Fish-vegetable symbiotic system hydroponic vegetable nitrogen nutrition profit and loss identification method, equipment, medium and product

Abstract

The invention discloses a fish and vegetable symbiotic system hydroponic vegetable nitrogen nutrition profit and loss identification method and device, a medium and a product, and relates to the field of aquaculture. The method comprises the following steps: taking hydroponic vegetables in a fish and vegetable symbiotic system as a production group, and setting hydroponic vegetables which are in the same climate condition as the production group and adopt optimal nutrition supply as a control group; respectively acquiring canopy image data of the production group and the control group by adopting a depth camera; based on a lightweight instance segmentation model, determining vegetable nitrogen nutrition status indexes of the production group and the control group according to the canopy image data of the production group and the control group; using the vegetable nitrogen nutrition status index of the control group as a nitrogen nutrition profit and loss identification reference value; and judging the vegetable nitrogen nutrition profit and loss condition of the production group according to the nitrogen nutrition profit and loss identification reference value and the vegetable nitrogen nutrition condition index of the production group. According to the invention, accurate identification of vegetable nitrogen nutrition profit and loss conditions adapting to climatic changes can be realized.

Description

Technical Field

[0001] The present application relates to the field of aquaculture, and in particular to a method, equipment, medium and product for identifying nitrogen nutrient deficit of hydroponic vegetables in a fish-vegetable symbiosis system. Background Art

[0002] The fish-vegetable symbiotic system is a new type of farming model that is green, ecological, environmentally friendly and pollution-free. It effectively connects the nitrogen supply and demand relationship between aquaculture and vegetable hydroponics, achieving the goals of low water change rate for fish farming, less fertilizer for vegetable farming, and low environmental pollution. However, there are still many problems in the actual production process of the existing fish-vegetable symbiotic system: (1) Managers generally attach importance to the economic value of fish, only regard vegetables as a tool for purifying aquaculture water, and ignore the economic value of vegetables. (2) The life cycle of fish and vegetables is asynchronous, and the optimal growth of vegetables is difficult to ensure. The nitrogen nutrition required for vegetable growth mainly comes from aquaculture tail water. The richness of nitrogen nutrition in aquaculture tail water shows an overall trend of gradually increasing with the increase of aquaculture stage. The nitrogen demand of vegetables in the early growth stage is small, and the nitrogen demand in the middle and late growth stages is large. Insufficient nitrogen nutrition supply will lead to slow growth of vegetables, which in turn leads to nitrogen nutrition deficiency in vegetables. (3) The nitrogen nutrition absorption capacity of vegetables in different seasons and different climatic conditions is different, and the external growth performance is different. (4) There are differences in the growth of individual plants, and the identification of nitrogen nutrition profit and loss status at a single point is one-sided. Therefore, accurate identification of nitrogen nutritional surplus and deficit status of vegetables in aquaponics systems is the key to optimal growth regulation of subsequent crops.

[0003] Currently, there is almost no research on the diagnosis of nitrogen nutrition status of vegetables in aquaponics scenarios. Most existing studies use spectral technology and visual technology to collect field or facility crop data and build nitrogen nutrition status diagnosis models, ignoring the impact of climate differences caused by different regions or seasons on the nitrogen nutrition absorption capacity of crops. Although the model can be constructed by collecting nitrogen response data sets of crops in different regions and seasonal conditions to ensure the applicability of the model, the data collection process is very time-consuming and requires a large investment in manpower and material resources. Summary of the invention

[0004] The purpose of this application is to provide a method, equipment, medium and product for identifying nitrogen nutrient surplus and deficit of hydroponic vegetables in a fish-vegetable symbiosis system, which can realize accurate identification of nitrogen nutrient surplus and deficit status of vegetables that adapt to climate change.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for identifying nitrogen nutrient surplus and deficit of hydroponic vegetables in a fish-vegetable symbiosis system, the method comprising:

[0007] The hydroponic vegetables in the aquaponics system were used as the production group, and the hydroponic vegetables in the same climatic conditions as the production group and with the best nutrient supply were set as the control group;

[0008] Depth cameras were used to collect canopy image data of the production group and the control group;

[0009] Based on the lightweight instance segmentation model, the vegetable nitrogen nutritional status indicators of the production group and the control group are determined according to the canopy image data of the production group and the control group; the vegetable nitrogen nutritional status indicators include: the mean canopy coverage and the mean plant height; the lightweight instance segmentation model is constructed based on the YOLOv8 instance segmentation model;

[0010] The nitrogen nutrition status index of the vegetables in the control group is used as a nitrogen nutrition profit and loss identification benchmark value; the nitrogen nutrition profit and loss identification benchmark value includes: a canopy coverage benchmark value and a plant height benchmark value;

[0011] The nitrogen nutrition profit and loss status of vegetables in the production group is judged based on the nitrogen nutrition profit and loss identification benchmark value and the vegetable nitrogen nutrition status indicators of the production group.

[0012] Optionally, the lightweight instance segmentation model uses the YOLOv8 instance segmentation model as a benchmark model, and uses the StarNet structure to replace the backbone network of the benchmark model, uses group normalization to replace the batch normalization in the head network of the benchmark model, and uses the DEConv structure to replace the 5 3×3 convolutional layers in the head network of the benchmark model.

[0013] Optionally, based on the lightweight instance segmentation model, the vegetable nitrogen nutritional status indicators of the production group and the control group are determined according to the canopy image data of the production group and the control group, including:

[0014] The canopy image data of the production group and the control group are respectively input into the lightweight instance segmentation model to obtain the corresponding target areas of different plant individuals in the current field of view;

[0015] Calculate the ratio of the number of pixels of the target area of ​​different individual plants in the current field of view corresponding to the production group divided by the number of pixels of the canopy image data of the production group to obtain the canopy coverage of the group plants of the production group, and divide the canopy coverage of the group plants of the production group by the number of plants in the production group to obtain the mean canopy coverage of the production group;

[0016] Calculate the average value of the height values ​​of the center points of the target areas of different plant individuals in the current field of view corresponding to the production group to obtain the average plant height of the production group;

[0017] Calculate the ratio of the number of pixels of the target area of ​​different plant individuals in the current field of view corresponding to the control group divided by the number of pixels of the canopy image data of the control group to obtain the canopy coverage of the group plants in the control group, and divide the canopy coverage of the group plants in the control group by the number of plants in the control group to obtain the mean canopy coverage of the control group;

[0018] The average value of the height values ​​of the center points of the target areas of different plant individuals in the current field of view corresponding to the control group is calculated to obtain the average plant height of the control group.

[0019] Optionally, judging the nitrogen nutritional surplus or deficit status of the vegetables of the production group according to the nitrogen nutritional surplus or deficit identification benchmark value and the vegetable nitrogen nutritional status index of the production group includes:

[0020] If the mean canopy coverage of the production group is less than the canopy coverage benchmark value, and the mean plant height of the production group is less than the plant height benchmark value, then the nitrogen nutrition surplus and deficit status of the vegetables in the production group is a nitrogen deficiency state;

[0021] If the mean canopy coverage of the production group is equal to the canopy coverage benchmark value, and the mean plant height of the production group is equal to the plant height benchmark value, then the nitrogen nutritional surplus and deficit status of the vegetables in the production group is the optimal nitrogen status;

[0022] If the mean canopy coverage of the production group is greater than the canopy coverage benchmark value, and the mean plant height of the production group is greater than the plant height benchmark value, then the nitrogen nutrition surplus and deficit status of the vegetables in the production group is a nitrogen surplus state;

[0023] If the mean canopy coverage of the production group is less than the canopy coverage benchmark value, and the mean plant height of the production group is greater than the plant height benchmark value, or the mean canopy coverage of the production group is greater than the canopy coverage benchmark value, and the mean plant height of the production group is less than the plant height benchmark value, then the vegetable growth of the production group is abnormal or the data collection and calculation is abnormal, and the nitrogen nutrition surplus or deficit status cannot be determined.

[0024] Optionally, the maximum allowable difference between the mean canopy coverage of the production group and the canopy coverage benchmark value is 5%. When the absolute value of the difference between the mean canopy coverage of the production group and the canopy coverage benchmark value is less than or equal to 5%, the mean canopy coverage of the production group is deemed to be equal to the canopy coverage benchmark value, otherwise, the mean canopy coverage of the production group is deemed to be not equal to the canopy coverage benchmark value; the maximum allowable difference between the mean plant height of the production group and the plant height benchmark value is 0.2 cm. When the absolute value of the difference between the mean plant height of the production group and the plant height benchmark value is less than or equal to 0.2 cm, the mean plant height of the production group is deemed to be equal to the plant height benchmark value, otherwise, the mean plant height of the production group is deemed to be not equal to the plant height benchmark value.

[0025] Optionally, the depth camera is arranged parallel to the plane of the culture tank of the fish and vegetable symbiosis system, and the height from the plane of the culture tank of the fish and vegetable symbiosis system is 50 cm.

[0026] Optionally, the method for identifying nitrogen nutrient surplus or deficit of hydroponic vegetables in the aquaponics system further comprises:

[0027] Different nitrogen treatment gradients were set according to the nitrogen content range of aquaculture tail water in the aquaponics system;

[0028] The sample vegetables were transplanted into cultivation tanks under different nitrogen treatment gradients for cultivation, and the canopy image data of the sample vegetables throughout their growth period were collected using a depth camera;

[0029] The canopy image data of the sample vegetables during the whole growth period is input into the lightweight instance segmentation model to obtain the target areas of different plant individuals in the current field of view of the sample vegetables;

[0030] According to the target areas of different plant individuals in the current visual area of ​​the sample vegetables under different nitrogen treatment gradients, the corresponding canopy coverage mean and plant height mean are determined;

[0031] The mean change curves of canopy coverage and plant height under different nitrogen treatment gradients and different growth days are drawn, and the nitrogen nutrition profit and loss identification baseline is determined; the nitrogen treatment gradient of the control group is set based on the nitrogen nutrition profit and loss identification baseline.

[0032] In a second aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for identifying nitrogen nutrient profit and deficit of hydroponic vegetables in the fish-vegetable symbiosis system.

[0033] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for identifying nitrogen nutrient surplus or deficit of hydroponic vegetables in the aquaponics system.

[0034] In a fourth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method for identifying nitrogen nutrient surplus or deficit of hydroponic vegetables in the fish-vegetable symbiosis system.

[0035] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0036] The present application provides a method, equipment, medium and product for identifying nitrogen nutrient profit and loss of hydroponic vegetables in a fish-vegetable symbiotic system. By adding an additional group of hydroponic vegetables that are in the same climatic conditions as the production group and use the best nutrient supply as the control group, it can adapt to climate change and give the most standard nitrogen nutrient profit and loss identification benchmark with the mean canopy coverage and the mean plant height as discrimination indicators, thereby achieving accurate identification of nitrogen nutrient profit and loss status of vegetables that adapt to climate change. In addition, the construction of a lightweight instance segmentation model realizes the automated collection of canopy coverage and plant height of individual plants, which can improve the accuracy and efficiency of identifying nitrogen nutrient profit and loss of vegetables. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A flow chart of the method for identifying nitrogen nutrient deficits in hydroponic vegetables in aquaponics system provided in this application;

[0039] Figure 2 Schematic diagram of canopy image data acquisition provided for this application;

[0040] Figure 3 The network structure diagram of the lightweight and improved YOLOv8 instance segmentation model provided in this application;

[0041] Figure 4 The head network structure diagram of the lightweight and improved YOLOv8 instance segmentation model provided in this application;

[0042] Figure 5 The canopy coverage mean change curve and the nitrogen nutrition profit and loss identification baseline diagram of the canopy coverage mean provided in this application;

[0043] Figure 6 The plant height mean change curve and the nitrogen nutrition profit and loss identification baseline diagram of the plant height mean provided in this application;

[0044] Figure 7 Implementation diagram of the method for identifying nitrogen nutrient profit and deficit of hydroponic vegetables in aquaponics system provided in this application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0046] This application aims to solve the problem of difficulty in identifying the nitrogen nutritional profit and loss status of vegetables due to the imbalance of nitrogen supply and demand in aquaculture tail water under the asynchronous life cycle of fish and vegetables in the fish-vegetable symbiotic system and the different nitrogen absorption capacity of vegetables under different climatic conditions. By combining the steps of vegetable nitrogen profit and loss experiment design, multimodal data collection, lightweight instance segmentation model construction, core evaluation parameter determination, nitrogen nutritional profit and loss identification strategy and system construction, the application can realize the accurate judgment of the nitrogen nutritional status of vegetables in the fish-vegetable symbiotic system scenario.

[0047] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0048] In an exemplary embodiment, the present application provides a method for identifying nitrogen nutrient deficit of hydroponic vegetables in a fish-vegetable symbiotic system. In the embodiment of the present application, Figure 1 As shown, the method includes the following steps 1 to 5.

[0049] Step 1: Use the hydroponic vegetables in the aquaponic system as the production group, and set up the hydroponic vegetables in the same climatic conditions as the production group and with the best nutritional supply as the control group.

[0050] Step 2: Use a depth camera to collect canopy image data of the production group and the control group respectively.

[0051] The depth camera is arranged parallel to the plane of the culture tank of the aquaponics system, and the height from the plane of the culture tank of the aquaponics system is 50 cm. Exemplarily, the depth camera is an Intel realsense D435i depth camera.

[0052] Step 3: Based on the lightweight instance segmentation model, the vegetable nitrogen nutritional status indicators of the production group and the control group are determined according to the canopy image data of the production group and the control group. The vegetable nitrogen nutritional status indicators include: the mean canopy coverage and the mean plant height.

[0053] The lightweight instance segmentation model is built based on the YOLOv8 instance segmentation model. Specifically, the lightweight instance segmentation model uses the YOLOv8 instance segmentation model as the benchmark model, and uses the StarNet structure to replace the backbone network of the benchmark model, uses group normalization to replace the batch normalization in the head network of the benchmark model, and uses the DEConv structure to replace the 5 3×3 convolutional layers in the head network of the benchmark model.

[0054] Step 3 specifically includes: inputting the canopy image data of the production group and the control group into the lightweight instance segmentation model respectively to obtain the corresponding target areas of different individual plants in the current field of view; calculating the ratio of the number of pixels of the target areas of different individual plants in the current field of view corresponding to the production group divided by the number of pixels of the canopy image data of the production group to obtain the group plant canopy coverage of the production group, and dividing the group plant canopy coverage of the production group by the number of plants in the production group to obtain the mean canopy coverage of the production group; calculating the average value of the height values ​​of the center points of the target areas of different individual plants in the current field of view corresponding to the production group to obtain the mean plant height of the production group; calculating the ratio of the number of pixels of the target areas of different individual plants in the current field of view corresponding to the control group divided by the number of pixels of the canopy image data of the control group to obtain the group plant canopy coverage of the control group, and dividing the group plant canopy coverage of the control group by the number of plants in the control group to obtain the mean canopy coverage of the control group; calculating the average value of the height values ​​of the center points of the target areas of different individual plants in the current field of view corresponding to the control group to obtain the mean plant height of the control group.

[0055] Step 4: Use the nitrogen nutrition status index of the vegetables in the control group as the nitrogen nutrition profit and loss identification benchmark value. The nitrogen nutrition profit and loss identification benchmark value includes: canopy coverage benchmark value and plant height benchmark value.

[0056] Step 5: Determine the nitrogen nutrition profit and loss status of the vegetables in the production group based on the nitrogen nutrition profit and loss identification benchmark value and the vegetable nitrogen nutrition status index of the production group.

[0057] Step 5 specifically includes: if the mean canopy coverage of the production group is less than the canopy coverage benchmark value, and the mean plant height of the production group is less than the plant height benchmark value, then the nitrogen nutrition profit and loss status of the vegetables in the production group is a nitrogen deficiency state; if the mean canopy coverage of the production group is equal to the canopy coverage benchmark value, and the mean plant height of the production group is equal to the plant height benchmark value, then the nitrogen nutrition profit and loss status of the vegetables in the production group is an optimal nitrogen state; if the mean canopy coverage of the production group is greater than the canopy coverage benchmark value, and the mean plant height of the production group is greater than the plant height benchmark value, then the nitrogen nutrition profit and loss status of the vegetables in the production group is a nitrogen surplus state; if the mean canopy coverage of the production group is less than the canopy coverage benchmark value, and the mean plant height of the production group is greater than the plant height benchmark value, or the mean canopy coverage of the production group is greater than the canopy coverage benchmark value, and the mean plant height of the production group is less than the plant height benchmark value, then the vegetable growth of the production group is abnormal or the data collection calculation is abnormal, and the nitrogen nutrition profit and loss status cannot be determined.

[0058] Among them, the maximum allowable difference between the mean canopy coverage of the production group and the canopy coverage benchmark value is 5%. When the absolute value of the difference between the mean canopy coverage of the production group and the canopy coverage benchmark value is less than or equal to 5%, the mean canopy coverage of the production group is deemed to be equal to the canopy coverage benchmark value, otherwise, the mean canopy coverage of the production group is deemed to be unequal to the canopy coverage benchmark value; the maximum allowable difference between the mean plant height of the production group and the plant height benchmark value is 0.2 cm. When the absolute value of the difference between the mean plant height of the production group and the plant height benchmark value is less than or equal to 0.2 cm, the mean plant height of the production group is deemed to be equal to the plant height benchmark value, otherwise, the mean plant height of the production group is deemed to be unequal to the plant height benchmark value.

[0059] Furthermore, the method also includes: setting different nitrogen treatment gradients according to the variation range of nitrogen content in the tail water of the aquaculture system; transplanting sample vegetables to cultivation troughs under different nitrogen treatment gradients for cultivation, and using a depth camera to collect canopy image data of the sample vegetables during the entire growth period; inputting the canopy image data of the sample vegetables during the entire growth period into a lightweight instance segmentation model to obtain the target area of ​​different plant individuals in the current field of view of the sample vegetables; determining the corresponding canopy coverage mean and plant height mean according to the target area of ​​different plant individuals in the current field of view of the sample vegetables under different nitrogen treatment gradients; drawing the canopy coverage mean change curve and plant height mean change curve under different nitrogen treatment gradients and different growth days, and determining the nitrogen nutrition profit and loss identification baseline. The nitrogen treatment gradient of the above-mentioned control group is set based on the nitrogen nutrition profit and loss identification baseline.

[0060] Combine the following Figures 2 to 7, the specific implementation process of the method for identifying nitrogen nutrient profit and loss of hydroponic vegetables in the above-mentioned fish-vegetable symbiosis system is described in detail, including the design of vegetable nitrogen profit and loss experiments, multimodal data collection, lightweight instance segmentation model construction, core evaluation parameter determination, nitrogen nutrient profit and loss identification strategy and system construction.

[0061] The first step is to design the vegetable nitrogen profit and loss experiment, which is mainly to design different nitrogen treatment experiments according to the variation range of nitrogen content in aquaculture effluent in the fish-vegetable symbiotic system, laying the foundation for the subsequent accurate collection of multimodal data.

[0062] During the whole life cycle of aquaponics from juvenile to adult fish, the nitrogen content of the aquaculture tail water after biochemical treatment is about 30mg / L-350mg / L. In order to keep consistent with the actual aquaculture scene, this application is based on the formula of Yamazaki lettuce nutrient solution, and takes hydroponic lettuce as the research object, and analyzes the nitrogen response ability of hydroponic lettuce by setting different nitrogen treatment gradients. The specific nitrogen treatment gradient is shown in Table 1 (where the nitrogen concentration of different nitrogen treatment gradients is an arithmetic progression, the difference is 76.18375mg / L, and the nitrogen concentration in the table is rounded to two decimal places), where N0, N1, N2, N3, and N4 belong to nitrogen deficiency treatment, N5 belongs to nitrogen optimal treatment, and N6, N7, and N8 belong to nitrogen excess treatment. Compared with the nitrogen treatment gradients previously studied, the nitrogen treatment gradients of this application are set more densely, and this setting can more accurately reflect the nitrogen response ability of vegetables.

[0063] Table 1 Nitrogen treatment gradient of hydroponic lettuce

[0064]

[0065] The second step is multimodal data collection, which is mainly to collect RGB images and depth images at the same time, so as to facilitate the subsequent acquisition of individual plant canopy coverage and plant height.

[0066] Based on the first step of the vegetable nitrogen profit and loss test design, after the vegetables are transplanted to the cultivation troughs under different nitrogen treatments, the Intel realsense D435i depth camera is connected to the laptop. The camera plane is parallel to the plane of the cultivation trough and the height is maintained at 50cm. The canopy image data (including RGB images and depth images) of the vegetables under different nitrogen treatments are collected. During the data collection process, when the camera has collected the current area, it slides parallel to the next area. No repeated plant samples can appear in the previous and next areas. The specific data collection diagram is as follows: Figure 2 shown.

[0067] The third step is to build a lightweight instance segmentation model, which is mainly to realize the automated collection of individual plant canopy coverage and plant height, and to improve the accuracy and efficiency of identifying nitrogen nutrition gains and losses in vegetables.

[0068] Based on the vegetable canopy image data under different nitrogen treatments collected in the second step, the data annotation software labelme is used to annotate the vegetable target area in the RGB images in the collected data. After all data annotation is completed, the overall data set is divided into training set, validation set and test set. In order to ensure the prediction accuracy and reasoning speed of the model in actual application, this application uses the YOLOv8 instance segmentation model as the benchmark model. Under the premise of minimizing the loss of model accuracy, the backbone network and head network of the YOLOv8 instance segmentation model are lightweight improved to meet the lightweight deployment requirements of actual production scenarios. Among them, this application uses the StarNet structure to replace the backbone network of the original YOLOv8 instance segmentation model. This backbone network enables the model to capture richer and more complex feature information without significantly increasing the computational complexity; this application uses group normalization to replace the batch normalization in the head network of the original YOLOv8 instance segmentation model, and uses the detail enhancement convolution DEConv structure to replace the 5 3×3 convolution layers in the head network of the original YOLOv8 instance segmentation model. Some convolution layers are set to share weights to minimize model performance loss while reducing the number of parameters. The lightweight and improved YOLOv8 instance segmentation model network structure is shown below: Figure 3 As shown in the figure, the lightweight and improved YOLOv8 instance segmentation model head network is as follows Figure 4 shown.

[0069] Step 4: Determine the core evaluation parameters, mainly by analyzing the change curves of the mean canopy coverage of individual plants and the mean plant height under different nitrogen treatments, and then determine the baseline for identifying nitrogen nutrition profit and loss.

[0070] Based on the lightweight instance segmentation model constructed in the third step, an Intel realsense D435i depth camera is used to connect a laptop computer, the camera plane is kept parallel to the plane of the cultivation trough and the height is kept at 50 cm, and the canopy image data of vegetables under different nitrogen treatments are collected during the entire growth period of the vegetables. The obtained canopy image is used as input, and the pre-trained lightweight instance segmentation model is called to output the target area of ​​different plant individuals in the current field of view. By calculating the ratio of the number of pixels in the vegetable plant area to the number of pixels in the entire input image, the canopy coverage of the group plants can be obtained. Then, by dividing the canopy coverage of the group plants by the number of plants, the mean canopy coverage can be obtained. The Intel realsense D435i depth camera itself can obtain the height value in the vegetable plant area. This application obtains the height value of the center point of the target area obtained by segmenting each vegetable, and then obtains the mean plant height by taking the average value. Among them, the mean canopy coverage and plant height of different plant individuals in the current field of view under N0 treatment are set as Ci0 and Hi0 respectively; the mean canopy coverage and plant height of different plant individuals in the current field of view under N1 treatment are set as Ci1 and Hi1 respectively; the mean canopy coverage and plant height of different plant individuals in the current field of view under N2 treatment are set as Ci2 and Hi2 respectively; the mean canopy coverage and plant height of different plant individuals in the current field of view under N3 treatment are set as Ci3 and Hi3 respectively; the canopy coverage and plant height of different plant individuals in the current field of view under N4 treatment are set as Ci1 and Hi1 respectively. The mean coverage and plant height are Ci4 and Hi4 respectively; the mean canopy coverage and plant height of different plants in the current field of view under N5 treatment are Ci5 and Hi5 respectively; the mean canopy coverage and plant height of different plants in the current field of view under N6 treatment are Ci6 and Hi6 respectively; the mean canopy coverage and plant height of different plants in the current field of view under N7 treatment are Ci7 and Hi7 respectively; the mean canopy coverage and plant height of different plants in the current field of view under N8 treatment are Ci8 and Hi8 respectively. C represents the mean canopy coverage, H represents the mean plant height, i represents the number of growing days, and 0-8 represents different nitrogen treatments.

[0071] The mean change curves of canopy coverage and plant height under different nitrogen treatments and different growing days were drawn, and the differences in the mean canopy coverage and plant height under different nitrogen treatments were analyzed. The mean change curves of canopy coverage and plant height under the best nitrogen treatment (N5) were selected as the baseline for identifying nitrogen nutritional profit and loss, providing the core evaluation parameter support basis for the accurate identification of nitrogen nutritional profit and loss of vegetables in subsequent actual production. Figure 5 and Figure 6As shown, the nitrogen nutrition surplus and deficit identification baseline obtained through different nitrogen treatment experiments can explain the change pattern of the mean canopy coverage and the mean plant height as the growing days increase under nitrogen deficiency, optimal nitrogen and nitrogen surplus conditions, as well as the relationship between them, indicating that the mean canopy coverage and the mean plant height can reflect the nitrogen nutrition status of vegetables.

[0072] Step 5: Nitrogen nutrition profit and loss identification strategy and system construction, mainly through setting up a control group and a production group, using the nitrogen nutrition profit and loss identification baseline to compare the core evaluation indicators of the control group and the production group, and then determine the current nitrogen nutrition profit and loss status of vegetables.

[0073] Based on the lightweight instance segmentation model obtained by the third step and the nitrogen nutrition profit and loss identification baseline determined by the fourth step experiment with the canopy coverage mean and plant height mean as the discrimination index, in the actual fish and vegetable symbiotic system production process, in order to better adapt to the impact of climate change on the precise diagnosis of vegetable nitrogen nutrition profit and loss, this application proposes a reference strategy for optimal nutrient supply based on climate adaptation. This strategy is to add an additional group of optimal nutrient supply control groups in actual production, and to obtain the core evaluation parameters of vegetable plants in different regions of the control group and the production group cultivation trough respectively (i.e., vegetable nitrogen nutrition status indicators, including canopy coverage mean and plant height mean) for real-time comparison to judge the nitrogen nutrition profit and loss status of vegetables in the fish and vegetable symbiotic system under current climatic conditions. Because the growth rate of vegetables in different regions and different climatic conditions is not completely consistent, the relationship between nitrogen deficiency, optimal nitrogen and nitrogen surplus reflected by the above-mentioned nitrogen nutrition profit and loss identification baseline is determined. Therefore, in order to adapt to climate change and regional changes, it is necessary to set up a separate optimal nutrient supply control group. At this time, the average canopy coverage and plant height obtained by the optimal nutrient supply control group as the number of growth days increases are the benchmark values ​​on the nitrogen nutrition profit and loss identification baseline. Among them, the average canopy coverage and plant height obtained by the control group (i.e., the canopy coverage benchmark value and the plant height benchmark value) are named CC and CH respectively, and the average canopy coverage and plant height obtained by the production group are named PC and PH respectively. Specific demonstration as follows Figure 7 shown.

[0074] The specific criteria for identifying the nitrogen surplus and deficit status of vegetables are as follows:

[0075] (1) If CC>PC and CH>PH in the data collected at different times, it means that the vegetables in the aquaponics system are in a state of nitrogen deficiency at the current stage.

[0076] (2) If CC≈PC (|CC-PC|≤5%) and CH≈PH (|CH-PH|≤0.2cm) in the data collected at different periods, it means that the vegetables in the fish-vegetable symbiosis system are in the optimal nitrogen state at the current stage.

[0077] (3) If CC < PC and CH < PH in the data collected at different times, it indicates that the vegetables in the aquaponics system are in a state of nitrogen surplus at the current stage.

[0078] (4) If CC > PC and CH < PH in the data collected at different times, it indicates that the vegetables in the aquaponics system are growing abnormally at the current stage (possibly due to the influence of continuous high-temperature weather leading to bolting), and it is impossible to judge the nitrogen nutrition profit and loss situation.

[0079] (5) If CC < PC and CH > PH in the data collected at different times, it indicates that the vegetables in the aquaponics system are growing abnormally at the current stage (or there is an abnormality in data collection and calculation), and it is impossible to judge the nitrogen nutrition profit and loss situation.

[0080] Through the implementation of the above strategies, no matter which region or climate conditions the aquaponics system is in, the additional set of optimal nutrient supply control groups in this application can always adapt to climate changes and give the most standard nitrogen nutrition profit and loss identification benchmarks with the average canopy coverage and the average plant height as the discrimination indicators, so as to achieve the accurate identification of the nitrogen nutrition profit and loss situation of vegetables adapting to climate changes.

[0081] In an exemplary embodiment, the present application also provides a computer device, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0082] In an exemplary embodiment, the present application also provides a computer-readable storage medium, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0083] In an exemplary embodiment, the present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0084] In the present application, all actions of obtaining signals, information or data are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where the location is located and obtaining the authorization given by the owner of the corresponding device. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws and regulations.

[0085] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0086] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0087] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0088] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for identifying nitrogen nutrient deficit in hydroponic vegetables in a fish-vegetable symbiotic system, characterized in that: include: The hydroponic vegetables in the aquaponics system were used as the production group, and the hydroponic vegetables in the same climatic conditions as the production group and with the best nutrient supply were set as the control group; Depth cameras were used to collect canopy image data of the production group and the control group; Based on the lightweight instance segmentation model, the nitrogen nutritional status indicators of vegetables in the production group and the control group were determined according to the canopy image data of the production group and the control group. The vegetable nitrogen nutrition status indicators include: canopy coverage mean and plant height mean; the lightweight instance segmentation model is constructed based on the YOLOv8 instance segmentation model; The nitrogen nutrition status index of the vegetables in the control group is used as a nitrogen nutrition profit and loss identification benchmark value; the nitrogen nutrition profit and loss identification benchmark value includes: a canopy coverage benchmark value and a plant height benchmark value; The nitrogen nutrition profit and loss status of vegetables in the production group is judged based on the nitrogen nutrition profit and loss identification benchmark value and the vegetable nitrogen nutrition status indicators of the production group.

2. The method for identifying nitrogen nutrient deficit of hydroponic vegetables in aquaponics system according to claim 1, characterized in that: The lightweight instance segmentation model uses the YOLOv8 instance segmentation model as the benchmark model, and uses the StarNet structure to replace the backbone network of the benchmark model, uses group normalization to replace the batch normalization in the head network of the benchmark model, and uses the DEConv structure to replace the 5 3×3 convolutional layers in the head network of the benchmark model.

3. The method for identifying nitrogen nutrient deficit of hydroponic vegetables in aquaponics system according to claim 1, characterized in that: Based on the lightweight instance segmentation model, the nitrogen nutritional status indicators of vegetables in the production group and the control group were determined according to the canopy image data of the production group and the control group, including: The canopy image data of the production group and the control group are respectively input into the lightweight instance segmentation model to obtain the corresponding target areas of different plant individuals in the current field of view; Calculate the ratio of the number of pixels of the target area of ​​different individual plants in the current field of view corresponding to the production group divided by the number of pixels of the canopy image data of the production group to obtain the canopy coverage of the group plants of the production group, and divide the canopy coverage of the group plants of the production group by the number of plants in the production group to obtain the mean canopy coverage of the production group; Calculate the average value of the height values ​​of the center points of the target areas of different plant individuals in the current field of view corresponding to the production group to obtain the average plant height of the production group; Calculate the ratio of the number of pixels of the target area of ​​different plant individuals in the current field of view corresponding to the control group divided by the number of pixels of the canopy image data of the control group to obtain the canopy coverage of the group plants in the control group, and divide the canopy coverage of the group plants in the control group by the number of plants in the control group to obtain the mean canopy coverage of the control group; The average value of the height values ​​of the center points of the target areas of different plant individuals in the current field of view corresponding to the control group is calculated to obtain the average plant height of the control group.

4. The method for identifying nitrogen nutrient deficit of hydroponic vegetables in aquaponics system according to claim 1, characterized in that: The nitrogen nutrition profit and loss status of the vegetables in the production group is determined based on the nitrogen nutrition profit and loss identification benchmark value and the vegetable nitrogen nutrition status index of the production group, including: If the mean canopy coverage of the production group is less than the canopy coverage benchmark value, and the mean plant height of the production group is less than the plant height benchmark value, then the nitrogen nutrition surplus and deficit status of the vegetables in the production group is a nitrogen deficiency state; If the mean canopy coverage of the production group is equal to the canopy coverage benchmark value, and the mean plant height of the production group is equal to the plant height benchmark value, then the nitrogen nutritional surplus and deficit status of the vegetables in the production group is the optimal nitrogen status; If the mean canopy coverage of the production group is greater than the canopy coverage benchmark value, and the mean plant height of the production group is greater than the plant height benchmark value, then the nitrogen nutrition surplus and deficit status of the vegetables in the production group is a nitrogen surplus state; If the mean canopy coverage of the production group is less than the canopy coverage benchmark value, and the mean plant height of the production group is greater than the plant height benchmark value, or the mean canopy coverage of the production group is greater than the canopy coverage benchmark value, and the mean plant height of the production group is less than the plant height benchmark value, then the vegetable growth of the production group is abnormal or the data collection and calculation is abnormal, and the nitrogen nutrition surplus or deficit status cannot be determined.

5. The method for identifying nitrogen nutrient deficit of hydroponic vegetables in aquaponics system according to claim 4, characterized in that: The maximum allowable difference between the mean canopy coverage of the production group and the canopy coverage benchmark value is 5%. When the absolute value of the difference between the mean canopy coverage of the production group and the canopy coverage benchmark value is less than or equal to 5%, the mean canopy coverage of the production group is deemed to be equal to the canopy coverage benchmark value, otherwise, the mean canopy coverage of the production group is deemed to be unequal to the canopy coverage benchmark value; the maximum allowable difference between the mean plant height of the production group and the plant height benchmark value is 0.2 cm. When the absolute value of the difference between the mean plant height of the production group and the plant height benchmark value is less than or equal to 0.2 cm, the mean plant height of the production group is deemed to be equal to the plant height benchmark value, otherwise, the mean plant height of the production group is deemed to be unequal to the plant height benchmark value.

6. The method for identifying nitrogen nutrient deficit of hydroponic vegetables in aquaponics system according to claim 1, characterized in that: The depth camera is arranged parallel to the plane of the culture tank of the fish and vegetable symbiosis system, and the height from the plane of the culture tank of the fish and vegetable symbiosis system is 50 cm.

7. The method for identifying nitrogen nutrient deficit of hydroponic vegetables in aquaponics system according to claim 1, characterized in that: Also includes: Different nitrogen treatment gradients were set according to the nitrogen content range of aquaculture tail water in the aquaponics system; The sample vegetables were transplanted into cultivation tanks under different nitrogen treatment gradients for cultivation, and the canopy image data of the sample vegetables throughout their growth period were collected using a depth camera; The canopy image data of the sample vegetables during the whole growth period is input into the lightweight instance segmentation model to obtain the target areas of different plant individuals in the current field of view of the sample vegetables; According to the target areas of different plant individuals in the current visual area of ​​the sample vegetables under different nitrogen treatment gradients, the corresponding canopy coverage mean and plant height mean are determined; The mean change curves of canopy coverage and plant height under different nitrogen treatment gradients and different growth days are drawn, and the nitrogen nutrition profit and loss identification baseline is determined; the nitrogen treatment gradient of the control group is set based on the nitrogen nutrition profit and loss identification baseline.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for identifying nitrogen nutrient surplus and deficit of hydroponic vegetables in a fish-vegetable symbiosis system according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for identifying nitrogen nutrient surplus and deficit of hydroponic vegetables in a fish-vegetable symbiosis system according to any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for identifying nitrogen nutrient surplus and deficit of hydroponic vegetables in a fish-vegetable symbiosis system according to any one of claims 1 to 7 is implemented.

Images