CN110455340B - Agricultural product planting environment detection system based on big data - Google Patents

Agricultural product planting environment detection system based on big data Download PDF

Info

Publication number
CN110455340B
CN110455340B CN201910774185.4A CN201910774185A CN110455340B CN 110455340 B CN110455340 B CN 110455340B CN 201910774185 A CN201910774185 A CN 201910774185A CN 110455340 B CN110455340 B CN 110455340B
Authority
CN
China
Prior art keywords
soil
content
agricultural product
planting
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.)
Active
Application number
CN201910774185.4A
Other languages
Chinese (zh)
Other versions
CN110455340A (en
Inventor
许四五
吴爱美
朱国英
魏良胜
吴明来
钱一华
张征
方向丽
杜长春
金来加
李明智
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.)
Chizhou Agricultural Product Quality Safety Monitoring Center
Original Assignee
Chizhou Agricultural Product Quality Safety Monitoring Center
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 Chizhou Agricultural Product Quality Safety Monitoring Center filed Critical Chizhou Agricultural Product Quality Safety Monitoring Center
Priority to CN201910774185.4A priority Critical patent/CN110455340B/en
Publication of CN110455340A publication Critical patent/CN110455340A/en
Application granted granted Critical
Publication of CN110455340B publication Critical patent/CN110455340B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

The invention discloses an agricultural product planting environment detection system based on big data, which comprises a cloud server, a species type input module, a soil detection module, an environment detection analysis module, an image acquisition module, a screening processing module, a feature extraction module, a data storage library and a display terminal, wherein the soil detection module, the environment detection analysis module, the image acquisition module, the screening processing module, the feature extraction module, the data storage library and the display terminal are connected with the cloud server, the data storage library is respectively connected with the species type input module and the environment detection analysis module, and the screening processing module is respectively connected with the image acquisition. According to the method, the influence of growth of the agricultural products in each growth stage can be counted according to the detected planting environment, reliable reference data can be provided for later-stage comprehensive evaluation of the growth of the agricultural products, the quality of the agricultural products can be comprehensively evaluated, the comprehensive prediction reaction coefficient can be comprehensively evaluated, the method has the characteristics of high detection accuracy and high analysis accuracy, guiding reference data can be provided for later-stage planting personnel to plant the agricultural products, the quality of the agricultural products can be conveniently improved, and the development of the agricultural products can be promoted.

Description

Agricultural product planting environment detection system based on big data
Technical Field
The invention belongs to the technical field of agricultural informatization, and relates to a big data-based agricultural product planting environment detection system.
Background
With the continuous improvement of living standard of people, people pursue the quality of agricultural products to be gradually improved, the quality of the agricultural products is mainly influenced by the growth condition of the agricultural products in each growth stage, the factors influencing the growth of the agricultural products mainly comprise the content, temperature, humidity, illumination intensity and the like of each element in soil, the planting environment of the agricultural products is a natural environment in the existing agricultural product planting process, and the planting personnel fertilize, water and other operations on the agricultural products according to the planting experience and control the growth of the agricultural products through fertilization, but the growth condition of the agricultural products can not be comprehensively analyzed according to the content, temperature, humidity and illumination intensity of each element in the soil of the agricultural products at each growth stage, and the final quality problem of the agricultural products can not be evaluated according to the planting environment, further, the quality of agricultural products is unstable and is easily affected by the environment, and there are problems of poor quality stability and poor quality of agricultural products.
Disclosure of Invention
The invention aims to provide a big data-based agricultural product planting environment detection system, the soil detection module is used for collecting nitrogen content, phosphorus content, potassium content, calcium content and magnesium content in soil and temperature and humidity corresponding to each soil depth, the environment detection and analysis module is used for collecting illumination intensity of agricultural products, illumination intensity grades corresponding to the illumination intensity and illumination time corresponding to each illumination intensity grade, and combines with the influence coefficient of the cloud server on the growth inhibition of the agricultural product species in each growth stage, meanwhile, the quality of the agricultural products is evaluated, the comprehensive pre-estimation reaction coefficient is obtained, the problems that the influence on the growth of the agricultural products cannot be analyzed according to planting environment parameters in the existing agricultural product planting process, the stability of the quality of the agricultural product planting is poor, and the accuracy of detection and analysis is poor are solved, and guiding reference data cannot be provided for planting of the agricultural products by planting personnel in the later period.
The purpose of the invention can be realized by the following technical scheme:
a big data-based agricultural product planting environment detection system comprises a species input module, a soil detection module, an environment detection analysis module, an image acquisition module, a screening processing module, a feature extraction module, a data storage library, a cloud server and a display terminal;
the cloud server is respectively connected with the soil detection module, the environment detection and analysis module, the image acquisition module, the screening processing module, the feature extraction module, the data storage library and the display terminal, the data storage library is respectively connected with the species type input module and the environment detection and analysis module, and the screening processing module is respectively connected with the image acquisition module and the feature extraction module;
the species type input module is used for inputting types of agricultural products planted in various planting sub-regions, establishing corresponding connection relations between the types of the planted agricultural products and numbers corresponding to the various planting sub-regions, and sending the numbers of the various planting sub-regions and the types of the agricultural products planted in the planting sub-regions to the data storage library;
the soil detection module comprises a plurality of soil detection devices and temperature and humidity detection devices, the soil detection devices are respectively installed in various plant subareas and used for detecting nitrogen content, phosphorus content, potassium content, calcium content and magnesium content in soil in the various plant subareas and sending the detected nitrogen content, phosphorus content, potassium content, calcium content and magnesium content to the cloud server, the temperature and humidity detection devices are temperature and humidity sensors which are respectively installed in soil corresponding to various soil depth levels in the various plant subareas and used for detecting temperature and humidity in the soil corresponding to different soil depth levels in the various plant subareas in a fixed time period and sending the detected temperature and humidity in the soil corresponding to the various soil depth levels in the various plant subareas to the cloud server;
the environment detection and analysis module is used for detecting the illumination intensity in the planting area in real time, comparing the detected illumination intensity with illumination intensity ranges corresponding to different illumination intensity grades stored in the data storage library, screening out the illumination intensity grade corresponding to the illumination intensity, counting the illumination time corresponding to each illumination intensity grade according to the illumination intensity grade corresponding to the illumination intensity, and sending the counted illumination intensity grade and the illumination time corresponding to each illumination intensity grade to the cloud server;
the image acquisition module is used for acquiring images of plants planted in various plant regions and respectively sending the acquired images in the various plant regions to the cloud server and the screening processing module;
the image acquisition module comprises a plurality of image acquisition units, the image acquisition units are numbered, the numbers corresponding to the image acquisition units are consistent with the numbers in the planting subareas where the image acquisition units are located, the image acquisition units are high-definition cameras and are respectively installed in the various planting subareas, the number of the high-definition cameras installed in each planting subarea is the same, and the image acquisition units are used for acquiring the image information of plant leaves in the various planting subareas and respectively sending the image information of the plant leaves acquired by the cameras in the various planting subareas to the screening processing module and the cloud server;
the screening processing module is used for receiving plant image information acquired by the cameras in various plant areas sent by the image acquisition module, screening the received plant images by using various different rectangular screening frames, extracting the smallest rectangle capable of wrapping the plant leaves, and removing image cutting outside the rectangular area so as to remove images irrelevant to the leaf images and reduce the difficulty and workload of extracting features of the whole acquired image; and scaling the image of the remaining rectangular area in the X direction to fxScaling by f in the Y directionyNormalizing the images to the same image size, performing image enhancement processing on the images after the normalization processing, and finally respectively sending the images after the image enhancement processing to a feature extraction module and a cloud server;
the feature extraction module is used for receiving the image which is sent by the screening processing module and subjected to image enhancement processing, dividing the received image into a plurality of sub-images with the same area, numbering the sub-images according to a set sequence, wherein the number of the sub-images is 1,2, 1ji(βji1,βji2,...,βjik,...,βjiN)，βjik represents the kth leaf feature in the ith sub-image in the image acquired for the jth seed sub-region, N represents the number of leaf features in each sub-image, and the extracted leaf feature set β isjiSending the data to a cloud server;
the data storage library is used for storing serial numbers corresponding to various planting subareas and agricultural product types planted in the planting subareas, storing standard blade images corresponding to different agricultural product types and standard blade features corresponding to the standard blade images, and forming a standard blade feature set S by the standard blade features corresponding to various agricultural product typesr(sr1,sr2,...,srv)，srv is expressed as the v standard leaf characteristic corresponding to the r agricultural product species, and the standard leaf characteristic set SrThe weight coefficients corresponding to the standard blade features are gs respectivelyr1,gsr2,...,gsrv，gsrv is expressed as a weight coefficient of the v standard leaf feature corresponding to the r agricultural product species, and gsr1+gsr2+...+gsrv is 1, and is used for storing illumination intensity ranges corresponding to different illumination intensity levels, illumination intensity level thresholds corresponding to each growth stage and time thresholds corresponding to the illumination intensity levels corresponding to each growth stage, wherein the illumination intensity levels are sorted from low to high and are respectively R1, R2, R3 and R4, the illumination intensity ranges corresponding to R1, R2, R3 and R4 are sequentially increased, and the requirements of different agricultural product types on the standard humidity range and the standard temperature range of each soil depth at different growth stages are stored;
in addition, the storage database stores standard nitrogen content ranges, phosphorus content ranges, potassium content ranges, calcium content ranges and magnesium content ranges required by soil of various agricultural product types in various growth stages, and stores the weight coefficients of growth influence ratios of the nitrogen content, the phosphorus content, the potassium content, the calcium content and the magnesium content on various agricultural products in various growth stages, wherein the weight coefficients are gNt,gPt,gKt,gCat,gMgt，gNt is expressed in the tth growth stageGrowth-affecting proportional weight coefficients for nitrogen, and similarly, T ═ T1, T2, T3, T4, T5, T6, and gNt+gPt+gKt+gCat+gMgt is 1, the leaf color corresponding to each agricultural product type and the leaf color grade corresponding to the leaf color are stored, and the leaf color grades corresponding to the plant leaf color grades of the same agricultural product are respectively Q1, Q2, Q3, Q1, Q2 and Q3 and are sequentially increased;
the data storage library also stores the numbers in the planting sub-areas and the agricultural product types in the various planting sub-areas, and stores sowing dates and current dates of the agricultural products in the various planting sub-areas and time ranges corresponding to the agricultural product types in the growth stages;
the cloud server is used for receiving the blade feature set β sent by the feature extraction modulejiAnd collecting β leaf feature sets in each sub-image corresponding to the agricultural products in the collected planting sub-areajiObtaining a comparison leaf feature set delta S corresponding to the standard leaf feature set stored in the data storage libraryr(Δsr1,Δsr2,...,Δsrv)，Δsrv is expressed as the comparison condition of the v standard blade feature corresponding to the r agricultural product species and the blade feature in each sub-image in the collected planting sub-area, if the v standard blade feature corresponding to the r agricultural product species exists in the blade feature set in each sub-image, the delta s is takenrv is equal to a fixed constant which is more than 1, if the characteristic set of the blades in each acquired sub-image does not have the v standard blade characteristic corresponding to the r agricultural product species, the value of deltas is takenrv is equal to 0, the goodness of fit coefficient between the agricultural products and various agricultural product types in the collected planting sub-area is counted according to the comparison blade feature set, and the calculation formula of the goodness of fit coefficient of the agricultural product types is
Figure BDA0002174522950000051
Δsrv is expressed as the comparison of the characteristic of the v standard leaf corresponding to the r agricultural product species with the characteristic of the leaf in each sub-image in the collected planting sub-area, gsrv is denoted as the r-thScreening out the agricultural product type corresponding to the maximum goodness-of-fit coefficient according to the weight coefficient of the characteristic of the v-th standard leaf corresponding to the agricultural product type, extracting the number corresponding to the collected planting subregion, extracting the agricultural product type corresponding to the planting subarea number in the data storage bank according to the planting subarea number, and comparing the extracted agricultural product type with the agricultural product type corresponding to the maximum goodness of fit coefficient, if the extracted agricultural product type is the same as the agricultural product type corresponding to the maximum goodness of fit coefficient, indicating that the types of the agricultural products planted in the planting subarea are correct, if the types of the extracted agricultural products are different from the types of the agricultural products corresponding to the maximum goodness of fit coefficient, it indicates that the types of agricultural products planted in the planting sub-area are not matched with the types of agricultural products actually planted, replacing agricultural product types planted in various planting sub-areas in the data storage library with the agricultural product types corresponding to the maximum goodness of fit coefficients;
the cloud server is used for receiving the image information of the plant leaves in various plant regions sent by the image acquisition module, comparing the received image information of the plant leaves with the leaf colors corresponding to the leaf color grades of the agricultural products stored in the data storage library, and extracting the leaf color grades corresponding to the similar leaf colors; the cloud server extracts sowing time, current date and time corresponding to each growth stage of agricultural products in various planting sub-areas in the storage database, judges the growth stage corresponding to the agricultural product variety planted in various planting sub-areas according to the sowing time, current date and time corresponding to each growth stage of the agricultural products in various planting sub-areas, extracts standard nitrogen content range, phosphorus content range, potassium content range, calcium content range and magnesium content range corresponding to the growth stage of the agricultural products in various planting sub-areas and temperature and humidity range corresponding to each soil depth, and is used for receiving nitrogen content, phosphorus content, potassium content, calcium content and magnesium content in soil of various planting sub-areas and temperature and humidity in soil corresponding to different soil depth levels sent by the soil detection module, and enables the received nitrogen content, phosphorus content, potassium content, calcium content and magnesium content in the soil to be, The phosphorus content, the potassium content, the calcium content and the magnesium content sequentially form a soil element content set A (a)N,aP,aK,aCa,aMg)，aNExpressed as the nitrogen content in the soil, aPExpressed as the phosphorus content in the soil, aKExpressed as potassium content in the soil, aCaExpressed as the calcium content in the soil, aMgThe content is expressed as the magnesium content in the soil, the cloud server compares the received nitrogen content, phosphorus content, potassium content, calcium content and magnesium content in the soil with a standard nitrogen content range, a standard phosphorus content range, a standard potassium content range, a standard calcium content range and a standard magnesium content range corresponding to the current growth stage respectively to obtain a soil element content comparison set delta A (delta a)N,ΔaP,ΔaK,ΔaCa,ΔaMg)，ΔaNExpressed as the difference between the nitrogen content in the soil and the standard nitrogen content range corresponding to this growth phase, Δ aPExpressed as the difference between the phosphorus content in the soil and the standard range of phosphorus content corresponding to that growth phase, Δ aKExpressed as the difference between the potassium content in the soil and the standard potassium content range corresponding to that growth phase, Δ aCaExpressed as the difference between the calcium content in the soil and the standard calcium content range corresponding to this growth phase, Δ aMgExpressed as the difference between the magnesium content in the soil and the standard magnesium content range corresponding to the growth phase;
the cloud server compares the received temperature and humidity in the soil corresponding to different soil depth levels with a standard humidity range and a standard temperature range corresponding to the soil depth level corresponding to the growth stage in the data repository respectively to obtain a soil depth level parameter comparison set B (X)W1,XW2,XW3,XW4,LW1,LW2,LW3,LW4)，XWfExpressed as the comparison between the soil temperature corresponding to the Wf th soil depth level and the standard soil temperature range corresponding to the Wf th soil depth level, LWfShowing the comparison condition between the soil humidity corresponding to the Wf-th soil depth grade and the soil standard humidity range corresponding to the Wf-th soil depth grade, wherein Wf is W1, W2, W3 and W4;
the cloud server receives each illumination intensity grade and illumination time corresponding to each illumination intensity grade sent by the environment detection and analysis module, compares each received illumination intensity grade with a preset illumination intensity grade threshold corresponding to each growth stage, counts the illumination time of each illumination intensity grade more than or equal to the illumination intensity grade threshold, predicts the illumination time of each illumination intensity grade more than or equal to the illumination intensity grade threshold according to a soil element content comparison set delta A and a soil depth grade parameter comparison set B corresponding to each growth stage, and counts the growth inhibition influence coefficient of agricultural product varieties corresponding to each growth stage
Figure BDA0002174522950000071
The cloud server evaluates a comprehensive quality estimation reaction coefficient, pi r, of the agricultural products according to the growth inhibition influence coefficients of the agricultural product types corresponding to the growth stages and by combining with the leaf color grades corresponding to the agricultural product types, and sends the statistical growth inhibition influence coefficients of the agricultural product types corresponding to the growth stages, the comprehensive quality estimation reaction coefficients of the agricultural products, illumination time corresponding to the agricultural products under each illumination intensity grade, nitrogen content, phosphorus content, potassium content, calcium content and magnesium content in soil in a planting sub-area and temperature and humidity in the soil corresponding to each soil depth grade to the display terminal;
the display terminal is used for receiving and displaying an agricultural product type growth hindering influence coefficient, an agricultural product quality comprehensive estimation reaction coefficient, illumination time corresponding to each illumination intensity level corresponding to the agricultural product, nitrogen content, phosphorus content, potassium content, calcium content and magnesium content in soil in a planting sub-area and temperature and humidity in the soil corresponding to each soil depth level, wherein the agricultural product type growth hindering influence coefficient corresponds to each agricultural product type in each growth stage and is sent by the cloud server.
Further, the data repository stores various agricultural product species from planting to harvest including T1, T2, T3, T4, T5, T6 growth stages, T1, T2, T3, T4, T5, T6 growth stages denoted as seed germination stage, shoot development stage, pre-growth stage, mid-growth stage, post-growth stage and maturation stage, respectively.
Further, the image enhancement processing is image gray scale stretching processing, namely the image enhancement processing adopts the formula
Figure BDA0002174522950000081
x is expressed as the pixel value before image enhancement processing, x' is expressed as the pixel value after image enhancement processing of the corresponding pixel point, JmaxExpressed as the maximum pixel value, J, in the normalized rectangular regionminExpressed as the smallest pixel value within the normalized rectangular area.
Further, the growth inhibition influence coefficient of the agricultural product species corresponding to each growth stage
Figure BDA0002174522950000082
R is agricultural product species, lambda is illumination intensity influence coefficient, and 1, 58 and R are takentThe threshold value is expressed as a preset light intensity level threshold value in the tth growth stage, T is T1, T2, T3, T4, T5, T6 and TIRRepresenting the illumination time corresponding to the R-th illumination intensity level which is greater than or equal to the preset illumination intensity level threshold, wherein R is equal to R1, R2, R3, R4, delta ahvExpressed as the comparative difference between the content of hv element and the standard element content range corresponding to this growth phase, ghvt is expressed as a growth influence proportion weight coefficient corresponding to hv element in the tth growth stage, and hv is equal to h1, · hv,. ·, h5, h1,... h, hv,. a.. h, h5 are respectively expressed as N, P, K, Ca, Mg, ahvmaxExpressed as the upper limit content, a, of the content range of the hv elementhvminExpressed as the lower limit content, X, in the range of the content of hv elementsWfExpressed as the comparison between the soil temperature corresponding to the Wf th soil depth level and the standard soil temperature range corresponding to the Wf th soil depth level, LWfThe comparison between the soil humidity corresponding to the Wf-th soil depth grade and the soil standard humidity range corresponding to the Wf-th soil depth grade is shown, wherein Wf is W1, W2, W3 and W4.
Further, the quality of the agricultural products is comprehensively estimated to obtain the reaction coefficient
Figure BDA0002174522950000091
ξ is represented by insect pest influence factor, 0.6 is taken when there is insect pest, 0.95 is taken when there is no insect pest, Q is represented by leaf color grade of agricultural product in the collected image, and Q is equal to Q1, Q2, Q3, QPreset ofExpressing the preset leaf color grade threshold value corresponding to the agricultural product type,
Figure BDA0002174522950000092
expressed as the growth inhibition influence coefficient, TI, corresponding to the r-th agricultural product species at the t-th growth stageRExpressed as illumination time, TI, corresponding to the R-th illumination intensity levelR is presetAnd expressing the illumination time corresponding to the preset R-th illumination intensity level.
The planting device further comprises a region dividing module, wherein the region dividing module is used for dividing a region to be planted into a plurality of planting sub-regions according to the types of planted agricultural products, the divided planting sub-regions are numbered sequentially from left to right, and are respectively 1,2,. fara, j,. fara, n, n represents the number of the planting sub-regions, j represents the jth planting sub-region, and each planting sub-region only plants a single type of agricultural product.
The invention has the beneficial effects that:
compared with the prior art, the agricultural product planting environment detection system based on the big data provided by the invention has the advantages that the images of agricultural product plants in the planting sub-area are collected, the collected images are screened and normalized, the time and the task amount required by image analysis are reduced by all target images, the normalized images are subjected to plant leaf feature extraction, the extracted plant leaf features are compared with the standard leaf features corresponding to all the agricultural product types by the cloud server, the agricultural product types corresponding to the collected leaf features are screened out, the identified agricultural product types are compared with the agricultural product types planted in the planting sub-area input by the species type input module, whether the identified agricultural product types are input agricultural product types is judged, the agricultural product types are determined, and the error rate caused by manual input of the agricultural product types is reduced, and a foundation is laid for later-stage statistics of the growth conditions of agricultural products in each growth stage in the planting process.
The invention collects nitrogen content, phosphorus content, potassium content, calcium content and magnesium content in soil and temperature and humidity corresponding to each soil depth through a soil detection module, collects illumination intensity of agricultural products, illumination intensity grade corresponding to the illumination intensity and illumination time corresponding to each illumination intensity grade through an environment detection and analysis module, combines a cloud server through the soil detection module and the environment detection and analysis module, counts the growth inhibition influence coefficient of agricultural product types corresponding to each agricultural product in a growth stage according to the element content in the soil, the temperature and humidity corresponding to each soil depth and the illumination time of the agricultural products in each illumination intensity grade, can intuitively evaluate the influence of each element content, temperature and humidity and illumination in the current soil on the growth of each growth stage of the agricultural products, and provides reliable reference data for later-stage comprehensive evaluation of the growth of the agricultural products, the method has the characteristic of high detection accuracy, and in addition, the planting environment of the agricultural products is detected, and is artificially controlled according to the soil element content, the temperature, the humidity and the illumination intensity required by each growth stage of the agricultural products, so that the growth of the agricultural products is promoted, and the yield and the quality of the agricultural products are greatly improved.
According to the invention, the cloud server comprehensively evaluates the comprehensive quality estimation reaction coefficient of the agricultural products through the agricultural product type growth obstruction influence coefficient corresponding to each growth stage of the agricultural products and combining with whether insect damage occurs or not, the leaf color of agricultural product plants and the time corresponding to each illumination intensity level, the growth condition of the agricultural products in the whole growth process is visually displayed through the comprehensive quality estimation reaction coefficient of the agricultural products, the quality of the agricultural products can be estimated, the cloud server has the characteristic of high accuracy, a reliable basis is provided for stable agricultural product quality planted in the later period, digital display of the agricultural products is conveniently realized, guiding reference data is provided for planting of each agricultural product by planting personnel in the later period, the quality of the agricultural products is conveniently improved, the development of the agricultural products is promoted, and meanwhile, the quality of the products can be estimated according to the environmental parameters in.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic diagram of a big data-based agricultural product planting environment detection system according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a big data-based agricultural product planting environment detection system includes a region division module, a species type input module, a soil detection module, an environment detection analysis module, an image acquisition module, a screening processing module, a feature extraction module, a data storage library, a cloud server, and a display terminal;
the cloud server is respectively connected with the soil detection module, the environment detection and analysis module, the image acquisition module, the screening processing module, the feature extraction module, the data storage library and the display terminal, the data storage library is respectively connected with the species type input module and the environment detection and analysis module, and the screening processing module is respectively connected with the image acquisition module and the feature extraction module.
The area dividing module is used for dividing an area to be planted into a plurality of planting sub-areas according to the types of planted agricultural products, numbering the various planting sub-areas in sequence from left to right, wherein the various planting sub-areas are respectively 1,2,. the.,. the.n, and the n are expressed as the number of the planting sub-areas, and j is expressed as the jth planting sub-area, and each planting sub-area only plants a single type of agricultural products;
dividing the soil depth into a plurality of soil depth levels, namely W1, W2, W3 and W4, wherein each soil level corresponds to different soil depths, and the soil depths corresponding to the soil depth levels are 0-12cm, 12-24cm, 24-36cm and 36-48cm respectively.
The species type input module is used for inputting types of agricultural products planted in various planting subareas, establishing corresponding connection relations between the types of the planted agricultural products and the numbers corresponding to the various planting subareas, and sending the numbers of the various planting subareas and the types of the agricultural products planted in the planting subareas to the data storage library;
the soil detection module comprises a plurality of soil detection devices and temperature and humidity detection devices, the soil detection devices are respectively installed in various plant subareas and used for detecting nitrogen content, phosphorus content, potassium content, calcium content and magnesium content in soil in the various plant subareas and sending the detected nitrogen content, phosphorus content, potassium content, calcium content and magnesium content to the cloud server, the temperature and humidity detection devices are temperature and humidity sensors which are respectively installed in soil corresponding to various soil depth levels in the various plant subareas and used for detecting temperature and humidity in the soil corresponding to different soil depth levels in the various plant subareas in a fixed time period and sending the detected temperature and humidity in the soil corresponding to the various soil depth levels in the various plant subareas to the cloud server;
the environment detection and analysis module is used for detecting the illumination intensity in the planting area in real time, comparing the detected illumination intensity with illumination intensity ranges corresponding to different illumination intensity grades stored in the data repository, screening out the illumination intensity grade corresponding to the illumination intensity, counting the illumination time corresponding to each illumination intensity grade according to the illumination intensity grade corresponding to the illumination intensity, and sending each counted illumination intensity grade and the illumination time corresponding to each illumination intensity grade to the cloud server;
the image acquisition module is used for acquiring images of plants planted in various plant regions and respectively sending the acquired images in the various plant regions to the cloud server and the screening processing module;
the image acquisition module comprises a plurality of image acquisition units, the image acquisition units are numbered, the numbers corresponding to the image acquisition units are consistent with the numbers in the planting subareas where the image acquisition units are located, the image acquisition units are high-definition cameras and are respectively installed in various planting subareas, the number of the high-definition cameras installed in each planting subarea is the same, and the image acquisition units are used for acquiring the image information of plant leaves in various planting subareas and respectively sending the image information of the plant leaves acquired by the cameras in the various planting subareas to the screening processing module and the cloud server;
the screening processing module is used for receiving plant image information acquired by the cameras in various plant areas sent by the image acquisition module, screening the received plant images by using various different rectangular screening frames, extracting the smallest rectangle capable of wrapping the plant leaves, and removing image cutting outside the rectangular area so as to remove images irrelevant to the leaf images and reduce the difficulty and workload of extracting features of the whole acquired image; and scaling the image of the remaining rectangular area in the X direction to fxScaling by f in the Y directionyNormalizing the images to the same image size, performing image enhancement processing on the images after the normalization processing, and finally respectively sending the images after the image enhancement processing to a feature extraction module and a cloud server;
wherein, the image enhancement processing is image gray scale stretching processing, namely, the formula adopted by the image enhancement processing is
Figure BDA0002174522950000131
x is expressed as the pixel value before image enhancement processing, x' is expressed as the pixel value after image enhancement processing of the corresponding pixel point, JmaxExpressed as the maximum pixel value, J, in the normalized rectangular regionminExpressed as the smallest pixel value within the normalized rectangular area.
The feature extraction module is used for receivingDividing the image subjected to image enhancement processing and sent by the screening processing module into a plurality of sub-images with the same area, numbering the sub-images according to a set sequence, wherein the number of the sub-images is 1,2, 1, i, m, extracting the characteristics of plant leaves in the sub-images, and forming a leaf characteristic set β by the extracted characteristics corresponding to the sub-imagesji(βji1,βji2,...,βjik,...,βjiN)，βjik represents the kth leaf feature in the ith sub-image in the image acquired for the jth seed sub-region, N represents the number of leaf features in each sub-image, and the extracted leaf feature set β isjiSending the data to a cloud server;
the data storage library is used for storing serial numbers corresponding to various planting sub-regions and agricultural product types planted in the planting sub-regions, storing standard blade images corresponding to different agricultural product types and standard blade features corresponding to the standard blade images, and forming a standard blade feature set S by the standard blade features corresponding to various agricultural product typesr(sr1,sr2,...,srv)，srv is expressed as the v standard leaf characteristic corresponding to the r agricultural product species, and the standard leaf characteristic set SrThe weight coefficients corresponding to the standard blade features are gs respectivelyr1,gsr2,...,gsrv，gsrv is expressed as a weight coefficient of the v standard leaf feature corresponding to the r agricultural product species, and gsr1+gsr2+...+gsrv is 1, and is used for storing illumination intensity ranges corresponding to different illumination intensity levels, illumination intensity level thresholds corresponding to each growth stage and time thresholds corresponding to the illumination intensity levels corresponding to each growth stage, the illumination intensity levels are sorted from low to high and are respectively R1, R2, R3 and R4, the illumination intensity ranges corresponding to R1, R2, R3 and R4 are sequentially increased, and the requirements of different agricultural product types on the standard humidity ranges and the standard temperature ranges of the soil depths in different growth stages are stored, wherein the growth stages of the agricultural product types from planting to harvesting comprise T1, T2, T3, T4, T5 and T6, T1, T2, T3, T4, T5 and T6 are respectively expressed as seed germinationA germination stage, a bud development stage, a prophase growth stage, a metaphase growth stage, a anaphase growth stage and a maturation stage;
in addition, the storage database stores standard nitrogen content ranges, phosphorus content ranges, potassium content ranges, calcium content ranges and magnesium content ranges required by soil of various agricultural product types in various growth stages, and stores the weight coefficients of growth influence ratios of the nitrogen content, the phosphorus content, the potassium content, the calcium content and the magnesium content on various agricultural products in various growth stages, wherein the weight coefficients are gNt,gPt,gKt,gCat,gMgt，gNT is expressed as a growth influence ratio weight coefficient corresponding to nitrogen element in the tth growth stage, and similarly, T is T1, T2, T3, T4, T5, T6, and gNt+gPt+gKt+gCat+gMgt is 1, the leaf colors corresponding to the varieties of the agricultural products and the leaf color grades corresponding to the leaf colors are stored, the plant leaf color grades corresponding to the same agricultural products are respectively Q1, Q2, Q3, Q1, Q2 and Q3, the leaf color grades are sequentially increased, and the higher the leaf color grade is, the more the leaf color corresponding to the leaf color grade is similar to the leaf color of the agricultural product with sufficient nutrition;
the data storage library also stores the numbers in the planting sub-areas and the agricultural product types in the various planting sub-areas, and stores sowing dates and current dates of the agricultural products in the various planting sub-areas and time ranges corresponding to the agricultural product types in the growth stages;
the cloud server is used for receiving the blade feature set β sent by the feature extraction modulejiAnd collecting β leaf feature sets in each sub-image corresponding to the agricultural products in the collected planting sub-areajiObtaining a comparison leaf feature set delta S corresponding to the standard leaf feature set stored in the data storage libraryr(Δsr1,Δsr2,...,Δsrv)，Δsrv is expressed as the comparison condition of the v standard leaf characteristic corresponding to the r agricultural product species and the leaf characteristic in each sub-image in the collected planting sub-area, if the v standard leaf characteristic corresponding to the r agricultural product species exists in the leaf characteristic set in each sub-imageIf yes, take Δ srv is equal to a fixed constant which is more than 1, if the characteristic set of the blades in each acquired sub-image does not have the v standard blade characteristic corresponding to the r agricultural product species, the value of deltas is takenrv is equal to 0, the goodness of fit coefficient between the agricultural products and various agricultural product types in the collected planting sub-area is counted according to the comparison blade feature set, and the calculation formula of the goodness of fit coefficient of the agricultural product types is
Figure BDA0002174522950000151
Δsrv is expressed as the comparison of the characteristic of the v standard leaf corresponding to the r agricultural product species with the characteristic of the leaf in each sub-image in the collected planting sub-area, gsrv is expressed as a weight coefficient of a v standard blade characteristic corresponding to an r agricultural product species, an agricultural product type corresponding to a maximum goodness of fit coefficient is screened out, a collected number corresponding to a planting subregion is extracted, an agricultural product type corresponding to the planting subregion number in a data storage library is extracted according to the planting subregion number, the extracted agricultural product type is compared with the agricultural product type corresponding to the maximum goodness of fit coefficient, if the extracted agricultural product type is the same as the agricultural product type corresponding to the maximum goodness of fit coefficient, the agricultural product type planted in the planting subregion is correct, if the extracted agricultural product type is different from the agricultural product type corresponding to the maximum goodness of fit coefficient, the agricultural product type planted in the planting subregion is not matched with the agricultural product type actually planted, and the agricultural product type corresponding to the maximum goodness of fit coefficient is substituted for the agricultural product type planted in various planting subregions in the data storage library, ensuring that the types of agricultural products planted in the planting sub-area are consistent with the types of agricultural products identified by the characteristics;
the method comprises the steps of comparing the characteristics of the leaf image corresponding to the collected agricultural product types with the standard leaf characteristics in the standard leaf image corresponding to each agricultural product type to screen out the agricultural product types planted in the planting subarea, and comparing the agricultural product types with the input agricultural product types planted in the planting subarea, so that the agricultural product types are determined, and a foundation is laid for later counting the growth conditions of the agricultural products in the planting process for judging the growth stages.
The cloud server is used for receiving the image information of the plant leaves in various plant regions sent by the image acquisition module, comparing the received image information of the plant leaves with the leaf colors corresponding to the leaf color grades of the agricultural products stored in the data storage library, and extracting the leaf color grades corresponding to the similar leaf colors; the cloud server extracts sowing time, current date and time corresponding to each growth stage of agricultural products in various planting sub-areas in the storage database, judges the growth stage corresponding to the agricultural product variety planted in various planting sub-areas according to the sowing time, current date and time corresponding to each growth stage of the agricultural products in various planting sub-areas, extracts standard nitrogen content range, phosphorus content range, potassium content range, calcium content range and magnesium content range corresponding to the growth stage of the agricultural products in various planting sub-areas and temperature and humidity range corresponding to each soil depth, and is used for receiving nitrogen content, phosphorus content, potassium content, calcium content and magnesium content in soil of various planting sub-areas and temperature and humidity in soil corresponding to different soil depth levels sent by the soil detection module, and enables the received nitrogen content, phosphorus content, potassium content, calcium content and magnesium content in the soil to be, The phosphorus content, the potassium content, the calcium content and the magnesium content sequentially form a soil element content set A (a)N,aP,aK,aCa,aMg)，aNExpressed as the nitrogen content in the soil, aPExpressed as the phosphorus content in the soil, aKExpressed as potassium content in the soil, aCaExpressed as the calcium content in the soil, aMgThe content is expressed as the magnesium content in the soil, the cloud server compares the received nitrogen content, phosphorus content, potassium content, calcium content and magnesium content in the soil with a standard nitrogen content range, a standard phosphorus content range, a standard potassium content range, a standard calcium content range and a standard magnesium content range corresponding to the current growth stage respectively to obtain a soil element content comparison set delta A (delta a)N,ΔaP,ΔaK,ΔaCa,ΔaMg)，ΔaNExpressed as the difference between the nitrogen content in the soil and the standard nitrogen content range corresponding to this growth phase, Δ aPExpressed as the difference between the phosphorus content in the soil and the standard range of phosphorus content corresponding to that growth phase, Δ aKExpressed as the difference between the potassium content in the soil and the standard potassium content range corresponding to that growth phase, Δ aCaExpressed as the difference between the calcium content in the soil and the standard calcium content range corresponding to this growth phase, Δ aMgExpressed as the difference between the magnesium content in the soil and the standard magnesium content range corresponding to the growth phase;
if the nitrogen content detected in the growth stage exceeds the upper limit nitrogen content in the standard nitrogen content range corresponding to the growth stage, comparing the nitrogen content with the difference value delta aNEqual to the difference between the upper nitrogen content in the standard nitrogen content range and the detected nitrogen content, and comparing the nitrogen content with the difference delta a if the detected nitrogen content in the growth phase is less than the lower nitrogen content in the standard nitrogen content range corresponding to the growth phaseNIs equal to the difference between the detected nitrogen content and the lower nitrogen content in the standard nitrogen content range, if the detected nitrogen content in the growth phase is in the standard nitrogen content range corresponding to the growth phase, the nitrogen content is compared with the difference delta aNEqual to 0; if the phosphorus content detected in the growth stage exceeds the upper limit phosphorus content in the standard phosphorus content range corresponding to the growth stage, comparing the phosphorus content with the difference value delta aPEqual to the difference between the upper limit phosphorus content in the standard phosphorus content range and the detected phosphorus content, and if the phosphorus content detected in the growth stage is less than the lower limit phosphorus content in the standard phosphorus content range corresponding to the growth stage, comparing the phosphorus content with the difference delta aPIs equal to the difference between the detected phosphorus content and the lower limit phosphorus content in the standard phosphorus content range, if the phosphorus content detected in the growth stage is in the standard phosphorus content range corresponding to the growth stage, the phosphorus content is compared with the difference delta aPEqual to 0, wherein the potassium content contrasts with the difference DeltaaKCalcium content comparison difference Δ aCaAnd Δ aMgMethod for calculating difference between magnesium content and nitrogen content respectivelyNDifference Δ a in comparison with phosphorus contentPThe calculation method is the same.
The cloud server receives the soil corresponding to different soil depth gradesThe temperature and the humidity in the data base are respectively compared with a standard humidity range and a standard temperature range corresponding to the soil depth grade corresponding to the growth stage in the data base to obtain a soil depth grade parameter comparison set B (X)W1,XW2,XW3,XW4,LW1,LW2,LW3,LW4)，XWfExpressed as the comparison between the soil temperature corresponding to the Wf th soil depth level and the standard soil temperature range corresponding to the Wf th soil depth level, LWfShowing the comparison condition between the soil humidity corresponding to the Wf-th soil depth grade and the soil standard humidity range corresponding to the Wf-th soil depth grade, wherein Wf is W1, W2, W3 and W4, and if the soil temperature corresponding to the Wf-th soil depth grade is in the soil standard temperature range corresponding to the Wf-th soil depth grade, taking XWfEqual to 0, if the soil temperature corresponding to the Wf-th soil depth grade is not in the soil standard temperature range corresponding to the Wf-th soil depth grade, XWfEqual to the absolute value of the difference between the average values of the upper limit temperature and the lower limit temperature in the soil temperature corresponding to the Wf-th soil depth grade and the soil standard temperature range corresponding to the Wf-th soil depth grade, and if the soil humidity corresponding to the Wf-th soil depth grade is in the soil humidity range corresponding to the Wf-th soil depth grade, taking X as the soil humidityWfEqual to 0, if the soil humidity corresponding to the Wf-th soil depth level is not in the soil standard humidity range corresponding to the Wf-th soil depth level, XWfThe absolute value of the difference value between the soil humidity corresponding to the Wf-th soil depth grade and the average value of the sum of the upper limit humidity and the lower limit humidity in the soil standard humidity range corresponding to the Wf-th soil depth grade is equal to or greater than the absolute value of the difference value between the upper limit humidity and the average value of the sum of the lower limit humidity in the soil standard humidity range corresponding to the Wf-;
the cloud server receives each illumination intensity grade and illumination time corresponding to each illumination intensity grade sent by the environment detection and analysis module, compares each received illumination intensity grade with a preset illumination intensity grade threshold corresponding to each growth stage, counts the illumination time of each illumination intensity grade more than or equal to the illumination intensity grade threshold, and collects the content contrast set delta A of the soil elements corresponding to each growth stage and the depth of the soil according to the content contrast set delta A of the soil elements corresponding to each growth stageThe grade parameter comparison set B predicts the illumination time of each illumination intensity grade which is more than or equal to the illumination intensity grade threshold value, and counts the growth inhibition influence coefficient of the agricultural product variety corresponding to each growth stage
Figure BDA0002174522950000181
R is agricultural product species, lambda is illumination intensity influence coefficient, and 1, 58 and R are takentThe threshold value is expressed as a preset light intensity level threshold value in the tth growth stage, T is T1, T2, T3, T4, T5, T6 and TIRRepresenting the illumination time corresponding to the R-th illumination intensity level which is greater than or equal to the preset illumination intensity level threshold, wherein R is equal to R1, R2, R3, R4, delta ahvExpressed as the comparative difference between the content of hv element and the standard element content range corresponding to this growth phase, ghvt is expressed as a growth influence proportion weight coefficient corresponding to hv element in the tth growth stage, and hv is equal to h1, · hv,. ·, h5, h1,... h, hv,. a.. h, h5 are respectively expressed as N, P, K, Ca, Mg, ahvmaxExpressed as the upper limit content, a, of the content range of the hv elementhvmin is expressed as the lower limit content in the content range of hv element, XWfExpressed as the comparison between the soil temperature corresponding to the Wf th soil depth level and the standard soil temperature range corresponding to the Wf th soil depth level, LWfThe comparison between the soil humidity corresponding to the Wf-th soil depth level and the soil standard humidity range corresponding to the Wf-th soil depth level is shown, wherein Wf is W1, W2, W3 and W4, and the larger the influence coefficient of growth inhibition of agricultural product species is, the larger the inhibition of growth of agricultural product planting is shown.
The cloud server evaluates the quality comprehensive estimation reaction coefficient of the agricultural product according to the growth inhibition influence coefficient of the agricultural product type corresponding to each growth stage and by combining the leaf color grade corresponding to the agricultural product type
Figure BDA0002174522950000191
ξ is represented by insect pest influence factor, 0.6 is taken when there is insect pest, 0.95 is taken when there is no insect pest, Q is represented by leaf color grade of agricultural product in the collected image, and Q is equal to Q1, Q2, Q3, QPreset ofThe color of the leaves is expressed as the preset corresponding color of the agricultural productThe level of the threshold value is set to be,
Figure BDA0002174522950000192
expressed as the growth inhibition influence coefficient, TI, corresponding to the r-th agricultural product species at the t-th growth stageRExpressed as illumination time, TI, corresponding to the R-th illumination intensity levelR is presetThe lighting time corresponding to the preset Rth lighting intensity level is represented, the quality comprehensive estimation reaction coefficient of the agricultural products is larger, the quality of the agricultural products is better when the agricultural products are harvested, the statistical growth blocking influence coefficient of the agricultural product types corresponding to the agricultural product types in each growth stage and the quality comprehensive estimation reaction coefficient of the agricultural products are sent to the display terminal, and meanwhile, the cloud server sends the received lighting time corresponding to each lighting intensity level corresponding to each agricultural product, the nitrogen content, the phosphorus content, the potassium content, the calcium content and the magnesium content in the soil and the temperature and the humidity in the soil corresponding to different soil depth levels to the display terminal.
The display terminal is used for receiving the growth hindering influence coefficient of the agricultural product types corresponding to the agricultural product types in each growth stage sent by the cloud server, the comprehensive pre-estimation reaction coefficient of the quality of the agricultural product, the illumination time corresponding to each illumination intensity level corresponding to the agricultural product, the nitrogen content, the phosphorus content, the potassium content, the calcium content and the magnesium content in soil in a planting sub-area and the temperature and the humidity in the soil corresponding to different soil depth levels, displaying the result, facilitating planting management personnel to visually know the influence of the planting environment on the agricultural product, and counting the influence of each growth stage on the plant growth of the planting environment by detecting the planting environment of the agricultural product.
The foregoing is merely exemplary and illustrative of the principles of the present invention and various modifications, additions and substitutions of the specific embodiments described herein may be made by those skilled in the art without departing from the principles of the present invention or exceeding the scope of the claims set forth herein.

Claims (4)

1. The utility model provides an agricultural product planting environment detecting system based on big data which characterized in that: the system comprises a species type input module, a soil detection module, an environment detection and analysis module, an image acquisition module, a screening processing module, a feature extraction module, a data storage library, a cloud server and a display terminal;
the cloud server is respectively connected with the soil detection module, the environment detection and analysis module, the image acquisition module, the screening processing module, the feature extraction module, the data storage library and the display terminal, the data storage library is respectively connected with the species type input module and the environment detection and analysis module, and the screening processing module is respectively connected with the image acquisition module and the feature extraction module;
the species type input module is used for inputting types of agricultural products planted in various planting sub-regions, establishing corresponding connection relations between the types of the planted agricultural products and numbers corresponding to the various planting sub-regions, and sending the numbers of the various planting sub-regions and the types of the agricultural products planted in the planting sub-regions to the data storage library;
the soil detection module comprises a plurality of soil detection devices and temperature and humidity detection devices, the soil detection devices are respectively installed in various plant subareas and used for detecting nitrogen content, phosphorus content, potassium content, calcium content and magnesium content in soil in the various plant subareas and sending the detected nitrogen content, phosphorus content, potassium content, calcium content and magnesium content to the cloud server, the temperature and humidity detection devices are temperature and humidity sensors which are respectively installed in soil corresponding to various soil depth levels in the various plant subareas and used for detecting temperature and humidity in the soil corresponding to different soil depth levels in the various plant subareas in a fixed time period and sending the detected temperature and humidity in the soil corresponding to the various soil depth levels in the various plant subareas to the cloud server;
the environment detection and analysis module is used for detecting the illumination intensity in the planting area in real time, comparing the detected illumination intensity with illumination intensity ranges corresponding to different illumination intensity grades stored in the data storage library, screening out the illumination intensity grade corresponding to the illumination intensity, counting the illumination time corresponding to each illumination intensity grade according to the illumination intensity grade corresponding to the illumination intensity, and sending the counted illumination intensity grade and the illumination time corresponding to each illumination intensity grade to the cloud server;
the image acquisition module is used for acquiring images of plants planted in various plant regions and respectively sending the acquired images in the various plant regions to the cloud server and the screening processing module;
the image acquisition module comprises a plurality of image acquisition units, the image acquisition units are numbered, the numbers corresponding to the image acquisition units are consistent with the numbers in the planting subareas where the image acquisition units are located, the image acquisition units are high-definition cameras and are respectively installed in the various planting subareas, the number of the high-definition cameras installed in each planting subarea is the same, and the image acquisition units are used for acquiring the image information of plant leaves in the various planting subareas and respectively sending the image information of the plant leaves acquired by the cameras in the various planting subareas to the screening processing module and the cloud server;
the screening processing module is used for receiving plant image information acquired by the cameras in various plant areas sent by the image acquisition module, screening the received plant images by using various different rectangular screening frames, extracting the smallest rectangle capable of wrapping the plant leaves, and removing image cutting outside the rectangular area so as to remove images irrelevant to the leaf images and reduce the difficulty and workload of extracting features of the whole acquired image; and scaling the image of the remaining rectangular area in the X direction to fxScaling by f in the Y directionyNormalizing the images to the same image size, performing image enhancement processing on the images after the normalization processing, and finally respectively sending the images after the image enhancement processing to a feature extraction module and a cloud server;
the characteristic extraction module is used for receiving the image which is sent by the screening processing module and subjected to image enhancement processing, dividing the received image into a plurality of sub-images with the same area, numbering the sub-images according to a set sequence, wherein the number of the sub-images is 1,2, 1And (4) constructing a leaf feature set β by using the features corresponding to the extracted sub-imagesji(βji1,βji2,...,βjik,...,βjiN)，βjik represents the kth leaf feature in the ith sub-image in the image acquired for the jth seed sub-region, N represents the number of leaf features in each sub-image, and the extracted leaf feature set β isjiSending the data to a cloud server;
the data storage library is used for storing serial numbers corresponding to various planting subareas and agricultural product types planted in the planting subareas, storing standard blade images corresponding to different agricultural product types and standard blade features corresponding to the standard blade images, and forming a standard blade feature set S by the standard blade features corresponding to various agricultural product typesr(sr1,sr2,...,srv)，srv is expressed as the v standard leaf characteristic corresponding to the r agricultural product species, and the standard leaf characteristic set SrThe weight coefficients corresponding to the standard blade features are gs respectivelyr1,gsr2,...,gsrv，gsrv is expressed as a weight coefficient of the v standard leaf feature corresponding to the r agricultural product species, and gsr1+gsr2+...+gsrv is 1, and is used for storing illumination intensity ranges corresponding to different illumination intensity levels, illumination intensity level thresholds corresponding to each growth stage and time thresholds corresponding to the illumination intensity levels corresponding to each growth stage, wherein the illumination intensity levels are sorted from low to high and are respectively R1, R2, R3 and R4, the illumination intensity ranges corresponding to R1, R2, R3 and R4 are sequentially increased, and the requirements of different agricultural product types on the standard humidity range and the standard temperature range of each soil depth at different growth stages are stored;
in addition, the storage database stores standard nitrogen content ranges, phosphorus content ranges, potassium content ranges, calcium content ranges and magnesium content ranges required by soil of various agricultural product types in various growth stages, and stores the weight coefficients of growth influence ratios of the nitrogen content, the phosphorus content, the potassium content, the calcium content and the magnesium content on various agricultural products in various growth stages, wherein the weight coefficients are gNt,gPt,gKt,gCat,gMgt，gNT is expressed as a growth influence proportion weight coefficient corresponding to nitrogen element in the tth growth stage, and in the same way, the growth stages of T ═ T1, T2, T3, T4, T5, T6, T1, T2, T3, T4, T5 and T6 are expressed as a seed germination stage, a bud development stage, a prophase growth stage, a metaphase growth stage, a anaphase growth stage and a maturation stage respectively, and g is expressed asNt+gPt+gKt+gCat+gMgt is 1, the leaf color corresponding to each agricultural product type and the leaf color grade corresponding to the leaf color are stored, and the leaf color grades corresponding to the plant leaf color grades of the same agricultural product are respectively Q1, Q2, Q3, Q1, Q2 and Q3 and are sequentially increased;
the data storage library also stores the numbers in the planting sub-areas and the agricultural product types in the various planting sub-areas, and stores sowing dates and current dates of the agricultural products in the various planting sub-areas and time ranges corresponding to the agricultural product types in the growth stages;
the cloud server is used for receiving the blade feature set β sent by the feature extraction modulejiAnd collecting β leaf feature sets in each sub-image corresponding to the agricultural products in the collected planting sub-areajiObtaining a comparison leaf feature set delta S corresponding to the standard leaf feature set stored in the data storage libraryr(Δsr1,Δsr2,...,Δsrv)，Δsrv is expressed as the comparison condition of the v standard blade feature corresponding to the r agricultural product species and the blade feature in each sub-image in the collected planting sub-area, if the v standard blade feature corresponding to the r agricultural product species exists in the blade feature set in each sub-image, the delta s is takenrv is equal to a fixed constant which is more than 1, if the characteristic set of the blades in each acquired sub-image does not have the v standard blade characteristic corresponding to the r agricultural product species, the value of deltas is takenrv is equal to 0, the goodness of fit coefficient between the agricultural products and various agricultural product types in the collected planting sub-area is counted according to the comparison blade feature set, and the calculation formula of the goodness of fit coefficient of the agricultural product types is
Figure FDA0002388773140000041
Δsrv is expressed as the comparison of the characteristic of the v standard leaf corresponding to the r agricultural product species with the characteristic of the leaf in each sub-image in the collected planting sub-area, gsrv is expressed as a weight coefficient of the characteristic of the v standard blade corresponding to the r agricultural product species, the agricultural product species corresponding to the maximum goodness of fit coefficient is screened out, the number corresponding to the collected planting subregion is extracted, extracting the agricultural product type corresponding to the planting subarea number in the data storage bank according to the planting subarea number, and comparing the extracted agricultural product type with the agricultural product type corresponding to the maximum goodness of fit coefficient, if the extracted agricultural product type is the same as the agricultural product type corresponding to the maximum goodness of fit coefficient, indicating that the types of the agricultural products planted in the planting subarea are correct, if the types of the extracted agricultural products are different from the types of the agricultural products corresponding to the maximum goodness of fit coefficient, it indicates that the types of agricultural products planted in the planting sub-area are not matched with the types of agricultural products actually planted, replacing agricultural product types planted in various planting sub-areas in the data storage library with the agricultural product types corresponding to the maximum goodness of fit coefficients;
the cloud server is used for receiving the image information of the plant leaves in various plant regions sent by the image acquisition module, comparing the received image information of the plant leaves with the leaf colors corresponding to the leaf color grades of the agricultural products stored in the data storage library, and extracting the leaf color grades corresponding to the similar leaf colors; the cloud server extracts sowing time, current date and time corresponding to each growth stage of agricultural products in various planting sub-areas in the storage database, judges the growth stage corresponding to the type of the agricultural products planted in various planting sub-areas according to the sowing time, the current date and the time corresponding to each growth stage of the agricultural products in various planting sub-areas, extracts standard nitrogen content range, phosphorus content range, potassium content range, calcium content range and magnesium content range corresponding to the growth stage of the agricultural products in various planting sub-areas and temperature and humidity range corresponding to each soil depth, and is used for receiving soil of various planting sub-areas sent by the soil detection moduleThe nitrogen content, the phosphorus content, the potassium content, the calcium content and the magnesium content in the received soil are sequentially formed into a soil element content set A (a) by the nitrogen content, the phosphorus content, the potassium content, the calcium content and the magnesium content in the received soil and the temperature and the humidity in the soil corresponding to different soil depth levelsN,aP,aK,aCa,aMg)，aNExpressed as the nitrogen content in the soil, aPExpressed as the phosphorus content in the soil, aKExpressed as potassium content in the soil, aCaExpressed as the calcium content in the soil, aMgThe content is expressed as the magnesium content in the soil, the cloud server compares the received nitrogen content, phosphorus content, potassium content, calcium content and magnesium content in the soil with a standard nitrogen content range, a standard phosphorus content range, a standard potassium content range, a standard calcium content range and a standard magnesium content range corresponding to the current growth stage respectively to obtain a soil element content comparison set delta A (delta a)N,ΔaP,ΔaK,ΔaCa,ΔaMg)，ΔaNExpressed as the difference between the nitrogen content in the soil and the standard nitrogen content range corresponding to this growth phase, Δ aPExpressed as the difference between the phosphorus content in the soil and the standard range of phosphorus content corresponding to that growth phase, Δ aKExpressed as the difference between the potassium content in the soil and the standard potassium content range corresponding to that growth phase, Δ aCaExpressed as the difference between the calcium content in the soil and the standard calcium content range corresponding to this growth phase, Δ aMgExpressed as the difference between the magnesium content in the soil and the standard magnesium content range corresponding to the growth phase;
the cloud server compares the received temperature and humidity in the soil corresponding to different soil depth levels with a standard humidity range and a standard temperature range corresponding to the soil depth level corresponding to the growth stage in the data repository respectively to obtain a soil depth level parameter comparison set B (X)W1,XW2,XW3,XW4,LW1,LW2,LW3,LW4)，XWfExpressed as the soil temperature corresponding to the Wf th soil depth level corresponds to the Wf th soil depth levelComparison between the soil standard temperature ranges, LWfShowing the comparison condition between the soil humidity corresponding to the Wf-th soil depth grade and the soil standard humidity range corresponding to the Wf-th soil depth grade, wherein Wf is W1, W2, W3 and W4;
the cloud server receives each illumination intensity grade and illumination time corresponding to each illumination intensity grade sent by the environment detection and analysis module, compares each received illumination intensity grade with a preset illumination intensity grade threshold corresponding to each growth stage, and counts the illumination time of each illumination intensity grade greater than or equal to the illumination intensity grade threshold, the cloud server predicts the illumination time of each illumination intensity grade greater than or equal to the illumination intensity grade threshold according to a soil element content comparison set delta A and a soil depth grade parameter comparison set B corresponding to each growth stage, and counts the growth blocking influence coefficient of the agricultural product variety corresponding to each growth stage, and the growth blocking influence coefficient of the agricultural product variety
Figure FDA0002388773140000071
R is expressed as agricultural product species, lambda is expressed as illumination intensity influence coefficient, and R is 1.58t threshold valueThe method is represented as a preset illumination intensity level threshold in the tth growth stage, wherein T is T1, T2, T3, T4, T5, T6, T1, T2, T3, T4, T5 and T6 growth stages are respectively represented as a seed germination stage, a bud development stage, a prophase growth stage, a metaphase growth stage, a anaphase growth stage and a maturation stage, and TI is represented as a growth stageRRepresenting the illumination time corresponding to the R-th illumination intensity level which is greater than or equal to the preset illumination intensity level threshold, wherein R is equal to R1, R2, R3, R4, delta ahvExpressed as the comparative difference between the content of hv element and the standard element content range corresponding to this growth phase, ghvt is expressed as a growth influence proportion weight coefficient corresponding to hv element in the tth growth stage, and hv is equal to h1, · hv,. ·, h5, h1,... h, hv,. a.. h, h5 are respectively expressed as N, P, K, Ca, Mg, ahvmaxExpressed as the upper limit content, a, of the content range of the hv elementhvminExpressed as the lower limit content, X, in the range of the content of hv elementsWfExpressed as the soil temperature corresponding to the Wf th soil depth grade and the Wf th soil depth grade pairComparison between the soil Standard temperature ranges, LWfShowing the comparison condition between the soil humidity corresponding to the Wf-th soil depth grade and the soil standard humidity range corresponding to the Wf-th soil depth grade, wherein Wf is W1, W2, W3 and W4;
the cloud server evaluates the comprehensive quality estimation reaction coefficient Πr of the agricultural products according to the growth inhibition influence coefficients of the agricultural product types corresponding to the growth stages and by combining the leaf color grades corresponding to the agricultural product types,
Figure FDA0002388773140000072
ξ is represented by insect pest influence factor, 0.6 is taken when there is insect pest, 0.95 is taken when there is no insect pest, Q is represented by leaf color grade of agricultural product in the collected image, and Q is equal to Q1, Q2, Q3, QPreset ofExpressing the preset leaf color grade threshold value corresponding to the agricultural product type,
Figure FDA0002388773140000073
expressed as the growth inhibition influence coefficient, TI, corresponding to the r-th agricultural product species at the t-th growth stageRExpressed as illumination time, TI, corresponding to the R-th illumination intensity levelR is presetRepresenting the illumination time corresponding to the preset R-th illumination intensity level;
the cloud server sends the counted growth hindering influence coefficient of the agricultural product types corresponding to the agricultural product types in each growth stage, the comprehensive quality pre-estimation reaction coefficient of the agricultural products, the illumination time of the agricultural products corresponding to each illumination intensity level, the nitrogen content, the phosphorus content, the potassium content, the calcium content and the magnesium content in the soil in the planting sub-area and the temperature and the humidity in the soil corresponding to each soil depth level to the display terminal;
the display terminal is used for receiving and displaying an agricultural product type growth hindering influence coefficient, an agricultural product quality comprehensive estimation reaction coefficient, illumination time corresponding to each illumination intensity level corresponding to the agricultural product, nitrogen content, phosphorus content, potassium content, calcium content and magnesium content in soil in a planting sub-area and temperature and humidity in the soil corresponding to each soil depth level, wherein the agricultural product type growth hindering influence coefficient corresponds to each agricultural product type in each growth stage and is sent by the cloud server.
2. The big-data-based agricultural product planting environment detection system according to claim 1, wherein: the data repository stores various agricultural product species from planting to harvest including T1, T2, T3, T4, T5, T6 growth stages, T1, T2, T3, T4, T5, T6 growth stages denoted as seed germination stage, shoot development stage, early growth stage, mid growth stage, late growth stage and maturity stage, respectively.
3. The big-data-based agricultural product planting environment detection system according to claim 1, wherein: the image enhancement processing is image gray scale stretching processing, namely the image enhancement processing adopts a formula of
Figure FDA0002388773140000081
x is expressed as the pixel value before image enhancement processing, x' is expressed as the pixel value after image enhancement processing of the corresponding pixel point, JmaxExpressed as the maximum pixel value, J, in the normalized rectangular regionminExpressed as the smallest pixel value within the normalized rectangular area.
4. A big data based agricultural product planting environment detection system according to any one of claims 1-3, wherein: the agricultural planting machine also comprises a region dividing module, wherein the region dividing module is used for dividing a region to be planted into a plurality of planting sub-regions according to the types of planted agricultural products, the divided planting sub-regions are numbered sequentially from left to right, and are respectively 1,2,. once, j,. once, n, wherein n represents the number of the planting sub-regions, j represents the jth planting sub-region, and each planting sub-region only plants a single type of agricultural product.
CN201910774185.4A 2019-08-21 2019-08-21 Agricultural product planting environment detection system based on big data Active CN110455340B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910774185.4A CN110455340B (en) 2019-08-21 2019-08-21 Agricultural product planting environment detection system based on big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910774185.4A CN110455340B (en) 2019-08-21 2019-08-21 Agricultural product planting environment detection system based on big data

Publications (2)

Publication Number Publication Date
CN110455340A CN110455340A (en) 2019-11-15
CN110455340B true CN110455340B (en) 2020-05-15

Family

ID=68488313

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910774185.4A Active CN110455340B (en) 2019-08-21 2019-08-21 Agricultural product planting environment detection system based on big data

Country Status (1)

Country Link
CN (1) CN110455340B (en)

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111340872B (en) * 2020-02-28 2021-02-19 苏州乐米凡电气科技有限公司 Analysis and treatment system and method for biomass solid waste
CN111279952B (en) * 2020-03-18 2021-10-12 嘉应学院 Water and fertilizer integrated management system based on cloud platform
CN111415205B (en) * 2020-03-26 2021-01-22 北京市建壮咨询有限公司 Building engineering cost evaluation system based on big data
CN111505010B (en) * 2020-04-28 2021-02-09 安徽伟达建设集团有限公司 Bridge safety detection system based on cloud platform
CN113570177A (en) * 2020-04-28 2021-10-29 徐锦麟 Quality determination system for agricultural products and method of using the same
CN111982187A (en) * 2020-06-23 2020-11-24 司梦实 Agricultural product planting environment safety situation monitoring system
CN112419356A (en) * 2020-12-08 2021-02-26 江苏科技大学 Method and device for detecting and recording planting growth of small trees in greenhouse
CN112913393B (en) * 2021-01-20 2023-01-03 中国农业机械化科学研究院 Crop sowing depth intelligent decision-making system, method, storage medium and equipment
CN113029984A (en) * 2021-03-13 2021-06-25 深圳市威视佰科科技有限公司 Soil monitoring method and device based on multi-channel spectral sensor
CN113327003B (en) * 2021-04-16 2022-05-20 蒲惠智造科技股份有限公司 Product quality assessment prediction system based on industrial big data
CN113850132A (en) * 2021-08-23 2021-12-28 湖北工程学院 Crop identification method, device, equipment and storage medium
CN113933299B (en) * 2021-10-12 2022-10-14 一鼎(福建)生态园林建设有限公司 Fruit and vegetable planting management system based on Internet of things
CN115034693B (en) * 2022-08-11 2022-11-15 深圳市宝安区石岩人民医院 Biological information data security management method, system and storage medium based on Internet of things
CN116228454A (en) * 2023-03-20 2023-06-06 广东七天牧草种养殖有限公司 Big data-based planting management control method, system and readable storage medium
CN117309881B (en) * 2023-10-07 2024-05-17 广东省农业科学院设施农业研究所 Fruit defect nondestructive detection method and system based on neural network

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019032648A1 (en) * 2017-08-08 2019-02-14 Indigo Ag, Inc. Machine learning in agricultural planting, growing, and harvesting contexts
CN109655108A (en) * 2018-12-28 2019-04-19 李清华 A kind of field planting real-time monitoring system and method based on Internet of Things
CN208862877U (en) * 2018-10-30 2019-05-14 北京点熠科技有限公司 A kind of long-range plant monitoring system based on bluetooth Yu NB-lot technology
CN109785179A (en) * 2019-03-15 2019-05-21 安徽新宇生态产业股份有限公司 A kind of intelligence park maintenance system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019032648A1 (en) * 2017-08-08 2019-02-14 Indigo Ag, Inc. Machine learning in agricultural planting, growing, and harvesting contexts
CN208862877U (en) * 2018-10-30 2019-05-14 北京点熠科技有限公司 A kind of long-range plant monitoring system based on bluetooth Yu NB-lot technology
CN109655108A (en) * 2018-12-28 2019-04-19 李清华 A kind of field planting real-time monitoring system and method based on Internet of Things
CN109785179A (en) * 2019-03-15 2019-05-21 安徽新宇生态产业股份有限公司 A kind of intelligence park maintenance system

Also Published As

Publication number Publication date
CN110455340A (en) 2019-11-15

Similar Documents

Publication Publication Date Title
CN110455340B (en) Agricultural product planting environment detection system based on big data
CN106971167B (en) Crop growth analysis method and system based on unmanned aerial vehicle platform
EP3482630B1 (en) Method, system and computer program for performing a pest forecast
WO2019081567A1 (en) Yield estimation in the cultivation of crop plants
CN111753646A (en) Agricultural pest detection and classification method fusing population season growth and elimination information
CN110110595A (en) A kind of farmland portrait and medicine hypertrophy data analysing method based on satellite remote-sensing image
CN115456476B (en) Homeland space planning data acquisition and analysis system based on machine vision
EP3528609A1 (en) Yield prediction for a cornfield
CN115294518B (en) Intelligent monitoring method and system for precise greenhouse cultivation of horticultural plants
CN113469112A (en) Crop growth condition image identification method and system
CN115392576A (en) Mushroom growth state space-time prediction method
CN116227758B (en) Agricultural product maturity prediction method and system based on remote sensing technology and deep learning
WO2021225528A1 (en) System and method for ai-based improvement of harvesting operations
CN117033810A (en) Agricultural data analysis management system and method based on big data
CN117036926A (en) Weed identification method integrating deep learning and image processing
CN118097422A (en) Agricultural environment monitoring and early warning method
CN118261488A (en) Intelligent management system based on digital farm
CN113377062B (en) Multifunctional early warning system with disease and pest damage and drought monitoring functions
CN116310806B (en) Intelligent agriculture integrated management system and method based on image recognition
CN117456523A (en) Crop type identification method and device, electronic equipment and medium
CN115438934A (en) Crop growth environment monitoring method and system based on block chain
CN110232345A (en) The program and weed identification device of weed identification model are generated using computer
CN114049297A (en) Carrot planting field intelligent detection method and system
CN116740651B (en) Edible fungus cultivation monitoring method and system based on intelligent decision
CN117789023B (en) Remote sensing identification system of crop planting structure

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
GR01 Patent grant
GR01 Patent grant