r m , for mature edible fungi, the proportion is less than the threshold value bc bt Optimize the environmental parameters of the planting area.

2. The method for monitoring edible fungus cultivation based on machine vision according to claim 1, characterized in that: The edible fungus classification process includes the following steps: Set the pixel boundary threshold s of edible fungi during the growth period and maturity period bt ; According to the set pixel boundary threshold s bt Performing a preliminary classification of the growth cycle of the edible fungi to be classified, and screening out the edible fungi that are not in the growth stage; Get the minimum perimeter value l of the contour of the edible fungi to be classified that are not in the growth period min and the maximum value l max , respectively calculate the distance between the fth edible fungus to be classified and the one with the smallest contour perimeter The distance between the edible fungus with the largest contour perimeter The calculation formulas are: In the formula, l f 、s f are the contour perimeter value and pixel value of the fth edible fungus to be classified; α and β are weight coefficients, where α, β∈(0,1), α+β=1; Calculate the maturity representation value C of the fth edible fungus to be classified f and maturity representation mean Among them, the maturity characterization value C f The calculation formula is: Maturity Characterization Mean The calculation formula is: F is the total amount of edible fungi to be classified that are not in the growth stage; The mean value of maturity representation is obtained The threshold value between maturity and picking period is used as the dividing line for secondary classification of edible fungi that are not in the growth period, and edible fungi in the maturity period are screened out.

3. The method for monitoring edible fungus cultivation based on machine vision according to claim 1, characterized in that: The relevance acquisition process includes the following steps: To obtain the proportion of mature edible fungi in the same period bc i The data constructs the reference sequence E, with the corresponding environmental parameters Data construction comparison sequence F, where E = {bc i }; F = {F1, F2, ..., F m }, F m It is represented as the mth environmental parameter set; The data points in the reference sequence E and the comparison sequence F are standardized using the formula: In the formula, e k is the kth data point in the reference sequence E; e' k is the normalized value of the kth data point in the reference sequence E; is the mean of all data points in the reference sequence E; f mk is the kth data point of the mth environmental parameter in the comparison sequence F; f' mk is the normalized value of the kth data point of the mth environmental parameter in the comparison sequence F; is the mean of all data points of the mth environmental parameter in the comparison sequence F; Calculate the correlation coefficient r between all data points in the comparison sequence F and the reference sequence E mk , the calculation formula is: In the formula, ρ is a constant coefficient, generally ρ = 0.5; Δ min and Δ max They are the minimum difference between the two levels of data and the maximum difference between the two levels, and the calculation formulas are: D min =min m (min) k (|e' k -f' mk |)); D max =max m (max. k (|e' k -f' mk |)); In the formula, min(min()) means first taking the minimum value of all factors in (), and then taking the minimum value of all minimum values; max(max()) means first taking the maximum value of all factors in (), and then taking the maximum value of all maximum values; According to the obtained correlation coefficient, the grey correlation degree R between the mth environmental parameter and the proportion of mature edible fungi is calculated. m , the calculation formula is: K is the total amount of data.

4. The method for monitoring edible fungus cultivation based on machine vision according to claim 1, characterized in that: The environmental parameters include at least two of temperature, humidity, water content, light, pH, oxygen, carbon dioxide content, and fertilizer application amount.

5. The method for monitoring edible fungus cultivation based on machine vision according to claim 2, characterized in that: The classification principles for the initial classification are: When the pixel value of the edible fungus to be classified is less than the pixel boundary threshold s bt When the pixel value of the edible fungus to be classified is greater than the pixel boundary threshold s bt , its classification result is not the growth period.

6. The method for monitoring edible fungus cultivation based on machine vision according to claim 2, characterized in that: The classification principles of secondary classification are: When the maturity representation value of the fth edible fungus to be classified When , the classification result is picking period; When the maturity representation value of the fth edible fungus to be classified , the classification result is mature stage.

7. The edible fungus cultivation monitoring system based on machine vision is characterized by: It includes an image acquisition module, an environmental parameter acquisition module, an image preprocessing module, an edible fungus classification module, a data analysis module, and an environmental parameter control module; The image acquisition module is used to acquire the image P in the edible fungus planting area. i , where P i It is represented as the image in the i-th planting area; i = 1, 2, ... n; n is the total number of planting areas; The environmental parameter acquisition module is used to acquire the environmental parameters in the edible fungus planting area. in, It is represented as the mth environmental parameter in the i-th planting area; m = 1, 2, ... M, where M is the type of environmental parameter; The image preprocessing module is used to preprocess the acquired image, extract the outline of the edible fungus in the image, and obtain the growth information of the edible fungus in the planting area, wherein the growth information includes the number information of the edible fungus c i , profile information ij , color information ij , c i It is represented by the number of edible fungi in the i-th planting area; l ij It is represented as the perimeter value of the contour of the jth edible fungus in the i-th planting area; s ij It is represented as the pixel value of the jth edible fungus in the i-th planting area; The edible fungus classification module is used to obtain the outline information l ij , color information ij Classify the identified edible fungi into growth period, maturity period, and picking period, and obtain the proportion of mature edible fungi in the i-th planting area bc i ,in, cc i It is represented by the number of mature edible fungi in the i-th planting area; wherein the edible fungi classification process includes the following steps: Set the pixel boundary threshold s of edible fungi during the growth period and maturity period bt ; According to the set pixel boundary threshold s bt The growth cycle of the edible fungi to be classified is initially classified to screen out the edible fungi that are not in the growth stage. The classification principles for the initial classification are: When the pixel value of the edible fungus to be classified is less than the pixel boundary threshold s bt When the pixel value of the edible fungus to be classified is greater than the pixel boundary threshold s bt When the classification result is not the growth period; Get the minimum perimeter value l of the contour of the edible fungi to be classified that are not in the growth period min and the maximum value l max , respectively calculate the distance between the fth edible fungus to be classified and the one with the smallest contour perimeter The distance between the edible fungus with the largest contour perimeter The calculation formulas are: In the formula, l f 、s f are the contour perimeter value and pixel value of the fth edible fungus to be classified; α and β are weight coefficients, where α, β∈(0,1), α+β=1; Calculate the maturity representation value C of the fth edible fungus to be classified f and maturity representation mean Among them, the maturity characterization value C f The calculation formula is: Maturity Characterization Mean The calculation formula is: F is the total amount of edible fungi to be classified that are not in the growth stage; The mean value of maturity representation is obtained As the dividing threshold between the maturity period and the picking period, the edible fungi that are not in the growth period are secondary classified to screen out the edible fungi in the maturity period. The classification principles of the secondary classification are: When the maturity representation value of the fth edible fungus to be classified When , the classification result is picking period; When the maturity representation value of the fth edible fungus to be classified When , its classification result is mature stage; The data analysis module is used to obtain the proportion of mature edible mushrooms bc i and environmental parameters Grey correlation analysis was performed to calculate the correlation r between the mth environmental parameter and the proportion of mature edible fungi. m ; The association degree acquisition process includes the following steps: To obtain the proportion of mature edible fungi in the same period bc i The data constructs the reference sequence E, with the corresponding environmental parameters Data construction comparison sequence F, where E = {bc i }; F = {F1, F2, ..., F m }, F m It is represented as the mth environmental parameter set; The data points in the reference sequence E and the comparison sequence F are standardized using the formula: In the formula, e k is the kth data point in the reference sequence E; e' k is the normalized value of the kth data point in the reference sequence E; is the mean of all data points in the reference sequence E; f mk is the kth data point of the mth environmental parameter in the comparison sequence F; f' mk is the normalized value of the kth data point of the mth environmental parameter in the comparison sequence F; is the mean of all data points of the mth environmental parameter in the comparison sequence F; Calculate the correlation coefficient r between all data points in the comparison sequence F and the reference sequence E mk , the calculation formula is: In the formula, ρ is a constant coefficient, generally ρ = 0.5; Δ min and Δ max They are the minimum difference between the two levels of data and the maximum difference between the two levels, and the calculation formulas are: D min =min m (min) k (|e' k -f' mk |)); D max =max m (max. k (|e' k -f' mk |)); In the formula, min(min()) means first taking the minimum value of all factors in (), and then taking the minimum value of all minimum values; max(max()) means first taking the maximum value of all factors in (), and then taking the maximum value of all maximum values; According to the obtained correlation coefficient, the grey correlation degree R between the mth environmental parameter and the proportion of mature edible fungi is calculated. m , the calculation formula is: K is the total amount of data; The environmental parameter control module is used to set the ratio threshold of mature edible fungi bc bt , and according to the obtained correlation r m , for mature edible fungi, the proportion is less than the threshold value bc bt Optimize the environmental parameters of the planting area.

8. The machine vision-based edible fungus cultivation monitoring system according to claim 7, characterized in that: The system comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the steps of the method according to any one of claims 1 to 6 are implemented when the processor executes the program.

Images