Nitrogen absorption analysis method, device and equipment for flue-cured tobacco leaves and storage medium

Abstract

The invention discloses a nitrogen absorption analysis method, device and equipment for flue-cured tobacco leaves and a storage medium, and relates to the technical field of plant cultivation. According to the method, tobacco plant growth has a linear relation based on the time progress, meanwhile, absorption of nitrogen fertilizer in soil is driven, and the linear relation based on the time progress is also achieved, the relation between the nitrogen absorption amount and the biomass of each part of the tobacco plant is analyzed with the biomass of the tobacco plant as an index, and after the mutual relation is analyzed, the nitrogen absorption amount of each part of the tobacco plant is calculated. The nitrogen content of each part of the tobacco plant can be predicted, so that the measurement result is in a continuous state from the past to the future based on the time progress, and the continuity and the foresight of the measurement result are realized.

Description

Technical Field

[0001] The present application relates to the technical field of plant cultivation, and particularly relates to a method, device, equipment and storage medium for analyzing nitrogen absorption of flue-cured tobacco leaves. Background Art

[0002] Flue-cured tobacco is an important agricultural product among economic crops in China. It is the main raw material for cigarette production and one of the bulk agricultural products exported from China.

[0003] The nitrogen content is one of the important indicators reflecting the growth status and leaf quality of tobacco. The nitrogen content is closely related to aspects such as the growth and development of tobacco, quality control, economic benefits, and environmental protection. Timely and accurately grasping the nitrogen content level of tobacco is conducive to precise fertilization of tobacco fields, controlling the quality of tobacco, improving the economic benefits of the industry, and achieving environmental friendliness at the same time.

[0004] Currently, most traditional tobacco plantings and fertilizer selection and application usually rely on the subjective experience of planters to judge the cultivation cycle, fertilization amount, and fertilization cycle of tobacco fields, without quantitative indicators, or the quantification cost is high. Only a very small number of tobacco fields have the conditions for monitoring nitrogen content.

[0005] Nitrogen content analysis technology is usually determined by the chemical nitrogen determination method or the spectral method, but the determination results can only reflect the instantaneous state of the nitrogen content of tobacco plants at the time of sample collection. Due to the characteristics of plants growing and continuously absorbing nutrients, the component content of tobacco plants is constantly changing, resulting in poor timeliness of the determination results and lacking continuity and forward-lookingness. Summary of the Invention

[0006] The main purpose of the present application is to provide a method, device, equipment and storage medium for analyzing nitrogen absorption of flue-cured tobacco leaves, so as to solve the problem in the prior art that the determination results can only reflect the instantaneous state of the nitrogen content of tobacco plants at the time of sample collection, resulting in poor timeliness of the determination results and lacking continuity and forward-lookingness.

[0007] To achieve the above purpose, the present application provides the following technical solutions:

[0008] A method for analyzing nitrogen absorption of flue-cured tobacco leaves, the nitrogen absorption analysis method is applied to a plurality of tobacco plants planted in soil applied with nitrogen fertilizer, and the nitrogen absorption analysis method includes:

[0009] Step S1, marking the nitrogen of all nitrogen fertilizers by the 15N tracer method to obtain marked nitrogen;

[0010] Step S2, randomly sampling all tobacco plants based on a plurality of preset time periods, and obtaining a plurality of complete tobacco plant samples based on one preset time period;

[0011] Step S3, obtain the tobacco plant biomass of each complete tobacco plant sample respectively;

[0012] Step S4, obtain the biomass average value of all tobacco plant biomass in the current preset time period, and obtain a biomass average value based on a preset time period;

[0013] Step S5, classify the plant organs of all complete tobacco plant samples in the current preset time period through a classification algorithm based on the preset tobacco plant organ types, and obtain a plant organ classification set based on a preset time period;

[0014] Step S6, obtain the labeled nitrogen content of all plant organs in each plant organ classification set through isotope analysis respectively;

[0015] Step S7, obtain the average value of the labeled nitrogen content of each preset tobacco plant organ type in the current plant organ classification set, and obtain a nitrogen content average value based on a preset tobacco plant organ type;

[0016] Step S8, analyze the linear regression relationship between the biomass average value and all nitrogen content average values in the same preset time period through a multiple linear regression model to obtain a prediction model;

[0017] Step S9, predict a number of nitrogen content prediction values for each preset tobacco plant organ type respectively based on the preset prediction steps through the prediction model.

[0018] As a further improvement of the present application, Step S5, classify the plant organs of all complete tobacco plant samples in the current preset time period through a classification algorithm based on the preset tobacco plant organ types, and obtain a plant organ classification set based on a preset time period, including:

[0019] Step S51, obtain the visual images of each complete tobacco plant sample respectively;

[0020] Step S52, obtain all plant organs in each visual image through an object detection algorithm respectively;

[0021] Step S53, integrate all plant organs in the same preset time period into a dataset to be classified;

[0022] Step S54, define a plant organ category set according to the number of types of all preset tobacco plant organ types;

[0023] Step S55, calculate the conditional probability of each plant organ in the dataset to be classified in the same preset time period under each preset plant organ type respectively;

[0024] Step S56: Classify all plant organs in the dataset to be classified within the same preset time period into their respective preset plant organ types with the highest conditional probability, and obtain a plant organ classification set based on one preset time period.

[0025] As a further improvement of this application, in step S52, all plant organs in each visual image are obtained respectively through an object detection algorithm, including:

[0026] Step S521: Divide the current visual image evenly into several square grids;

[0027] Step S522: Predict several bounding boxes for all plant organs based on all the square grids, and each bounding box includes at least one square grid;

[0028] Step S523: Obtain the confidence of each bounding box based on the current preset plant organ type respectively;

[0029] Step S524: Mark the bounding box with the highest confidence as the first-order bounding box;

[0030] Step S525: Calculate the intersection over union (IoU) of each of the other bounding boxes with the first-order bounding box respectively;

[0031] Step S526: Select the bounding boxes with an IoU greater than or equal to the preset threshold as the second-order bounding boxes;

[0032] Step S527: Obtain the second-order bounding box with the highest confidence and define it as the plant organ of the current preset plant organ type.

[0033] As a further improvement of this application, in step S8, the linear regression relationship between the average biomass and the average nitrogen content within the same preset time period is analyzed through a multiple linear regression model to obtain a prediction model, including:

[0034] Step S81: Define the linear regression relationship between the average biomass and the average nitrogen content within the same preset time period through the multiple linear regression model;

[0035] Step S82: Solve all the linear regression coefficients of the multiple linear regression model through the least squares method;

[0036] Step S83: Substitute all the obtained regression coefficients into the multiple linear regression model to obtain the multiple linear regression model;

[0037] Step S84: Define the multiple linear regression model as the prediction model.

[0038] As a further improvement of the present application, in step S9, based on a preset prediction step number, a plurality of nitrogen content prediction values are respectively predicted for each preset tobacco plant organ type by the prediction model, including:

[0039] Step S91, randomly sample all tobacco plants again to obtain a plurality of complete prediction samples for predicting the future labeled nitrogen content;

[0040] Step S92, respectively obtain the real-time biomass of each complete prediction sample;

[0041] Step S93, substitute all the real-time biomass into the prediction model to obtain a nitrogen content prediction value based on one preset tobacco plant organ type.

[0042] As a further improvement of the present application, in step S93, after substituting all the real-time biomass into the prediction model to obtain a nitrogen content prediction value based on one preset tobacco plant organ type, it includes:

[0043] Step S100, judge the content difference between all the nitrogen content prediction values and all the labeled nitrogen contents based on the same preset tobacco plant organ type;

[0044] Step S200, define the preset tobacco plant organ type with the content difference greater than or equal to the preset content threshold as the organ with good absorption;

[0045] Step S300, define the preset tobacco plant organ type with the content difference less than the preset content threshold as the organ with absorption disorder.

[0046] As a further improvement of the present application, in step S93, after substituting all the real-time biomass into the prediction model to obtain a nitrogen content prediction value based on one preset tobacco plant organ type, it includes:

[0047] Step S1000, obtain the tobacco plant biomass, all plant organ classification sets, all labeled nitrogen contents, and nitrogen content prediction values of all complete tobacco plant samples, and send them to an external visual monitoring terminal.

[0048] To achieve the above object, the present application also provides the following technical solutions:

[0049] A nitrogen absorption analysis device for flue-cured tobacco leaves, the nitrogen absorption analysis device is applied to the nitrogen absorption analysis method as described above, and the nitrogen absorption analysis device includes:

[0050] A nitrogen fertilizer nitrogen labeling module, used to label the nitrogen of all nitrogen fertilizers by the 15N tracer method to obtain labeled nitrogen;

[0051] A tobacco plant random sampling module, which is used to randomly sample all tobacco plants based on a number of preset time periods, and obtain a number of complete tobacco plant samples based on one preset time period;

[0052] A tobacco plant biomass acquisition module, which is used to obtain the biomass of each complete tobacco plant sample respectively;

[0053] A biomass average value acquisition module, which is used to obtain the biomass average value of all tobacco plant biomasses in the current preset time period, and obtain a biomass average value based on one preset time period;

[0054] A tobacco plant organ classification module, which is used to classify the plant organs of all complete tobacco plant samples in the current preset time period through a classification algorithm based on the preset tobacco plant organ types, and obtain a plant organ classification set based on one preset time period;

[0055] A labeled nitrogen content acquisition module, which is used to obtain the labeled nitrogen content of all plant organs in each plant organ classification set respectively through isotope analysis;

[0056] A nitrogen content average value acquisition module, which is used to obtain the average value of the labeled nitrogen content of each preset tobacco plant organ type in the current plant organ classification set, and obtain a nitrogen content average value based on one preset tobacco plant organ type;

[0057] A biomass and nitrogen amount relationship definition module, which is used to analyze the linear regression relationship between the biomass average value and all nitrogen content average values in the same preset time period through a multiple linear regression model to obtain a prediction model;

[0058] A nitrogen content prediction module, which is used to predict a number of nitrogen content prediction values for each preset tobacco plant organ type respectively based on a preset number of prediction steps through the prediction model.

[0059] To achieve the above object, the present application also provides the following technical solutions:

[0060] An electronic device, including a processor and a memory coupled to the processor, where the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, it implements the nitrogen absorption analysis method of flue-cured tobacco leaves as described above.

[0061] To achieve the above object, the present application also provides the following technical solutions:

[0062] A storage medium, where program instructions are stored in the storage medium, and when the program instructions are executed by a processor, they can implement the nitrogen absorption analysis method of flue-cured tobacco leaves as described above.

[0063] In this application, the nitrogen in all nitrogen fertilizers is labeled by the 15N tracing method to obtain labeled nitrogen; based on several preset time periods, all tobacco plants are randomly sampled, and several complete tobacco plant samples are obtained based on one preset time period; the biomass of each complete tobacco plant sample is obtained respectively; the average biomass of all tobacco plant biomasses in the current preset time period is obtained, and an average biomass is obtained based on one preset time period; based on the preset tobacco plant organ types, all complete tobacco plant samples in the current preset time period are classified into plant organs by a classification algorithm, and a plant organ classification set is obtained based on one preset time period; the labeled nitrogen content of all plant organs in each plant organ classification set is obtained through isotope analysis; the average labeled nitrogen content of each preset tobacco plant organ type in the current plant organ classification set is obtained, and an average nitrogen content is obtained based on one preset tobacco plant organ type; the linear regression relationship between the average biomass and all average nitrogen contents in the same preset time period is analyzed through a multiple linear regression model to obtain a prediction model; based on the preset prediction steps, several predicted nitrogen content values are predicted for each preset tobacco plant organ type respectively by the prediction model. This application utilizes the linear relationship of tobacco plant growth based on the time process, and at the same time drives the absorption of nitrogen fertilizers in the soil to also have a linear relationship based on the time process. This application uses the biomass of tobacco plants as an index to analyze the relationship between the nitrogen absorption amount and biomass of each part of the tobacco plant. After analyzing the mutual relationship, the nitrogen content prediction of each part of the tobacco plant can be realized, making the measurement results of this application a continuous state from the past to the future based on the time process, and realizing the continuity and forward-looking of the measurement results. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a schematic flowchart of the steps of an embodiment of the method for analyzing nitrogen absorption in flue-cured tobacco leaves of this application;

[0065] Figure 2 It is a schematic diagram of the functional modules of an embodiment of the device for analyzing nitrogen absorption in flue-cured tobacco leaves of this application;

[0066] Figure 3 It is a schematic structural diagram of an embodiment of an electronic device of this application;

[0067] Figure 4 It is a schematic structural diagram of an embodiment of a storage medium of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0068] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0069] The terms "first", "second", and "third" in this application are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", and "third" may explicitly or implicitly include at least one of such features. In the description of this application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically and clearly defined. In the embodiments of this application, all directional indications (such as up, down, left, right, front, back...) are only used to explain the relative positional relationship, movement conditions, etc. between components in a specific posture (as shown in the drawings). If the specific posture changes, then the directional indication also changes accordingly. In addition, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product, or equipment that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or equipment.

[0070] Referring to "embodiment" herein means that a specific feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of this application. The appearance of this phrase at various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0071] As Figure 1 shown, this embodiment provides an embodiment of a method for analyzing nitrogen uptake in flue-cured tobacco leaves. In this embodiment, the nitrogen uptake analysis method is applied to several tobacco plants planted in soil with nitrogen fertilizer applied.

[0072] Preferably, the nitrogen fertilizers for tobacco mainly include the following types:

[0073] ① Nitrate nitrogen fertilizers: The nitrogen in these nitrogen fertilizers exists in the form of nitrate ions, such as sodium nitrate, calcium nitrate, potassium nitrate, etc. They can promote the accumulation of citric acid and malic acid in tobacco plants, thereby improving the combustibility of tobacco leaves.

[0074] ② Ammonium nitrogen fertilizers: The nitrogen in ammonium nitrogen fertilizers exists in the form of ammonium salts, such as ammonium sulfate, ammonium chloride, ammonium bicarbonate, diammonium phosphate, and the ammonium part of ammonium nitrate. These nitrogen fertilizers can promote the formation of aromatic volatile oils in tobacco plants, thus enhancing the fragrance of tobacco leaves.

[0075] ③Other types of nitrogen fertilizers: In addition to nitrate and ammonium nitrogen fertilizers, there are also amide nitrogen fertilizers and long-acting nitrogen fertilizers (or slow-release nitrogen fertilizers) available for selection on the market. These types of nitrogen fertilizers are also applied to a certain extent in tobacco cultivation, but the specific application effects may vary depending on factors such as soil conditions, climate conditions, and tobacco varieties.

[0076] Specifically, the nitrogen absorption analysis method includes the following steps:

[0077] Step S1, label the nitrogen of all nitrogen fertilizers by the 15N tracer method to obtain labeled nitrogen.

[0078] Preferably, the 15N tracer method is an effective method for studying the nitrogen nutrition of flue-cured tobacco. This method sets up pot experiments in the field and uses nitrogen fertilizers labeled with 15N isotopes to trace the absorption and utilization of nitrogen by flue-cured tobacco and the dynamic changes of nitrogen in the soil.

[0079] Specifically, the 15N tracer method can reveal the sources of nitrogen absorbed by flue-cured tobacco during the whole growth period, mainly from soil available nitrogen. With the increase in the amount of nitrogen fertilizer applied, the amount of fertilizer nitrogen absorbed by flue-cured tobacco will increase, while the amount of soil nitrogen absorbed will decrease accordingly. At the same time, this method can also reflect the fixation of fertilizer nitrogen by the soil and the loss of nitrogen fertilizer, both of which will change with the increase in the amount of nitrogen used.

[0080] In addition, the 15N tracer method can also provide information on the nitrogen utilization rate of fertilizers. By comparing the nitrogen utilization rates at different nitrogen application levels, the optimal amount of nitrogen application can be found, thereby improving the utilization efficiency of nitrogen fertilizers and reducing nitrogen waste and environmental pollution.

[0081] In summary, the 15N tracer method plays an important role in the study of nitrogen nutrition of flue-cured tobacco. It can help researchers deeply understand the absorption and utilization mechanisms of nitrogen by flue-cured tobacco and provide a scientific basis for formulating reasonable fertilization strategies.

[0082] Step S2, randomly sample all tobacco plants based on a number of preset time periods, and obtain a number of complete tobacco plant samples based on one preset time period.

[0083] Preferably, one preset time period can be set as one natural day, and one complete tobacco plant sample should at least include complete roots, stems, and leaves. If there are other organs such as flowers, fruits, and seeds, they should also be included in the biomass described below.

[0084] Among them, the root system of tobacco consists of a main root, lateral roots and adventitious roots, forming a taproot system. The main root grows and elongates during seed germination. With the emergence of true leaves, the number of lateral roots gradually increases, and secondary lateral roots are formed. After transplantation, the main root stops growing, and the lateral roots and adventitious roots become the main part of the root system, playing an important role in supporting the growth of tobacco and increasing the absorption function; The stem of tobacco is erect and cylindrical, formed by the continuous growth and differentiation of the apical bud. It is the main organ connecting the root system, supporting leaves, flowers and fruits, and transporting water and nutrients. The height of the stem varies by variety, usually between 70 and 200 centimeters; The cotyledons of tobacco are opposite, and the true leaves are borne on the stem, arranged in an alternate spiral pattern. The true leaf is an incomplete leaf without stipules. Some varieties have petioles, while some varieties do not. In addition, tobacco plants also include organs such as flowers, fruits and seeds, and these organs together constitute the complete form of tobacco plants.

[0085] Step S3: Obtain the tobacco plant biomass of each complete tobacco plant sample respectively.

[0086] Preferably, the tobacco plant biomass can be obtained by direct weighing, but the attached soil and water should be removed before weighing.

[0087] Step S4: Obtain the biomass average value of all tobacco plant biomasses in the current preset time period, and obtain a biomass average value based on a preset time period.

[0088] Preferably, to ensure data accuracy, multiple samples are taken in each preset time period. For the convenience of subsequent calculations, the relevant parameters of all samples in a preset time period are averaged. The same applies hereinafter.

[0089] Step S5: Classify all complete tobacco plant samples in the current preset time period through a classification algorithm based on the preset tobacco plant organ types, and obtain a plant organ classification set based on a preset time period.

[0090] Preferably, the preset tobacco plant organ types can be the above-mentioned roots, stems and leaves, and if there are flowers, fruits and seeds, they are also calculated together.

[0091] Step S6: Obtain the labeled nitrogen content of all plant organs in each plant organ classification set through isotope analysis respectively.

[0092] Preferably, isotope analysis can be performed using one of a gas chromatography-isotope ratio mass spectrometer (GC-IRMS), an isotope mass spectrometer, and a fully automatic carbon and nitrogen isotope mass spectrometer.

[0093] Among them, the gas chromatography-isotope ratio mass spectrometer (GC-IRMS) can accurately measure the relative isotope abundance of 15N and is suitable for isotope labeling analysis of target volatile and semi-volatile organic small molecule compounds in a mixed system.

[0094] Isotope mass spectrometers can also be used for the determination of 15N isotopes, with high analysis accuracy and can meet the needs of scientific research and experiments.

[0095] The fully automatic carbon and nitrogen isotope mass spectrometer is a device that integrates sample combustion, purification, and mass spectrometry measurement, and is dedicated to measuring isotopes such as 15N and 13C, with the characteristics of high efficiency and accuracy.

[0096] It should be noted that isotope analysis is a mature existing technology. In this embodiment, isotope analysis is a conventional application, and the detailed analysis steps of isotope analysis will not be elaborated in this embodiment.

[0097] Step S7, obtain the average marked nitrogen content of each preset tobacco plant organ type in the current plant organ classification set, and obtain an average nitrogen content based on one preset tobacco plant organ type.

[0098] Step S8, analyze the linear regression relationship between the average biomass of the same preset time period and all average nitrogen contents through a multiple linear regression model to obtain a prediction model.

[0099] Step S9, based on the preset prediction steps, predict a number of nitrogen content prediction values for each preset tobacco plant organ type through the prediction model.

[0100] Preferably, the preset prediction steps can also be set to one natural day.

[0101] Further, in step S5, based on the preset tobacco plant organ type, classify all complete tobacco plant samples in the current preset time period through a classification algorithm, and obtain a plant organ classification set based on one preset time period, including:

[0102] Step S51, respectively obtain the visual images of each complete tobacco plant sample.

[0103] Step S52, respectively obtain all plant organs in each visual image through an object detection algorithm.

[0104] Preferably, the object detection algorithm can be implemented through object detection algorithms such as VJ, HOG, DPMDetector; deep learning two-stage object detection algorithms such as RCNN, SPPNet, FastRCNN, FasterRCNN; object detection Trick algorithms such as FPN, CascadeRCNN; deep learning one-stage object detection algorithms such as Yolo, X, SSD, RetinaNet; deep learning anchor-free object detection algorithms such as CornerNet, CenterNet, FCOS; object detection algorithms based on Transformer such as DETR, etc.

[0105] Step S53: Integrate all plant organs within the same preset time period into a dataset to be classified.

[0106] For example, a dataset to be classified consists of all the organs of a complete tobacco plant sample, including 24 leaves, a main stem, possibly branches, and a conical root system.

[0107] Preferably, the dataset to be classified in the current preset time period can be expressed as X = {x1, x2, …, x j , …, x m}, where x j is the j-th plant organ, and m is the number of all plant organs.

[0108] Step S54: Define a set of plant organ categories according to the number of types of all preset tobacco plant organ types.

[0109] Preferably, the set of plant organ categories can be expressed as C = {y1, y2, …, y k , …, y n}, where y k is the k-th preset tobacco plant organ type in the set of plant organ categories C, and n is the number of types of all preset tobacco plant organ types.

[0110] Step S55: Calculate the conditional probability of each plant organ in the dataset to be classified within the same preset time period under each preset plant organ type.

[0111] Preferably, the conditional probability of the dataset to be classified under each preset tobacco plant organ type can be calculated by the following formula:

[0112]

[0113] where P(Xy k ) is the conditional probability of the dataset to be classified X under the k-th preset tobacco plant organ type; P(y k ) is the marginal probability of the k-th preset tobacco plant organ type; P(x j y k ) is the conditional probability of the j-th plant organ under the k-th preset tobacco plant organ type.

[0114] Step S56: Classify all plant organs in the dataset to be classified within the same preset time period into the preset plant organ type with the highest conditional probability for each of them, and obtain a set of plant organ classifications based on one preset time period.

[0115] Furthermore, in step S52, all plant organs in each visual image are obtained respectively through an object detection algorithm, including the following steps:

[0116] Step S521: Divide the current visual image evenly into a number of square grids.

[0117] Preferably, the number of square grids can be set to 448×448, and the size of the visual image is adjusted to conform to the specification of 448×448. Then, the resized picture is evenly divided into S×S (for example, 7×7) square grids, and the size of each square grid is 64×64.

[0118] Step S522: Based on all the square grids, predict a number of bounding boxes for all plant organs, and each bounding box includes at least one square grid.

[0119] Step S523: Obtain the confidence of each bounding box based on the current preset plant organ type respectively.

[0120] Step S524: Take the bounding box with the highest confidence and mark it as the first-order bounding box.

[0121] Step S525: Calculate the intersection over union (IoU) of each of the other bounding boxes with the first-order bounding box respectively.

[0122] Preferably, the intersection over union is the ratio obtained by dividing the intersection of the first-order bounding box with each bounding box by the union of the first-order bounding box with each bounding box (which can be an area ratio).

[0123] Step S526: Select the bounding boxes with an intersection over union greater than or equal to the preset threshold as the second-order bounding boxes.

[0124] Step S527: Obtain the second-order bounding box with the highest confidence and define it as the plant organ of the current preset plant organ type.

[0125] Preferably, each grid is used to predict the coordinates, width, and height of N first-order bounding boxes, as well as the confidence of each first-order bounding box, that is, each grid needs to predict N×(4 + 1) values.

[0126] It can be understood that each grid needs to predict N (x, y, w, h, confidence); where (x, y) is the offset of the center of the first-order bounding box relative to the grid, (w, h) is the ratio of the first-order bounding box relative to the resized picture, and (confidence) is the confidence of the grid, with a value of 1 or 0.

[0127] Preferably, the confidence can be understood as whether there is a target in the current grid and the accuracy of the first-order bounding box.

[0128] For example: Suppose there is a target in a resized picture, and the width and height of the resized picture are (w a , ha ) Then:

[0129] Divide the picture evenly into 7×7 (S×S) grids. There is a grid located at the center of the target, and the coordinates of this grid are (x a , y a ). Let the coordinates of the center of the target be (x b , y b ). Then, the above offset can be calculated according to .

[0130] Preferably, in actual detection, if the predicted first-order bounding box and the actual bounding box perfectly overlap, the value of the intersection over union is 1. In the actual application process, the value of the preset ratio is generally set to 0.5 first to determine whether the predicted second-order bounding box is correct, and the accuracy of the second-order bounding box is positively correlated with the intersection over union.

[0131] Preferably, the YOLO algorithm also needs to train the first-order bounding box to improve the accuracy of object detection.

[0132] Next, train the above training model through a preset object training set, and use the backpropagation algorithm to iteratively adjust the weights and biases of the training model a certain number of times to reduce the value of the loss function of the training model.

[0133] Preferably, the loss function is

[0134] Where is an indicator function indicating whether the j-th first-order bounding box of the i-th grid is responsible for the target, taking a value of 1 or 0; x i , y i , w i , h i , C i correspond to the (x, y, w, h, confidence) prediction values of the i-th grid respectively.

[0135] It can be understood that the loss function includes the deviation of the coordinate values of the first-order bounding box, the deviation of the confidence, and the deviation of the prediction probability (or class deviation).

[0136] Where is the loss of the midpoint of the first-order bounding box in the coordinate value deviation, is the loss of the width and height of the first-order bounding box in the coordinate value deviation, is the deviation of the confidence, is the deviation of the prediction probability (or class deviation).

[0137] Where λ coord is the positioning error penalty. Generally, λ coord = 5; S2 are the above-mentioned S×S grids; B is the number of first-order bounding boxes; and are the estimated values of the abscissa and ordinate of the midpoint of the i-th first-order bounding box; and are the estimated values of the width and height of the i-th first-order bounding box; C i is the confidence of the i-th first-order bounding box; is the estimated value of the confidence of the i-th first-order bounding box; λ noobj is the confidence prediction loss. Generally, λ noobj = 0.5; p i (c) is the class probability of the i-th first-order bounding box; is the estimated value of the class probability of the i-th first-order bounding box; p i (c) and the c in corresponds to classes.

[0138] It should be noted that since each grid may not necessarily contain a target, if there is no target in the grid, it will cause the value of (confidence) to be 0, resulting in an overly large gradient span in the subsequent backpropagation algorithm. Therefore, λ is introduced coord to control the loss of the predicted position of the first-order bounding box, and λ is introduced noobj to control the loss of the absence of a target within a single grid.

[0139] It should be noted that the above additional content is only for principle explanation, and the symbolic meanings of the above additional content are not interoperable with the symbolic meanings in other positions of this embodiment.

[0140] Furthermore, in step S8, a multiple linear regression model is used to analyze the linear regression relationship between the average biomass and the average nitrogen content of all in the same preset time period, and a prediction model is obtained, including the following steps:

[0141] Step S81, define the linear regression relationship between the average biomass and the average nitrogen content of all in the same preset time period through a multiple linear regression model.

[0142] Preferably, the multiple linear regression model is shown as the following formula:

[0143]

[0144] where, y i is the dependent variable of the i-th preset time period, n is the total number of all preset time periods, β0 is the intercept of the linear regression relationship, β j is the linear regression coefficient of the j-th independent variable, m is the total number of independent variables in a group of independent variables, x j,iis the j-th independent variable for the i-th preset time period, and δ is the random error of the linear regression relationship.

[0145] It should be noted that the above additional content is only for principle explanation, and the symbolic meanings of the above additional content are not interoperable with the symbolic meanings in other parts of this embodiment. If there are repeated symbols in the additional content in different positions, please understand them separately and do not connect them with each other.

[0146] Step S82, solve all linear regression coefficients of the multiple linear regression model by the least squares method.

[0147] Preferably, the least squares method is shown as the following formula:

[0148]

[0149] where is the estimated value of β j , j = 1, 2, …, m, X is the matrix of all independent variables, X T is the transpose matrix of matrix X.

[0150] It should be noted that the above additional content is only for principle explanation, and the symbolic meanings of the above additional content are not interoperable with the symbolic meanings in other parts of this embodiment. If there are repeated symbols in the additional content in different positions, please understand them separately and do not connect them with each other.

[0151] Step S83, substitute all the obtained regression coefficients into the multiple linear regression model to obtain the multiple linear regression model.

[0152] Step S84, define the multiple linear regression model as the prediction model.

[0153] Preferably, the residual sum of squares of linear regression can be used to judge the fitting effect of the model by comparing its magnitude. The residual sum of squares (RSS) is the sum of the squares of the differences between the actual observed values and the values predicted by the regression equation, and is used to quantify the difference between the model predicted value and the actual value.

[0154] Preferably, the judgment criterion for the residual sum of squares is that the smaller the better, that is, the smaller the residual sum of squares, the closer the predicted value of the model is to the actual observed value, and the better the fitting effect of the model; on the contrary, if the residual sum of squares is larger, it indicates that there is a large deviation between the predicted value of the model and the actual observed value, and the fitting effect of the model is poor.

[0155] Furthermore, step S9, based on the preset prediction steps, predict a number of nitrogen content prediction values for each preset tobacco plant organ type respectively through the prediction model, including the following steps:

[0156] Step S91: Conduct another random sampling on all tobacco plants to obtain a number of complete prediction samples for predicting the future labeled nitrogen content.

[0157] Step S92: Obtain the real-time biomass of each complete prediction sample respectively.

[0158] Step S93: Substitute all the real-time biomass into the prediction model to obtain a nitrogen content prediction value based on a preset tobacco plant organ type.

[0159] Further, in Step S93, after substituting all the real-time biomass into the prediction model to obtain a nitrogen content prediction value based on a preset tobacco plant organ type, it includes:

[0160] Step S100: Judge the content difference between all the nitrogen content prediction values and all the labeled nitrogen contents based on the same preset tobacco plant organ type.

[0161] Step S200: Define the preset tobacco plant organ type with a content difference greater than or equal to the preset content threshold as the organ with good absorption.

[0162] Step S300: Define the preset tobacco plant organ type with a content difference less than the preset content threshold as the organ with absorption disorder.

[0163] Preferably, the numerical change of the nitrogen content during the whole life cycle of the tobacco plant shows a trend of first increasing and then decreasing.

[0164] In the initial growth stage of the tobacco plant, including seed germination and seedling stage, the nitrogen absorption is relatively small. During this period, the tobacco plant mainly uses the nutrients stored in the seeds and a small amount of nitrogen initially absorbed by the roots from the soil to support its growth.

[0165] As the tobacco plant grows into the vigorous growth stage, its demand for and absorption of nitrogen increase significantly. In this stage, the leaves of the tobacco plant gradually unfold, photosynthesis is enhanced, and a large amount of nitrogen is needed to synthesize proteins and other nitrogen-containing compounds to support the growth and function of the leaves. At this time, the absorption of fertilizer nitrogen by the tobacco plant also reaches a peak, mainly concentrated within 40 to 60 days after transplanting.

[0166] When the tobacco plant enters the mature stage, the nitrogen content in the leaves begins to gradually decrease. This is because during the maturity and aging process of the tobacco plant, nutrients will be transferred from the leaves to the roots to supply the maturity and reproductive processes of the tobacco plant. At this time, the nitrogen absorption of the tobacco plant will also decrease accordingly.

[0167] Specifically, the nitrogen content in the leaves reaches its maximum 40 - 60 days after transplanting and then decreases; the nitrogen content in the roots and stems of the tobacco plants decreases 60 days after transplanting and then slightly increases; during the entire growth period, the nitrogen percentage content in the inflorescence is the highest. From topping to maturity, the accumulation of fertilizer nitrogen in the tobacco plants slightly decreases, and there is a negative nitrogen growth in the mature organs in the later growth stage.

[0168] For example, for every 1000 kg of flue-cured tobacco leaves produced, the tobacco plants need approximately 22 kg of nitrogen (N). At different growth stages of the tobacco plants, the absorption and utilization of nitrogen also vary. For example, in the seedbed stage, less fertilizer is needed before the cross stage, and the fertilizer requirement gradually increases after the cross stage. The peak fertilizer requirement period is within 15 days before transplanting. In the field stage, less nutrients are absorbed within 30 days after transplanting. The period of intensive fertilizer absorption is from 45 days to 75 days after transplanting, and the absorption peak is at the rosette and budding stages.

[0169] In addition, the total nitrogen content of flue-cured tobacco also has a certain range, generally 1.5% - 3.5%, and the optimal content is 2.5%. If the total nitrogen content is too low, the taste will be bland; if the total nitrogen content is too high, strong and pungent smoke will be produced, with a greater irritation.

[0170] To sum up, the specific values of the nitrogen content in the whole life cycle of tobacco plants are affected by various factors. Generally speaking, for every 1000 kg of flue-cured tobacco leaves produced, about 22 kg of nitrogen is needed, and the total nitrogen content of flue-cured tobacco should be controlled within the range of 1.5% - 3.5%.

[0171] Therefore, the preset content threshold can be set to 2%.

[0172] Further, in step S93, all real-time biomass is substituted into the prediction model, and a nitrogen content prediction value is obtained based on a preset tobacco plant organ type. After that, it includes:

[0173] Step S1000, obtain the tobacco plant biomass, all plant organ classification sets, all marked nitrogen contents, and nitrogen content prediction values of all complete tobacco plant samples, and send them to the external visual monitoring terminal.

[0174] In this embodiment, the nitrogen of all nitrogen fertilizers is labeled by the 15N tracer method to obtain labeled nitrogen; a number of tobacco plants are randomly sampled based on several preset time periods, and a number of complete tobacco plant samples are obtained based on one preset time period; the biomass of each complete tobacco plant sample is obtained respectively; the biomass average value of all tobacco plant biomasses in the current preset time period is obtained, and a biomass average value is obtained based on one preset time period; all complete tobacco plant samples in the current preset time period are classified into plant organs by a classification algorithm based on the preset tobacco plant organ types, and a plant organ classification set is obtained based on one preset time period; the labeled nitrogen content of all plant organs in each plant organ classification set is obtained by isotope analysis; the average value of the labeled nitrogen content of each preset tobacco plant organ type in the current plant organ classification set is obtained, and a nitrogen content average value is obtained based on one preset tobacco plant organ type; the linear regression relationship between the biomass average value and all nitrogen content average values in the same preset time period is analyzed by a multiple linear regression model to obtain a prediction model; based on the preset prediction steps, a number of nitrogen content prediction values are predicted for each preset tobacco plant organ type by the prediction model. This embodiment utilizes the linear relationship of tobacco plant growth based on the time process, and at the same time drives the absorption of nitrogen fertilizer in the soil to also have a linear relationship based on the time process. This embodiment uses the biomass of tobacco plants as an index to analyze the relationship between the nitrogen uptake amount of each part of the tobacco plant and the biomass. After analyzing the mutual relationship, the nitrogen content prediction of each part of the tobacco plant can be realized, making the measurement results of this embodiment a continuous state from the past to the future based on the time process, and realizing the continuity and foresight of the measurement results.

[0175] As Figure 2 shown, this embodiment provides an embodiment of a nitrogen uptake analysis device for flue-cured tobacco leaves. In this embodiment, the nitrogen uptake analysis device is applied to the nitrogen uptake analysis method in the above-mentioned embodiment.

[0176] Specifically, the nitrogen uptake analysis device includes a nitrogen fertilizer nitrogen labeling module 1, a tobacco plant random sampling module 2, a tobacco plant biomass acquisition module 3, a biomass average value acquisition module 4, a tobacco plant organ classification module 5, a labeled nitrogen content acquisition module 6, a nitrogen content average value acquisition module 7, a biomass-nitrogen relationship definition module 8, and a nitrogen content prediction module 9 that are electrically connected in sequence.

[0177] Among them, the nitrogen fertilizer nitrogen labeling module 1 is used to label the nitrogen of all nitrogen fertilizers by the 15N tracer method to obtain labeled nitrogen; the tobacco plant random sampling module 2 is used to randomly sample all tobacco plants based on several preset time periods, and obtain several complete tobacco plant samples based on one preset time period; the tobacco plant biomass acquisition module 3 is used to obtain the biomass of each complete tobacco plant sample respectively; the biomass average value acquisition module 4 is used to obtain the biomass average value of all tobacco plant biomasses in the current preset time period, and obtain a biomass average value based on one preset time period; the tobacco plant organ classification module 5 is used to classify the plant organs of all complete tobacco plant samples in the current preset time period through a classification algorithm based on the preset tobacco plant organ types, and obtain a plant organ classification set based on one preset time period; the labeled nitrogen content acquisition module 6 is used to obtain the labeled nitrogen content of all plant organs in each plant organ classification set through isotope analysis respectively; the nitrogen content average value acquisition module 7 is used to obtain the average value of the labeled nitrogen content of each preset tobacco plant organ type in the current plant organ classification set, and obtain a nitrogen content average value based on one preset tobacco plant organ type; the biomass-nitrogen relationship definition module 8 is used to analyze the linear regression relationship between the biomass average value and all nitrogen content average values in the same preset time period through a multiple linear regression model to obtain a prediction model; the nitrogen content prediction module 9 is used to predict several nitrogen content prediction values for each preset tobacco plant organ type based on the preset prediction steps through the prediction model.

[0178] Further, the tobacco plant organ classification module 5 specifically includes a first tobacco plant organ classification sub-module, a second tobacco plant organ classification sub-module, a third tobacco plant organ classification sub-module, a fourth tobacco plant organ classification sub-module, a fifth tobacco plant organ classification sub-module, and a sixth tobacco plant organ classification sub-module that are electrically connected in sequence; the first tobacco plant organ classification sub-module is electrically connected to the biomass average value acquisition module 4, and the sixth tobacco plant organ classification sub-module is electrically connected to the labeled nitrogen content acquisition module 6.

[0179] Among them, the first tobacco plant organ classification sub-module is used to obtain the visual images of each complete tobacco plant sample respectively; the second tobacco plant organ classification sub-module is used to obtain all plant organs in each visual image respectively through the target detection algorithm; the third tobacco plant organ classification sub-module is used to integrate all plant organs in the same preset time period into a data set to be classified; the fourth tobacco plant organ classification sub-module is used to define the plant organ category set according to the number of types of all preset tobacco plant organ types; the fifth tobacco plant organ classification sub-module is used to calculate the conditional probability of each plant organ in the data set to be classified in the same preset time period under each preset plant organ type respectively; the sixth tobacco plant organ classification sub-module is used to classify all plant organs in the data set to be classified in the same preset time period into the preset plant organ type with the highest conditional probability for each of them, and obtain a plant organ classification set based on a preset time period.

[0180] Further, the second tobacco plant organ classification sub-module specifically includes a first tobacco plant organ classification unit, a second tobacco plant organ classification unit, a third tobacco plant organ classification unit, a fourth tobacco plant organ classification unit, a fifth tobacco plant organ classification unit, a sixth tobacco plant organ classification unit, and a seventh tobacco plant organ classification unit that are electrically connected in sequence; the first tobacco plant organ classification unit is electrically connected to the first tobacco plant organ classification sub-module, and the seventh tobacco plant organ classification unit is electrically connected to the third tobacco plant organ classification sub-module.

[0181] Among them, the first tobacco plant organ classification unit is used to evenly divide the current visual image into several square grids; the second tobacco plant organ classification unit is used to predict several bounding boxes for all plant organs based on all square grids, and each bounding box includes at least one square grid; the third tobacco plant organ classification unit is used to obtain the confidence of each bounding box based on the current preset plant organ type respectively; the fourth tobacco plant organ classification unit is used to combine the bounding box with the highest confidence and mark it as the first-order bounding box; the fifth tobacco plant organ classification unit is used to calculate the intersection-over-union ratio of each of the other bounding boxes with the first-order bounding box respectively; the sixth tobacco plant organ classification unit is used to select the bounding boxes with the intersection-over-union ratio greater than or equal to the preset threshold as the second-order bounding boxes; the seventh tobacco plant organ classification unit is used to obtain the second-order bounding box with the highest confidence and define it as the plant organ of the current preset plant organ type.

[0182] Further, the biomass-nitrogen quantity relationship defining module 8 specifically includes a first biomass-nitrogen quantity relationship defining sub-module, a second biomass-nitrogen quantity relationship defining sub-module, a third biomass-nitrogen quantity relationship defining sub-module, and a fourth biomass-nitrogen quantity relationship defining sub-module that are electrically connected in sequence; the first biomass-nitrogen quantity relationship defining sub-module is electrically connected to the nitrogen content average value obtaining module 7, and the fourth biomass-nitrogen quantity relationship defining sub-module is electrically connected to the nitrogen content predicting module 9.

[0183] Among them, the first biomass-nitrogen quantity relationship defining sub-module is used to define the linear regression relationship between the average biomass of the same preset time period and all average nitrogen content values through a multiple linear regression model; the second biomass-nitrogen quantity relationship defining sub-module is used to solve all linear regression coefficients of the multiple linear regression model by the least squares method; the third biomass-nitrogen quantity relationship defining sub-module is used to substitute all the solved regression coefficients into the multiple linear regression model to obtain the multiple linear regression model; the fourth biomass-nitrogen quantity relationship defining sub-module is used to define the multiple linear regression model as a prediction model.

[0184] Further, the nitrogen content predicting module 9 specifically includes a first nitrogen content predicting sub-module, a second nitrogen content predicting sub-module, and a third nitrogen content predicting sub-module that are electrically connected in sequence; the first nitrogen content predicting sub-module is electrically connected to the fourth biomass-nitrogen quantity relationship defining sub-module.

[0185] Among them, the first nitrogen content predicting sub-module is used to randomly sample all tobacco plants again to obtain a number of complete prediction samples for predicting the future labeled nitrogen content; the second nitrogen content predicting sub-module is used to obtain the real-time biomass of each complete prediction sample respectively; the third nitrogen content predicting sub-module is used to substitute all the real-time biomass into the prediction model to obtain a nitrogen content prediction value based on a preset tobacco plant organ type.

[0186] Further, the nitrogen absorption analysis device further includes a content difference obtaining module, a good absorption organ defining module, and an absorption disorder organ defining module that are electrically connected in sequence; the content difference obtaining module is electrically connected to the third nitrogen content predicting sub-module.

[0187] Among them, the content difference obtaining module is used to judge the content difference between all nitrogen content prediction values and all labeled nitrogen content values based on the same preset tobacco plant organ type; the good absorption organ defining module is used to define the preset tobacco plant organ type with a content difference greater than or equal to a preset content threshold as a good absorption organ; the absorption disorder organ defining module is used to define the preset tobacco plant organ type with a content difference less than the preset content threshold as an absorption disorder organ.

[0188] Further, the nitrogen absorption analysis device further includes a complete tobacco plant sample parameter sending module electrically connected to the third nitrogen content prediction sub-module. This module is used to obtain the tobacco plant biomass, all plant organ classification sets, all labeled nitrogen contents, and nitrogen content prediction values of all complete tobacco plant samples, and send them to an external visual monitoring terminal.

[0189] It should be noted that this embodiment is a functional module item embodiment based on the above method embodiment. For additional content such as the preference, expansion, limitation, and illustrative examples of this embodiment, refer to the above method embodiment, and this embodiment will not be elaborated further.

[0190] In this embodiment, the nitrogen of all nitrogen fertilizers is labeled by the 15N tracer method to obtain labeled nitrogen; based on several preset time periods, all tobacco plants are randomly sampled, and several complete tobacco plant samples are obtained based on one preset time period; the tobacco plant biomass of each complete tobacco plant sample is obtained respectively; the biomass average value of all tobacco plant biomasses in the current preset time period is obtained, and a biomass average value is obtained based on one preset time period; all complete tobacco plant samples in the current preset time period are classified into plant organs by a classification algorithm based on the preset tobacco plant organ type, and a plant organ classification set is obtained based on one preset time period; the labeled nitrogen content of all plant organs in each plant organ classification set is obtained through isotope analysis; the average value of the labeled nitrogen content of each preset tobacco plant organ type in the current plant organ classification set is obtained, and a nitrogen content average value is obtained based on one preset tobacco plant organ type; the linear regression relationship between the biomass average value and all nitrogen content average values in the same preset time period is analyzed through a multiple linear regression model to obtain a prediction model; based on the preset prediction steps, several nitrogen content prediction values are predicted for each preset tobacco plant organ type through the prediction model. This embodiment utilizes the linear relationship of tobacco plant growth based on the time process, and at the same time drives the absorption of nitrogen fertilizer in the soil to also have a linear relationship based on the time process. This embodiment uses the tobacco plant biomass as an index to analyze the relationship between the nitrogen absorption amount and biomass of each part of the tobacco plant. After analyzing the mutual relationship, the nitrogen content prediction of each part of the tobacco plant can be realized, making the measurement result of this embodiment a continuous state from the past to the future based on the time process, and realizing the continuity and forward-looking of the measurement result.

[0191] Figure 3 Shows an embodiment of the electronic device of the present application. Refer to Figure 3 The electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101.

[0192] The memory 102 stores program instructions for implementing the nitrogen absorption analysis method of flue-cured tobacco leaves in any of the above embodiments.

[0193] The processor 101 is used to execute the program instructions stored in the memory 102 for nitrogen absorption analysis of flue-cured tobacco leaves.

[0194] Among them, the processor 101 can also be called a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip with signal processing capabilities. The processor 101 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0195] Furthermore, Figure 4 For the structural schematic diagram of the storage medium according to an embodiment of the present application, see Figure 4 The storage medium 11 of the embodiment of the present application stores program instructions 111 that can implement all the above methods. Among them, the program instructions 111 can be stored in the above storage medium in the form of a software product, including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media that can store program codes such as USB flash drives, external hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, or terminal devices such as computers, servers, mobile phones, and tablets.

[0196] In several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms.

[0197] In addition, in each embodiment of the present application, each functional unit may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit. The above is only the implementation manner of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be included in the patent protection scope of the present application by the same token.

[0198] The specific implementation manners of the present application have been described in detail above, but they are only examples, and the present application is not limited to the specific implementation manners described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the present application. Therefore, any equivalent transformation, modification, improvement, etc. made without departing from the spirit and principle scope of the present application should be covered by the scope of the present application.

Claims

1. A method for analyzing nitrogen absorption of flue-cured tobacco leaves, the nitrogen absorption analysis method being applied to a plurality of tobacco plants planted in soil applied with nitrogen fertilizer, characterized in that, The nitrogen absorption analysis method includes: Step S1: Label the nitrogen of all nitrogen fertilizers by the 15N tracer method to obtain labeled nitrogen; Step S2: Randomly sample all tobacco plants based on a number of preset time periods, and obtain a number of complete tobacco plant samples based on one preset time period; Step S3: Obtain the tobacco plant biomass of each complete tobacco plant sample respectively; Step S4: Obtain the biomass average value of all tobacco plant biomasses in the current preset time period, and obtain a biomass average value based on one preset time period; Step S5: Classify all complete tobacco plant samples in the current preset time period into plant organs based on the preset tobacco plant organ types through a classification algorithm, and obtain a plant organ classification set based on one preset time period; Step S6: Obtain the labeled nitrogen content of all plant organs in each plant organ classification set through isotope analysis respectively; Step S7: Obtain the average value of the labeled nitrogen content of each preset tobacco plant organ type in the current plant organ classification set, and obtain a nitrogen content average value based on one preset tobacco plant organ type; Step S8: Analyze the linear regression relationship between the biomass average value and all nitrogen content average values in the same preset time period through a multiple linear regression model to obtain a prediction model; Step S9: Predict a number of nitrogen content prediction values for each preset tobacco plant organ type respectively based on the preset prediction steps through the prediction model.

2. The nitrogen absorption analysis method according to claim 1, characterized in that Step S5: Classify all complete tobacco plant samples in the current preset time period into plant organs based on the preset tobacco plant organ types through a classification algorithm, and obtain a plant organ classification set based on one preset time period, including: Step S51: Obtain the visual image of each complete tobacco plant sample respectively; Step S52: Obtain all plant organs in each visual image through an object detection algorithm respectively; Step S53: Integrate all plant organs in the same preset time period into a dataset to be classified; Step S54: Define a plant organ category set according to the number of types of all preset tobacco plant organ types; Step S55: Calculate the conditional probability of each plant organ in the dataset to be classified in the same preset time period under each preset plant organ type respectively; Step S56: Classify all plant organs in the dataset to be classified in the same preset time period into the preset plant organ type with the highest conditional probability for each of them, and obtain a plant organ classification set based on one preset time period.

3. The nitrogen absorption analysis method according to claim 1, characterized in that Step S52: Obtain all plant organs in each visual image through an object detection algorithm respectively, including: Step S521: Divide the current visual image evenly into a number of square grids; Step S522: Predict a number of bounding boxes for all plant organs based on all square grids, and each bounding box includes at least one square grid; Step S523: Obtain the confidence of each bounding box based on the current preset plant organ type respectively; Step S524: Mark the bounding box with the highest confidence as the first-order bounding box; Step S525: Calculate the intersection over union of each of the other bounding boxes with the first-order bounding box respectively; Step S526: Select the bounding boxes with an intersection over union (IoU) greater than or equal to a preset threshold as the second-order bounding boxes; Step S527: Obtain the second-order bounding box with the highest confidence and define it as the plant organ of the current preset plant organ type.

4. The nitrogen uptake analysis method according to claim 1, wherein Step S8: Analyze the linear regression relationship between the average biomass and the average nitrogen content of all nitrogen forms within the same preset time period through a multiple linear regression model to obtain a prediction model, including: Step S81: Define the linear regression relationship between the average biomass and the average nitrogen content of all nitrogen forms within the same preset time period through the multiple linear regression model; Step S82: Solve all the linear regression coefficients of the multiple linear regression model by the least squares method; Step S83: Substitute all the obtained regression coefficients into the multiple linear regression model to obtain the multiple linear regression model; Step S84: Define the multiple linear regression model as the prediction model.

5. The nitrogen absorption analysis method according to claim 1, characterized in that, Step S9: Based on a preset prediction step, predict several nitrogen content prediction values for each preset tobacco plant organ type through the prediction model, including: Step S91: Conduct another random sampling of all tobacco plants to obtain several complete prediction samples for predicting future labeled nitrogen content; Step S92: Respectively obtain the real-time biomass of each complete prediction sample; Step S93: Substitute all the real-time biomass into the prediction model to obtain a nitrogen content prediction value based on one preset tobacco plant organ type.

6. The nitrogen absorption analysis method according to claim 5, characterized in that, Step S93: Substitute all the real-time biomass into the prediction model to obtain a nitrogen content prediction value based on one preset tobacco plant organ type. After that, it includes: Step S100: Judge the content difference between all the nitrogen content prediction values and all the labeled nitrogen content based on the same preset tobacco plant organ type; Step S200: Define the preset tobacco plant organ type with a content difference greater than or equal to the preset content threshold as the organ with good absorption; Step S300: Define the preset tobacco plant organ type with a content difference less than the preset content threshold as the organ with absorption disorder.

7. The nitrogen absorption analysis method according to claim 5, characterized in that, Step S93: Substitute all the real-time biomass into the prediction model to obtain a nitrogen content prediction value based on one preset tobacco plant organ type. After that, it includes: Step S1000: Obtain the tobacco plant biomass of all complete tobacco plant samples, all plant organ classification sets, all labeled nitrogen content, and nitrogen content prediction values, and send them to an external visual monitoring terminal.

8. An apparatus for analyzing nitrogen absorption of flue-cured tobacco leaves, the nitrogen absorption analysis apparatus being applied to the nitrogen absorption analysis method according to any one of claims 1 to 7, characterized in that, The nitrogen absorption analysis device includes: A nitrogen fertilizer nitrogen labeling module, which is used to label the nitrogen of all nitrogen fertilizers by the 15N tracer method to obtain labeled nitrogen; A tobacco plant random sampling module, which is used to randomly sample all tobacco plants based on several preset time periods to obtain several complete tobacco plant samples based on one preset time period; A tobacco plant biomass acquisition module, which is used to respectively obtain the tobacco plant biomass of each complete tobacco plant sample; A biomass average value acquisition module, which is used to obtain the biomass average value of all tobacco plant biomass in the current preset time period to obtain a biomass average value based on one preset time period; A tobacco plant organ classification module, which is used to classify all complete tobacco plant samples in the current preset time period into plant organs through a classification algorithm based on a preset tobacco plant organ type, and obtain a plant organ classification set based on a preset time period; A labeled nitrogen content acquisition module, which is used to obtain the labeled nitrogen content of all plant organs in each plant organ classification set through isotope analysis; A nitrogen content average value acquisition module, which is used to obtain the average value of the labeled nitrogen content of each preset tobacco plant organ type in the current plant organ classification set, and obtain an average value of the nitrogen content based on a preset tobacco plant organ type; A biomass-nitrogen amount relationship definition module, which is used to analyze the linear regression relationship between the average biomass and all nitrogen content average values in the same preset time period through a multiple linear regression model to obtain a prediction model; A nitrogen content prediction module, which is used to predict a plurality of nitrogen content prediction values for each preset tobacco plant organ type based on a preset prediction step through the prediction model.

9. An electronic device, characterized in that, It includes a processor and a memory coupled to the processor, and the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, it implements the nitrogen absorption analysis method according to any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores program instructions, and when the program instructions are executed by a processor, they can implement the nitrogen absorption analysis method according to any one of claims 1 to 7.

Images