CN114155526A - Tomato fruit growth prediction method, device, equipment and product - Google Patents
Tomato fruit growth prediction method, device, equipment and product Download PDFInfo
- Publication number
- CN114155526A CN114155526A CN202111322534.2A CN202111322534A CN114155526A CN 114155526 A CN114155526 A CN 114155526A CN 202111322534 A CN202111322534 A CN 202111322534A CN 114155526 A CN114155526 A CN 114155526A
- Authority
- CN
- China
- Prior art keywords
- leaf
- tomato
- fruits
- neural network
- canopy
- 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.)
- Granted
Links
- 235000013399 edible fruits Nutrition 0.000 title claims abstract description 284
- 235000007688 Lycopersicon esculentum Nutrition 0.000 title claims abstract description 221
- 238000000034 method Methods 0.000 title claims abstract description 79
- 240000003768 Solanum lycopersicum Species 0.000 title claims description 222
- 230000003595 spectral effect Effects 0.000 claims abstract description 96
- 238000003062 neural network model Methods 0.000 claims abstract description 85
- 238000001514 detection method Methods 0.000 claims abstract description 17
- 230000008569 process Effects 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 230000000243 photosynthetic effect Effects 0.000 claims description 34
- 238000010586 diagram Methods 0.000 claims description 28
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 27
- 238000001228 spectrum Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 12
- 238000011282 treatment Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 8
- 230000000877 morphologic effect Effects 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 5
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 abstract description 18
- 229910052799 carbon Inorganic materials 0.000 abstract description 18
- 241000227653 Lycopersicon Species 0.000 abstract 8
- 239000000523 sample Substances 0.000 description 15
- 238000004088 simulation Methods 0.000 description 9
- 230000008859 change Effects 0.000 description 8
- 241000196324 Embryophyta Species 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 210000000056 organ Anatomy 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 230000009418 agronomic effect Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000004907 flux Effects 0.000 description 2
- 230000002262 irrigation Effects 0.000 description 2
- 238000003973 irrigation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005070 ripening Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 230000007613 environmental effect Effects 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
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 238000005381 potential energy Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits
Abstract
The invention provides a tomato fruit growth prediction method, a device, equipment and a product, which relate to the technical field of agriculture, and the method comprises the following steps: acquiring a canopy spectral image of a tomato canopy, and respectively extracting a leaf spectral image only containing leaves and a fruit form binary image only containing fruits; inputting the spectral image of the blade only containing the blade into a blade neural network model to obtain blade parameters; performing angular point detection analysis on the fruit shape binary image only containing the fruits to obtain the number of the tomatoes; acquiring phloem sugar concentrations under different planting conditions based on the canopy spectral image, the leaf parameters and the number of the tomatoes; inputting the phloem sugar concentrations under different planting conditions into a tomato fruit growth model to obtain the growth dynamic process of fresh weight and dry weight of the tomato fruits. The method can effectively reflect the influence of different planting conditions on the carbon supply level of the tomato fruits, and further improve the prediction precision of the tomato fruit growth.
Description
Technical Field
The invention relates to the technical field of agriculture, in particular to a tomato fruit growth prediction method, device, equipment and product.
Background
External environmental factors and agronomic management can affect water and carbon flux between plants and fruits, and further affect growth dynamics of dry weight and fresh weight of fruits. The tomato fruit growth model (TOM-GRO model) considers the change process of the moisture and dry matter of tomato fruits, and simulates the water and carbon flux entering the fruits from plants by inputting air temperature, relative humidity, stem water potential and phloem sugar concentration (Cp), thereby predicting the change process of the dry weight and fresh weight of the tomato fruits. Among them, phloem sugar concentration is a key factor that governs the quality of dry fruits input into plants, and in previous studies, it is generally assumed that the Cp varies in the same range under different conditions. However, the actual planting conditions such as environment and agricultural measures may change the growth process of plants and fruits, change the variation range of Cp, and further influence the accumulation of dry weight and fresh weight of fruits. Therefore, it is necessary to quantify Cp under different planting conditions.
Disclosure of Invention
The invention provides a tomato fruit growth prediction method, a device, equipment and a product, which are used for solving the defect that the actual planting conditions such as environment and agricultural measures in the prior art can change the growth process of plants and fruits, effectively reflecting the influence of different planting conditions on the carbon supply level of tomato fruits and further improving the prediction precision of the tomato fruit growth.
The invention provides a tomato fruit growth prediction method, which comprises the following steps:
acquiring a canopy spectral image of a tomato canopy, and extracting a leaf spectral image only containing leaves and a fruit form binary image only containing fruits from the canopy spectral image;
inputting the leaf spectral image only containing the leaves into a leaf neural network model to obtain leaf parameters of the tomato canopy output by the leaf neural network model; wherein the leaf parameters comprise leaf photosynthetic rate, leaf water content and leaf area;
performing angular point detection analysis on the fruit shape binary image only containing the fruits to obtain the number of the tomatoes;
obtaining phloem sugar concentrations under different planting conditions based on the leaf parameters and the number of the tomato fruits;
inputting the phloem sugar concentrations under different planting conditions into a tomato fruit growth model to obtain the dynamic growth process of fresh weight and dry weight of the tomato fruits under different planting conditions output by the tomato fruit growth model; the tomato fruit growth model is obtained by training based on the phloem sugar concentration of a sample under different planting conditions.
According to the tomato fruit growth prediction method provided by the invention, the phloem sugar concentration under different planting conditions is obtained based on the leaf parameters and the number of the tomato fruits, and the method specifically comprises the following steps:
acquiring tomato source-to-library ratios under different planting conditions and full treatment conditions based on the leaf parameters and the number of the tomatoes;
obtaining the phloem sugar concentration under different planting conditions based on the tomato source-to-sink ratio and the phloem sugar concentration under the full treatment conditions.
According to the tomato fruit growth prediction method provided by the invention, the acquiring of the canopy spectrum image of the tomato canopy and the extracting of the leaf spectrum image only containing the leaves and the fruit shape binary image only containing the fruits from the canopy spectrum image respectively comprise:
and removing the background in the canopy spectral image to obtain a leaf spectral image only containing leaves and a fruit shape binary image only containing fruits.
According to the tomato fruit growth prediction method provided by the invention, the background in the canopy spectrum image is removed to obtain the leaf spectrum image only containing the leaves and the fruit shape binary image only containing the fruits, and the method specifically comprises the following steps:
clustering, dividing and other processing are carried out on the canopy spectral image to obtain a leaf vector diagram only containing leaves and a fruit vector diagram only containing fruits;
carrying out mask processing on the canopy spectral image by using the blade vector diagram only containing the blades, and extracting to obtain the blade spectral image only containing the blades;
and carrying out binarization processing on the canopy spectral image by using the fruit vector diagram only containing the fruits to obtain a fruit form binary image only containing the fruits.
According to the tomato fruit growth prediction method provided by the invention, the leaf spectral image only containing the leaves is input into the leaf neural network model to obtain the leaf parameters of the tomato canopy output by the leaf neural network model, and the method specifically comprises the following steps:
inputting a leaf spectral image only containing leaves into a leaf photosynthetic rate neural network model to obtain the leaf photosynthetic rate output by the leaf photosynthetic rate neural network model;
inputting a blade spectral image only containing blades into a blade area neural network model to obtain the blade area output by the blade area neural network model;
inputting a leaf spectral image only containing leaves into a leaf water content neural network model to obtain the leaf water content output by the leaf water content neural network model;
the leaf photosynthetic rate neural network model, the leaf area neural network model and the leaf moisture content neural network model form the leaf neural network model, and the leaf photosynthetic rate neural network model, the leaf area neural network model and the leaf moisture content neural network model are obtained based on sample leaf spectral image training only including leaves.
According to the tomato fruit growth prediction method provided by the invention, the angular point detection analysis is carried out on the fruit shape binary image only containing fruits to obtain the number of tomato fruits, and the method specifically comprises the following steps:
identifying a fruit shape binary image shape structure only containing fruits to obtain a skeleton extraction image;
and performing corner detection on the skeleton extraction image based on the R language to obtain the number of the tomato fruits.
The present invention also provides a tomato fruit growth prediction device, comprising:
the extraction module is used for acquiring a canopy spectral image of a tomato canopy and extracting a leaf spectral image only containing leaves and a fruit form binary image only containing fruits from the canopy spectral image;
the first acquisition module is used for inputting the leaf spectral image only containing the leaves into a leaf neural network model to obtain leaf parameters of the tomato canopy output by the leaf neural network model; wherein the leaf parameters comprise leaf photosynthetic rate, leaf water content and leaf area;
the second acquisition module is used for carrying out angular point detection analysis on the fruit shape binary image only containing the fruits to obtain the number of the tomato fruits;
the third acquisition module is used for acquiring phloem sugar concentrations under different planting conditions based on the leaf parameters and the number of the tomato fruits;
the prediction module is used for inputting the phloem sugar concentration under different planting conditions into a tomato fruit growth model to obtain the growth dynamic process of the fresh weight and the dry weight of the tomato fruit under different planting conditions output by the tomato fruit growth model; the tomato fruit growth model is obtained by training based on the phloem sugar concentration of a sample under different planting conditions.
The invention also provides an electronic device, comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the tomato fruit growth prediction method.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method for tomato fruit growth prediction as described in any one of the above.
The present invention also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of the method for predicting tomato fruit growth as described in any one of the above.
According to the tomato fruit growth prediction method, device, equipment and product provided by the invention, based on the canopy spectrum image of the tomato canopy, the leaf parameters and the number of tomato fruits are obtained, so that the tomato source library ratio under different planting conditions is obtained, the carbon supply level of the fruits in the tomato growth model is adjusted, the tomato source library ratio which is more suitable for actual planting and production is obtained, the influence of the different planting conditions on the phloem sugar concentration is further quantized, the influence of the different planting conditions on the carbon supply level of the tomato fruits can be effectively reflected, the tomato fruit growth prediction precision is further improved, and the method has the advantages of nondestructive observation, continuous high efficiency, forward-looking diagnosis and the like in the aspects of guiding tomato planting, fruit growth prediction and the like.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of the tomato fruit growth prediction method provided by the present invention;
FIG. 2 is a schematic flow chart of step S100 in the method for predicting tomato fruit growth provided by the present invention;
fig. 3 is a specific flowchart of step S200 in the method for predicting tomato fruit growth provided by the present invention;
FIG. 4 is a flowchart illustrating the specific step S300 of the method for predicting tomato fruit growth according to the present invention;
fig. 5 is a schematic diagram of a fruit morphology binary image only including fruits obtained in the method for predicting tomato fruit growth provided by the present invention;
FIG. 6 is a schematic diagram of skeleton extraction diagram obtained in the method for predicting tomato fruit growth provided by the present invention;
FIG. 7 is a schematic diagram of the number of tomato fruits obtained by the method for predicting tomato fruit growth provided by the present invention;
FIG. 8 is a schematic diagram of phloem sugar concentration over time under fully processed conditions obtained in the tomato fruit growth prediction method provided by the present invention;
fig. 9 is a schematic structural view of a tomato fruit growth prediction device provided by the present invention;
FIG. 10 is a schematic structural diagram of an extraction module in the tomato fruit growth prediction device provided by the present invention;
fig. 11 is a schematic structural diagram of a first obtaining module in the tomato fruit growth prediction apparatus provided by the present invention;
fig. 12 is a schematic structural diagram of a second obtaining module in the tomato fruit growth prediction apparatus provided by the present invention;
FIG. 13 is a schematic representation of a tomato fruit growth model used in the present invention;
fig. 14 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The tomato fruit growth prediction method of the present invention is described below with reference to fig. 1, and comprises the following steps:
s100, acquiring a canopy spectral image of a tomato canopy, and extracting a leaf spectral image only containing leaves and a fruit form binary image only containing fruits from the canopy spectral image.
S200, inputting the leaf spectral image only containing the leaf into a leaf neural network model to obtain leaf parameters of the tomato canopy output by the leaf neural network model, wherein the leaf parameters comprise leaf photosynthetic rate (Pn), Leaf Water Content (LWC) and Leaf Area (LA).
In the method, the leaf neural network model is trained on a sample leaf spectral image containing only leaves.
S300, performing angular point detection analysis on the fruit shape binary image only containing the fruits to obtain the number (Fn) of the tomato fruits.
S400, acquiring tomato source-to-library ratios (SS) under different planting conditions and full treatment conditions based on leaf parameters and tomato fruit numberiAnd SSck) And based on the tomato source-to-pool ratio (SS) under sufficient treatment conditionsck) And phloem sugar concentration (Cp)ck) Obtaining phloem sugar concentration (Cp) under different planting conditionsi)。
Under the planting condition of i, the tomato source library is compared with SSiThe calculation formula of (2) is as follows:
fully treating tomato source-to-store ratio SS under planting conditionsckThe calculation formula of (2) is as follows:
wherein LAck、Pnck、FnckAnd LWCckRespectively under the condition of fully treating the plantingLeaf area, photosynthetic rate of the leaves, number of tomato fruits and water content of the leaves.
According to the present study, the phloem sugar concentration CpckIt shows a sinusoidal variation with the solar radiation during the day, so in this example, in combination with the previous findings under adequate treatment conditions, CpckThe value is 0.15-0.35mol L-1Within one day CpckThe variation of (c) is shown in fig. 8.
Phloem sugar concentration Cp under different planting conditionsiThe calculation formula of (2) is as follows:
s500, phloem sugar concentration (Cp) under different planting conditionsi) Inputting the fresh weight and dry weight of the tomato fruits into a tomato fruit growth model to obtain the growth dynamic process of the fresh weight and the dry weight of the tomato fruits under different planting conditions output by the tomato fruit growth model. The tomato fruit growth model is obtained by training based on the phloem sugar concentration of a sample under different planting conditions.
In this example, the tomato fruit growth model was the TOM-GRO model. A schematic diagram of the TOM-GRO model is shown in FIG. 13. The model drives the fruit to expand by the water potential of the tomato stem, and drives the dry matter accumulation of the fruit by the sugar concentration Cp of the phloem of the stem, thereby simulating the fresh weight and dry weight change of the fruit.
In step S500, the influence of different planting conditions on the growth of the tomato plants and fruits and the relationship between the tomato plants and fruits can be considered, so that the dynamic changes of the dry weight and fresh weight of the tomato fruits under different planting conditions can be effectively simulated.
Since tomato leaves and fruits are important source and sink items, the correlation between source and sink strengths can affect the carbon input of fruits. The source-to-pool ratio of plants is a relatively abstract and dynamic index, wherein the source organ, the source intensity and the pool organ and pool intensity are involved, and the characterization mode is less clear. In the input parameters of the existing tomato fruit growth model, the phloem sugar concentration Cp representing the carbon supply of tomato fruits is the same level under different planting conditions, but obviously, the method does not meet the practical requirements of planting and production because the carbon supply of tomato fruits is influenced by the change of external environment and agricultural measures. Therefore, the existing methods cannot effectively characterize the influence of different planting conditions on the carbon supply of tomato fruits, i.e. the phloem sugar concentration Cp value.
According to the tomato fruit growth prediction method, leaf parameters and the number of tomato fruits are obtained based on the canopy spectrum image of the tomato canopy, so that the tomato source-base ratios under different planting conditions are obtained, the carbon supply level of the fruits in the tomato growth model is adjusted, the tomato source-base ratio which is more suitable for actual planting and production is obtained, the influence of the different planting conditions on the phloem sugar concentration is further quantized, the influence of the different planting conditions on the carbon supply level of the tomato fruits can be effectively reflected, the tomato fruit growth prediction precision is further improved, and the method has the advantages of nondestructive observation, continuous high efficiency, forward-looking diagnosis and the like in the aspects of guiding tomato planting, fruit growth prediction and the like.
In the embodiment, during the period from fruit setting to color turning and maturing of the tomato fruits, a handheld multispectral probe is used for shooting and acquiring data above tomato plants, and canopy spectrum images of tomato canopies are acquired every 5-7 days.
It should be noted that the period from fruit setting to ripening and color changing of the tomato fruit is an important period for the tomato fruit to accumulate moisture and dry matter, so that the handheld multispectral probe can be used for scanning above the tomato plant at intervals of 5-7 days in the period to obtain the canopy spectrum image of the tomato canopy.
In consideration of the quality of the acquired canopy spectral images, the method can select 11:00-13:00 times with sufficient light and no wind or low wind speed to shoot, and canopy spectral images of tomato growth in various growth stages are obtained.
The method for extracting the leaf spectral image only including the leaf and the fruit form binary image only including the fruit from the canopy spectral image specifically includes: and removing the background in the canopy spectral image to obtain a leaf spectral image only containing leaves and a fruit form binary image only containing fruits.
In step S100, software such as enii removes the background in the obtained canopy spectral image by means of support vector machine segmentation, clustering, or the like, and obtains a leaf spectral image including only leaves and a fruit morphology binary image including only fruits.
The method for predicting tomato fruit growth of the present invention is described below with reference to fig. 2, and step S100 specifically includes the following steps:
and S110, performing segmentation, clustering and other modes on the canopy spectral image to obtain a leaf vector diagram only containing leaves and a fruit vector diagram only containing fruits.
And S120, performing mask processing on the canopy spectral image by using the vector diagram only containing the blades, and extracting to obtain a blade spectral image only containing the blades, specifically to obtain a spectral TIFF format image file only containing the blades.
S130, binarizing the canopy spectrum image by using the fruit vector image containing only fruits to obtain a fruit shape binary image containing only fruits, as shown in fig. 5.
The method for predicting tomato fruit growth of the present invention is described below with reference to fig. 3, and step S200 specifically includes the following steps:
s210, inputting the leaf spectral image only containing the leaves into the leaf photosynthetic rate neural network model to obtain the leaf photosynthetic rate (Pn) output by the leaf photosynthetic rate neural network model.
And S220, inputting the leaf spectral image only containing the leaf into the leaf area neural network model to obtain the Leaf Area (LA) output by the leaf area neural network model.
S230, inputting the spectral image of the leaf only comprising the leaf into a leaf water content neural network model to obtain the Leaf Water Content (LWC) output by the leaf water content neural network model
The leaf photosynthetic rate neural network model, the leaf area neural network model and the leaf moisture content neural network model form the leaf neural network model in the step S200, and the three models of the neural network model are obtained based on the sample leaf spectral image training only including leaves.
Therefore, in the step S200, the spectral TIFF format image file including only the leaf is input to the leaf photosynthetic rate neural network model, the leaf area neural network model, and the leaf moisture content neural network model, and the leaf photosynthetic rate (Pn), the Leaf Area (LA), and the leaf moisture content (LWC) are obtained through respective output.
In this embodiment, the leaf photosynthetic rate neural network model, the leaf area neural network model, and the leaf moisture content neural network model are all built by using the RSNNS package based on the R language.
The method for predicting tomato fruit growth of the present invention is described below with reference to fig. 4, and step S300 specifically includes the following steps:
and S310, identifying the morphological structure of the fruit morphological binary image only containing the fruit to obtain a skeleton extraction image.
S320, performing corner detection on the skeleton extraction image based on the R language to obtain the number (Fn) of tomato fruits.
In step S300, analyzing the binary image of the fruit morphology only including fruits by using R language, firstly, in step S310, identifying the crop morphological structure based on the image skeleton extraction method of potential energy balance to obtain a skeleton extraction diagram, as shown in fig. 6; in step S320, the number (Fn) of tomato fruits is obtained by performing Harris corner detection based on the image of R language, cornerdetectionharris package, as shown in fig. 7.
The present invention provides a device for predicting tomato fruit growth, which can be referred to as a device for predicting tomato fruit growth described below and a method for predicting tomato fruit growth described above.
The tomato fruit growth prediction apparatus of the present invention is described below with reference to fig. 9, and includes:
the extraction module 100 is configured to acquire a canopy spectral image of a canopy of a tomato, and extract a leaf spectral image only including leaves and a fruit morphology binary image only including fruits from the canopy spectral image.
The first obtaining module 200 is configured to input a leaf spectral image only including leaves into a leaf neural network model, and obtain leaf parameters of a tomato canopy output by the leaf neural network model, where the leaf parameters include a leaf photosynthetic rate (Pn), a Leaf Water Content (LWC), and a Leaf Area (LA).
In the device, the leaf neural network model is trained on a sample leaf spectral image only containing leaves.
The second obtaining module 300 is configured to perform corner detection analysis on the fruit shape binary image only including the fruit to obtain the number (Fn) of the tomato fruits.
A third obtaining module 400, configured to obtain a tomato source-to-library ratio (SS) under different planting conditions and sufficient treatment conditions based on the leaf parameters and the number of the tomatoesiAnd SSck) And based on the tomato source-to-pool ratio (SS) under sufficient treatment conditionsck) And phloem sugar concentration (Cp)ck) Obtaining phloem sugar concentration (Cp) under different planting conditionsi)。
A prediction module 500 for predicting phloem sugar concentration (Cp) under different planting conditionsi) Inputting the fresh weight and dry weight of the tomato fruits into a tomato fruit growth model to obtain the growth dynamic process of the fresh weight and the dry weight of the tomato fruits under different planting conditions output by the tomato fruit growth model. The tomato fruit growth model is obtained by training different phloem sugar concentrations of different samples under different planting conditions.
In this example, the tomato fruit growth model was the TOM-GRO model.
In the prediction module 500, the influence of different planting conditions on the growth of tomato plants and fruits and the relationship between the tomato plants and the fruits can be considered, and the dynamic changes of the dry weight and the fresh weight of the tomato fruits under different planting conditions can be effectively simulated.
Since tomato leaves and fruits are important source and sink items, the correlation between source and sink strengths can affect the carbon input of fruits. The source-to-pool ratio of plants is a relatively abstract and dynamic index, wherein the source organ, the source intensity and the pool organ and pool intensity are involved, and the characterization mode is less clear. In the input parameters of the existing tomato fruit growth model, the phloem sugar concentration Cp representing the carbon supply of tomato fruits is the same level under different planting conditions, but obviously, the method does not meet the practical requirements of planting and production because the carbon supply of tomato fruits is influenced by the change of external environment and agricultural measures. Therefore, the existing devices are not able to effectively characterize the effect of different planting conditions on the carbon supply of tomato fruits, i.e. the phloem sugar concentration Cp value.
The tomato fruit growth prediction device obtains the leaf parameters and the number of the tomato fruits based on the canopy spectrum image of the tomato canopy, thereby obtaining the tomato source-base ratio under different planting conditions, adjusting the carbon supply level of the fruits in the tomato growth model, obtaining the tomato source-base ratio which is more suitable for actual planting and production, further quantifying the influence of the different planting conditions on the phloem sugar concentration, effectively reflecting the influence of the different planting conditions on the carbon supply level of the tomato fruits, further improving the prediction precision of the tomato fruit growth, and having the advantages of nondestructive observation, continuous high efficiency, prospective diagnosis and the like in the aspects of guiding the tomato planting, fruit growth prediction and the like.
In the embodiment, during the period from fruit setting to color turning and maturing of the tomato fruits, a handheld multispectral probe is used for shooting and acquiring data above tomato plants, and canopy spectrum images of tomato canopies are acquired every 5-7 days.
It should be noted that the period from fruit setting to ripening and color changing of the tomato fruit refers to the important period of water and dry matter accumulation of the tomato fruit, so that the handheld multispectral probe can be used for scanning above the tomato plant at intervals of 5-7 days in the period to obtain the canopy spectrum image of the tomato canopy.
In consideration of the quality of the acquired canopy spectral image, the device can select the time with sufficient light from 11:00 to 13:00, no wind or low wind speed for shooting, and the spectral image of the tomato canopy growth in each growth stage is obtained.
The extraction module 100 specifically includes: and removing the background in the canopy spectral image to obtain a leaf spectral image only containing leaves and a fruit form binary image only containing fruits.
In the extraction module 100, software such as enii is used to remove the background in the obtained canopy spectral image by means of support vector machine segmentation, clustering, and the like, and a leaf spectral image including only leaves and a fruit shape binary image including only fruits are obtained.
The tomato fruit growth prediction device of the present invention is described below with reference to fig. 10, and the extraction module 100 specifically includes:
the first processing unit 110 is configured to perform processing such as segmentation and clustering on the canopy spectral image to obtain a leaf vector diagram including only leaves and a fruit vector diagram including only fruits.
The second processing unit 120 performs mask processing on the canopy spectral image using the vector diagram containing only the blades, extracts a blade spectral image containing only the blades, and specifically obtains a spectral TIFF format image file containing only the blades.
The tomato fruit growth prediction apparatus of the present invention is described below with reference to fig. 11, where the first obtaining module 200 specifically includes:
the first obtaining unit 210 is configured to input the leaf spectral image only including the leaf into the leaf photosynthetic rate neural network model, so as to obtain a leaf photosynthetic rate (Pn) output by the leaf photosynthetic rate neural network model.
The second obtaining unit 220 is configured to input the spectral image of the blade, which only includes the blade, into the blade area neural network model, so as to obtain a blade area (LA) output by the blade area neural network model.
The third obtaining unit 230 is configured to input the spectral image of the blade, which only includes the blade, to the neural network model of the water content of the blade, so as to obtain the water content (LWC) of the blade output by the neural network model of the water content of the blade.
The leaf photosynthetic rate neural network model, the leaf area neural network model and the leaf moisture content neural network model form a leaf neural network model in the first acquisition module 200, and the three models of the neural network model are obtained based on the sample leaf spectral image training only including leaves.
Therefore, the leaf photosynthetic rate neural network model, the leaf area neural network model, and the leaf moisture content neural network model in the first obtaining module 200 respectively input the spectral TIFF format image file including only the leaves into the three models, and respectively output to obtain the leaf photosynthetic rate (Pn), the Leaf Area (LA), and the leaf moisture content (LWC).
In this embodiment, the leaf photosynthetic rate neural network model, the leaf area neural network model, and the leaf moisture content neural network model are all built by using the RSNNS package based on the R language.
The tomato fruit growth prediction apparatus of the present invention is described below with reference to fig. 12, and the second obtaining module 300 specifically includes:
a fourth obtaining unit 310, configured to identify a morphological structure of the fruit morphological binary image that only includes the fruit, to obtain a skeleton extraction map.
A fifth obtaining unit 320, configured to perform corner detection on the skeleton extraction diagram based on the R language to obtain the number (Fn) of tomato fruits.
Referring to table 1, table 1 shows the comparison of the present invention with the existing simulation method in terms of various indexes, and compared with the original fixed phloem sugar concentration Cp to simulate the fresh weight and dry weight of the fruit, the present invention can effectively consider the influence of the growth condition of the tomato plant on the tomato fruit under different agronomic measures, thereby improving the fruit weight simulation precision.
TABLE 1 evaluation indexes of fresh weight and dry weight effects simulated by tomato fruit growth model under different phloem sugar concentration (Cp) input modes
In table 1, N2Wck, N2W1, N2W2, N2W3 represent test treatments of tomatoes with full irrigation during the whole growth period and deficit irrigation during 3 growth periods, respectively, at the nitrogen application level of N2; fresh weight and dry weight average are mean values taken over a number of measurements; in table 1, Cp0 represents the simulation effect of the original Cp mode, and Cps-s represents the simulation result of adjusting the phloem sugar concentration input by using the source-to-library ratio of the present invention, wherein MAE represents the average absolute error, RASE represents the root mean square error, RRMSE represents the relative root mean square error, and smaller values of MAE, RASE, and RRMSE indicate smaller simulation errors, EF represents the simulation efficiency, and a value of EF closer to 1 indicates better simulation effect.
The model simulation evaluation index calculation formula is as follows:
in the above formula, OiIs a test observed value, SiIs a value of a simulation of the model,
is the average of the observed values and is,
is the average of the analog values, and n is the number of observed samples.
Fig. 14 illustrates a physical structure diagram of an electronic device, and as shown in fig. 14, the electronic device may include: a processor (processor)810, a communication Interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication Interface 820 and the memory 830 communicate with each other via the communication bus 840. The processor 810 may call logic instructions in the memory 830 to perform a tomato fruit growth prediction method comprising the steps of:
s100, acquiring a canopy spectral image of a tomato canopy, and extracting a leaf spectral image only containing leaves and a fruit form binary image only containing fruits from the canopy spectral image;
s200, inputting the leaf spectral image only containing the leaves into a leaf neural network model to obtain leaf parameters of the tomato canopy output by the leaf neural network model; wherein the leaf parameters comprise leaf photosynthetic rate, leaf water content and leaf area;
s300, performing corner detection analysis on the fruit shape binary image only containing the fruits to obtain the number of the tomatoes;
s400, obtaining phloem sugar concentrations under different planting conditions based on the leaf parameters and the number of the tomatoes;
s500, inputting phloem sugar concentrations under different planting conditions into a tomato fruit growth model to obtain the dynamic growth process of fresh weight and dry weight of the tomato fruits under different planting conditions output by the tomato fruit growth model; the tomato fruit growth model is obtained by training based on the phloem sugar concentration of a sample under different planting conditions.
In addition, the logic instructions in the memory 830 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and 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 stored on a non-transitory computer readable storage medium, wherein when the computer program is executed by a processor, the computer is capable of executing the method for predicting tomato fruit growth provided by the above methods, the method comprising the following steps:
s100, acquiring a canopy spectral image of a tomato canopy, and extracting a leaf spectral image only containing leaves and a fruit form binary image only containing fruits from the canopy spectral image;
s200, inputting the leaf spectral image only containing the leaves into a leaf neural network model to obtain leaf parameters of the tomato canopy output by the leaf neural network model; wherein the leaf parameters comprise leaf photosynthetic rate, leaf water content and leaf area;
s300, performing corner detection analysis on the fruit shape binary image only containing the fruits to obtain the number of the tomatoes;
s400, obtaining phloem sugar concentrations under different planting conditions based on the leaf parameters and the number of the tomato fruits;
s500, inputting phloem sugar concentrations under different planting conditions into a tomato fruit growth model to obtain the dynamic growth process of fresh weight and dry weight of the tomato fruits under different planting conditions output by the tomato fruit growth model; the tomato fruit growth model is obtained by training based on the phloem sugar concentration of a sample under different planting conditions.
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, implements a method for predicting tomato fruit growth provided by the above methods, the method comprising the steps of:
s100, acquiring a canopy spectral image of a tomato canopy, and extracting a leaf spectral image only containing leaves and a fruit form binary image only containing fruits from the canopy spectral image;
s200, inputting the leaf spectral image only containing the leaves into a leaf neural network model to obtain leaf parameters of the tomato canopy output by the leaf neural network model; wherein the leaf parameters comprise leaf photosynthetic rate, leaf water content and leaf area;
s300, performing corner detection analysis on the fruit shape binary image only containing the fruits to obtain the number of the tomatoes;
s400, obtaining phloem sugar concentrations under different planting conditions based on the leaf parameters and the number of the tomato fruits;
s500, inputting phloem sugar concentrations under different planting conditions into a tomato fruit growth model to obtain the dynamic growth process of fresh weight and dry weight of the tomato fruits under different planting conditions output by the tomato fruit growth model; the tomato fruit growth model is obtained by training based on the phloem sugar concentration of a sample under different planting conditions.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present 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 solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. The tomato fruit growth prediction method is characterized by comprising the following steps:
acquiring a canopy spectral image of a tomato canopy, and respectively extracting a leaf spectral image only containing leaves and a fruit form binary image only containing fruits from the canopy spectral image;
inputting the leaf spectral image only containing the leaves into a leaf neural network model to obtain leaf parameters of the tomato canopy output by the leaf neural network model; wherein the leaf parameters comprise leaf photosynthetic rate, leaf water content and leaf area;
performing angular point detection analysis on the fruit shape binary image only containing the fruits to obtain the number of the tomatoes;
obtaining phloem sugar concentrations under different planting conditions based on the leaf parameters and the number of the tomato fruits;
inputting the phloem sugar concentrations under different planting conditions into a tomato fruit growth model to obtain the dynamic growth process of fresh weight and dry weight of the tomato fruits under different planting conditions output by the tomato fruit growth model; the tomato fruit growth model is obtained by training based on the phloem sugar concentration of a sample under different planting conditions.
2. The tomato fruit growth prediction method of claim 1, wherein the obtaining of phloem sugar concentration under different planting conditions based on the leaf parameters and the number of tomato fruits comprises the following steps:
acquiring tomato source-to-library ratios under different planting conditions and full treatment conditions based on the leaf parameters and the number of the tomatoes;
obtaining the phloem sugar concentration under different planting conditions based on the tomato source-to-sink ratio and the phloem sugar concentration under the full treatment conditions.
3. The method for predicting tomato fruit growth according to claim 1, wherein the obtaining of the canopy spectrum image of the canopy of the tomato and the extracting of the leaf spectrum image only including leaves and the fruit shape binary image only including fruits from the canopy spectrum image respectively comprise:
and removing the background in the canopy spectral image to obtain a leaf spectral image only containing leaves and a fruit shape binary image only containing fruits.
4. The tomato fruit growth prediction method of claim 3, wherein the background in the canopy spectrum image is removed to obtain a spectrum image only including leaves and a fruit shape binary image only including fruits, and the method specifically comprises the following steps:
carrying out segmentation and clustering processing on the canopy spectral image to obtain a leaf vector diagram only containing leaves and a fruit vector diagram only containing fruits;
carrying out mask processing on the canopy spectral image by using a blade vector diagram only containing blades to obtain a blade spectral image only containing the blades;
and (4) carrying out binarization processing on the canopy spectral image by using a fruit vector diagram only containing fruits to obtain a fruit shape binary diagram only containing fruits.
5. The tomato fruit growth prediction method of claim 1, wherein the leaf spectral image only including leaves is inputted into a leaf neural network model to obtain leaf parameters of the tomato canopy outputted by the leaf neural network model, and the method specifically comprises the following steps:
inputting a leaf spectral image only containing leaves into a leaf photosynthetic rate neural network model to obtain the leaf photosynthetic rate output by the leaf photosynthetic rate neural network model;
inputting a blade spectral image only containing blades into a blade area neural network model to obtain the blade area output by the blade area neural network model;
inputting a leaf spectral image only containing leaves into a leaf water content neural network model to obtain the leaf water content output by the leaf water content neural network model;
the leaf photosynthetic rate neural network model, the leaf area neural network model and the leaf moisture content neural network model form the leaf neural network model, and the leaf photosynthetic rate neural network model, the leaf area neural network model and the leaf moisture content neural network model are obtained based on sample leaf spectral image training only including leaves.
6. The method for predicting tomato fruit growth according to claim 1, wherein the angular point detection analysis is performed on the fruit shape binary image only containing fruits to obtain the number of tomato fruits, and the method specifically comprises the following steps:
identifying the morphological structure of a fruit morphological binary image only comprising fruits to obtain a skeleton extraction image;
and performing corner detection on the skeleton extraction image based on the R language to obtain the number of the tomato fruits.
7. A tomato fruit growth prediction device, comprising:
the extraction module is used for acquiring a canopy spectral image of a tomato canopy and extracting a leaf spectral image only containing leaves and a fruit form binary image only containing fruits from the canopy spectral image;
the first acquisition module is used for inputting the leaf spectral image only containing the leaves into a leaf neural network model to obtain leaf parameters of the tomato canopy output by the leaf neural network model; wherein the leaf parameters comprise leaf photosynthetic rate, leaf water content and leaf area;
the second acquisition module is used for carrying out angular point detection analysis on the fruit form binary image only containing the fruits to obtain the number of the tomato fruits;
the third acquisition module is used for acquiring phloem sugar concentrations under different planting conditions based on the leaf parameters and the number of the tomato fruits;
the prediction module is used for inputting the phloem sugar concentration under different planting conditions into a tomato fruit growth model to obtain the growth dynamic process of the fresh weight and the dry weight of the tomato fruit under different planting conditions output by the tomato fruit growth model; the tomato fruit growth model is obtained by training based on the phloem sugar concentration of a sample under different planting conditions.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the tomato fruit growth prediction method of any one of claims 1 to 6.
9. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the tomato fruit growth prediction method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, wherein the computer program when executed by a processor implements the steps of the tomato fruit growth prediction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111322534.2A CN114155526B (en) | 2021-11-09 | 2021-11-09 | Tomato fruit growth prediction method, device, equipment and product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111322534.2A CN114155526B (en) | 2021-11-09 | 2021-11-09 | Tomato fruit growth prediction method, device, equipment and product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114155526A true CN114155526A (en) | 2022-03-08 |
| CN114155526B CN114155526B (en) | 2024-04-16 |
Family
ID=80459853
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111322534.2A Active CN114155526B (en) | 2021-11-09 | 2021-11-09 | Tomato fruit growth prediction method, device, equipment and product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114155526B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103793686A (en) * | 2014-01-16 | 2014-05-14 | 中国农业大学 | Method for early-prediction of fruit tree yield |
| CN108062602A (en) * | 2017-12-28 | 2018-05-22 | 江苏大学 | A kind of method for predicting greenhouse solanaceous vegetables crop assimilation products yield |
| WO2018103137A1 (en) * | 2016-12-09 | 2018-06-14 | 江苏大学 | Method for predicting greenhouse tomato fruit growth |
| CN108184564A (en) * | 2017-12-28 | 2018-06-22 | 江苏大学 | A kind of method for building greenhouse solanaceous vegetables crop assimilation products distribution model |
| CN112465893A (en) * | 2020-11-05 | 2021-03-09 | 内蒙古工业大学 | Vegetation leaf area measuring method and device, terminal and storage medium |
| CN113343464A (en) * | 2021-06-08 | 2021-09-03 | 中国农业大学 | Tomato fruit sugar efficient prediction improvement method based on fruit diameter nondestructive observation |
-
2021
- 2021-11-09 CN CN202111322534.2A patent/CN114155526B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103793686A (en) * | 2014-01-16 | 2014-05-14 | 中国农业大学 | Method for early-prediction of fruit tree yield |
| WO2018103137A1 (en) * | 2016-12-09 | 2018-06-14 | 江苏大学 | Method for predicting greenhouse tomato fruit growth |
| CN108062602A (en) * | 2017-12-28 | 2018-05-22 | 江苏大学 | A kind of method for predicting greenhouse solanaceous vegetables crop assimilation products yield |
| CN108184564A (en) * | 2017-12-28 | 2018-06-22 | 江苏大学 | A kind of method for building greenhouse solanaceous vegetables crop assimilation products distribution model |
| CN112465893A (en) * | 2020-11-05 | 2021-03-09 | 内蒙古工业大学 | Vegetation leaf area measuring method and device, terminal and storage medium |
| CN113343464A (en) * | 2021-06-08 | 2021-09-03 | 中国农业大学 | Tomato fruit sugar efficient prediction improvement method based on fruit diameter nondestructive observation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114155526B (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108760655B (en) | Apple taste map information visualization method | |
| CN112001901A (en) | Apple defect detection method and system based on convolutional neural network | |
| CN110579186A (en) | Crop growth monitoring method based on inversion of leaf area index by inverse Gaussian process | |
| Li et al. | In situ and non-destructive detection of the lipid concentration of Scenedesmus obliquus using hyperspectral imaging technique | |
| CN113607656A (en) | Leaf chlorophyll content monitoring method and system based on hyperspectral imaging | |
| Carolina et al. | Classification of oranges by maturity, using image processing techniques | |
| Li et al. | Two-wavelength image detection of early decayed oranges by coupling spectral classification with image processing | |
| Przybył et al. | Health properties and evaluation of quality of dried strawberry fruit produced using the convective drying method with neural image analysis | |
| CN114155526B (en) | Tomato fruit growth prediction method, device, equipment and product | |
| CN113763455A (en) | Tracing method and device for greenhouse gas emission, computer equipment and medium | |
| CN111968087A (en) | Plant disease area detection method | |
| CN117131758A (en) | Training method and device of irrigation water estimation model and irrigation water estimation method | |
| CN116524279A (en) | Artificial intelligent image recognition crop growth condition analysis method for digital agriculture | |
| Yu et al. | Nondestructive testing of external defects on Nanguo pear | |
| Zhou et al. | Hyperspectral imaging technology for detection of moisture content of tomato leaves | |
| Hu et al. | An efficient model transfer approach to suppress biological variation in elastic modulus and firmness regression models using hyperspectral data | |
| Zhao et al. | Detection of water content in lettuce canopies based on hyperspectral imaging technology under outdoor conditions | |
| Mahanti et al. | Non-destructive estimation of spinach leaf area: image processing and artificial neural network based approach | |
| Li et al. | Early warning potential of banana spoilage based on 3D fluorescence data of storage room gas | |
| Berdugo-Lattke et al. | P-type based dimensionality reduction for open contours of colombian páramo plant species | |
| Concepcion et al. | Towards the integration of computer vision and applied artificial intelligence in postharvest storage systems: Non-invasive harvested crop monitoring | |
| CN110530843A (en) | The detection method and system of content of starch in a kind of corn kernel | |
| CN117726052A (en) | Yield prediction method, device, equipment and medium based on fractal dimension | |
| CN114019082B (en) | Soil organic matter content monitoring method and system | |
| Wang et al. | Estimation of paddy rice maturity using digital imaging |
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 |