Edible mushroom cultivation remote monitoring management system

Abstract

The invention discloses a remote monitoring management system for edible mushroom cultivation, and belongs to the technical field of cultivation supervision. A first monitoring image processing set and a second monitoring image processing set which are obtained through processing of different dimensions are subjected to local digital processing calculation and overall digital processing calculation, so that form identification marks and shape identification marks, corresponding to different local parts, of different divided areas and overall local cultivation integration validity are obtained; according to the method, processing analysis is carried out on edible mushroom cultivation states corresponding to different individual monitoring areas and data processing analysis is carried out on abnormal coverage states, and targeted alarm prompts of different abnormal types are carried out on the different individual monitoring areas according to analysis results; the method is used for solving the technical problems that in the prior art, processing analysis and expansion mining in different aspects cannot be carried out on edible mushroom cultivation remote monitoring data, so that the multi-dimensional recognition analysis effect of edible mushroom cultivation remote monitoring management is poor, and the autonomous alarm prompting effect is poor.

Description

Technical Field

[0001] The invention relates to the technical field of cultivation supervision, and in particular to a remote monitoring and management system for edible fungus cultivation. Background Art

[0002] Remote supervision of edible fungus cultivation refers to a management method that uses modern information technology, such as the Internet of Things (IoT), sensor technology, wireless communication technology, cloud computing, and big data analysis, to monitor and control the cultivation environment of edible fungi in real time. This method allows managers to remotely access the monitoring system through the Internet even if they are not on site, view various parameters of the edible fungus growth environment, such as temperature, humidity, carbon dioxide concentration, light intensity, etc., and adjust environmental conditions based on these data to optimize the growth of edible fungi.

[0003] The existing remote monitoring and management scheme of edible fungus cultivation based on image recognition has certain defects in implementation. For example, the invention patent with application number CN2023110112318 and name of edible fungus cultivation monitoring method and system based on intelligent decision-making discloses processing, identification and analysis based on monitoring images. However, it only stays on a single aspect of image recognition and processing analysis. It cannot perform different aspects of processing, analysis and expansion mining on the remote monitoring data of edible fungus cultivation for abnormal cultivation states and abnormal cultivation types appearing in different locations, resulting in poor multi-dimensional recognition and analysis effect of remote monitoring and management of edible fungus cultivation and poor autonomous alarm prompt effect. Summary of the invention

[0004] The purpose of the present invention is to provide a remote monitoring and management system for edible fungus cultivation, which is used to solve the technical problems that the existing solutions cannot perform different aspects of processing and analysis and expansion mining on the remote monitoring data of edible fungus cultivation, resulting in poor multi-dimensional recognition and analysis effects of remote monitoring and management of edible fungus cultivation and poor autonomous alarm prompt effects.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A remote monitoring and management system for edible fungus cultivation, comprising:

[0007] The cultivation area monitoring identification processing module is used to periodically obtain monitoring images corresponding to edible fungi cultivated in different divided areas, divide and process them, and obtain a first monitoring image processing set and a second monitoring image processing set with different monitoring angle processing combinations;

[0008] The cultivation area monitoring multidimensional analysis module is used to perform local digital processing calculations and overall digital processing calculations on the first monitoring image processing set and the second monitoring image processing set obtained by different dimensional processing, and obtain different local morphological recognition marks and shape recognition marks corresponding to different divided areas, as well as the overall local cultivation integration validity;

[0009] The cultivation area analysis exception management module is used to perform data processing and analysis on the health status of edible fungus cultivation for all digitally processed data in different divided areas, dynamically mark different divided areas according to the analysis results, and implement targeted abnormal alarm prompts.

[0010] Preferably, according to a preset monitoring cycle, first monitoring images and second monitoring images corresponding to edible fungi cultivated in different divided areas are acquired in sequence;

[0011] According to a preset first division ratio and a second division ratio, different first monitoring images and different second monitoring images are respectively divided to obtain a plurality of first division images corresponding to different first monitoring images and a plurality of second division images corresponding to different second monitoring images;

[0012] All first segmented images belonging to the same first monitoring image are sorted and combined to obtain a first monitoring image processing set; all second segmented images belonging to the same second monitoring image are sorted and combined to obtain a second monitoring image processing set.

[0013] Preferably, a plurality of first segmented images in the first monitoring image processing set and a plurality of second segmented images in the second monitoring image processing set are numbered and marked respectively, and morphological parameters corresponding to different first segmented images and shape parameters corresponding to the second segmented images are obtained;

[0014] When the morphological parameters corresponding to different first divided images and the shape parameters corresponding to the second divided images are digitally processed, the morphological parameters corresponding to the different first divided images are subjected to data analysis through a morphological health recognition function to obtain a corresponding morphological recognition identifier XTB; the morphological parameters include a first morphological value and a second morphological value.

[0015] Preferably, the expression of the morphological health identification function is: Wherein, xt1 and xt2 are the first morphological value and the second morphological value in the morphological parameters respectively; U1 and U2 are the first morphological standard range corresponding to the first morphological value and the second morphological standard range corresponding to the second morphological value respectively;

[0016] The pattern identifier contains a value of 0, 1, or 2.

[0017] Preferably, the shape parameters corresponding to the different second segmented images are subjected to data analysis through a shape health recognition function to obtain a corresponding shape recognition mark XZB; the shape parameters include a first shape value and a second shape value;

[0018] Among them, the expression of shape health identification function is: Wherein, xz1 and xz2 are the first shape value and the second shape value in the shape parameter respectively; U3 and U4 are the first shape standard range corresponding to the first shape value and the second shape standard range corresponding to the second shape value respectively;

[0019] The shape identifier contains a value of 0, -1, or -2.

[0020] Preferably, by the formula Calculate and obtain the first local cultivation validity JX1 corresponding to the first monitoring image; where α is the first calculation influence coefficient, and the value range is (1, 2); n1 and n2 are the total number of morphological identification marks with a value of 1 and the total number of morphological identification marks with a value of 2, respectively; N is the total number of all first divided images contained in the first monitoring image; A is the first local cultivation standard value;

[0021] By formula Calculate and obtain the second local cultivation validity JX2 corresponding to the second monitoring image; where β is the second calculation influence coefficient, and the value range is (1, 2); n3 and n4 are the total number of shape recognition identifiers with a value of 1 and the total number of shape recognition identifiers with a value of 2, respectively; B is the second local cultivation standard value;

[0022] By formula Calculate and obtain the local cultivation integration validity ZX corresponding to different divided areas; where C is the local cultivation integration standard value.

[0023] Preferably, the first local cultivation validity, the second local cultivation validity and the local cultivation integration validity obtained by remote monitoring processing corresponding to different divided areas are processed and analyzed respectively to determine the edible fungus cultivation health status corresponding to different divided areas;

[0024] The first local cultivation validity, the second local cultivation validity and the local cultivation integration validity of the different divided areas are sequentially analyzed through the cultivation health identification function, and the cultivation health value ZJ corresponding to the different divided areas is output; the cultivation health value includes the value of 0, a or b.

[0025] Preferably, the expression of the cultivation health identification function is: In the formula, a and b are constants greater than 0;

[0026] According to the cultivation health value with a value of a, the corresponding divided area is marked as a slightly abnormal cultivation area, and according to the cultivation health value with a value of b, the corresponding divided area is marked as a severely abnormal cultivation area.

[0027] Preferably, the total number of mild abnormalities N1 in the mildly abnormal cultivation area and the total number of severe abnormalities N2 in the severe abnormal cultivation area are counted respectively, and the total number of severe abnormalities N2 in the severe abnormal cultivation area is calculated by the formula Calculate and obtain the abnormal coverage value YF corresponding to the cultivation of all divided areas; where NZ is the total number of all divided areas; D is the abnormal coverage standard value.

[0028] Preferably, if the abnormal coverage value is less than or equal to 0, a local abnormality alarm prompt is implemented for all cultivation areas with slight abnormality or cultivation areas with severe abnormality;

[0029] If the abnormal coverage value is greater than 0, an overall abnormal alarm will be issued for all cultivation areas with slight abnormalities or cultivation areas with severe abnormalities.

[0030] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0031] The present invention performs local digital processing calculations and overall digital processing calculations on the first monitoring image processing set and the second monitoring image processing set obtained by processing different dimensions, thereby obtaining morphological recognition identifiers and shape recognition identifiers corresponding to different local areas in different divided areas, as well as the overall local cultivation integration validity, thereby realizing the expansion and mining analysis of the division of the previous monitoring images, and digitally representing the cultivation effects in different aspects, and at the same time providing reliable multi-dimensional local cultivation effect supervision data support for the subsequent edible fungus cultivation health status processing and analysis in different divided areas.

[0032] The present invention processes and analyzes the edible fungus cultivation status corresponding to different individual monitoring areas, and performs data processing and analysis on the overall abnormal coverage status of the analysis results corresponding to the individual monitoring areas. According to the analysis results, targeted alarm prompts of different abnormal types are implemented for different individual monitoring areas, thereby improving the reliability and diversity of remote monitoring analysis and alarm prompts in different edible fungus cultivation areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 The present invention is a module block diagram of a remote monitoring and management system for edible fungus cultivation.

[0034] Figure 2 The present invention is a flowchart of the implementation steps of a remote monitoring and management system for edible fungus cultivation. DETAILED DESCRIPTION

[0035] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings and specific embodiments.

[0036] like Figure 1 , Figure 2 As shown, the present invention is a remote monitoring and management system for edible fungus cultivation, comprising a cultivation area monitoring identification processing module, a cultivation area monitoring multidimensional analysis module and a cultivation area analysis abnormality management module;

[0037] The cultivation area monitoring identification processing module is used to periodically obtain monitoring images corresponding to edible fungi cultivated in different divided areas, divide and process them, and obtain a first monitoring image processing set and a second monitoring image processing set with different monitoring angle processing combinations; it includes:

[0038] According to the preset monitoring cycle, the unit of the monitoring cycle is minutes, that is, the monitoring image processing and analysis is performed every few minutes, and the specific interval time is not limited, and the first monitoring image and the second monitoring image corresponding to the edible fungi cultivated in different divided areas are obtained in turn; the first monitoring image is used to photograph the cultivated edible fungi from directly above; the second monitoring image is used to photograph the cultivated edible fungi from the side, and the side in the embodiment of the present invention can be a single left side or a right side, and multiple sides can be added according to the actual application requirements of the actual application scenario; the camera can be realized by the existing monitoring equipment, and the specific type of edible fungi can be determined according to the application requirements of the actual application scenario;

[0039] Different first surveillance images and different second surveillance images are divided according to a preset first division ratio and a second division ratio, respectively. Specifically, the first division ratio and the second division ratio can be divided equally according to specific sizes of the first surveillance image and the second surveillance image. There is no limitation here. The purpose of dividing the first surveillance image and the second image is to enable more comprehensive and detailed recognition and processing of the first surveillance image and the second surveillance image to be performed later, so as to obtain a plurality of first division images corresponding to different first surveillance images and a plurality of second division images corresponding to different second surveillance images;

[0040] All first segmented images belonging to the same first monitoring image are sorted and combined to obtain a first monitoring image processing set; all second segmented images belonging to the same second monitoring image are sorted and combined to obtain a second monitoring image processing set;

[0041] In the embodiment of the present invention, by periodically acquiring monitoring images corresponding to edible fungi cultivated in different divided areas and dividing and processing them, modular processing of images from different monitoring angles is achieved, so as to provide reliable data support for subsequent identification data processing and analysis in different aspects.

[0042] The cultivation area monitoring multidimensional analysis module is used to perform local digital processing calculations and overall digital processing calculations on the first monitoring image processing set and the second monitoring image processing set obtained by different dimensional processing, and obtain different local morphological recognition marks and shape recognition marks corresponding to different divided areas, as well as the overall local cultivation integration validity; including:

[0043] Respectively numbering a plurality of first segmented images in the first monitoring image processing set and a plurality of second segmented images in the second monitoring image processing set, and obtaining morphological parameters corresponding to different first segmented images and shape parameters corresponding to the second segmented images;

[0044] The morphological parameters include a first morphological value and a second morphological value, which may be the smoothness and roughness of the surface of the edible fungus, and are determined by the median values ​​corresponding to all single smoothness values ​​and the median values ​​corresponding to all single roughness values ​​obtained by processing the surfaces of all edible fungi in the first segmented image;

[0045] The shape parameter includes a first shape value and a second shape value, which may be specifically the height and width of the side of the edible fungus, and is determined by the median corresponding to all single heights and the median corresponding to all single widths obtained by processing the side of all edible fungi in the second segmented image;

[0046] In addition, the single smoothness and single roughness obtained by the surface treatment of the edible fungus, as well as the single height and single width obtained by the side treatment of the edible fungus, are all realized through the existing image recognition processing scheme, and the specific implementation steps are not repeated here;

[0047] When the morphological parameters corresponding to the different first segmented images and the shape parameters corresponding to the second segmented images are digitally processed, the morphological parameters corresponding to the different first segmented images are subjected to data analysis through a morphological health recognition function to obtain a corresponding morphological recognition identifier XTB;

[0048] Among them, the expression of the morphological health identification function is: In the formula, xt1 and xt2 are the first morphological value and the second morphological value in the morphological parameters respectively; U1 and U2 are the first morphological standard range corresponding to the first morphological value and the second morphological standard range corresponding to the second morphological value respectively, which are determined according to the historical cultivation data and cultivation test data corresponding to the current cultivation stage of the edible fungus;

[0049] The morphological identification flag contains a value of 0, 1, or 2;

[0050] It should be noted that the morphological recognition identifier is used to process and calculate the surface monitoring data of the edible fungus cultivation in the monitoring image to digitally represent the morphological health status corresponding to all the cultivated edible fungi in the monitoring image;

[0051] The morphological identification mark with a value of 0 indicates that the morphology of the cultivated edible fungi monitored in the first segmented image is healthy;

[0052] The morphological identification mark with a value of 1 indicates that the morphological part of the cultivated edible fungi monitoring corresponding to the first segmented image is abnormal;

[0053] The morphological identification mark with a value of 2 indicates that the morphological changes of the cultivated edible fungi monitored in the corresponding second segmented image are all abnormal;

[0054] And, performing data analysis on shape parameters corresponding to different second segmented images through a shape health recognition function to obtain a corresponding shape recognition mark XZB;

[0055] Among them, the expression of shape health identification function is: In the formula, xz1 and xz2 are the first shape value and the second shape value in the shape parameter respectively; U3 and U4 are the first shape standard range corresponding to the first shape value and the second shape standard range corresponding to the second shape value respectively, which can also be determined according to the historical cultivation data and cultivation test data corresponding to the current cultivation stage of the edible fungus;

[0056] The shape identification flag contains a value of 0, -1, or -2;

[0057] It should be noted that the shape recognition identifier is used to process and calculate the side monitoring data of the edible fungus cultivation in the monitoring image to digitally represent the shape health status corresponding to all the cultivated edible fungi in the monitoring image;

[0058] The shape recognition identifier with a value of 0 indicates that the shapes of the cultivated edible fungi monitored in the second segmented image are all healthy;

[0059] The shape recognition flag with a value of -1 indicates that the shape part of the cultivated edible fungus monitoring corresponding to the second segmented image is abnormal;

[0060] The shape recognition identifier with a value of -2 indicates that the shapes of the cultivated edible fungi monitored in the second segmented image are all abnormal;

[0061] Obtain the morphological identification marks of all first segmented images and the shape identification marks of all second segmented images corresponding to the first monitoring image, and use the formula Calculate and obtain the first local cultivation validity JX1 corresponding to the first monitoring image; where α is the first calculation influence coefficient, and the value range is (1, 2), which can be 1.74; n1 and n2 are the total number of morphological identification marks with a value of 1 and the total number of morphological identification marks with a value of 2, respectively; N is the total number of all first divided images contained in the first monitoring image; A is the first local cultivation standard value, which can be determined according to the design requirement data corresponding to the edible fungus cultivation, or according to the previous cultivation test data;

[0062] The first local cultivation validity is used to integrate and calculate all the morphological identification marks obtained in the previous processing to digitally represent the local surface cultivation effect corresponding to the first monitoring image;

[0063] By formula The second local cultivation validity JX2 corresponding to the second monitoring image is calculated; wherein, β is the second calculation influence coefficient, and the value range is (1, 2), and the value can be 1.51; n3 and n4 are the total number of shape recognition identifiers with a value of 1 and a value of 2, respectively; B is the second local cultivation standard value, which can be determined according to the design requirement data corresponding to the edible fungus cultivation, or according to the previous cultivation test data;

[0064] The second local cultivation validity is used to integrate and calculate all shape recognition marks obtained in the previous processing to digitally represent the local side cultivation effect corresponding to the first monitoring image;

[0065] And, through the formula Calculate and obtain the local cultivation integration validity ZX corresponding to different divided areas; where C is the local cultivation integration standard value, which can be determined based on the design requirement data corresponding to edible fungus cultivation, or based on the previous cultivation test data;

[0066] The local cultivation integration validity is used to integrate and calculate all the morphological identification marks and shape identification marks obtained in the previous processing to digitally represent the local side cultivation effect corresponding to the divided area;

[0067] In the embodiment of the present invention, by performing local digital processing calculations and overall digital processing calculations on the first monitoring image processing set and the second monitoring image processing set obtained by processing different dimensions, morphological recognition identifiers and shape recognition identifiers corresponding to different local areas and the overall local cultivation integration validity are obtained, thereby expanding and mining the division of the previous monitoring images, and digitally representing the cultivation effects in different aspects. At the same time, reliable multi-dimensional local cultivation effect supervision data support can be provided for the subsequent processing and analysis of the health status of edible fungus cultivation in different divided areas.

[0068] The cultivation area analysis abnormal management module is used to process and analyze all the data digitally processed in different divided areas according to the health status of edible fungi cultivation, dynamically mark different divided areas according to the analysis results, and implement targeted abnormal alarm prompts; including:

[0069] The first local cultivation validity, the second local cultivation validity and the local cultivation integration validity obtained by remote monitoring processing corresponding to different divided areas are processed and analyzed respectively to determine the health status of edible fungus cultivation corresponding to different divided areas;

[0070] The first local cultivation validity, the second local cultivation validity and the local cultivation integration validity of the different divided areas are sequentially analyzed through the cultivation health identification function, and the cultivation health value ZJ corresponding to the different divided areas is output;

[0071] Among them, the expression of the cultivation health identification function is: In the formula, a and b are constants greater than 0;

[0072] The cultivation health value contains the value of 0, a or b;

[0073] A cultivation health value of 0 indicates that the cultivation of edible fungi in the corresponding divided area is healthy;

[0074] According to the cultivation health value with a value of a, the corresponding divided area is marked as a slightly abnormal cultivation area, and according to the cultivation health value with a value of b, the corresponding divided area is marked as a severely abnormal cultivation area;

[0075] In an embodiment of the present invention, by further expanding and calculating the local cultivation effect supervision data of different dimensions in the early stage, the cultivation health values ​​corresponding to different divided areas are obtained, and the different divided areas are dynamically marked by performing data analysis on the cultivation health values, which can provide reliable divided area marking data support for subsequent diversified alarm prompt analysis.

[0076] The total number of mild anomalies N1 in the mildly abnormal cultivation area and the total number of severe anomalies N2 in the severe abnormal cultivation area are counted respectively, and the formula is used to calculate the total number of mild anomalies N1 in the mildly abnormal cultivation area and the total number of severe anomalies N2 in the severe abnormal cultivation area. Calculate and obtain the abnormal coverage value YF corresponding to the cultivation of all divided areas; where NZ is the total number of all divided areas; D is the abnormal coverage standard value, which can be determined based on the design requirement data corresponding to the edible fungus cultivation, or based on the previous cultivation test data;

[0077] If the abnormal coverage value is less than or equal to 0, a local abnormal alarm prompt will be implemented for all cultivation areas with slight abnormalities or cultivation areas with severe abnormalities;

[0078] If the abnormal coverage value is greater than 0, an overall abnormal alarm will be issued for all cultivation areas with slight abnormalities or cultivation areas with severe abnormalities;

[0079] Different from the prior art solution in which the analysis results of the edible fungus cultivation status corresponding to different monitoring areas are directly used to issue alarm prompts, in the embodiment of the present invention, the edible fungus cultivation status corresponding to different individual monitoring areas is processed and analyzed, and the analysis results corresponding to the individual monitoring areas are subjected to data processing and analysis of the overall abnormal coverage status. According to the analysis results, targeted alarm prompts of different abnormal types are implemented for different individual monitoring areas, thereby improving the reliability and diversity of remote monitoring analysis and alarm prompts in different edible fungus cultivation areas.

[0080] In addition, the formulas involved in the above are all dimensionless and numerical calculations. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and simulating it with simulation software.

[0081] In the several embodiments provided by the present invention, it should be understood that the disclosed system can be implemented in other ways. For example, the above-described embodiments of the invention are only illustrative, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0082] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0083] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, and these modifications and equivalent replacements are within the protection scope of the present invention.

Claims

1. A remote monitoring and management system for edible fungus cultivation, characterized in that: include: The cultivation area monitoring identification processing module is used to periodically obtain monitoring images corresponding to edible fungi cultivated in different divided areas, divide and process them, and obtain a first monitoring image processing set and a second monitoring image processing set with different monitoring angle processing combinations; The cultivation area monitoring multidimensional analysis module is used to perform local digital processing calculations and overall digital processing calculations on the first monitoring image processing set and the second monitoring image processing set obtained by different dimensional processing, and obtain different local morphological recognition marks and shape recognition marks corresponding to different divided areas, as well as the overall local cultivation integration validity; The cultivation area analysis exception management module is used to perform data processing and analysis on the health status of edible fungus cultivation for all digitally processed data in different divided areas, dynamically mark different divided areas according to the analysis results, and implement targeted abnormal alarm prompts.

2. The remote monitoring and management system for edible fungus cultivation according to claim 1, characterized in that: According to a preset monitoring cycle, first monitoring images and second monitoring images corresponding to edible fungi cultivated in different divided areas are sequentially acquired; According to a preset first division ratio and a second division ratio, different first monitoring images and different second monitoring images are respectively divided to obtain a plurality of first division images corresponding to different first monitoring images and a plurality of second division images corresponding to different second monitoring images; All first segmented images belonging to the same first monitoring image are sorted and combined to obtain a first monitoring image processing set; all second segmented images belonging to the same second monitoring image are sorted and combined to obtain a second monitoring image processing set.

3. The remote monitoring and management system for edible fungus cultivation according to claim 2, characterized in that: Respectively numbering a plurality of first segmented images in the first monitoring image processing set and a plurality of second segmented images in the second monitoring image processing set, and obtaining morphological parameters corresponding to different first segmented images and shape parameters corresponding to the second segmented images; When the morphological parameters corresponding to different first divided images and the shape parameters corresponding to the second divided images are digitally processed, the morphological parameters corresponding to the different first divided images are subjected to data analysis through a morphological health recognition function to obtain a corresponding morphological recognition identifier XTB; the morphological parameters include a first morphological value and a second morphological value.

4. The remote monitoring and management system for edible fungus cultivation according to claim 3, characterized in that: The expression of the morphological health identification function is: Wherein, xt1 and xt2 are the first morphological value and the second morphological value in the morphological parameters respectively; U1 and U2 are the first morphological standard range corresponding to the first morphological value and the second morphological standard range corresponding to the second morphological value respectively; The pattern identifier contains a value of 0, 1, or 2.

5. The remote monitoring and management system for edible fungus cultivation according to claim 3, characterized in that: The shape parameters corresponding to different second segmented images are analyzed by a shape health recognition function to obtain a corresponding shape recognition mark XZB; the shape parameters include a first shape value and a second shape value; Among them, the expression of shape health identification function is: Wherein, xz1 and xz2 are the first shape value and the second shape value in the shape parameter respectively; U3 and U4 are the first shape standard range corresponding to the first shape value and the second shape standard range corresponding to the second shape value respectively; The shape identifier contains a value of 0, -1, or -2.

6. A remote monitoring and management system for edible fungus cultivation according to claim 3 or 5, characterized in that: By formula Calculate and obtain the first local cultivation validity JX1 corresponding to the first monitoring image; where α is the first calculation influence coefficient, and the value range is (1, 2); n1 and n2 are the total number of morphological identification marks with a value of 1 and the total number of morphological identification marks with a value of 2, respectively; N is the total number of all first divided images contained in the first monitoring image; A is the first local cultivation standard value; By formula Calculate and obtain the second local cultivation validity JX2 corresponding to the second monitoring image; where β is the second calculation influence coefficient, and the value range is (1, 2); n3 and n4 are the total number of shape recognition identifiers with a value of 1 and the total number of shape recognition identifiers with a value of 2, respectively; B is the second local cultivation standard value; By formula Calculate and obtain the local cultivation integration validity ZX corresponding to different divided areas; where C is the local cultivation integration standard value.

7. The remote monitoring and management system for edible fungus cultivation according to claim 6, characterized in that: The first local cultivation validity, the second local cultivation validity and the local cultivation integration validity obtained by remote monitoring processing corresponding to different divided areas are processed and analyzed respectively to determine the health status of edible fungus cultivation corresponding to different divided areas; The first local cultivation validity, the second local cultivation validity and the local cultivation integration validity of the different divided areas are sequentially analyzed through the cultivation health identification function, and the cultivation health value ZJ corresponding to the different divided areas is output; the cultivation health value includes the value of 0, a or b.

8. The remote monitoring and management system for edible fungus cultivation according to claim 7, characterized in that: The expression of the cultivation health identification function is In the formula, a and b are constants greater than 0; According to the cultivation health value with a value of a, the corresponding divided area is marked as a slightly abnormal cultivation area, and according to the cultivation health value with a value of b, the corresponding divided area is marked as a severely abnormal cultivation area.

9. The remote monitoring and management system for edible fungus cultivation according to claim 8, characterized in that: The total number of mild anomalies N1 in the mildly abnormal cultivation area and the total number of severe anomalies N2 in the severe abnormal cultivation area are counted respectively, and the formula is used to calculate the total number of mild anomalies N1 in the mildly abnormal cultivation area and the total number of severe anomalies N2 in the severe abnormal cultivation area. Calculate and obtain the abnormal coverage value YF corresponding to the cultivation of all divided areas; where NZ is the total number of all divided areas; D is the abnormal coverage standard value.

10. The remote monitoring and management system for edible fungus cultivation according to claim 9, characterized in that: If the abnormal coverage value is less than or equal to 0, a local abnormal alarm prompt will be implemented for all cultivation areas with slight abnormalities or cultivation areas with severe abnormalities; If the abnormal coverage value is greater than 0, an overall abnormal alarm will be issued for all cultivation areas with slight abnormalities or cultivation areas with severe abnormalities.

Images