CN110332957A - Crop cultivation information processing system and method - Google Patents
Crop cultivation information processing system and method Download PDFInfo
- Publication number
- CN110332957A CN110332957A CN201910627439.XA CN201910627439A CN110332957A CN 110332957 A CN110332957 A CN 110332957A CN 201910627439 A CN201910627439 A CN 201910627439A CN 110332957 A CN110332957 A CN 110332957A
- Authority
- CN
- China
- Prior art keywords
- crop
- module
- information processing
- arviculture
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 20
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims abstract description 120
- 229910052757 nitrogen Inorganic materials 0.000 claims abstract description 60
- 238000012544 monitoring process Methods 0.000 claims abstract description 50
- 235000016709 nutrition Nutrition 0.000 claims abstract description 42
- 230000035764 nutrition Effects 0.000 claims abstract description 42
- 230000007613 environmental effect Effects 0.000 claims abstract description 25
- 239000002689 soil Substances 0.000 claims abstract description 20
- 241000607479 Yersinia pestis Species 0.000 claims abstract description 17
- 201000010099 disease Diseases 0.000 claims abstract description 16
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 16
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 238000005286 illumination Methods 0.000 claims abstract description 9
- 238000004519 manufacturing process Methods 0.000 claims description 32
- 235000015097 nutrients Nutrition 0.000 claims description 15
- 238000003672 processing method Methods 0.000 claims description 14
- 238000005259 measurement Methods 0.000 claims description 13
- 239000000243 solution Substances 0.000 claims description 13
- 238000001802 infusion Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 9
- 238000010790 dilution Methods 0.000 claims description 8
- 239000012895 dilution Substances 0.000 claims description 8
- 230000001419 dependent effect Effects 0.000 claims description 5
- 238000009313 farming Methods 0.000 claims description 5
- 239000007789 gas Substances 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- GWEVSGVZZGPLCZ-UHFFFAOYSA-N Titan oxide Chemical compound O=[Ti]=O GWEVSGVZZGPLCZ-UHFFFAOYSA-N 0.000 claims 2
- 241000208340 Araliaceae Species 0.000 claims 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 229910052799 carbon Inorganic materials 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 239000004408 titanium dioxide Substances 0.000 claims 1
- 238000003745 diagnosis Methods 0.000 abstract description 5
- 241000209140 Triticum Species 0.000 description 12
- 235000021307 Triticum Nutrition 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004445 quantitative analysis Methods 0.000 description 3
- 241000238631 Hexapoda Species 0.000 description 2
- 238000000540 analysis of variance Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 235000003715 nutritional status Nutrition 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000001228 trophic effect Effects 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 235000013339 cereals Nutrition 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 235000013348 organic food Nutrition 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01C—PLANTING; SOWING; FERTILISING
- A01C21/00—Methods of fertilising, sowing or planting
- A01C21/007—Determining fertilization requirements
-
- 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
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Soil Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Environmental Sciences (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention belongs to the technical field of crop cultivation information processing, and discloses a crop cultivation information processing system and method, which comprises the following steps: the system comprises a video monitoring module, an environmental data acquisition module, a nutrition detection module, a main control module, a timing module, a transfusion module, a watering module, an illumination module, a yield prediction module, a soil quality monitoring module, a pest and disease damage monitoring module and a display module. The accuracy of the nitrogen nutrition diagnosis result is obviously improved through the nutrition detection module; the method provided by the invention can be used for diagnosing the nitrogen only by utilizing the greenness and the coverage extracted from one crop canopy image, is simple and convenient in data acquisition, low in nitrogen diagnosis cost and high in speed, and can be used for acquiring the nitrogen nutrition condition of crops in real time under the natural light condition of a field; meanwhile, a crop growth situation detection and yield estimation model based on a sparse deep belief network is constructed through a yield prediction module, so that artificial subjective influence is eliminated as much as possible, and the prediction reliability and accuracy are improved.
Description
Technical field
The invention belongs to arviculture technical field of information processing more particularly to a kind of arviculture information processing systems
System and method.
Background technique
Currently, the immediate prior art: crops refer to one kind of the various plants agriculturally cultivated, biology, including grain
Eat Zuo Wu ﹑ industrial crops (oil crops, vegetable crop, flower, grass, trees) two major classes.Edible crops are that the mankind are basic
One of source of food.The growth of crops, the energy that the scientific and technological production technology and infant industry for be unableing to do without science manufacture
Assist the mechanical equipment of agricultural production.Purpose is to maximally utilise resource, reduces waste, reduces cost.Using pollution-free
Soil, waters and natural surroundings, or use Ecological Technique Measures, improve plantation water quality and ecological environment, according to reaching firm kind
Specific cropping pattern is planted to be planted, without using chemical fertilizer, pesticide and other harmful substances matter etc., target be produce it is nuisanceless green
Color food and organic food.Realize the component profitable probliotics stoste etc. of ecologic planting.However, existing arviculture information processing
System cannot carry out quantitative analysis to crop nitrogen nutrition situation;Meanwhile being unable to Accurate Prediction crop yield data.
In conclusion problem of the existing technology is: existing arviculture information processing system cannot be to crop nitrogen
Plain nutrition condition carries out quantitative analysis;Meanwhile being unable to Accurate Prediction crop yield data.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of arviculture information processing system and methods.
The invention is realized in this way a kind of arviculture information processing method, the arviculture information processing
Method includes:
The first step carries out video prison to arviculture information processing situation using image pick-up device by video monitoring module
Control;By environmental data collecting module using sensor acquire the temperature of arviculture information processing environment, humidity, illumination,
Gas concentration lwevel data;Crop nitrogen nutrition status data is detected using detector by Nutrition monitoring module;
Second step, main control module utilize timer setting conveying nutrient solution, watering time by timing module;Pass through infusion
Module is operated using delivery pipe conveying nutrient solution;Watering operation is carried out to crop using sprinkler by watering module;Pass through photograph
Bright module carries out lighting operation to arviculture information processing using headlamp;
Third step predicts crop yield data by production forecast module;It is supervised by soil property monitoring modular using detector
Survey the content of nitrogen in soil;Whether there is pest and disease damage using detector monitors crops by pest and disease monitoring module;
4th step shows monitor video using display by display module, environmental data, crop nutrient data, produces
Measure prediction data information.
Further, the arviculture information processing method detects crop nitrogen nutrition status data side using detector
Method is as follows:
(1) it is directed to each crop growing spots for respectively corresponding default different nitrogen nutrition by detector, is made based on actual measurement
The greenness index and covering angle value of object canopy image, to cover angle value as variable, greenness index is the critical nitrogen dilution of dependent variable for building
Model;Meanwhile surveying the crop leaf nitrogen concentration or SPAD value for obtaining crop to be measured;
(2) actual measurement obtains the greenness index of crop canopies image to be measured and covering angle value, the greenness index are preced with as crop to be measured
The green degree measured value of layer;And it calculates by critical Nitrogen Dilution Model according to the covering angle value and obtains greenness index, as work to be measured
The green degree calculated value of object canopy;
(3) the green degree measured value of crop canopies to be measured and the ratio of green degree calculated value are obtained, as crop nitrogen nutrition to be measured
Index NNI;
(4) according to the relationship of crop canopies to be measured green degree measured value and crop leaf nitrogen concentration or SPAD value, divide situation needle
Crop nitrogen nutrition index NNI to be measured is analyzed, crop N Nutrition to be measured is obtained.
Further, crop canopies image actual measurement obtains greenness index, includes the following steps:
Actual measurement obtains the crop leaf nitrogen concentration or SPAD value of crop, while crop canopies image update being converted to default
The crop canopies image in designated color space;
The color basic value of each pixel of canopy in crop canopies image is extracted, and obtains being averaged for corresponding each channel color
Value, and then obtain the mutual ratio of each channel color average;
By the ratio that the corresponding default each channel color average in designated color space of crop canopies image is mutual, Yi Jizuo
Object canopy image corresponds to the standardized value of each channel color in RGB color, and the multiple color for constituting crop canopies image is special
Levy parameter;
For the multiple color characteristic parameter of crop canopies image, select linear with crop leaf nitrogen concentration or SPAD value
A kind of Color characteristics parameters of relationship, the greenness index as the crop canopies image.
Further, the arviculture information processing method prediction crop yield data method is as follows:
1) environmental information is obtained according to crop growth environment information collection and pretreatment by Prediction program;
2) acquisition of crops own physiological physicochemical data and pretreatment, obtain physiological and biochemical property vector;
3) acquisition of crops leaf image and feature extraction: crops blade figure is acquired in real time using video monitoring equipment
Picture, then extracts mean value, deviation and the third-order matrix of tri- components of R, G, B of figure, then is normalized, and obtains image
Color characteristic;
4) Environmental Information Feature, physiological and biochemical property feature vector and the color of image obtained step 1) to step 3) is special
Value indicative forms the union feature vector of farming growth, according to crop growth and the historical data and changing rule of yield, building
The union feature vector data library of crop growth situation and yield;
5) crop growth situation detection and yield prediction model of the building based on sparse depth belief network;
6) building crop growth situation and yield obtained in contrast difference's fast learning algorithm and step 4) are utilized
Union feature vector data library, crop yield prediction model carry out pre-training and fine tuning, obtain Production Forecast Models;
7) to obtain Production Forecast Models carry out reliability test: building crop growth situation obtained in step 4 and
Union feature vector to be tested is input to training and the production finely tuned in step 6 in the union feature vector data library of yield
It measures in prediction model, calculates crop yield estimation results, estimation results are compared with actual production, if estimation results are inclined
Greater than actual production, then step 6) again is needed, adjustment is optimized to crop yield prediction model, repetition training is produced
Measure prediction model.
Another object of the present invention is to provide a kind of crops cultivations for executing the arviculture information processing method
Information processing system is trained, the arviculture information processing system includes:
Video monitoring module is connect with main control module, for by image pick-up device to arviculture information processing situation into
Row video monitoring;
Environmental data collecting module, connect with main control module, for acquiring arviculture information processing by sensor
Temperature, humidity, illumination, the gas concentration lwevel data of environment;
Nutrition monitoring module, connect with main control module, for detecting crop nitrogen nutrition status data by detector;
Main control module, with video monitoring module, environmental data collecting module, Nutrition monitoring module, timing module, infusion mould
Block, watering module, lighting module, production forecast module, display module connection are normal for controlling modules by main controller
Work;
Timing module is connect with main control module, for setting conveying nutrient solution, watering time by timer;
Infusion module is connect with main control module, for conveying nutrient solution operation by delivery pipe;
Watering module, connect, for carrying out watering operation to crop by sprinkler with main control module;
Lighting module is connect with main control module, for carrying out illumination behaviour to arviculture information processing by headlamp
Make;
Production forecast module, connect with main control module, for predicting crop yield data by Prediction program;
Soil property monitoring modular, connect with main control module, for the content by nitrogen in detector monitors soil;
Pest and disease monitoring module, connect with main module, for whether having pest and disease damage by detector monitors crops;
Display module is connect with main control module, for showing monitor video, environmental data, crop nutrition by display
Whether nitrogen content, crops have pest and disease damage, production forecast data information in prime number evidence, soil.
Another object of the present invention is to provide a kind of information datas using the arviculture information processing method
Processing terminal.
Advantages of the present invention and good effect are as follows: the present invention by Nutrition monitoring module to the green degree of crop and coverage into
The analysis of row Fusion Features, has comprehensively considered the nitrogen nutritional status under crop different growing stage or development condition, and can be to it
Quantitative analysis is carried out, the accuracy of Nitrogen Nutrition Diagnosis result is significantly improved;And method designed by the present invention, merely with one
The green degree and coverage extracted in crop canopies image, can carry out nitrogen diagnosis, and data acquisition is simple and convenient, nitrogen diagnosis
It is at low cost, speed is fast, the nitrogen nutritional status of crop can be obtained in real time under the conditions of the natural light of crop field;Meanwhile passing through yield
Prediction module according to environmental information, physiological and biochemical property vector sum color of image feature, form the union feature of farming growth to
Amount constructs the detection of crop growth situation and yield prediction model based on sparse depth belief network, excludes as far as possible artificial
Subjective impact improves predicting reliability and accuracy.
Detailed description of the invention
Fig. 1 is arviculture information processing system structural block diagram provided in an embodiment of the present invention;
In figure: 1, video monitoring module;2, environmental data collecting module;3, Nutrition monitoring module;4, main control module;5, fixed
When module;6, infusion module;7, watering module;8, lighting module;9, production forecast module;10, soil property monitoring modular;11, sick
Insect pest monitoring modular;12, display module.
Specific embodiment
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and cooperate attached drawing
Detailed description are as follows.
In view of the problems of the existing technology, the present invention provides a kind of arviculture information processing system and method,
The present invention is explained in detail with reference to the accompanying drawing.
As shown in Figure 1, arviculture information processing system provided in an embodiment of the present invention include: video monitoring module 1,
Environmental data collecting module 2, Nutrition monitoring module 3, main control module 4, timing module 5, infusion module 6, watering module 7, illumination
Module 8, production forecast module 9, soil property monitoring modular 10, pest and disease monitoring module 11, display module 12.
Video monitoring module 1 is connect with main control module 4, for passing through image pick-up device to arviculture information processing situation
Carry out video monitoring;
Environmental data collecting module 2 is connect with main control module 4, for being acquired at arviculture information by sensor
Manage temperature, humidity, illumination, the gas concentration lwevel data of environment;
Nutrition monitoring module 3 is connect with main control module 4, for detecting crop nitrogen nutrition status data by detector;
Main control module 4, with video monitoring module 1, environmental data collecting module 2, Nutrition monitoring module 3, timing module 5,
Infusion module 6, watering module 7, lighting module 8, production forecast module 9, display module 10 connect, for being controlled by main controller
Modules work normally;
Timing module 5 is connect with main control module 4, for setting conveying nutrient solution, watering time by timer;
Infusion module 6 is connect with main control module 4, for conveying nutrient solution operation by delivery pipe;
Watering module 7, connect, for carrying out watering operation to crop by sprinkler with main control module 4;
Lighting module 8 is connect with main control module 4, for being illuminated by headlamp to arviculture information processing
Operation;
Production forecast module 9 is connect with main control module 4, for predicting crop yield data by Prediction program;
Soil property monitoring modular 10 is connect with main control module 4, for the content by nitrogen in detector monitors soil;
Pest and disease monitoring module 11 is connect with main module 4, for whether having pest and disease damage by detector monitors crops;
Display module 12 is connect with main control module 4, for showing that monitor video, environmental data, crop are sought by display
Support prime number evidence, production forecast data information.
3 detection method of Nutrition monitoring module provided by the invention is as follows:
(1) it is directed to each crop growing spots for respectively corresponding default different nitrogen nutrition by detector, is made based on actual measurement
The greenness index and covering angle value of object canopy image, to cover angle value as variable, greenness index is the critical nitrogen dilution of dependent variable for building
Model;Meanwhile surveying the crop leaf nitrogen concentration or SPAD value for obtaining crop to be measured;
(2) actual measurement obtains the greenness index of crop canopies image to be measured and covering angle value, the greenness index are preced with as crop to be measured
The green degree measured value of layer;And it calculates by critical Nitrogen Dilution Model according to the covering angle value and obtains greenness index, as work to be measured
The green degree calculated value of object canopy;
(3) the green degree measured value of crop canopies to be measured and the ratio of green degree calculated value are obtained, as crop nitrogen nutrition to be measured
Index NNI;
(4) according to the relationship of crop canopies to be measured green degree measured value and crop leaf nitrogen concentration or SPAD value, divide situation needle
Crop nitrogen nutrition index NNI to be measured is analyzed, crop N Nutrition to be measured is obtained;
Crop canopies image actual measurement provided by the invention obtains greenness index, includes the following steps:
Actual measurement obtains the crop leaf nitrogen concentration or SPAD value of crop, while crop canopies image update being converted to default
The crop canopies image in designated color space;
The color basic value of each pixel of canopy in crop canopies image is extracted, and obtains being averaged for corresponding each channel color
Value, and then obtain the mutual ratio of each channel color average;
By the ratio that the corresponding default each channel color average in designated color space of crop canopies image is mutual, Yi Jizuo
Object canopy image corresponds to the standardized value of each channel color in RGB color, and the multiple color for constituting crop canopies image is special
Levy parameter;
For the multiple color characteristic parameter of crop canopies image, select linear with crop leaf nitrogen concentration or SPAD value
A kind of Color characteristics parameters of relationship, the greenness index as the crop canopies image.
Step (1) provided by the invention, includes the following steps:
For the crop growing spots for respectively corresponding default at least four different nitrogen trophic level, when by the default period 1
It is long, the moment is acquired in each period, acquires the canopy image of crop in each crop growing spots respectively;
Respectively for the collected each width canopy image of acquisition moment in each period institute, actual measurement obtains the green degree in canopy image
Value and covering angle value;
The moment is acquired for each period respectively, for the coverage for acquiring each width canopy image in the acquisition moment in period
Value carries out variance analysis, and according to the results of analysis of variance, each width canopy figure coverage fluctuation range each other being in threshold value
As dividing one group into, realize for the grouping for acquiring each width canopy image in the acquisition moment in period;
The moment is acquired for each period respectively, divides corresponding canopy for maximal cover degree in the acquisition moment in period
Image grouping, selects canopy image corresponding to minimum greenness index in canopy image grouping, and by the green degree of the canopy image
Value and covering angle value are respectively as critical greenness index and critical coverage value in the acquisition moment in the period;
Using critical coverage value as variable, critical greenness index is dependent variable, and for the acquisition moment in each period, institute is right respectively
The critical greenness index and critical coverage value answered are fitted, and obtain critical Nitrogen Dilution Model.
9 prediction technique of production forecast module provided by the invention is as follows:
1) environmental information is obtained according to crop growth environment information collection and pretreatment by Prediction program;
2) acquisition of crops own physiological physicochemical data and pretreatment, obtain physiological and biochemical property vector;
3) acquisition of crops leaf image and feature extraction: crops blade figure is acquired in real time using video monitoring equipment
Picture, then extracts mean value, deviation and the third-order matrix of tri- components of R, G, B of figure, then is normalized, and obtains image
Color characteristic;
4) Environmental Information Feature, physiological and biochemical property feature vector and the color of image obtained step 1) to step 3) is special
Value indicative forms the union feature vector of farming growth, according to crop growth and the historical data and changing rule of yield, building
The union feature vector data library of crop growth situation and yield;
5) crop growth situation detection and yield prediction model of the building based on sparse depth belief network;
6) building crop growth situation and yield obtained in contrast difference's fast learning algorithm and step 4) are utilized
Union feature vector data library, crop yield prediction model carry out pre-training and fine tuning, obtain Production Forecast Models;
7) to obtain Production Forecast Models carry out reliability test: building crop growth situation obtained in step 4 and
Union feature vector to be tested is input to training and the production finely tuned in step 6 in the union feature vector data library of yield
It measures in prediction model, calculates crop yield estimation results, estimation results are compared with actual production, if estimation results are inclined
Greater than actual production, then step 6) again is needed, adjustment is optimized to crop yield prediction model, repetition training is produced
Measure prediction model.
When the invention works, firstly, by video monitoring module 1 using image pick-up device to arviculture information processing situation
Carry out video monitoring;By environmental data collecting module 2 using sensor acquire arviculture information processing environment temperature,
Humidity, illumination, gas concentration lwevel data;Crop nitrogen nutrition situation number is detected using detector by Nutrition monitoring module 3
According to;Secondly, main control module 4 utilizes timer setting conveying nutrient solution, watering time by timing module 5;Pass through infusion module 6
It is operated using delivery pipe conveying nutrient solution;Watering operation is carried out to crop using sprinkler by watering module 7;By illuminating mould
Block 8 carries out lighting operation to arviculture information processing using headlamp;Then, prediction is utilized by production forecast module 9
Program predicts crop yield data;The content of nitrogen in detector monitors soil is utilized by soil property monitoring modular 10;Pass through disease
Whether insect pest monitoring modular 11 has pest and disease damage using detector monitors crops;Finally, utilizing display by display module 12
Show monitor video, environmental data, crop nutrient data, production forecast data information.
Technical effect of the invention is explained in detail combined with specific embodiments below.
The wheat planting district of default 4 different nitrogen trophic level, by default period 1 duration, fine day 12: 00~
Between 13: 00, camera and ground level are 1.2m, and canopy angle is 60 °, and image resolution ratio uses 1024 × 768, storage format
With jpeg format, the canopy image of crop in each wheat planting district is acquired respectively;
Obtain wheat canopy image after, for measure wheat coverage, before sealing ridge by wheat image be divided into Soil Background,
Wheat is divided into the wheat for having hot spot, light wheat, in the wheat of shade after sealing ridge, utilizes remote sensing software ENVI's 3.5
The method of ISO-DATA method and Maximum likelihood classification and comprehensive 2 method advantages, is divided into soil, reflective blade face for wheat image
It with non-reflective blade face, is compareed with Adobe Photoshop software normal image processing method, comparative analysis wheat image is different
The correlation of 8 kinds of color parameters and SPAD value and total nitrogen of classification blade.The result shows that the reflective blade face of period of seedling establishment wheat
Color parameter and SPAD value correlation are best, followed by the blade of Adobe Photoshop software processing acquisition;Jointing stage is not anti-
The color parameter on light blade face reaches extremely significant level with total nitrogen correlation;
Then for the covering angle value progress variance analysis for acquiring each width canopy image in the acquisition moment in period, and according to
The results of analysis of variance divides each width canopy image that coverage fluctuation range each other is in threshold value into one group, realizes for week
The grouping of each width canopy image is acquired in acquisition moment phase;
Select canopy image corresponding to minimum greenness index in canopy image grouping, and by the greenness index of the canopy image
With covering angle value respectively as critical greenness index and critical coverage value in the acquisition moment in the period;
Using critical coverage value as variable, critical greenness index is dependent variable, and for the acquisition moment in each period, institute is right respectively
The critical greenness index and critical coverage value answered are fitted, and obtain critical Nitrogen Dilution Model.
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (6)
1. a kind of arviculture information processing method, which is characterized in that the arviculture information processing method includes:
The first step carries out video monitoring to arviculture information processing situation using image pick-up device by video monitoring module;It is logical
Environmental data collecting module is crossed using temperature, humidity, illumination, the titanium dioxide of sensor acquisition arviculture information processing environment
Concentration of carbon data;Crop nitrogen nutrition status data is detected using detector by Nutrition monitoring module;
Second step, main control module utilize timer setting conveying nutrient solution, watering time by timing module;Pass through infusion module
It is operated using delivery pipe conveying nutrient solution;Watering operation is carried out to crop using sprinkler by watering module;By illuminating mould
Block carries out lighting operation to arviculture information processing using headlamp;
Third step predicts crop yield data by production forecast module;Detector monitors soil is utilized by soil property monitoring modular
The content of nitrogen in earth;Whether there is pest and disease damage using detector monitors crops by pest and disease monitoring module;
4th step shows that monitor video, environmental data, crop nutrient data, yield are pre- using display by display module
Measured data information.
2. arviculture information processing method as described in claim 1, which is characterized in that at the arviculture information
Reason method is as follows using detector detection crop nitrogen nutrition status data method:
(1) each crop growing spots for respectively corresponding default different nitrogen nutrition are directed to by detector, based on actual measurement crop hat
The greenness index and covering angle value of tomographic image, to cover angle value as variable, greenness index is the critical Nitrogen Dilution Model of dependent variable for building;
Meanwhile surveying the crop leaf nitrogen concentration or SPAD value for obtaining crop to be measured;
(2) actual measurement obtains the greenness index and covering angle value of crop canopies image to be measured, and the greenness index is as crop canopies to be measured
Green degree measured value;And calculate by critical Nitrogen Dilution Model according to the covering angle value and obtain greenness index, it is preced with as crop to be measured
The green degree calculated value of layer;
(3) the green degree measured value of crop canopies to be measured and the ratio of green degree calculated value are obtained, as crop nitrogen nutrition index to be measured
NNI;
(4) according to the relationship of crop canopies to be measured green degree measured value and crop leaf nitrogen concentration or SPAD value, divide situation be directed to
It surveys crop nitrogen nutrition index NNI to be analyzed, obtains crop N Nutrition to be measured.
3. arviculture information processing method as claimed in claim 2, which is characterized in that the actual measurement of crop canopies image obtains
Greenness index includes the following steps:
Actual measurement obtains the crop leaf nitrogen concentration or SPAD value of crop, while crop canopies image update is converted to default specify
The crop canopies image of color space;
The color basic value of each pixel of canopy in crop canopies image is extracted, and obtains the average value of corresponding each channel color,
And then obtain the mutual ratio of each channel color average;
By the ratio and crop hat that the corresponding default each channel color average in designated color space of crop canopies image is mutual
Tomographic image corresponds to the standardized value of each channel color in RGB color, constitutes the multiple color feature ginseng of crop canopies image
Number;
For the multiple color characteristic parameter of crop canopies image, select in a linear relationship with crop leaf nitrogen concentration or SPAD value
A kind of Color characteristics parameters, the greenness index as the crop canopies image.
4. arviculture information processing method as described in claim 1, which is characterized in that at the arviculture information
Reason method predicts that crop yield data method is as follows:
1) environmental information is obtained according to crop growth environment information collection and pretreatment by Prediction program;
2) acquisition of crops own physiological physicochemical data and pretreatment, obtain physiological and biochemical property vector;
3) acquisition of crops leaf image and feature extraction: crops leaf image is acquired in real time using video monitoring equipment, so
Mean value, deviation and the third-order matrix of tri- components of R, G, B of figure are extracted afterwards, then is normalized, and color of image is obtained
Feature;
4) Environmental Information Feature, physiological and biochemical property feature vector and the color of image characteristic value obtained step 1) to step 3)
The union feature vector for forming farming growth constructs farming according to crop growth and the historical data and changing rule of yield
Object grows the union feature vector data library of situation and yield;
5) crop growth situation detection and yield prediction model of the building based on sparse depth belief network;
6) joint of building crop growth situation and yield obtained in contrast difference's fast learning algorithm and step 4) is utilized
Characteristic vector data library, crop yield prediction model carry out pre-training and fine tuning, obtain Production Forecast Models;
7) to obtain Production Forecast Models carry out reliability test: building crop growth situation and yield obtained in step 4
Union feature vector data library in union feature vector to be tested to be input to training and the yield finely tuned in step 6 pre-
Survey model in, calculate crop yield estimation results, estimation results are compared with actual production, if estimation results it is bigger than normal in
Actual production then needs step 6) again, optimizes adjustment to crop yield prediction model, it is pre- that repetition training obtains yield
Survey model.
5. a kind of perform claim requires the arviculture information processing system of the 1 arviculture information processing method,
It is characterized in that, the arviculture information processing system includes:
Video monitoring module is connect with main control module, for being regarded by image pick-up device to arviculture information processing situation
Frequency monitors;
Environmental data collecting module, connect with main control module, for acquiring arviculture information processing environment by sensor
Temperature, humidity, illumination, gas concentration lwevel data;
Nutrition monitoring module, connect with main control module, for detecting crop nitrogen nutrition status data by detector;
Main control module, with video monitoring module, environmental data collecting module, Nutrition monitoring module, timing module, infusion module,
Watering module, lighting module, production forecast module, display module connection control the normal work of modules for passing through main controller
Make;
Timing module is connect with main control module, for setting conveying nutrient solution, watering time by timer;
Infusion module is connect with main control module, for conveying nutrient solution operation by delivery pipe;
Watering module, connect, for carrying out watering operation to crop by sprinkler with main control module;
Lighting module is connect with main control module, for carrying out lighting operation to arviculture information processing by headlamp;
Production forecast module, connect with main control module, for predicting crop yield data by Prediction program;
Soil property monitoring modular, connect with main control module, for the content by nitrogen in detector monitors soil;
Pest and disease monitoring module, connect with main module, for whether having pest and disease damage by detector monitors crops;
Display module is connect with main control module, for showing monitor video, environmental data, crop nutrition prime number by display
Whether there are pest and disease damage, production forecast data information according to nitrogen content, crops in, soil.
6. a kind of information data using arviculture information processing method described in Claims 1 to 4 any one is handled eventually
End.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910627439.XA CN110332957A (en) | 2019-07-12 | 2019-07-12 | Crop cultivation information processing system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910627439.XA CN110332957A (en) | 2019-07-12 | 2019-07-12 | Crop cultivation information processing system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110332957A true CN110332957A (en) | 2019-10-15 |
Family
ID=68146505
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910627439.XA Pending CN110332957A (en) | 2019-07-12 | 2019-07-12 | Crop cultivation information processing system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110332957A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115344997A (en) * | 2022-07-11 | 2022-11-15 | 中国水利水电科学研究院 | Summer corn plant leaf-canopy-pixel scale nitrogen concentration collaborative prediction method |
CN115989796A (en) * | 2022-12-26 | 2023-04-21 | 中国农业大学 | Nitrogen nutrition regulation and control method and system in industrial fish and vegetable symbiotic system |
CN117957997A (en) * | 2024-04-02 | 2024-05-03 | 洛阳展尚建筑工程有限公司 | Automatic fertilizing method for garden trees |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN204347595U (en) * | 2015-01-21 | 2015-05-20 | 河南中维电子科技有限公司 | The anti-control and management system of a kind of agricultural pest based on Internet of Things |
US20160217228A1 (en) * | 2015-01-23 | 2016-07-28 | Iteris, Inc. | Modeling of crop growth for desired moisture content of targeted livestock feedstuff for determination of harvest windows using field-level diagnosis and forecasting of weather conditions and observations and user input of harvest condition states |
CN106841051A (en) * | 2016-12-19 | 2017-06-13 | 中国科学院南京土壤研究所 | A kind of crop nitrogen nutrition detection method based on visual image fusion value |
CN109060028A (en) * | 2018-08-13 | 2018-12-21 | 中国地质大学(武汉) | A kind of planting environment remote monitoring system based on NB-IOT |
CN109470299A (en) * | 2018-10-19 | 2019-03-15 | 江苏大学 | A kind of plant growth information monitoring system and method based on Internet of Things |
CN109508824A (en) * | 2018-11-07 | 2019-03-22 | 西京学院 | A kind of detection of crop growth situation and yield predictor method |
CN109738435A (en) * | 2018-12-13 | 2019-05-10 | 成都信息工程大学 | A kind of diagnosis of buckwheat growth monitoring and production prediction method |
CN109767038A (en) * | 2019-01-04 | 2019-05-17 | 平安科技(深圳)有限公司 | Crop yield prediction technique, device and computer readable storage medium |
CN109816181A (en) * | 2019-03-15 | 2019-05-28 | 合肥工业大学 | Crop planting crop forecast method based on soil property monitoring |
CN109845625A (en) * | 2018-12-12 | 2019-06-07 | 珠江水利委员会珠江水利科学研究院 | A kind of multidimensional parameter crops intelligent irrigation control method neural network based |
-
2019
- 2019-07-12 CN CN201910627439.XA patent/CN110332957A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN204347595U (en) * | 2015-01-21 | 2015-05-20 | 河南中维电子科技有限公司 | The anti-control and management system of a kind of agricultural pest based on Internet of Things |
US20160217228A1 (en) * | 2015-01-23 | 2016-07-28 | Iteris, Inc. | Modeling of crop growth for desired moisture content of targeted livestock feedstuff for determination of harvest windows using field-level diagnosis and forecasting of weather conditions and observations and user input of harvest condition states |
CN106841051A (en) * | 2016-12-19 | 2017-06-13 | 中国科学院南京土壤研究所 | A kind of crop nitrogen nutrition detection method based on visual image fusion value |
CN109060028A (en) * | 2018-08-13 | 2018-12-21 | 中国地质大学(武汉) | A kind of planting environment remote monitoring system based on NB-IOT |
CN109470299A (en) * | 2018-10-19 | 2019-03-15 | 江苏大学 | A kind of plant growth information monitoring system and method based on Internet of Things |
CN109508824A (en) * | 2018-11-07 | 2019-03-22 | 西京学院 | A kind of detection of crop growth situation and yield predictor method |
CN109845625A (en) * | 2018-12-12 | 2019-06-07 | 珠江水利委员会珠江水利科学研究院 | A kind of multidimensional parameter crops intelligent irrigation control method neural network based |
CN109738435A (en) * | 2018-12-13 | 2019-05-10 | 成都信息工程大学 | A kind of diagnosis of buckwheat growth monitoring and production prediction method |
CN109767038A (en) * | 2019-01-04 | 2019-05-17 | 平安科技(深圳)有限公司 | Crop yield prediction technique, device and computer readable storage medium |
CN109816181A (en) * | 2019-03-15 | 2019-05-28 | 合肥工业大学 | Crop planting crop forecast method based on soil property monitoring |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115344997A (en) * | 2022-07-11 | 2022-11-15 | 中国水利水电科学研究院 | Summer corn plant leaf-canopy-pixel scale nitrogen concentration collaborative prediction method |
CN115344997B (en) * | 2022-07-11 | 2024-05-31 | 中国水利水电科学研究院 | Synergistic prediction method for leaf-canopy-pixel scale nitrogen concentration of summer maize plant |
CN115989796A (en) * | 2022-12-26 | 2023-04-21 | 中国农业大学 | Nitrogen nutrition regulation and control method and system in industrial fish and vegetable symbiotic system |
CN117957997A (en) * | 2024-04-02 | 2024-05-03 | 洛阳展尚建筑工程有限公司 | Automatic fertilizing method for garden trees |
CN117957997B (en) * | 2024-04-02 | 2024-05-28 | 洛阳展尚建筑工程有限公司 | Automatic fertilizing method for garden trees |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10028426B2 (en) | Agronomic systems, methods and apparatuses | |
CN209517198U (en) | A kind of wisdom agricultural standardization management system | |
CN110332957A (en) | Crop cultivation information processing system and method | |
CN111507857A (en) | Digital agricultural planting system and method based on Internet of things technology | |
CN110771442A (en) | Agricultural planting method and system based on Internet of things | |
CN106777683A (en) | A kind of crop growth of cereal crop seedlings monitoring system and method | |
CN109003198A (en) | A kind of precision agriculture management platform and method based on big data technology | |
CN114442705B (en) | Intelligent agricultural system based on Internet of things and control method | |
Ahmad et al. | A review of best management practices for potato crop using precision agricultural technologies | |
CN112883230A (en) | Potato production management system | |
CN110262604A (en) | Wisdom agricultural management system based on cloud service | |
Scalisi et al. | Detecting, mapping and digitising canopy geometry, fruit number and peel colour in pear trees with different architecture | |
Mazzetto et al. | Comparing commercial optical sensors for crop monitoring tasks in precision viticulture | |
Meivel et al. | Optimization of agricultural smart system using remote sensible NDVI and NIR thermal image analysis techniques | |
Okamoto et al. | An image analysis method for lettuce leaf and root growth analysis in hydroponic culture | |
CN110308710A (en) | A kind of tomato planting monitor supervision platform | |
Feng et al. | A real-time monitoring and control system for crop | |
Marconi et al. | Application of unmanned aerial system for management of tomato cropping system | |
CN113642998A (en) | Agricultural production data processing system and method | |
Fu et al. | High-throughput phenotyping: The latest research tool for sustainable crop production under global climate change scenarios | |
Thalwatte et al. | Fully automatic hydroponic cultivation growth system | |
CN109475080B (en) | Method for determining plant attributes of useful plants | |
Ahmed et al. | Micronutrient classification in IoT based agriculture using machine learning (ML) Algorithm | |
Jansen et al. | Image processing for bioassays | |
KR102545118B1 (en) | Management for a fruit farm using plant map and system therefore |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191015 |
|
RJ01 | Rejection of invention patent application after publication |