CN113988465A - Banana plant nutrition judgment method based on machine learning - Google Patents

Banana plant nutrition judgment method based on machine learning Download PDF

Info

Publication number
CN113988465A
CN113988465A CN202111364501.4A CN202111364501A CN113988465A CN 113988465 A CN113988465 A CN 113988465A CN 202111364501 A CN202111364501 A CN 202111364501A CN 113988465 A CN113988465 A CN 113988465A
Authority
CN
China
Prior art keywords
banana
soil
irrigation
fertilization
growth
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111364501.4A
Other languages
Chinese (zh)
Inventor
覃敬源
梁海玲
龙宣佑
伍祚斌
温标堂
黄文娟
阳继辉
黄小娟
陈春莲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangxi Zhongyi Integrative Water And Fertilizer Biological Science & Technology Co ltd
Original Assignee
Guangxi Zhongyi Integrative Water And Fertilizer Biological Science & Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangxi Zhongyi Integrative Water And Fertilizer Biological Science & Technology Co ltd filed Critical Guangxi Zhongyi Integrative Water And Fertilizer Biological Science & Technology Co ltd
Priority to CN202111364501.4A priority Critical patent/CN113988465A/en
Publication of CN113988465A publication Critical patent/CN113988465A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Mining
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y10/00—Economic sectors
    • G16Y10/05—Agriculture
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • G16Y20/10—Information sensed or collected by the things relating to the environment, e.g. temperature; relating to location
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • G16Y20/20—Information sensed or collected by the things relating to the thing itself
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/10—Detection; Monitoring
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/20—Analytics; Diagnosis

Abstract

The invention discloses a banana plant nutrition judgment method based on machine learning, which comprises the following steps: the method comprises the steps of collecting photos of banana plants, processing images, judging the cultivation mode of the banana plants, judging the growing period of the banana plants, judging the growth vigor of the banana plants, judging the soil condition, judging the meteorological condition, judging the irrigation condition, judging the fertilization condition and judging the comprehensive nutrition of the banana plants. The invention can supplement related nutrient elements in time in the nutrient intake required by different stages of banana trees, improve the nutrition of crops, shorten the diagnosis and measurement time, reduce the diagnosis cost, reduce the labor expenditure, reduce the crop diseases and increase the yield of bananas.

Description

Banana plant nutrition judgment method based on machine learning
Technical Field
The invention relates to the technical field of banana plant planting, in particular to a banana plant nutrition judgment method based on machine learning.
Background
Bananas are perennial large herbaceous plants in tropical and subtropical regions, can be harvested after being planted for about one year, and can be planted in spring, summer, autumn and the like according to the planting time. Because the growth of bananas is seriously influenced by air temperature, and the growth periods of bananas planted in different seasons are different, the specific fertilization date is difficult to determine. The method is implemented on production according to the number of leaves and the growth fertilization method, and has strong operability. But needs experienced agricultural technicians or growers to judge the banana is in what stage and how much nutrients and fertilizers need to be put in. And local general professional agricultural technicians need to cultivate for a long time and need to go to the local for observation, which consumes manpower and material resources.
Disclosure of Invention
The invention provides a banana plant nutrition judgment method based on machine learning, which can supplement related nutrition elements in time in the nutrition intake required by different stages of a banana tree, improve crop nutrition, shorten diagnosis and measurement time, reduce diagnosis cost, reduce labor expenditure, reduce crop diseases and increase banana yield.
In order to solve the problems, the banana plant nutrition judgment method based on machine learning is provided, and comprises the following steps:
acquiring a banana plant photo, and shooting the banana plant photo; the banana plant photo comprises all leaves of the banana plant;
an image processing step, namely processing the picture of the banana plant to obtain a processed picture;
judging the cultivation mode of the banana plant, and determining the cultivation mode of the banana plant as a newly planted banana or a perennial banana;
a banana plant growth period judging step, wherein the number of the banana plants is obtained by carrying out leaf counting analysis on the processed photos; obtaining the leaf age of the banana plant by a growing period judging method by combining the cultivation mode and the number of leaves of the banana plant;
a banana plant growth judgment step, namely, carrying out growth judgment analysis on the processed photos and outputting the current banana plant growth condition of the banana plants;
a soil condition judgment step, namely acquiring soil information in the current banana plant planting area, and analyzing the soil information to obtain a soil influence factor; the soil information comprises soil data corresponding to a plurality of soil influence factors;
a weather condition judgment step, namely acquiring weather information in the current banana plant planting area, and analyzing the weather information to obtain weather influence factors; the weather information comprises weather data corresponding to a plurality of weather influence factors;
judging irrigation conditions, namely acquiring irrigation information in a current banana plant planting area, analyzing the irrigation information and acquiring irrigation influence factors; the irrigation information comprises irrigation data corresponding to a plurality of irrigation influencing factors;
a fertilization condition judgment step, namely acquiring fertilization information in a current banana plant planting area, and analyzing the fertilization information to obtain fertilization influence factors; the fertilization information comprises fertilization data corresponding to a plurality of fertilization influence factors;
a comprehensive nutrition judgment step of the banana plants, wherein an expert demarcates leaf age ranges according to actual growth conditions of leaf ages of the banana plants, and formulates an optimal growth condition, an optimal soil influence factor, an optimal meteorological influence factor, an optimal irrigation influence factor and an optimal fertilization influence factor corresponding to each leaf age range; finding out the leaf age range corresponding to the current leaf age of the banana plant, respectively comparing and analyzing the current growth condition of the banana plant, the soil influence factor, the meteorological influence factor, the irrigation influence factor and the fertilization influence factor, summarizing and fusing the data, and formulating a nutrition scheme after combining an antagonistic mechanism; the nutrition scheme is the supply amount and the supply frequency of the nutrients to the bananas;
wherein, the growth condition judgment analysis comprises the following substeps: the characteristic extraction substep is that color characteristic extraction, size characteristic extraction and texture characteristic extraction are respectively carried out on the processed picture; growth grading substep: dividing growth grades of a plurality of banana plants according to the leaf age and the quality degree of the growth of the banana plants by the experience of a planting expert, wherein each growth grade corresponds to the leaf age, the color characteristic, the size characteristic and the texture characteristic; a result output substep: establishing a banana photo gallery, performing classification training according to the growth grades of banana plants, performing machine learning judgment on the processed photos after feature extraction, and outputting the growth grade of each leaf; a result output substep: selecting the worst growth grade of all the growth grades of the leaves as the current growth condition of the banana plants and outputting the worst growth grade;
the soil information analysis comprises the following steps: determining a soil influence weight omega of an nth soil influence factornWherein n is 1, 2.. multidot.m; obtaining soil data e under ideal conditionsn(ii) a Normalizing the soil data and setting the normalized soil data as xn(ii) a Calculating soil influence factor
Figure BDA0003360132570000021
The meteorological information analysis comprises the following steps: determining a weather influence weight omega of the a-th weather influence factoraWherein, a is 1, 2,. and m; obtaining meteorological data f under ideal conditionsa(ii) a Normalizing the meteorological data and setting the normalized meteorological data as yaWherein, a is 1, 2,. and m; calculating weather influence factor
Figure BDA0003360132570000031
The irrigation information analysis comprises the following steps: determining an irrigation impact weight omega for the b-th irrigation impact factorbWherein, b is 1, 2.. multidot.m; obtaining irrigation data g under ideal conditionsb(ii) a Normalizing the irrigation data and setting the normalized irrigation data as zbWherein, b is 1, 2.. multidot.m; calculating irrigation impact factors
Figure BDA0003360132570000032
The fertilization information analysis comprises the following steps: determining a fertilization influence weight omega of the c-th fertilization influence factorcWherein, c is 1, 2.. multidot.m; obtaining fertilization data h under ideal conditionsc(ii) a Normalizing the fertilization data to be pcWherein, c is 1, 2.. multidot.m; calculating fertilization influence factors
Figure BDA0003360132570000033
Particularly, the specific steps of processing the images of the banana plants in the image processing step comprise:
(1) the banana plant photo is converted into an RGB numerical matrix, the brightness of the image is adjusted, and the contrast is enhanced;
(2) automatically screening out effective areas except the background by using a K-Means clustering algorithm;
(3) identifying a banana plant area where a single banana plant comprising all leaves is located by using an edge identification technology;
(4) and (5) deleting the area of the banana plants after counter selection to obtain a processed picture.
Particularly, the growing period judging method comprises a training step and an output step;
the training step comprises: the machine automatically inputs massive processing images, a feature database of leaf ages at different growth stages in different banana cultivation modes is established according to the banana plant cultivation modes, and then image features are classified according to the leaf ages according to the feature database; the machine continuously inputs massive processing images to circulate the steps until the training is finished;
the outputting step includes: and inputting the processed pictures into a machine after the training step is finished, and outputting the leaf age.
In particular, the soil influencing factors comprise soil structure attributes, soil organic matter content, soil pH value, permeability, water holding rate, types and contents of soil elements, soil air content, ground surface average temperature, different soil layer average temperatures, different soil layer average humidity, soil conductivity and microorganism content.
Specifically, the meteorological information includes illumination duration, illumination intensity, rainfall, atmospheric temperature, average temperature, limit temperature, wind speed and evaporation capacity.
Specifically, the irrigation information comprises the type, quality, irrigation time, irrigation amount and irrigation frequency of irrigation water.
Particularly, the fertilization information comprises the type, nutrient content, fertilization time, fertilization amount, fertilization concentration and fertilization frequency of the fertilizer.
In particular, the soil influence weights are respectively weights set by a planting expert through an analytic hierarchy process.
A system of a banana plant nutrition judgment method based on machine learning comprises the following steps: the system comprises a shooting device, a machine vision identification module, a field Internet of things system, a soil moisture content real-time online monitoring system, a fertilizer real-time monitoring device, an irrigation real-time detection module, a weather instrument and a nutrition judgment module;
the shooting device is used for shooting the picture of the banana plant; the banana plant photo comprises all leaves of the banana plant;
the machine vision identification module is used for executing the banana plant growing period judging step;
the field Internet of things system is used for providing and updating leaf age ranges provided by experts and optimal growth conditions, optimal soil influence factors, optimal meteorological influence factors, optimal irrigation influence factors and optimal fertilization influence factors corresponding to the leaf age ranges, and dividing growth grades of a plurality of banana plants according to the leaf ages and the growth degree of the banana plants;
the fertilizer real-time monitoring device is used for acquiring fertilizer application information in a current banana plant planting area;
the irrigation real-time detection module is used for acquiring irrigation information in the current banana plant planting area;
the weather instrument is used for acquiring weather information in the current banana plant planting area;
the nutrition judgment module is used for executing the banana plant growth period judgment step, the banana plant growth vigor judgment step, the soil condition judgment step, the meteorological condition judgment step, the irrigation condition judgment step, the fertilization condition judgment step and the banana plant comprehensive nutrition judgment step.
The invention has the beneficial effects that:
the invention collects the growth condition of banana leaves by spectral image remote sensing, machine vision recognition and a field Internet of things system, combines a real-time online monitoring system of soil moisture content, configures a weather instrument capable of monitoring parameters such as rainfall, soil humidity and the like, a fertilizer real-time monitoring device of fertilizer solution EC and pH and the like, combines the Internet of things to provide decision data such as uninterrupted weather, irrigation, fertilization and the like, learns and automatically recognizes the number and growth condition of the banana leaves, simultaneously utilizes the soil, weather, moisture, fertilizer data and the like to analyze influence factors, determines nutrition schemes in different stages according to the number of the banana leaves, realizes large-area, rapid and nondestructive detection of the banana leaves, realizes the real-time local and integral monitoring of the growth condition of the banana, realizes three-dimensional and intelligent management, reduces the investment of production data such as water, fertilizer, manpower and the like, provides an accurate formula for nutrition required by the growth of banana crops in different periods, and provides technical guarantee for increasing the quality and the yield of fruits.
The nutrition diagnosis is carried out on the banana trees by replacing the manual operation of agricultural personnel through a machine, a computer program and the like, the machine and the computer program automatically recognize according to the number of banana leaves and the growth situation of crops, so that the nutrition intake required by different stages of the banana trees is determined, related nutrient elements are supplemented in time, the nutrition of the crops is improved, the diagnosis and measurement time is shortened, the diagnosis cost is reduced, the labor expenditure is reduced, the crop diseases are reduced, the banana yield is increased, and the method is also one of the paths for realizing agricultural informatization.
Detailed Description
The following detailed description of the preferred embodiments of the present invention is provided to enable those skilled in the art to more readily understand the advantages and features of the present invention and to clearly and unequivocally define the scope of the present invention.
It should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," "outer," and the like are used in an orientation or positional relationship that is based on the orientation or positional relationship, or that is conventionally used in the practice of the invention, merely to facilitate the description and simplify the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the invention. Furthermore, the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
Furthermore, the terms "horizontal", "vertical", "overhang" and the like do not imply that the components are required to be absolutely horizontal or overhang, but may be slightly inclined. For example, "horizontal" merely means that the direction is more horizontal than "vertical" and does not mean that the structure must be perfectly horizontal, but may be slightly inclined.
In the description of the present invention, it should also be noted that, unless otherwise explicitly specified or limited, the terms "disposed," "mounted," "connected," and "connected" are to be construed broadly and may, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The banana plant nutrition judgment method based on machine learning comprises the following steps:
and acquiring a picture of the banana plant, and shooting the picture of the banana plant. The banana plant photo includes all leaves of the banana plant;
an image processing step, namely processing the picture of the banana plant to obtain a processed picture;
judging the cultivation mode of the banana plant, and determining the cultivation mode of the banana plant as a newly planted banana or a perennial banana;
a banana plant growth period judging step, wherein the number of the banana plants is obtained by carrying out leaf counting analysis on the processed photos; obtaining the leaf age of the banana plant by a growing period judging method by combining the cultivation mode and the number of leaves of the banana plant;
a banana plant growth judgment step, namely, carrying out growth judgment analysis on the processed photos and outputting the current banana plant growth condition of the banana plants;
and a soil condition judgment step, namely acquiring soil information in the current banana plant planting area, and analyzing the soil information to obtain a soil influence factor. The soil information comprises soil data corresponding to a plurality of soil influence factors; the soil influence factors comprise soil structure attribute, soil organic matter content, soil pH value, permeability, water holding rate, types and contents of soil elements, soil air content, earth surface average temperature, different soil layer average temperatures, different soil layer average humidity, soil conductivity and microorganism content.
And a weather condition judgment step, namely acquiring weather information in the current banana plant planting area, and analyzing the weather information to obtain weather influence factors. The meteorological information comprises meteorological data corresponding to a plurality of meteorological influence factors;
and judging the irrigation condition, namely acquiring irrigation information in the current banana plant planting area, analyzing the irrigation information and acquiring irrigation influence factors. The irrigation information comprises irrigation data corresponding to a plurality of irrigation influencing factors; the irrigation information comprises the type, quality, irrigation time, irrigation amount and irrigation frequency of irrigation water.
And a fertilization condition judgment step, namely acquiring fertilization information in the current banana plant planting area, and analyzing the fertilization information to obtain fertilization influence factors. The fertilization information comprises fertilization data corresponding to a plurality of fertilization influence factors; the fertilization information comprises the type, nutrient content, fertilization time, fertilization amount, fertilization concentration and fertilization frequency of the fertilizer.
A comprehensive nutrition judgment step of the banana plants, wherein an expert demarcates leaf age ranges according to actual growth conditions of leaf ages of the banana plants, and formulates an optimal growth condition, an optimal soil influence factor, an optimal meteorological influence factor, an optimal irrigation influence factor and an optimal fertilization influence factor corresponding to each leaf age range; finding out the leaf age range corresponding to the current leaf age of the banana plant, respectively comparing and analyzing the current growth condition of the banana plant, the soil influence factor, the meteorological influence factor, the irrigation influence factor and the fertilization influence factor, summarizing and fusing the data, and formulating a nutrition scheme after combining an antagonistic mechanism; the nutrition scheme is the supply amount and the supply frequency of the nutrients to the bananas;
wherein, the growth condition judgment analysis comprises the following substeps: a characteristic extraction substep: respectively extracting color features, size features and texture features of the processed photos; growth grading substep: dividing growth grades of a plurality of banana plants according to the leaf age and the quality degree of the growth of the banana plants by the experience of a planting expert, wherein each growth grade corresponds to the leaf age, the color characteristic, the size characteristic and the texture characteristic; a result output substep: establishing a banana photo gallery, performing classification training according to the growth grades of banana plants, performing machine learning judgment on the processed photos after feature extraction, and outputting the growth grade of each leaf; a result output substep: selecting the worst growth grade of all the growth grades of the leaves as the current growth condition of the banana plants and outputting the worst growth grade;
the soil information analysis comprises the following steps: determining a soil influence weight omega of an nth soil influence factornWherein n is 1, 2.. multidot.m; obtaining soil data e under ideal conditionsn(ii) a Normalizing the soil data and setting the normalized soil data as xn(ii) a Calculating soil influence factor
Figure BDA0003360132570000071
The meteorological information analysis comprises the following steps: determining a weather influence weight omega of the a-th weather influence factoraWherein, a is 1, 2,. and m; obtaining meteorological data f under ideal conditionsa(ii) a Normalizing the meteorological data and setting the normalized meteorological data as yaWherein, a is 1, 2,. and m; calculating weather influence factor
Figure BDA0003360132570000072
The meteorological information comprises illumination duration, illumination intensity, rainfall, atmospheric temperature, average temperature, limit temperature, wind speed and evaporation capacity.
The irrigation information analysis comprises the following steps: determining an irrigation impact weight omega for the b-th irrigation impact factorbWherein, b is 1, 2.. multidot.m; obtaining irrigation data g under ideal conditionsb(ii) a Normalizing the irrigation data and setting the normalized irrigation data as zbWherein, b is 1, 2.. multidot.m; calculating irrigation impact factors
Figure BDA0003360132570000073
The fertilization information analysis comprises the following steps: determining a fertilization influence weight omega of the c-th fertilization influence factorcWherein c is1, 2,.., m; obtaining fertilization data h under ideal conditionsc(ii) a Normalizing the fertilization data to be pcWherein, c is 1, 2.. multidot.m; calculating fertilization influence factors
Figure BDA0003360132570000081
The specific steps of processing the image of the banana plant photo in the image processing step comprise:
(1) the banana plant photo is converted into an RGB numerical matrix, the brightness of the image is adjusted, and the contrast is enhanced;
(2) automatically screening out effective areas except the background by using a K-Means clustering algorithm;
(3) identifying a banana plant area where a single banana plant comprising all leaves is located by using an edge identification technology;
(4) and (5) deleting the area of the banana plants after counter selection to obtain a processed picture.
The growing period judging method comprises a training step and an output step;
the training step comprises: the machine automatically inputs massive processing images, a feature database of leaf ages at different growth stages in different banana cultivation modes is established according to the banana plant cultivation modes, and then image features are classified according to the leaf ages according to the feature database; the machine continuously inputs massive processing images to circulate the steps until the training is finished;
the output step comprises: and inputting the processed pictures into a machine after the training step is finished, and outputting the leaf age.
The soil influence weights are respectively the weights set by the planting experts through an analytic hierarchy process.
A system of a banana plant nutrition judgment method based on machine learning comprises the following steps: the system comprises a shooting device, a machine vision identification module, a field Internet of things system, a soil moisture content real-time online monitoring system, a fertilizer real-time monitoring device, an irrigation real-time detection module, a weather instrument and a nutrition judgment module;
the shooting device is used for shooting the picture of the banana plant; the banana plant photo comprises all leaves of the banana plant;
the machine vision identification module is used for executing the banana plant growing period judging step;
the field Internet of things system is used for providing and updating leaf age ranges provided by experts and optimal growth conditions, optimal soil influence factors, optimal meteorological influence factors, optimal irrigation influence factors and optimal fertilization influence factors corresponding to the leaf age ranges, and dividing growth grades of a plurality of banana plants according to the leaf ages and the growth degree of the banana plants;
the fertilizer real-time monitoring device is used for acquiring fertilizer application information in the current banana plant planting area;
the irrigation real-time detection module is used for acquiring irrigation information in the current banana plant planting area;
the weather instrument is used for acquiring weather information in the current banana plant planting area;
the nutrition judgment module is used for executing the banana plant growth period judgment step, the banana plant growth vigor judgment step, the soil condition judgment step, the meteorological condition judgment step, the irrigation condition judgment step, the fertilization condition judgment step and the banana plant comprehensive nutrition judgment step.
Although the embodiments of the present invention have been described, various changes or modifications may be made by the patentee within the scope of the appended claims, and the scope of the present invention should be determined not to exceed the range described in the claims. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts of the present invention. It should be noted that there are no specific structures but a few objective structures due to the limited character expressions, and that those skilled in the art may make various improvements, decorations or changes without departing from the principle of the invention or may combine the above technical features in a suitable manner; such modifications, variations, combinations, or adaptations of the invention using its spirit and scope, as defined by the claims, may be directed to other uses and embodiments.

Claims (9)

1. A banana plant nutrition judgment method based on machine learning is characterized in that: the method comprises the following steps:
acquiring a banana plant photo, and shooting the banana plant photo; the banana plant photo comprises all leaves of the banana plant;
an image processing step, namely processing the picture of the banana plant to obtain a processed picture;
judging the cultivation mode of the banana plant, and determining the cultivation mode of the banana plant as a newly planted banana or a perennial banana;
a banana plant growth period judging step, wherein the number of the banana plants is obtained by carrying out leaf counting analysis on the processed photos; obtaining the leaf age of the banana plant by a growing period judging method by combining the cultivation mode and the number of leaves of the banana plant;
a banana plant growth judgment step, namely, carrying out growth judgment analysis on the processed photos and outputting the current banana plant growth condition of the banana plants;
a soil condition judgment step, namely acquiring soil information in the current banana plant planting area, and analyzing the soil information to obtain a soil influence factor; the soil information comprises soil data corresponding to a plurality of soil influence factors;
a weather condition judgment step, namely acquiring weather information in the current banana plant planting area, and analyzing the weather information to obtain weather influence factors; the weather information comprises weather data corresponding to a plurality of weather influence factors;
judging irrigation conditions, namely acquiring irrigation information in a current banana plant planting area, analyzing the irrigation information and acquiring irrigation influence factors; the irrigation information comprises irrigation data corresponding to a plurality of irrigation influencing factors;
a fertilization condition judgment step, namely acquiring fertilization information in a current banana plant planting area, and analyzing the fertilization information to obtain fertilization influence factors; the fertilization information comprises fertilization data corresponding to a plurality of fertilization influence factors;
a comprehensive nutrition judgment step of the banana plants, wherein an expert demarcates leaf age ranges according to actual growth conditions of leaf ages of the banana plants, and formulates an optimal growth condition, an optimal soil influence factor, an optimal meteorological influence factor, an optimal irrigation influence factor and an optimal fertilization influence factor corresponding to each leaf age range; finding out the leaf age range corresponding to the current leaf age of the banana plant, respectively comparing and analyzing the current growth condition of the banana plant, the soil influence factor, the meteorological influence factor, the irrigation influence factor and the fertilization influence factor, summarizing and fusing the data, and formulating a nutrition scheme after combining an antagonistic mechanism; the nutrition scheme is the supply amount and the supply frequency of the nutrients to the bananas;
wherein, the growth condition judgment analysis comprises the following substeps: a characteristic extraction substep: respectively extracting color features, size features and texture features of the processed photos; growth grading substep: dividing growth grades of a plurality of banana plants according to the leaf age and the quality degree of the growth of the banana plants by the experience of a planting expert, wherein each growth grade corresponds to the leaf age, the color characteristic, the size characteristic and the texture characteristic; a result output substep: establishing a banana photo gallery, performing classification training according to the growth grades of banana plants, performing machine learning judgment on the processed photos after feature extraction, and outputting the growth grade of each leaf; a result output substep: selecting the worst growth grade of all the growth grades of the leaves as the current growth condition of the banana plants and outputting the worst growth grade;
the soil information analysis comprises the following steps: determining a soil influence weight omega of an nth soil influence factornWherein n is 1, 2.. multidot.m; obtaining soil data e under ideal conditionsn(ii) a Normalizing the soil data and setting the normalized soil data as xn(ii) a Calculating soil influence factor
Figure FDA0003360132560000021
The meteorological information analysis comprises the following steps: determining a weather influence weight omega of the a-th weather influence factoraWherein, a is 1, 2,. and m; obtaining meteorological data f under ideal conditionsa(ii) a Normalizing the meteorological data and setting the normalized meteorological data as yaWherein, a is 1, 2,. and m; calculating weather influence factor
Figure FDA0003360132560000022
The irrigation information analysis comprises the following steps: determining an irrigation impact weight omega for the b-th irrigation impact factorbWherein, b is 1, 2.. multidot.m; obtaining irrigation data g under ideal conditionsb(ii) a Normalizing the irrigation data and setting the normalized irrigation data as zbWherein, b is 1, 2.. multidot.m; calculating irrigation impact factors
Figure FDA0003360132560000023
The fertilization information analysis comprises the following steps: determining a fertilization influence weight omega of the c-th fertilization influence factorcWherein, c is 1, 2.. multidot.m; obtaining fertilization data h under ideal conditionsc(ii) a Normalizing the fertilization data to be pcWherein, c is 1, 2.. multidot.m; calculating fertilization influence factors
Figure FDA0003360132560000024
2. The method for judging the nutrition of banana plants based on machine learning according to claim 1, wherein the method comprises the following steps: the specific steps of processing the banana plant photo by the image processing in the image processing step comprise:
(1) the banana plant photo is converted into an RGB numerical matrix, the brightness of the image is adjusted, and the contrast is enhanced;
(2) automatically screening out effective areas except the background by using a K-Means clustering algorithm;
(3) identifying a banana plant area where a single banana plant comprising all leaves is located by using an edge identification technology;
(4) and (5) deleting the area of the banana plants after counter selection to obtain a processed picture.
3. The method for judging the nutrition of banana plants based on machine learning according to claim 1, wherein the method comprises the following steps: the growing period judging method comprises a training step and an output step;
the training step comprises: the machine automatically inputs massive processing images, a feature database of leaf ages at different growth stages in different banana cultivation modes is established according to the banana plant cultivation modes, and then image features are classified according to the leaf ages according to the feature database; the machine continuously inputs massive processing images to circulate the steps until the training is finished;
the outputting step includes: and inputting the processed pictures into a machine after the training step is finished, and outputting the leaf age.
4. The method for judging the nutrition of banana plants based on machine learning according to claim 1, wherein the method comprises the following steps: the soil influence factors comprise soil structure attribute, soil organic matter content, soil pH value, permeability, water holding rate, types and contents of soil elements, soil air content, earth surface average temperature, different soil layer average temperatures, different soil layer average humidity, soil conductivity and microorganism content.
5. The method for judging the nutrition of banana plants based on machine learning according to claim 1, wherein the method comprises the following steps: the meteorological information comprises illumination duration, illumination intensity, rainfall, atmospheric temperature, average temperature, limit temperature, wind speed and evaporation capacity.
6. The method for judging the nutrition of banana plants based on machine learning according to claim 1, wherein the method comprises the following steps: the irrigation information comprises the type, quality, irrigation time, irrigation amount and irrigation frequency of irrigation water.
7. The method for judging the nutrition of banana plants based on machine learning according to claim 1, wherein the method comprises the following steps: the fertilization information comprises the type, nutrient content, fertilization time, fertilization amount, fertilization concentration and fertilization frequency of the fertilizer.
8. The method for judging the nutrition of banana plants based on machine learning according to claim 1, wherein the method comprises the following steps: the soil influence weights are respectively weights set by planting experts through an analytic hierarchy process.
9. A system for the machine learning based banana plant nutrition determination method according to any one of claims 1-8, comprising: the system comprises a shooting device, a machine vision identification module, a field Internet of things system, a soil moisture content real-time online monitoring system, a fertilizer real-time monitoring device, an irrigation real-time detection module, a weather instrument and a nutrition judgment module;
the shooting device is used for shooting the picture of the banana plant; the banana plant photo comprises all leaves of the banana plant;
the machine vision identification module is used for executing the banana plant growing period judging step;
the field Internet of things system is used for providing and updating leaf age ranges provided by experts and optimal growth conditions, optimal soil influence factors, optimal meteorological influence factors, optimal irrigation influence factors and optimal fertilization influence factors corresponding to the leaf age ranges, and dividing growth grades of a plurality of banana plants according to the leaf ages and the growth degree of the banana plants;
the fertilizer real-time monitoring device is used for acquiring fertilizer application information in a current banana plant planting area;
the irrigation real-time detection module is used for acquiring irrigation information in the current banana plant planting area;
the weather instrument is used for acquiring weather information in the current banana plant planting area;
the nutrition judgment module is used for executing the banana plant growth period judgment step, the banana plant growth vigor judgment step, the soil condition judgment step, the meteorological condition judgment step, the irrigation condition judgment step, the fertilization condition judgment step and the banana plant comprehensive nutrition judgment step.
CN202111364501.4A 2021-11-17 2021-11-17 Banana plant nutrition judgment method based on machine learning Pending CN113988465A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111364501.4A CN113988465A (en) 2021-11-17 2021-11-17 Banana plant nutrition judgment method based on machine learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111364501.4A CN113988465A (en) 2021-11-17 2021-11-17 Banana plant nutrition judgment method based on machine learning

Publications (1)

Publication Number Publication Date
CN113988465A true CN113988465A (en) 2022-01-28

Family

ID=79749145

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111364501.4A Pending CN113988465A (en) 2021-11-17 2021-11-17 Banana plant nutrition judgment method based on machine learning

Country Status (1)

Country Link
CN (1) CN113988465A (en)

Similar Documents

Publication Publication Date Title
CN108346142B (en) Plant growth state identification method based on plant illumination image
CN100416590C (en) Method for automatically identifying field weeds in crop seeding-stage using site and grain characteristic
CN111652756A (en) Green wisdom green house planting environment monitoring management system
CN108710766B (en) Greenhouse plant liquid manure machine fertilizer regulation parameter calculation method based on growth model
CN108739052A (en) A kind of system and method for edible fungi growth parameter optimization
CN115456476B (en) Homeland space planning data acquisition and analysis system based on machine vision
Selvi et al. Weed detection in agricultural fields using deep learning process
CN113469112B (en) Crop growth condition image identification method and system
CN116129260A (en) Forage grass image recognition method based on deep learning
CN108718890A (en) A kind of grape breeding method based on big data analysis
CN114782840A (en) Real-time wheat phenological period classification method based on unmanned aerial vehicle RGB images
Zhao et al. Transient multi-indicator detection for seedling sorting in high-speed transplanting based on a lightweight model
Desiderio et al. Health Classification System of Romaine Lettuce Plants in Hydroponic Setup Using Convolutional Neural Networks (CNN)
CN113988465A (en) Banana plant nutrition judgment method based on machine learning
CN115728249A (en) Prediction method for chlorophyll content of tomato seedlings and processing terminal
Wang et al. Research on application of smart agriculture in cotton production management
Yihang et al. Automatic recognition of rape seeding emergence stage based on computer vision technology
CN114494689A (en) Identification method of tomato drought stress
Guo et al. High-throughput estimation of plant height and above-ground biomass of cotton using digital image analysis and Canopeo
Yang et al. Feature extraction of cotton plant height based on DSM difference method
CN112034912A (en) Greenhouse crop disease control method based on real-time feedback
Shuai et al. Image segmentation of field rape based on template matching and K-means clustering
Kavitha et al. Categorization of Nutritional Deficiencies in Plants With Random Forest
Feng et al. A Real-time Monitoring and Control System for Crop
CN110135481A (en) A kind of crops lesion detection method and detection device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination