CN118209502B - Method and device for estimating potassium content of flue-cured tobacco leaves, electronic equipment and storage medium - Google Patents
Method and device for estimating potassium content of flue-cured tobacco leaves, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN118209502B CN118209502B CN202410637619.7A CN202410637619A CN118209502B CN 118209502 B CN118209502 B CN 118209502B CN 202410637619 A CN202410637619 A CN 202410637619A CN 118209502 B CN118209502 B CN 118209502B
- Authority
- CN
- China
- Prior art keywords
- flue
- cured tobacco
- estimated
- subarea
- tobacco
- 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
Links
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 738
- 241000208125 Nicotiana Species 0.000 title claims abstract description 724
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 title claims abstract description 343
- 229910052700 potassium Inorganic materials 0.000 title claims abstract description 343
- 239000011591 potassium Substances 0.000 title claims abstract description 343
- 238000000034 method Methods 0.000 title claims abstract description 83
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000003745 diagnosis Methods 0.000 claims abstract description 72
- 208000019025 Hypokalemia Diseases 0.000 claims abstract description 39
- 208000007645 potassium deficiency Diseases 0.000 claims abstract description 39
- 230000003595 spectral effect Effects 0.000 claims description 46
- 238000009826 distribution Methods 0.000 claims description 22
- 238000004422 calculation algorithm Methods 0.000 claims description 20
- 238000010586 diagram Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 13
- 238000012706 support-vector machine Methods 0.000 claims description 9
- 238000007637 random forest analysis Methods 0.000 claims description 8
- 238000002310 reflectometry Methods 0.000 claims description 8
- 239000003086 colorant Substances 0.000 claims description 4
- 239000003337 fertilizer Substances 0.000 abstract description 11
- 239000000523 sample Substances 0.000 description 101
- 230000000875 corresponding effect Effects 0.000 description 48
- 244000061176 Nicotiana tabacum Species 0.000 description 14
- 238000007726 management method Methods 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 12
- 239000002689 soil Substances 0.000 description 9
- 238000005070 sampling Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000001514 detection method Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000002411 adverse Effects 0.000 description 2
- 238000003556 assay Methods 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 229940070017 potassium supplement Drugs 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- SNICXCGAKADSCV-JTQLQIEISA-N (-)-Nicotine Chemical compound CN1CCC[C@H]1C1=CC=CN=C1 SNICXCGAKADSCV-JTQLQIEISA-N 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 239000003513 alkali Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000007636 ensemble learning method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000004720 fertilization Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000006101 laboratory sample Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229960002715 nicotine Drugs 0.000 description 1
- SNICXCGAKADSCV-UHFFFAOYSA-N nicotine Natural products CN1CCCC1C1=CC=CN=C1 SNICXCGAKADSCV-UHFFFAOYSA-N 0.000 description 1
- 235000015816 nutrient absorption Nutrition 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 230000003204 osmotic effect Effects 0.000 description 1
- 230000029553 photosynthesis Effects 0.000 description 1
- 238000010672 photosynthesis Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/55—Specular reflectivity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Manufacture Of Tobacco Products (AREA)
Abstract
The invention provides a method, a device, electronic equipment and a storage medium for estimating potassium content of flue-cured tobacco leaves, and relates to the technical field of intelligent agriculture, wherein the method comprises the following steps: acquiring tobacco leaf potassium diagnosis indexes of the flue-cured tobacco to be estimated in each subarea of the flue-cured tobacco planting area to be estimated based on the multispectral image of the flue-cured tobacco planting area to be estimated; and inputting the tobacco leaf potassium element diagnosis index of the flue-cured tobacco to be estimated in each subarea into a flue-cured tobacco leaf potassium content estimation model to obtain an estimated value of the potassium content of the flue-cured tobacco leaf in each subarea. The method, the device, the electronic equipment and the storage medium for estimating the potassium content of the flue-cured tobacco leaves can more accurately, more efficiently and more comprehensively estimate the potassium content of the flue-cured tobacco leaves in a large-area flue-cured tobacco planting area, can more timely discover the potassium deficiency condition of the flue-cured tobacco in the large-area flue-cured tobacco planting area, can provide a data basis for the potassium fertilizer management work of the flue-cured tobacco planting area, and can improve the precision and the efficiency of the potassium fertilizer management work of the flue-cured tobacco planting area.
Description
Technical Field
The invention relates to the technical field of intelligent agriculture, in particular to a method and a device for estimating potassium content of flue-cured tobacco leaves, electronic equipment and a storage medium.
Background
Flue-cured tobacco is an important commercial crop, and proper potassium element supply has a significant effect on the yield and quality of flue-cured tobacco in the flue-cured tobacco planting process. The potassium content of the flue-cured tobacco leaves can be used for guiding the potassium fertilizer management work in the flue-cured tobacco planting area.
Under normal conditions, the potassium content of the flue-cured tobacco leaves can be obtained through modes of manual sampling, field detection or acquisition of physicochemical characteristics of soil and flue-cured tobacco plants.
However, the traditional method for estimating the potassium content of the flue-cured tobacco leaves needs to input a great deal of labor cost and time cost, and the efficiency for estimating the potassium content of the flue-cured tobacco leaves is low. In addition, the traditional method for estimating the potassium content of the flue-cured tobacco leaves can only sample a limited number of sample points in a large-area flue-cured tobacco planting area, so that the potassium content of the detected flue-cured tobacco leaves is lack of comprehensiveness and representativeness, and the potassium content of the flue-cured tobacco leaves in the large-area flue-cured tobacco planting area is difficult to accurately obtain. Therefore, how to obtain the potassium content of flue-cured tobacco leaves in a large-area flue-cured tobacco planting area more accurately, more efficiently and more comprehensively is a technical problem to be solved in the field.
Disclosure of Invention
The invention provides a method, a device, electronic equipment and a storage medium for estimating the potassium content of flue-cured tobacco leaves, which are used for solving the defect that the potassium content of the flue-cured tobacco leaves in a large-area flue-cured tobacco planting area is difficult to accurately, efficiently and comprehensively obtain in the prior art, and realizing more accurate, more efficient and more comprehensive obtaining of the potassium content of the flue-cured tobacco leaves in the large-area flue-cured tobacco planting area.
The invention provides a method for estimating potassium content of flue-cured tobacco leaves, which comprises the following steps:
acquiring multispectral images of a flue-cured tobacco planting area to be estimated, wherein flue-cured tobacco to be estimated is planted in the flue-cured tobacco planting area to be estimated;
Based on the multispectral image, acquiring a tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea of the flue-cured tobacco planting area to be estimated;
Inputting the tobacco leaf potassium element diagnostic index of the tobacco leaf to be estimated in each subarea into a tobacco leaf potassium content estimation model of the tobacco leaf to be estimated, and obtaining an estimated value of the potassium content of the tobacco leaf in each subarea output by the tobacco leaf potassium content estimation model of the tobacco leaf to be estimated;
the tobacco leaf potassium content estimation model is obtained by training based on tobacco leaf potassium diagnosis indexes corresponding to sample tobacco planting areas and actual values of sample tobacco leaf potassium content in the sample tobacco planting areas; the flue-cured tobacco to be estimated and the sample flue-cured tobacco are in the same growth period.
According to the method for estimating the potassium content of the flue-cured tobacco, provided by the invention, the tobacco potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea of the planting area of the flue-cured tobacco to be estimated is obtained based on the multispectral image, and the method comprises the following steps:
Based on the correlation between each original wave band and the actual value of the potassium content of the sample flue-cured tobacco leaves, respectively determining two original wave bands with the strongest correlation with the actual value of the potassium content of the sample flue-cured tobacco leaves as sensitive wave bands, wherein each original wave band comprises a blue light wave band, a green light wave band, a red edge wave band and a near infrared wave band;
acquiring the canopy spectral reflectivity of the sensitive wave band of each subarea based on the multispectral image;
And calculating and obtaining the tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea based on the canopy spectral reflectance of the sensitive wave band in each subarea.
According to the method for estimating the potassium content of the flue-cured tobacco, the sensitive wave bands comprise a first sensitive wave band and a second sensitive wave band, and the potassium diagnosis index of the tobacco to be estimated in each subarea is calculated based on the canopy spectral reflectance of the sensitive wave band of each subarea, and the method comprises the following steps:
Calculating the difference between the crown spectral reflectance of the first sensitive wave band and the crown spectral reflectance of the second sensitive wave band of each subarea, and taking the difference as a first intermediate result corresponding to each subarea, and calculating the sum of the crown spectral reflectance of the first sensitive wave band of each subarea and the crown spectral reflectance of the second sensitive wave band of each subarea, and taking the sum as a second intermediate result corresponding to each subarea;
and calculating the quotient of the first intermediate result and the second intermediate result corresponding to each subarea as a tobacco potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea.
According to the method for estimating the potassium content of the flue-cured tobacco, provided by the invention, before the tobacco potassium element diagnostic index of the flue-cured tobacco to be estimated in each subarea is input into the flue-cured tobacco potassium content estimation model, the method further comprises the following steps:
Respectively constructing a first initial model, a second initial model and a third initial model based on a random forest algorithm, a support vector machine algorithm and a gradient lifting algorithm;
Taking a tobacco leaf potassium diagnosis index corresponding to the sample flue-cured tobacco planting area as a sample, taking an actual value of the potassium content of sample flue-cured tobacco leaves in the sample flue-cured tobacco planting area as a sample label, and respectively training the first initial model, the second initial model and the third initial model to obtain a trained first initial model, a trained second initial model and a trained third initial model;
and determining the model with the best calculation precision and stability among the trained first initial model, the trained second initial model and the trained third initial model as the flue-cured tobacco leaf potassium content estimation model.
According to the method for estimating the potassium content of the flue-cured tobacco leaves, which is provided by the invention, the multispectral image of the planting area of the flue-cured tobacco leaves to be estimated is obtained, and the method comprises the following steps:
Acquiring an unmanned aerial vehicle image of the flue-cured tobacco planting area to be estimated;
And acquiring the multispectral image based on the unmanned aerial vehicle image.
According to the method for estimating the potassium content of the flue-cured tobacco leaves provided by the invention, after the estimated value of the potassium content of the flue-cured tobacco leaves in each subarea output by the potassium content estimation model of the flue-cured tobacco leaves is obtained, the method further comprises:
And drawing a potassium content distribution map of the flue-cured tobacco corresponding to the flue-cured tobacco planting area to be estimated based on the estimated value of the potassium content of the flue-cured tobacco in each sub-area.
According to the method for estimating the potassium content of the flue-cured tobacco leaves, which is provided by the invention, the potassium content distribution diagram of the flue-cured tobacco leaves corresponding to the flue-cured tobacco planting area to be estimated is drawn based on the estimated value of the potassium content of the flue-cured tobacco leaves in each subarea, and the method comprises the following steps:
Determining the potassium deficiency grade of the flue-cured tobacco leaves in each subarea based on the estimated value of the potassium content of the flue-cured tobacco leaves in each subarea;
And filling colors corresponding to the potassium deficiency grades of the flue-cured tobacco leaves in each subarea in the corresponding area of each subarea in the blank canvas, and obtaining a potassium content distribution diagram of the flue-cured tobacco leaves corresponding to the flue-cured tobacco planting area to be estimated.
The invention also provides a device for estimating the potassium content of the flue-cured tobacco leaves, which comprises the following steps:
The image acquisition module is used for acquiring multispectral images of a flue-cured tobacco planting area to be estimated, wherein flue-cured tobacco to be estimated is planted in the flue-cured tobacco planting area to be estimated;
the data processing module is used for acquiring tobacco leaf potassium diagnosis indexes of the flue-cured tobacco to be estimated in each subarea of the planting area of the flue-cured tobacco to be estimated based on the multispectral image;
The result output module is used for inputting the tobacco leaf potassium element diagnosis index of the tobacco leaf to be estimated in each subarea into a tobacco leaf potassium content estimation model of the tobacco leaf to be estimated, and obtaining an estimated value of the potassium content of the tobacco leaf in each subarea output by the tobacco leaf potassium content estimation model of the tobacco leaf to be estimated;
the tobacco leaf potassium content estimation model is obtained by training based on tobacco leaf potassium diagnosis indexes corresponding to sample tobacco planting areas and actual values of sample tobacco leaf potassium content in the sample tobacco planting areas; the flue-cured tobacco to be estimated and the sample flue-cured tobacco are in the same growth period.
The invention also provides electronic equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the potassium content estimation method of the flue-cured tobacco leaves when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for estimating the potassium content of flue-cured tobacco leaves as described in any one of the above.
The invention also provides a computer program product comprising a computer program which when executed by a processor implements the flue-cured tobacco leaf potassium content estimation method as described in any one of the above.
According to the method, the device, the electronic equipment and the storage medium for estimating the potassium content of the tobacco leaves of the tobacco, provided by the invention, after the tobacco potassium diagnosis index of the tobacco leaves to be estimated in each subarea of the tobacco planting area to be estimated is obtained based on the multispectral image of the tobacco planting area to be estimated, the tobacco potassium diagnosis index of the tobacco leaves to be estimated in each subarea is input into the tobacco potassium content estimation model of the tobacco leaves to be estimated, and the estimated value of the potassium content of the tobacco leaves of the tobacco in each subarea output by the potassium content estimation model of the tobacco leaves is obtained, so that the potassium content of the tobacco leaves of the tobacco in the tobacco planting area to be estimated in a large area can be estimated more accurately and more efficiently and more comprehensively, the potassium deficiency condition of the tobacco leaves in the tobacco planting area to be estimated in a large area can be found more timely, a data basis can be provided for the potassium fertilizer management work of the tobacco planting area, the precision and the efficiency of the potassium fertilizer management work of the tobacco planting area can be improved, and the benefit of the tobacco production can be improved.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for estimating the potassium content of flue-cured tobacco leaves;
Fig. 2 is a schematic diagram of a potassium content distribution diagram of flue-cured tobacco leaves corresponding to a planting area of flue-cured tobacco leaves to be estimated in the potassium content estimation method of flue-cured tobacco leaves provided by the invention;
FIG. 3 is a second flow chart of the method for estimating the potassium content of flue-cured tobacco leaves;
fig. 4 is a schematic structural view of the flue-cured tobacco leaf potassium content estimation device provided by the invention;
Fig. 5 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the invention, it should be noted that, unless explicitly stated and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
In the description of the present application, the terms "first," "second," and the like are used for distinguishing between similar objects and not for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type, and are not limited to the number of objects, such as the first object may be one or more. In addition, in the description of the present application, "and/or" means at least one of the connected objects, and the character "/", generally means a relationship in which the front and rear associated objects are one kind of "or".
In the flue-cured tobacco growing process, proper potassium element supply has a significant effect on the yield and quality of flue-cured tobacco in the flue-cured tobacco planting process.
Firstly, the potassium element is a key element for maintaining the stable osmotic pressure inside and outside the cells of the flue-cured tobacco leaves, is beneficial to maintaining the stable cell structure and promoting nutrient delivery, and is important to the growth and development of the flue-cured tobacco leaves; secondly, the potassium element can improve the resistance of the flue-cured tobacco plant to various adverse conditions, whether the flue-cured tobacco plant is faced with drought, high temperature, saline-alkali and other adverse conditions, and the proper potassium element supply can help the flue-cured tobacco plant to better adapt to the pressures and keep the normal growth state; thirdly, the potassium element can also directly influence the chemical components of the flue-cured tobacco, and sufficient potassium element supply is helpful for regulating and controlling the nicotine content in the flue-cured tobacco, thus having important effects on controlling the tobacco quality and improving the tobacco quality; finally, the potassium element plays a key role in improving the yield and quality of tobacco leaves, and can improve the photosynthesis efficiency of tobacco plants and promote sugar synthesis and nutrient absorption and utilization, so that the yield of the tobacco leaves is increased and the quality of the tobacco leaves is improved.
Under normal conditions, the potassium content of the flue-cured tobacco leaves can be obtained through modes of manual sampling, field detection or acquisition of physicochemical characteristics of soil and flue-cured tobacco plants.
Wherein, manual sampling is a common method, and after a representative sample point is selected in a flue-cured tobacco planting area, flue-cured tobacco leaves or soil samples of flue-cured tobacco plants at the sample point can be manually collected. After the flue-cured tobacco leaves or soil samples of the flue-cured tobacco plants at the sample points are acquired, the samples are sent to a laboratory for testing or analysis, so that the potassium content of the flue-cured tobacco leaves at the sample points can be determined. However, the potassium content of the flue-cured tobacco leaves is obtained by adopting a manual sampling mode, so that the problems of limited sampling quantity, strong subjectivity of sample point selection, large consumption of manpower and material resources and the like exist, and the representativeness and the accuracy of the potassium content of the obtained flue-cured tobacco leaves are not high.
The field test is a method with higher accuracy, and the potassium content of the flue-cured tobacco leaves can be determined by carrying out the field test on the flue-cured tobacco leaves or soil samples. However, although the potassium content of the flue-cured tobacco leaves can be accurately obtained by adopting an on-site assay mode, the operation of performing the on-site assay is complex, a great deal of time cost and equipment cost are required to be input, and the comprehensive detection of the flue-cured tobacco planting area is difficult to realize.
The physicochemical characteristics of the soil and the tobacco plant are collected, and the potassium content of the tobacco leaf can be indirectly deduced by measuring the physicochemical characteristics of the soil or the tobacco plant, such as parameters of soil pH value, conductivity and the like, or the characteristics of the color, the shape and the like of the tobacco leaf. However, the physicochemical characteristics of the soil or tobacco plant are susceptible to environmental conditions and sampling methods, resulting in limited accuracy and comprehensiveness of the results obtained.
In summary, the traditional method for estimating the potassium content of the flue-cured tobacco leaves needs to input a great deal of labor cost and time cost, and the efficiency of estimating the potassium content of the flue-cured tobacco leaves is low. In addition, the traditional method for estimating the potassium content of the flue-cured tobacco leaves can only sample a limited number of sample points in a large-area flue-cured tobacco planting area, so that the potassium content of the detected flue-cured tobacco leaves lacks comprehensiveness and representativeness, and the potassium content of the flue-cured tobacco leaves in the large-area flue-cured tobacco planting area is difficult to accurately obtain, so that the precision and efficiency of potassium fertilizer management work in the flue-cured tobacco planting area are limited.
By using the unmanned aerial vehicle low-altitude remote sensing technology, high-definition images of a large-area flue-cured tobacco planting area can be efficiently and accurately acquired. The multispectral sensor technology is a technology for acquiring characteristics of a target object by utilizing spectral information of a plurality of wave bands. Multispectral sensor technology can provide richer information, helping users more fully understand the nature and characteristics of a target object.
Aiming at the limitations of the traditional flue-cured tobacco leaf potassium content estimation method, the invention provides a flue-cured tobacco leaf potassium content estimation method. The method for estimating the potassium content of the flue-cured tobacco leaves can obtain the potassium content of the flue-cured tobacco leaves more accurately, more efficiently and more comprehensively by using the unmanned aerial vehicle low-altitude remote sensing technology and the multispectral sensor technology, and provides a brand-new solution for monitoring the potassium deficiency problem of the flue-cured tobacco leaves.
According to the method for estimating the potassium content of the flue-cured tobacco leaves, provided by the invention, the unmanned aerial vehicle with the multispectral sensor can monitor the potassium content of the flue-cured tobacco leaves in a large-area flue-cured tobacco planting area with high resolution and high frequency, so that the potassium deficiency state of tobacco plants can be rapidly and comprehensively detected.
The method for estimating the potassium content of the flue-cured tobacco leaves provided by the invention introduces an unmanned aerial vehicle low-altitude remote sensing technology and a multispectral sensor technology, and solves the problems of limited sampling and inconvenient field operation of the traditional method for estimating the potassium content of the flue-cured tobacco leaves. The unmanned aerial vehicle can quickly cover a large-area flue-cured tobacco planting area, performs low-altitude non-loss remote sensing monitoring, does not need a large amount of manpower investment, reduces the cost investment of the potassium content estimation of flue-cured tobacco leaves, and improves the detection efficiency of the potassium content estimation of the flue-cured tobacco leaves. And the multispectral sensor can acquire spectral data of different wave bands of the flue-cured tobacco leaves, thereby being beneficial to more accurately acquiring the potassium content of the flue-cured tobacco leaves. The application of the method for estimating the potassium content of the flue-cured tobacco leaves can enable the potassium deficiency condition of tobacco plants to be discovered and managed more timely, is beneficial to tobacco growers to more scientifically adjust the potassium fertilizer management strategy in the flue-cured tobacco planting area, further improves the yield and quality of the flue-cured tobacco, and improves the benefit of flue-cured tobacco production.
Fig. 1 is a schematic flow chart of a method for estimating the potassium content of flue-cured tobacco leaves. The method for estimating the potassium content of flue-cured tobacco leaves according to the present invention is described below with reference to FIG. 1. As shown in fig. 1, the method includes: step 101, acquiring a multispectral image of a flue-cured tobacco planting area to be estimated, wherein flue-cured tobacco to be estimated is planted in the flue-cured tobacco planting area to be estimated;
it should be noted that, the execution main body of the embodiment of the invention is a flue-cured tobacco leaf potassium content estimation device.
Specifically, the flue-cured tobacco to be estimated in the embodiment of the invention is the flue-cured tobacco planted in the planting area of the flue-cured tobacco to be estimated, and the flue-cured tobacco to be estimated is an estimation object of the potassium content estimation method of the flue-cured tobacco. The potassium content estimation method for the flue-cured tobacco leaves can estimate the potassium content of the tobacco leaves of the flue-cured tobacco to be estimated.
It can be understood that the flue-cured tobacco planting area to be estimated in the embodiment of the present invention is an area with a larger area, for example, the flue-cured tobacco planting area to be estimated may be a square area with a length×width of 100×100.
It can be appreciated that the flue-cured tobacco planting area to be estimated in the embodiment of the invention can be determined based on actual requirements. In the embodiment of the invention, the flue-cured tobacco planting area to be estimated is not particularly limited.
In the embodiment of the invention, the multispectral image of the flue-cured tobacco planting area to be estimated can be acquired in various modes, for example: the multispectral image of the flue-cured tobacco planting area to be estimated can be obtained by using the unmanned aerial vehicle low-altitude remote sensing technology; or multispectral images of the flue-cured tobacco planting areas to be estimated can be acquired based on remote sensing satellites. The specific mode for acquiring the multispectral image of the flue-cured tobacco planting area to be estimated is not limited in the embodiment of the invention.
As an alternative embodiment, acquiring a multispectral image of a flue-cured tobacco planting area to be estimated includes: acquiring an unmanned aerial vehicle image of a flue-cured tobacco planting area to be estimated;
Specifically, in the embodiment of the invention, the unmanned aerial vehicle carrying the multispectral sensor can be controlled, and under the condition that the preset weather condition, the preset flight height, the preset course overlapping degree and the preset side overlapping degree are met, the unmanned aerial vehicle flies through the flue-cured tobacco planting area to be estimated according to the preset route, and the flue-cured tobacco to be estimated in the flue-cured tobacco planting area to be estimated is vertically shot to obtain the unmanned aerial vehicle image of the flue-cured tobacco planting area to be estimated. The multispectral sensor at least comprises a blue light wave band, a green light wave band, a red side wave band and a near infrared wave band.
Optionally, in the embodiment of the invention, in the weather that the air speed is lower than 3 levels and is clear and cloudless, the unmanned aerial vehicle with the multispectral sensor is controlled and controlled to fly through the flue-cured tobacco planting area to be estimated according to a preset air route between 10 am and 2 pm, and the flue-cured tobacco to be estimated in the flue-cured tobacco planting area to be estimated is vertically shot to obtain the unmanned aerial vehicle image of the flue-cured tobacco planting area to be estimated. The flying height of the unmanned aerial vehicle is set between 30 and 50 meters so as to ensure the accuracy of image acquisition. The heading overlap ratio of unmanned aerial vehicle flight is set to 80%, and the side overlap ratio is set to 75%.
It can be understood that the number of unmanned aerial vehicle images in the flue-cured tobacco planting area to be estimated is a plurality of.
Based on the unmanned aerial vehicle image, obtain multispectral image.
Specifically, after the unmanned aerial vehicle image of the flue-cured tobacco planting area to be estimated is acquired, the unmanned aerial vehicle image of the flue-cured tobacco planting area to be estimated can be corrected and spliced by using splicing software (for example, pix4D or Agisoft Metashape), so as to obtain the original multispectral image of the flue-cured tobacco planting area to be estimated.
In order to obtain the estimation accuracy of the potassium content of the flue-cured tobacco leaves to be estimated in the flue-cured tobacco planting area to be estimated, after the original multispectral image of the flue-cured tobacco planting area to be estimated is obtained, image preprocessing (including noise removal, color correction and the like) can be carried out on the original multispectral image, so that the multispectral image capable of better reflecting the real reflectivity of the ground surface object in the flue-cured tobacco planting area to be estimated is obtained.
It should be noted that, in the embodiment of the present invention, the multispectral image of the flue-cured tobacco planting area to be estimated adopts the geographic coordinate system gcs_wgs_1984 and the projection coordinate system utm_zone_50n, which has a spatial resolution of 0.05 m.
102, Acquiring tobacco leaf potassium diagnosis indexes of the flue-cured tobacco to be estimated in each subarea of the planting area of the flue-cured tobacco to be estimated based on multispectral images;
specifically, in the embodiment of the present invention, the flue-cured tobacco planting area to be estimated may be uniformly divided into a plurality of sub-areas by a plurality of modes, for example, in the embodiment of the present invention, each pixel in the multispectral image of the flue-cured tobacco planting area to be estimated may be determined as each sub-area in the flue-cured tobacco planting area to be estimated; or in the embodiment of the invention, the flue-cured tobacco planting area to be estimated can be grid-divided based on the preset distance, and each small area obtained after grid division is determined as a sub-area of the flue-cured tobacco planting area to be estimated, wherein the preset distance can be determined according to priori knowledge and/or actual requirements.
After the multispectral image of the flue-cured tobacco planting area to be estimated is obtained, the tobacco potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea of the flue-cured tobacco planting area to be estimated can be obtained through numerical calculation, mathematical statistics, deep learning and other modes based on the multispectral image.
As an alternative embodiment, based on the multispectral image, acquiring the tobacco potassium diagnosis index of the flue-cured tobacco to be estimated in each sub-area in the planting area of the flue-cured tobacco to be estimated comprises: based on the correlation between each original wave band and the actual value of the potassium content of the sample flue-cured tobacco leaves, respectively determining two original wave bands with the strongest correlation with the actual value of the potassium content of the sample flue-cured tobacco leaves as sensitive wave bands, wherein each original wave band comprises a blue wave band, a green wave band, a red wave band and a near infrared wave band;
It should be noted that, because the flue-cured tobacco in different growing periods has different degrees of potassium content of flue-cured tobacco leaves interfered by other factors, the sensitive wave bands corresponding to the flue-cured tobacco in different growing periods are different.
Accordingly, before the diagnosis index of potassium element of the flue-cured tobacco to be estimated in each subarea of the planting area of the flue-cured tobacco to be estimated is obtained, a sensitive wave band corresponding to the flue-cured tobacco to be estimated needs to be determined.
It should be noted that, in the embodiment of the present invention, the flue-cured tobacco in the same growth period as the flue-cured tobacco to be estimated is selected as the sample flue-cured tobacco. Accordingly, in the embodiment of the invention, the region planted with the sample flue-cured tobacco can be determined as the sample flue-cured tobacco planting region.
The actual value of the potassium content of the sample flue-cured tobacco leaves can be obtained by using an oven to carry out fixation and drying treatment on the sample flue-cured tobacco leaves, and then sending the sample flue-cured tobacco leaves to a laboratory for measuring the potassium content. The actual value of the potassium content of the sample flue-cured tobacco leaves is accurately obtained, and calibration data support can be provided for the estimation of the potassium content of the flue-cured tobacco leaves to be estimated.
The pearson correlation coefficient (Pearson correlation coefficient) is a statistical indicator that measures the strength and direction of the linear relationship between two variables. The pearson correlation coefficient has a value ranging from-1 to 1, wherein: in the case of a pearson correlation coefficient of 1, two variables are represented as being completely positively correlated; in the case of a pearson correlation coefficient of-1, it means that the two variables are completely inversely related; in the case where the pearson correlation coefficient is 0, it means that there is no linear relationship between the two variables.
In the embodiment of the invention, the pearson correlation coefficient between each original wave band and the actual value of the potassium content of the sample flue-cured tobacco leaf can be calculated in a numerical calculation mode. And further, the two original wave bands with the strongest correlation with the actual value of the potassium content of the sample flue-cured tobacco leaf can be determined by comparing the pearson correlation coefficient between each original wave band and the actual value of the potassium content of the sample flue-cured tobacco leaf, and the two original wave bands are respectively determined as sensitive wave bands corresponding to the flue-cured tobacco to be estimated.
Acquiring the spectral reflectance of the canopy of each sub-region sensitive band based on the multispectral image;
Specifically, after the sensitive wave band corresponding to the flue-cured tobacco to be estimated is determined, the canopy spectral reflectance of the sensitive wave band of each sub-region in the flue-cured tobacco planting region to be estimated can be obtained based on the multispectral image of the flue-cured tobacco planting region to be estimated.
And calculating to obtain the tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea based on the canopy spectral reflectance of the sensitive wave band of each subarea.
Specifically, after the canopy spectral reflectance of the sensitive wave band in each subarea in the flue-cured tobacco planting area to be estimated is obtained, the tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea can be calculated through a numerical calculation mode.
As an optional embodiment, each sensitive wave band includes a first sensitive wave band and a second sensitive wave band, and based on the canopy spectral reflectance of each sub-region sensitive wave band, a tobacco potassium diagnosis index of the flue-cured tobacco to be estimated in each sub-region is calculated, including: calculating the difference between the crown spectral reflectance of the first sensitive wave band and the crown spectral reflectance of the second sensitive wave band of each subarea, and taking the difference as a first intermediate result corresponding to each subarea, and calculating the sum of the crown spectral reflectance of the first sensitive wave band and the crown spectral reflectance of the second sensitive wave band of each subarea, and taking the sum as a second intermediate result corresponding to each subarea;
and calculating the quotient of the first intermediate result and the second intermediate result corresponding to each subarea as a tobacco potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea.
Specifically, in the construction method of the analogy normalized vegetation index NDVI, the absorption difference of two sensitive wave bands which are obviously related to the potassium content of the flue-cured tobacco to be estimated is quantized to be used as the tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated, so that the potassium content of the flue-cured tobacco to be estimated is quantized.
After the canopy spectral reflectance of the sensitive wave band of each subarea in the flue-cured tobacco planting area to be estimated is obtained, the tobacco potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea can be obtained through calculation according to the following formula.
Wherein,Representing the first region of flue-cured tobacco planting to be estimatedThe tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each sub-area,，Representing the total number of sub-areas in the flue-cured tobacco planting area to be estimated; Representing the first region of flue-cured tobacco planting to be estimated The spectral reflectance of the canopy of the first sensitive wave band of the sub-region; Representing the first region of flue-cured tobacco planting to be estimated And the spectral reflectivity of the top layer of the second sensitive wave band of the sub-region.
It should be noted that, in the flue-cured tobacco planting area to be estimatedTobacco leaf potassium diagnosis index of flue-cured tobacco to be estimated in individual subareaThe value of (2) is in the range of-1 to 1.
According to the embodiment of the invention, after the sensitive wave band corresponding to the flue-cured tobacco to be estimated is determined based on the actual value of the potassium content of the sample flue-cured tobacco in the same growth period as the flue-cured tobacco to be estimated, the tobacco acceleration diagnosis index of the flue-cured tobacco to be estimated in each subarea of the flue-cured tobacco to be estimated is calculated based on the multispectral image of the planting area of the flue-cured tobacco to be estimated in a numerical calculation mode, so that the spectral information in the multispectral image of the planting area of the flue-cured tobacco to be estimated can be converted into the numerical information which can more represent the potassium content of the flue-cured tobacco, further, a more accurate data basis can be provided for flue-cured tobacco estimation, and the efficiency of flue-cured tobacco estimation can be improved.
Step 103, inputting the tobacco leaf potassium element diagnostic index of the tobacco leaf to be estimated in each subarea into a tobacco leaf potassium content estimation model of the tobacco leaf to be estimated, and obtaining an estimated value of the potassium content of the tobacco leaf in each subarea output by the tobacco leaf potassium content estimation model;
The tobacco leaf potassium content estimation model is obtained by training based on tobacco leaf potassium diagnosis indexes corresponding to sample tobacco planting areas and actual values of sample tobacco leaf potassium content in the sample tobacco planting areas; the flue-cured tobacco to be estimated in the flue-cured tobacco planting area to be estimated and the sample flue-cured tobacco are in the same growing period.
It can be appreciated that the number of sample flue-cured tobacco planting areas in the embodiments of the present invention may be plural.
Optionally, the area of the sample flue-cured tobacco planting area in the embodiment of the invention is the same as the area of any subarea in the flue-cured tobacco planting area to be estimated.
It should be noted that the multispectral image of the sample flue-cured tobacco planting area may be obtained based on an unmanned aerial vehicle image of the sample flue-cured tobacco planting area. The unmanned aerial vehicle with the multispectral sensor is controlled to fly through the sample flue-cured tobacco planting area according to the preset air route under the condition of meeting the preset weather condition, the preset flight height, the preset course overlapping degree and the preset side direction overlapping degree, the flue-cured tobacco to be estimated in the sample flue-cured tobacco planting area is vertically shot, and the unmanned aerial vehicle image of the sample flue-cured tobacco planting area can be obtained.
Optionally, in the embodiment of the invention, in the weather that the air speed is lower than 3 levels and the weather is clear and cloudless, the unmanned aerial vehicle carrying the multispectral sensor is controlled and controlled to fly through the sample flue-cured tobacco planting area according to the preset air route, the sample flue-cured tobacco in the sample flue-cured tobacco planting area is vertically shot, and the unmanned aerial vehicle image of the sample flue-cured tobacco planting area is obtained. The flying height of the unmanned aerial vehicle is set between 30 and 50 meters so as to ensure the accuracy of image acquisition. The heading overlap ratio of unmanned aerial vehicle flight is set to 80%, and the side overlap ratio is set to 75%.
After the unmanned aerial vehicle image of the sample flue-cured tobacco planting area is obtained, the unmanned aerial vehicle image of the sample flue-cured tobacco planting area can be subjected to image preprocessing (including noise removal, color correction and the like) to obtain the multispectral image of the sample flue-cured tobacco planting area.
It should be noted that, the tobacco leaf potassium diagnosis index corresponding to the sample flue-cured tobacco planting area may be calculated based on the multispectral image of the sample flue-cured tobacco planting area by using the calculation method described in the above embodiment.
After obtaining the tobacco potassium diagnosis index corresponding to the sample flue-cured tobacco planting area and the actual value of the potassium content of the sample flue-cured tobacco in the sample flue-cured tobacco planting area, the tobacco potassium diagnosis index corresponding to the sample flue-cured tobacco planting area can be used as a sample, the sample label of the actual value of the potassium content of the sample flue-cured tobacco in the sample flue-cured tobacco planting area is used for training the initial model, and the trained model is determined to be a tobacco potassium content estimation model.
It should be noted that, the initial model in the embodiment of the present invention may be constructed based on a random forest algorithm, a support vector machine algorithm or a gradient lifting algorithm.
Obtaining the first tobacco planting area to be estimatedTobacco leaf potassium diagnosis index of flue-cured tobacco to be estimated in individual subareaThen, the first tobacco planting area to be estimatedTobacco leaf potassium diagnosis index of flue-cured tobacco to be estimated in individual subareaThe tobacco leaf content of the input flue-cured tobacco potassium amount estimation model.
The tobacco leaf potassium content estimation model outputs the first tobacco leaf potassium content in the tobacco planting area to be estimatedAnd (5) estimating the potassium content of the flue-cured tobacco leaves in each subregion.
As an alternative embodiment, before inputting the tobacco potassium element diagnosis index of the flue-cured tobacco to be estimated in each sub-area into the flue-cured tobacco potassium content estimation model, the method further comprises: respectively constructing a first initial model, a second initial model and a third initial model based on a random forest algorithm, a support vector machine model and a gradient lifting algorithm;
It should be noted that the random forest algorithm is an integrated learning method for solving the classification and regression problems. Random forest algorithms improve the performance and stability of the overall model by building multiple decision trees and combining them for prediction. The random forest algorithm can process a large number of input variables, does not need to perform feature selection, can effectively process high-dimensional data, is not easy to fit, has high accuracy, and can process a large-scale data set.
The support vector machine (Support Vector Machine, SVM) model is a supervised learning model for classification and regression analysis, which can be used to solve both linear and nonlinear problems. The basic idea of the support vector machine model is to find a hyperplane separating samples of different classes and maximizing the separation of the two classes. The support vector machine model has good performance in a high-dimensional space, is suitable for high-dimensional data, can effectively solve the problems of linearity and nonlinearity, has strong generalization capability, can also show better performance for a small sample data set, and has smaller memory occupation because the optimal solution is determined by a few support vectors.
Gradient boosting algorithm (Gradient Boosting) is an ensemble learning method that continuously improves the overall model performance by training a series of weak learners (typically decision trees) in series, each of which attempts to correct all the previous tree errors. The key of the gradient lifting algorithm is that each step advances in the gradient direction of decreasing the loss function, so that the model gradually approaches the optimal solution.
Taking a tobacco leaf potassium diagnosis index corresponding to a sample flue-cured tobacco planting area as a sample, taking an actual value of the potassium content of sample flue-cured tobacco leaves in the sample flue-cured tobacco planting area as a sample label, and respectively training the first initial model, the second initial model and the third initial model to obtain a trained first initial model, a trained second initial model and a trained third initial model;
and determining the model with optimal calculation precision and stability from the trained first initial model, the trained second initial model and the trained third initial model as a flue-cured tobacco leaf potassium content estimation model.
Specifically, after the trained first initial model, the trained second initial model and the trained third initial model are obtained, R (R-squared), RMSE (Root Mean Squared Error, root mean square error), MAPE (Mean Absolute Percentage Error ) and the like may be used as evaluation indexes to evaluate the calculation accuracy and stability of the trained first initial model, the trained second initial model and the trained third initial model, and further, the model with the best calculation accuracy and stability of the trained first initial model, the trained second initial model and the trained third initial model may be determined as the flue-cured tobacco potassium content estimation model.
Wherein R is an index for measuring the variance of the model interpretation, and reflects how much fluctuation of the dependent variable can be interpreted by fluctuation of the independent variable. The values range from 0 to 1.
RMSE measures the standard deviation of the difference between the predicted value and the actual value. RMSE is the square root of the MSE (mean square error) and is used to measure the degree of dispersion of data. The smaller the RMSE, the closer the prediction result of the representation model is to the true value, and the better the performance of the model.
MAPE is an indicator of prediction accuracy, expressed as the absolute value of the difference between the predicted value and the actual value, and is usually expressed in percent relative to the actual value. The smaller the MAPE, the higher the prediction accuracy of the representation model.
According to the embodiment of the invention, after the tobacco potassium diagnosis index of the to-be-estimated tobacco in each subarea of the to-be-estimated tobacco planting area is obtained based on the multispectral image of the to-be-estimated tobacco planting area, the tobacco potassium diagnosis index of the to-be-estimated tobacco in each subarea is input into the tobacco potassium content estimation model of the tobacco, and the estimated value of the potassium content of the tobacco in each subarea output by the tobacco potassium content estimation model of the tobacco is obtained, so that the potassium content of the tobacco in the large-area tobacco planting area can be estimated more accurately, more efficiently and more comprehensively, the potassium deficiency condition of the tobacco in the large-area tobacco planting area can be found more timely, a data basis can be provided for potassium fertilizer management work of the large-area tobacco planting area, the precision and the efficiency of the potassium fertilizer management work of the tobacco planting area can be improved, the yield and the quality of the tobacco can be further improved, and the benefit of the production of the tobacco can be improved.
As an optional embodiment, after obtaining the estimated value of the potassium content of the flue-cured tobacco leaf in each sub-area outputted by the potassium content estimation model of the flue-cured tobacco leaf, the method further includes: and drawing a potassium content distribution map of the flue-cured tobacco corresponding to the flue-cured tobacco planting area to be estimated based on the estimated value of the potassium content of the flue-cured tobacco in each subarea.
It should be noted that, the drawing of the potassium content distribution diagram of the flue-cured tobacco leaves in the global plot scale of the flue-cured tobacco planting area to be estimated aims at the overall monitoring and evaluation of the potassium content of the flue-cured tobacco leaves in the flue-cured tobacco planting area to be estimated, and aims at providing a more comprehensive and efficient display and management basis of the potassium content and the potassium deficiency condition of the flue-cured tobacco leaves in the flue-cured tobacco planting area to be estimated.
The traditional manual detection mode has the problems of uneven sampling, time consumption and labor consumption, is difficult to cover a large-scale flue-cured tobacco planting area, and is difficult to quickly acquire global information. Therefore, after the estimated value of the potassium content of the flue-cured tobacco leaves in each subarea of the flue-cured tobacco planting area to be estimated is obtained based on the method provided by the invention, the potassium content distribution map of the flue-cured tobacco leaves in the global land scale of the flue-cured tobacco planting area to be estimated can be drawn based on the estimated value of the potassium content of the flue-cured tobacco leaves in each subarea of the flue-cured tobacco planting area to be estimated through the modes of numerical calculation, mathematical statistics, condition judgment, deep learning technology and the like, so that the high-resolution and high-frequency monitoring of the potassium content and the potassium deficiency condition of the flue-cured tobacco leaves to be estimated in the flue-cured tobacco planting area to be estimated is realized, and more accurate and comprehensive data support is provided for agricultural management decisions.
As an optional embodiment, drawing a potassium content distribution map of flue-cured tobacco leaf corresponding to the flue-cured tobacco planting area to be estimated based on the estimated value of potassium content of the flue-cured tobacco leaf in each sub-area includes: determining the potassium deficiency grade of the flue-cured tobacco leaves in each subarea based on the estimated value of the potassium content of the flue-cured tobacco leaves in each subarea;
It should be noted that the lack of visual quantitative standards for potassium deficiency of cured tobacco leaves is a great challenge in the field of cured tobacco planting. In actual production, the potassium content of flue-cured tobacco leaves is usually expressed in percent, but these values may lack intuitive understanding and specific concepts for practitioners in the field of flue-cured tobacco planting. This results in the fact that practitioners in the field of flue-cured tobacco planting are difficult to accurately evaluate the potassium deficiency condition of flue-cured tobacco leaves, and therefore the health condition of flue-cured tobacco plants cannot be rapidly and accurately judged.
Therefore, there is a need to establish an operable, intuitive potassium deficiency ranking criteria. The potassium deficiency condition of the flue-cured tobacco leaves can be presented in a grade form which is easier to understand, so that practitioners in the field of flue-cured tobacco planting can intuitively know the potassium content of the flue-cured tobacco leaves.
The potassium deficiency grade classification standard is favorable for realizing rapid identification and distinction of the potassium deficiency condition of the flue-cured tobacco leaves, and provides an important basis for formulating corresponding potassium supplement schemes for different potassium deficiency grades. Therefore, a set of concise and easily understood potassium-deficiency grade classification standards of the flue-cured tobacco leaves are established, and the potassium-deficiency grade classification standards are very important for effectively managing and regulating potassium supply in the growth process of the flue-cured tobacco leaves.
The potassium deficiency grading standard is specifically shown in table 1.
TABLE 1 Potassium deficiency grading Standard
First in flue-cured tobacco planting area to be estimatedAfter the estimated value of the potassium content of the flue-cured tobacco leaves in the individual subareas, the first area of the planting area of the flue-cured tobacco to be estimated can be determined based on the table 1Potassium deficiency grade of flue-cured tobacco leaves in each subregion.
And filling colors corresponding to the potassium deficiency grades of the flue-cured tobacco leaves in each subarea in the areas corresponding to each subarea in the blank canvas, and obtaining a potassium content distribution diagram of the flue-cured tobacco leaves corresponding to the flue-cured tobacco planting areas to be estimated.
Specifically, after the potassium deficiency grade of the flue-cured tobacco leaves in each subarea in the flue-cured tobacco planting area to be estimated is obtained, the color corresponding to the potassium deficiency grade of the flue-cured tobacco leaves in each subarea can be filled in the area corresponding to each subarea in the blank canvas according to the potassium deficiency grade of the flue-cured tobacco leaves in each subarea, and a potassium content distribution map of the flue-cured tobacco leaves corresponding to the flue-cured tobacco planting area to be estimated is obtained.
Fig. 2 is a schematic diagram of a potassium content distribution diagram of flue-cured tobacco leaves corresponding to a planting area of flue-cured tobacco leaves to be estimated in the potassium content estimation method of flue-cured tobacco leaves provided by the invention.
According to the embodiment of the invention, the potassium deficiency condition grades of different plot areas can be effectively identified and divided through drawing the potassium content distribution map of the flue-cured tobacco leaves in the whole plot scale. The distribution diagram of the potassium content of the flue-cured tobacco leaves can intuitively display the distribution situation of the potassium deficiency grades of the tobacco leaves in different areas, so that farmers and related decision makers can quickly know the potassium deficiency situation in the flue-cured tobacco planting area under an integral view angle, and potassium supplement measures are formulated in a targeted manner, thereby optimizing a fertilization scheme and improving the potassium utilization efficiency. The drawing of the potassium content distribution diagram of the flue-cured tobacco leaves in the global land block scale is beneficial to promoting the application of the intelligent agricultural technology in the flue-cured tobacco planting field, and improves the precision and decision efficiency of agricultural management.
In order to facilitate understanding of the method for estimating the potassium content of flue-cured tobacco leaves provided by the invention, the method for estimating the potassium content of flue-cured tobacco leaves provided by the invention is described below by way of an example. Fig. 3 is a second flow chart of the potassium content estimation method for flue-cured tobacco leaves provided by the invention. As shown in fig. 3, the method for estimating potassium content in flue-cured tobacco leaves provided by the invention comprises the following steps: performing preparation work of potassium content estimation of tobacco leaves of the flue-cured tobacco to be estimated in the planting area of the flue-cured tobacco to be estimated, and confirming the growing period of the tobacco leaves of the flue-cured tobacco to be estimated;
Acquiring, processing and analyzing unmanned aerial vehicle images of a sample flue-cured tobacco planting area, acquiring a tobacco leaf potassium diagnosis index of the sample flue-cured tobacco in the sample flue-cured tobacco planting area, and acquiring an actual value of the potassium content of the sample flue-cured tobacco leaves;
acquiring a tobacco leaf potassium content estimation model based on the tobacco leaf potassium element diagnosis index of the sample tobacco leaf in the sample tobacco planting area and the actual value of the sample tobacco leaf potassium content;
Acquiring, processing and analyzing unmanned aerial vehicle images of the tobacco planting areas to be estimated, acquiring tobacco potassium diagnosis indexes of the tobacco to be estimated in each subarea of the tobacco planting areas to be estimated, and further acquiring estimated values of potassium content of the tobacco in each subarea of the tobacco planting areas to be estimated based on a tobacco potassium content estimation model;
Determining the potassium deficiency grade of the tobacco leaves in each subarea in the tobacco planting area to be estimated according to the estimated value of the potassium content of the tobacco leaves in each subarea in the tobacco planting area to be estimated;
and drawing a potassium content distribution diagram of the tobacco leaves corresponding to the tobacco planting area to be estimated according to the potassium deficiency grade of the tobacco leaves in each subarea in the tobacco planting area to be estimated.
According to the method for estimating the potassium content of the flue-cured tobacco leaves, provided by the invention, the unmanned aerial vehicle low-altitude remote sensing technology is utilized to rapidly acquire the images of the flue-cured tobacco planting area, and compared with the traditional manual detection, the monitoring period is greatly shortened, and the monitoring efficiency is improved. Based on multispectral images acquired by the multispectral sensor, the multispectral image is fully covered and spectrum data of a flue-cured tobacco planting area are acquired, so that the growth condition of flue-cured tobacco leaves can be accurately depicted, and the evaluation of global potassium deficiency condition is facilitated. By combining the multispectral image with the laboratory sample measurement result through a specially designed algorithm, a flue-cured tobacco leaf potassium content estimation model is constructed, and the estimated value of the potassium content of the flue-cured tobacco leaf can be more accurately obtained, so that the potassium deficiency grades of different land areas can be more accurately divided. Based on the obtained data, a potassium content distribution diagram of the flue-cured tobacco leaves in the global land block scale is drawn, the potassium deficiency conditions of different areas are more intuitively displayed, and a visual basis is provided for agricultural management and decision making.
Fig. 4 is a schematic structural view of the flue-cured tobacco leaf potassium content estimation device provided by the invention. The potassium content estimation device for flue-cured tobacco provided by the invention is described below with reference to fig. 4, and the potassium content estimation device for flue-cured tobacco described below and the potassium content estimation method for flue-cured tobacco provided by the invention described above can be referred to correspondingly. As shown in fig. 4, the apparatus includes: the device comprises an image acquisition module 401, a data processing module 402 and a result output module 403.
The image acquisition module 401 is configured to acquire a multispectral image of a flue-cured tobacco planting area to be estimated, in which flue-cured tobacco to be estimated is planted;
The data processing module 402 is configured to obtain a tobacco potassium diagnosis index of the flue-cured tobacco to be estimated in each sub-area in the planting area of the flue-cured tobacco to be estimated based on the multispectral image;
the result output module 403 is configured to input the tobacco potassium element diagnostic index of the flue-cured tobacco to be estimated in each sub-area into a flue-cured tobacco potassium content estimation model, and obtain an estimated value of the potassium content of the flue-cured tobacco in each sub-area output by the flue-cured tobacco potassium content estimation model;
the tobacco leaf potassium content estimation model is obtained by training based on tobacco leaf potassium diagnosis indexes corresponding to sample tobacco planting areas and actual values of sample tobacco leaf potassium content in the sample tobacco planting areas; the flue-cured tobacco to be estimated is in the same growth period as the sample flue-cured tobacco.
Specifically, the image acquisition module 401, the data processing module 402, and the result output module 403 are electrically connected.
Optionally, the data processing module 402 is specifically configured to determine, based on the correlation between each of the original bands and the actual value of the potassium content of the sample flue-cured tobacco, two original bands having the strongest correlation with the actual value of the potassium content of the sample flue-cured tobacco as sensitive bands, where each of the original bands includes a blue light band, a green light band, a red light band, and a near infrared band; acquiring the spectral reflectance of the canopy of each sub-region sensitive band based on the multispectral image; and calculating to obtain the tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea based on the canopy spectral reflectance of the sensitive wave band of each subarea.
Optionally, the data processing module 402 is further specifically configured to calculate a difference between a crown spectral reflectance of the first sensitive band and a crown spectral reflectance of the second sensitive band of each sub-region, as a first intermediate result corresponding to each sub-region, and calculate a sum of the crown spectral reflectance of the first sensitive band and the crown spectral reflectance of the second sensitive band of each sub-region, as a second intermediate result corresponding to each sub-region; and calculating the quotient of the first intermediate result and the second intermediate result corresponding to each subarea as a tobacco potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea.
Optionally, the image obtaining module 401 is specifically configured to obtain an unmanned aerial vehicle image of a flue-cured tobacco planting area to be estimated; based on the unmanned aerial vehicle image, obtain multispectral image.
Optionally, the result output module 403 may be further configured to construct a first initial model, a second initial model, and a third initial model based on a random forest algorithm, a support vector machine algorithm, and a gradient lifting algorithm, respectively; taking a tobacco leaf potassium diagnosis index corresponding to a sample flue-cured tobacco planting area as a sample, taking an actual value of the potassium content of sample flue-cured tobacco leaves in the sample flue-cured tobacco planting area as a sample label, and respectively training the first initial model, the second initial model and the third initial model to obtain a trained first initial model, a trained second initial model and a trained third initial model; and determining the model with optimal calculation precision and stability from the trained first initial model, the trained second initial model and the trained third initial model as a flue-cured tobacco leaf potassium content estimation model.
Optionally, the flue-cured tobacco leaf potassium content estimation device can further comprise an image drawing module.
The image drawing module is used for drawing a potassium content distribution map of the flue-cured tobacco corresponding to the flue-cured tobacco planting area to be estimated based on the estimated value of the potassium content of the flue-cured tobacco in each sub-area.
Optionally, the image drawing module is specifically configured to determine a potassium deficiency level of the flue-cured tobacco leaf in each sub-area based on an estimated value of the potassium content of the flue-cured tobacco leaf in each sub-area; and filling colors corresponding to the potassium deficiency grades of the flue-cured tobacco leaves in each subarea in the areas corresponding to each subarea in the blank canvas, and obtaining a potassium content distribution diagram of the flue-cured tobacco leaves corresponding to the flue-cured tobacco planting areas to be estimated.
According to the potassium content estimation device for the flue-cured tobacco leaves, after the potassium diagnosis index of the flue-cured tobacco leaves to be estimated in each subarea in the flue-cured tobacco planting area is obtained based on the multispectral image of the flue-cured tobacco planting area to be estimated, the potassium diagnosis index of the flue-cured tobacco leaves to be estimated in each subarea is input into the potassium content estimation model of the flue-cured tobacco leaves, the estimated value of the potassium content of the flue-cured tobacco leaves in each subarea output by the potassium content estimation model of the flue-cured tobacco leaves is obtained, the potassium content of the flue-cured tobacco leaves in the flue-cured tobacco planting area in a large area can be estimated more accurately, more efficiently and more comprehensively, the potassium deficiency condition of the flue-cured tobacco leaves in the flue-cured tobacco planting area in a large area can be found more timely, a data basis can be provided for potassium fertilizer management work of the flue-cured tobacco planting area, the precision and the efficiency of the potassium fertilizer management work of the flue-cured tobacco planting area can be improved, and the flue-cured tobacco yield and the flue-cured tobacco production benefit can be improved.
Fig. 5 illustrates a physical schematic diagram of an electronic device, as shown in fig. 5, which may include: processor 510, communication interface (Communications Interface) 520, memory 530, and communication bus 540, wherein processor 510, communication interface 520, memory 530 complete communication with each other through communication bus 540. Processor 510 may invoke logic instructions in memory 530 to perform a flue-cured tobacco potassium content estimation method comprising: acquiring multispectral images of a flue-cured tobacco planting area to be estimated, and planting flue-cured tobacco to be estimated in the flue-cured tobacco planting area to be estimated; based on the multispectral image, acquiring a tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea of the planting area of the flue-cured tobacco to be estimated; inputting the tobacco leaf potassium element diagnostic index of the flue-cured tobacco to be estimated in each subarea into a flue-cured tobacco leaf potassium content estimation model, and obtaining an estimated value of the potassium content of the flue-cured tobacco leaf in each subarea output by the flue-cured tobacco leaf potassium content estimation model; the tobacco leaf potassium content estimation model is obtained by training based on tobacco leaf potassium diagnosis indexes corresponding to sample tobacco planting areas and actual values of sample tobacco leaf potassium content in the sample tobacco planting areas; the flue-cured tobacco to be estimated is in the same growth period as the sample flue-cured tobacco.
Further, the logic instructions in the memory 530 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product comprising a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of executing the method for estimating the potassium content of flue-cured tobacco leaves provided by the above methods, the method comprising: acquiring multispectral images of a flue-cured tobacco planting area to be estimated, and planting flue-cured tobacco to be estimated in the flue-cured tobacco planting area to be estimated; based on the multispectral image, acquiring a tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea of the planting area of the flue-cured tobacco to be estimated; inputting the tobacco leaf potassium element diagnostic index of the flue-cured tobacco to be estimated in each subarea into a flue-cured tobacco leaf potassium content estimation model, and obtaining an estimated value of the potassium content of the flue-cured tobacco leaf in each subarea output by the flue-cured tobacco leaf potassium content estimation model; the tobacco leaf potassium content estimation model is obtained by training based on tobacco leaf potassium diagnosis indexes corresponding to sample tobacco planting areas and actual values of sample tobacco leaf potassium content in the sample tobacco planting areas; the flue-cured tobacco to be estimated is in the same growth period as the sample flue-cured tobacco.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the flue-cured tobacco leaf potassium content estimation method provided by the above methods, the method comprising: acquiring multispectral images of a flue-cured tobacco planting area to be estimated, and planting flue-cured tobacco to be estimated in the flue-cured tobacco planting area to be estimated; based on the multispectral image, acquiring a tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea of the planting area of the flue-cured tobacco to be estimated; inputting the tobacco leaf potassium element diagnostic index of the flue-cured tobacco to be estimated in each subarea into a flue-cured tobacco leaf potassium content estimation model, and obtaining an estimated value of the potassium content of the flue-cured tobacco leaf in each subarea output by the flue-cured tobacco leaf potassium content estimation model; the tobacco leaf potassium content estimation model is obtained by training based on tobacco leaf potassium diagnosis indexes corresponding to sample tobacco planting areas and actual values of sample tobacco leaf potassium content in the sample tobacco planting areas; the flue-cured tobacco to be estimated is in the same growth period as the sample flue-cured tobacco.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. The method for estimating the potassium content of the flue-cured tobacco leaves is characterized by comprising the following steps of:
acquiring multispectral images of a flue-cured tobacco planting area to be estimated, wherein flue-cured tobacco to be estimated is planted in the flue-cured tobacco planting area to be estimated;
Based on the multispectral image, acquiring a tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea of the flue-cured tobacco planting area to be estimated;
Inputting the tobacco leaf potassium element diagnostic index of the tobacco leaf to be estimated in each subarea into a tobacco leaf potassium content estimation model of the tobacco leaf to be estimated, and obtaining an estimated value of the potassium content of the tobacco leaf in each subarea output by the tobacco leaf potassium content estimation model of the tobacco leaf to be estimated;
The tobacco leaf potassium content estimation model is obtained by training based on tobacco leaf potassium diagnosis indexes corresponding to sample tobacco planting areas and actual values of sample tobacco leaf potassium content in the sample tobacco planting areas; the flue-cured tobacco to be estimated and the sample flue-cured tobacco are in the same growth period;
The obtaining the tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea of the planting area of the flue-cured tobacco to be estimated based on the multispectral image comprises the following steps:
Based on the correlation between each original wave band and the actual value of the potassium content of the sample flue-cured tobacco leaves, respectively determining two original wave bands with the strongest correlation with the actual value of the potassium content of the sample flue-cured tobacco leaves as sensitive wave bands, wherein each original wave band comprises a blue light wave band, a green light wave band, a red edge wave band and a near infrared wave band;
acquiring the canopy spectral reflectivity of the sensitive wave band of each subarea based on the multispectral image;
calculating to obtain a tobacco potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea based on the canopy spectral reflectivity of the sensitive wave band in each subarea; the sensitive wave bands comprise a first sensitive wave band and a second sensitive wave band, and the tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea is calculated based on the canopy spectral reflectance of the sensitive wave band of each subarea, and the method comprises the following steps:
Calculating the difference between the crown spectral reflectance of the first sensitive wave band and the crown spectral reflectance of the second sensitive wave band of each subarea, and taking the difference as a first intermediate result corresponding to each subarea, and calculating the sum of the crown spectral reflectance of the first sensitive wave band of each subarea and the crown spectral reflectance of the second sensitive wave band of each subarea, and taking the sum as a second intermediate result corresponding to each subarea;
Calculating the quotient of the first intermediate result and the second intermediate result corresponding to each subarea as a tobacco potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea;
the tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea is calculated by the following formula:
；
Wherein, Representing the first region of the flue-cured tobacco planting area to be estimatedThe tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each sub-area,，Representing the total number of sub-areas in the flue-cured tobacco planting area to be estimated; representing the first region of the flue-cured tobacco planting area to be estimated The spectral reflectance of the canopy of the first sensitive wave band of the sub-region; representing the first region of the flue-cured tobacco planting area to be estimated And the spectral reflectivity of the top layer of the second sensitive wave band of the sub-region.
2. The method for estimating the potassium content of flue-cured tobacco leaves according to claim 1, wherein before inputting the tobacco potassium diagnosis index of the flue-cured tobacco to be estimated in each of the sub-areas into the flue-cured tobacco leaf potassium content estimation model, the method further comprises:
Respectively constructing a first initial model, a second initial model and a third initial model based on a random forest algorithm, a support vector machine algorithm and a gradient lifting algorithm;
Taking a tobacco leaf potassium diagnosis index corresponding to the sample flue-cured tobacco planting area as a sample, taking an actual value of the potassium content of sample flue-cured tobacco leaves in the sample flue-cured tobacco planting area as a sample label, and respectively training the first initial model, the second initial model and the third initial model to obtain a trained first initial model, a trained second initial model and a trained third initial model;
and determining the model with the best calculation precision and stability among the trained first initial model, the trained second initial model and the trained third initial model as the flue-cured tobacco leaf potassium content estimation model.
3. The method for estimating the potassium content of flue-cured tobacco leaves according to claim 1, wherein the step of obtaining a multispectral image of a flue-cured tobacco planting area to be estimated comprises:
Acquiring an unmanned aerial vehicle image of the flue-cured tobacco planting area to be estimated;
And acquiring the multispectral image based on the unmanned aerial vehicle image.
4. The method for estimating the potassium content of flue-cured tobacco leaves according to any one of claims 1 to 3, wherein after the obtaining of the estimated value of the potassium content of flue-cured tobacco leaves in each of the sub-areas outputted by the flue-cured tobacco leaf potassium content estimation model, the method further comprises:
And drawing a potassium content distribution map of the flue-cured tobacco corresponding to the flue-cured tobacco planting area to be estimated based on the estimated value of the potassium content of the flue-cured tobacco in each sub-area.
5. The method for estimating the potassium content of flue-cured tobacco leaves according to claim 4, wherein the drawing the potassium content distribution map of flue-cured tobacco leaves corresponding to the flue-cured tobacco planting area to be estimated based on the estimated value of the potassium content of flue-cured tobacco leaves in each sub-area comprises:
Determining the potassium deficiency grade of the flue-cured tobacco leaves in each subarea based on the estimated value of the potassium content of the flue-cured tobacco leaves in each subarea;
And filling colors corresponding to the potassium deficiency grades of the flue-cured tobacco leaves in each subarea in the corresponding area of each subarea in the blank canvas, and obtaining a potassium content distribution diagram of the flue-cured tobacco leaves corresponding to the flue-cured tobacco planting area to be estimated.
6. A flue-cured tobacco leaf potassium content estimation device, characterized by comprising:
The image acquisition module is used for acquiring multispectral images of a flue-cured tobacco planting area to be estimated, wherein flue-cured tobacco to be estimated is planted in the flue-cured tobacco planting area to be estimated;
the data processing module is used for acquiring tobacco leaf potassium diagnosis indexes of the flue-cured tobacco to be estimated in each subarea of the planting area of the flue-cured tobacco to be estimated based on the multispectral image;
The result output module is used for inputting the tobacco leaf potassium element diagnosis index of the tobacco leaf to be estimated in each subarea into a tobacco leaf potassium content estimation model of the tobacco leaf to be estimated, and obtaining an estimated value of the potassium content of the tobacco leaf in each subarea output by the tobacco leaf potassium content estimation model of the tobacco leaf to be estimated;
The tobacco leaf potassium content estimation model is obtained by training based on tobacco leaf potassium diagnosis indexes corresponding to sample tobacco planting areas and actual values of sample tobacco leaf potassium content in the sample tobacco planting areas; the flue-cured tobacco to be estimated and the sample flue-cured tobacco are in the same growth period;
the data processing module obtains the tobacco potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea of the planting area of the flue-cured tobacco to be estimated based on the multispectral image, and the data processing module comprises the following steps:
Based on the correlation between each original wave band and the actual value of the potassium content of the sample flue-cured tobacco leaves, respectively determining two original wave bands with the strongest correlation with the actual value of the potassium content of the sample flue-cured tobacco leaves as sensitive wave bands, wherein each original wave band comprises a blue light wave band, a green light wave band, a red edge wave band and a near infrared wave band;
acquiring the canopy spectral reflectivity of the sensitive wave band of each subarea based on the multispectral image;
The tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea is calculated based on the canopy spectral reflectance of the sensitive wave band of each subarea;
The sensitive wave bands comprise a first sensitive wave band and a second sensitive wave band, the data processing module calculates and obtains a tobacco potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea based on the canopy spectral reflectance of the sensitive wave band of each subarea, and the data processing module comprises the following steps:
Calculating the difference between the crown spectral reflectance of the first sensitive wave band and the crown spectral reflectance of the second sensitive wave band of each subarea, and taking the difference as a first intermediate result corresponding to each subarea, and calculating the sum of the crown spectral reflectance of the first sensitive wave band of each subarea and the crown spectral reflectance of the second sensitive wave band of each subarea, and taking the sum as a second intermediate result corresponding to each subarea;
Calculating the quotient of the first intermediate result and the second intermediate result corresponding to each subarea as a tobacco potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea;
the tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each subarea is calculated by the following formula:
；
Wherein, Representing the first region of the flue-cured tobacco planting area to be estimatedThe tobacco leaf potassium diagnosis index of the flue-cured tobacco to be estimated in each sub-area,，Representing the total number of sub-areas in the flue-cured tobacco planting area to be estimated; representing the first region of the flue-cured tobacco planting area to be estimated The spectral reflectance of the canopy of the first sensitive wave band of the sub-region; representing the first region of the flue-cured tobacco planting area to be estimated And the spectral reflectivity of the top layer of the second sensitive wave band of the sub-region.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for estimating the potassium content of flue-cured tobacco leaves according to any one of claims 1 to 5 when executing the program.
8. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the flue-cured tobacco leaf potassium content estimation method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410637619.7A CN118209502B (en) | 2024-05-22 | 2024-05-22 | Method and device for estimating potassium content of flue-cured tobacco leaves, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410637619.7A CN118209502B (en) | 2024-05-22 | 2024-05-22 | Method and device for estimating potassium content of flue-cured tobacco leaves, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118209502A CN118209502A (en) | 2024-06-18 |
| CN118209502B true CN118209502B (en) | 2024-08-20 |
Family
ID=91446585
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410637619.7A Active CN118209502B (en) | 2024-05-22 | 2024-05-22 | Method and device for estimating potassium content of flue-cured tobacco leaves, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118209502B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112697724A (en) * | 2020-12-09 | 2021-04-23 | 云南省烟草农业科学研究院 | Hyperspectral field tobacco leaf potassium oxide content prediction method and system based on unmanned aerial vehicle |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3428966A1 (en) * | 1984-08-06 | 1986-02-06 | Institut po Techničeska Kibernetika i Robotika, Sofia/Sofija | Method and apparatus for sorting tobacco leaves |
| CN104593497B (en) * | 2015-01-15 | 2016-08-17 | 湖南农业大学 | Molecular marker, primer, test kit and detection method for quickly detection Potassium Content in Flue-cured Tobacco Leaves height |
| CN111912793A (en) * | 2020-08-21 | 2020-11-10 | 河南农业大学 | Method for measuring cadmium content in tobacco by hyperspectral and establishment of prediction model |
| CN113237836A (en) * | 2021-05-10 | 2021-08-10 | 福建省烟草公司南平市公司 | Flue-cured tobacco leaf moisture content estimation method based on hyperspectral image |
| CN114862858B (en) * | 2022-07-08 | 2022-11-11 | 湖北省烟草科学研究院 | Cigar harvesting maturity identification method and system based on ensemble learning |
-
2024
- 2024-05-22 CN CN202410637619.7A patent/CN118209502B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112697724A (en) * | 2020-12-09 | 2021-04-23 | 云南省烟草农业科学研究院 | Hyperspectral field tobacco leaf potassium oxide content prediction method and system based on unmanned aerial vehicle |
Non-Patent Citations (1)
| Title |
|---|
| 不同水分胁迫程度下烤烟叶片钾含量的光谱响应;李梦竹等;中国烟草学报;20200814;第26卷(第4期);86-92 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118209502A (en) | 2024-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Qiao et al. | UAV-based chlorophyll content estimation by evaluating vegetation index responses under different crop coverages | |
| Qi et al. | Monitoring of peanut leaves chlorophyll content based on drone-based multispectral image feature extraction | |
| Munnaf et al. | Site-specific seeding using multi-sensor and data fusion techniques: A review | |
| CN112903600B (en) | Rice nitrogen fertilizer recommendation method based on multispectral image of fixed-wing unmanned aerial vehicle | |
| US20150206255A1 (en) | Method and system to prescribe variable seeding density across a cultivated field using remotely sensed data | |
| Liu et al. | Estimating potato above-ground biomass by using integrated unmanned aerial system-based optical, structural, and textural canopy measurements | |
| CN110376167A (en) | Rice leaf nitrogen content monitoring method based on unmanned plane EO-1 hyperion | |
| CN108229403A (en) | A kind of mixed model construction method for being used to estimate vegetation leaf area index | |
| CN111399508A (en) | Intelligent agriculture system and intelligent agriculture method | |
| CN111028096A (en) | System and method for integrating space, air and ground data | |
| CN104408307A (en) | Method for rapidly monitoring morbidity degree of in-field wheat powdery mildew and monitoring model establishment method thereof | |
| CN111316802B (en) | Crop water and fertilizer monitoring method, device, equipment and medium based on large-scale sprinkler | |
| CN114140695B (en) | Prediction method and system for tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing | |
| Guo et al. | Identifying crop phenology using maize height constructed from multi-sources images | |
| CN116485757A (en) | Winter wheat total nitrogen content prediction method | |
| WO2023195863A1 (en) | Methods and systems for estimating crop yield from vegetation index data | |
| Zhai et al. | CatBoost algorithm for estimating maize above-ground biomass using unmanned aerial vehicle-based multi-source sensor data and SPAD values | |
| Bao et al. | Forecasting spring maize yield using vegetation indices and crop phenology metrics from UAV observations | |
| Pasichnyk et al. | Remote field monitoring results feasibility assessment for energy crops yield management. | |
| CN117074340A (en) | Wheat nitrogen content measuring and calculating method based on hyperspectral remote sensing image of unmanned aerial vehicle | |
| CN118209502B (en) | Method and device for estimating potassium content of flue-cured tobacco leaves, electronic equipment and storage medium | |
| CN116297243B (en) | Method and device for estimating dressing amount of flue-cured tobacco nitrogenous fertilizer, electronic equipment and storage medium | |
| Taylor et al. | Applications of optical sensing of crop health and vigour | |
| Sweet et al. | Plant height defined growth curves during vegetative development have the potential to predict end of season maize yield and assist with mid-season management decisions | |
| Grego et al. | Technologies developed in precision agriculture. |
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 |