Water and fertilizer management control method based on image data processing

Abstract

The invention relates to a water and fertilizer management control method based on image data processing, and the method comprises the steps: collecting a visible light image, a multispectral image and a thermal infrared image of a crop, carrying out the feature extraction, calculating the plant morphological parameters, vegetation indexes and vegetation canopy temperature distribution of the crop, creating a three-dimensional physiological feature matrix, creating an image segmentation network model, and carrying out the feature extraction. Inputting the visible light image, the multispectral image, the thermal infrared image and the three-dimensional physiological feature matrix into an image segmentation network model to segment plant organs, quantifying organ-level phenotypic parameters, and establishing a water and fertilizer decision model based on reinforcement learning; and taking real-time data of the three-dimensional physiological feature matrix, the organ-level phenotypic parameters and the soil specified parameters as state input, taking a water and fertilizer proportioning scheme as an action space, and implementing a water and fertilizer management scheme through a dynamic optimization control strategy. The technical problems that data integration of a single sensor is insufficient, phenotype analysis precision is limited, and adaptability of a decision model is poor in a traditional water and fertilizer regulation scheme are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of water and fertilizer management, and particularly relates to a water and fertilizer management control method based on image data processing. Background Art

[0002] In recent years, the technology of agricultural precision management has developed rapidly. As a key link in crop yield increase and quality improvement, water and fertilizer regulation has gradually shifted from an experience-driven mode to a data-driven mode. However, traditional methods still have significant technical bottlenecks in terms of the accuracy of multi-source data fusion, the real-time performance of dynamic decision-making, and the ability of organ-level phenotype analysis, which are specifically manifested in the following aspects: First, insufficient integration of single-sensor data: Traditional water and fertilizer regulation schemes mostly rely on single spectral bands (such as visible light or near-infrared) or soil sensor data, and it is difficult to synchronously capture the coupling relationship between crop physiological states and environmental stresses (such as heat stress, nutrient imbalance, soil indicators). Visible light images can only analyze morphological parameters (such as leaf area, plant height), but cannot quantify nitrogen content. Thermal infrared images can detect abnormal canopy temperature, but lack a dynamic association with photosynthetic capacity; soil indicators only reflect the rhizosphere environment and cannot directly map the physiological response of the canopy.

[0003] Second, limited accuracy of phenotype analysis: Existing image segmentation algorithms are mostly designed for rough organ-level segmentation, and have insufficient ability to analyze micro-morphological features such as leaf serration and stem curvature, resulting in an error rate of up to 15%-20% in the prediction of water and fertilizer requirements. In addition, two-dimensional image analysis ignores the three-dimensional spatial distribution (such as the impact of leaf inclination differences on light interception), and it is difficult to accurately evaluate the dynamics of biomass accumulation.

[0004] Third, adaptability defects of decision-making models: Mainstream water and fertilizer decision-making models, such as threshold-triggered and expert system-based models in the prior art, rely on fixed rule bases and cannot adapt to the time-varying nature of the field environment and the non-linear characteristics of crop growth. For example: Static fertilization formulas ignore the selective absorption differences of stomatal aperture for different nitrogen forms (nitrate nitrogen / ammonium nitrogen); irrigation strategies based on historical data are difficult to cope with the transpiration wave under extreme weather.

[0005] Therefore, the problems of insufficient integration of single-sensor data, limited accuracy of phenotype analysis, and adaptability defects of decision-making models existing in traditional water and fertilizer regulation schemes are the technical problems that need to be solved urgently at present. Summary of the Invention

[0006] The purpose of the present invention is to provide a water and fertilizer management control method based on image data processing to solve the technical problems of insufficient integration of single-sensor data, limited accuracy of phenotype analysis, and adaptability defects of decision-making models existing in traditional water and fertilizer regulation schemes.

[0007] To solve the above technical problems, the technical solution adopted by the present invention is as follows: A water and fertilizer management control method based on image data processing, comprising the following steps: S1: Collect visible light images, multispectral images and thermal infrared images of crops through an image acquisition module, respectively extract features from the visible light images, multispectral images and thermal infrared images, and obtain visible light image features, multispectral image features and thermal infrared image features; S2: Calculate the plant morphological parameters of the crops through the visible light image features, calculate the vegetation index through the multispectral image features, and obtain the vegetation canopy temperature distribution by providing the thermal infrared image features; S3: Create a three-dimensional physiological feature matrix of the crops based on the plant morphological parameters, vegetation index and canopy temperature distribution; S4: Create an image segmentation network model, input the visible light images, multispectral images, thermal infrared images and three-dimensional physiological feature matrix into the image segmentation network model to segment the plant organs, and quantify the organ-level phenotypic parameters; S5: Establish a water and fertilizer decision-making model based on reinforcement learning, use the real-time data of the three-dimensional physiological feature matrix, organ-level phenotypic parameters, and soil specified parameters as the state input, use the water and fertilizer ratio scheme as the action space, and dynamically optimize the control strategy through the Q-learning algorithm; S6: Implement the water and fertilizer management plan based on the optimized control strategy.

[0008] Preferably, the visible light images of the crops in step S1 are collected through a visible light image acquisition module, the multispectral images are collected through a multispectral image acquisition module, and the thermal infrared images are collected through a thermal infrared image acquisition module.

[0009] Preferably, the specific process of extracting features from the visible light images, multispectral images and thermal infrared images in step S1 to obtain visible light image features, multispectral image features and thermal infrared image features is as follows: S11: Standardize the visible light images, extract the plant leaf edge features and leaf skeleton features in the visible light images through an edge detection algorithm, generate a point cloud model by combining multi-view visible light images, and obtain the leaf inclination angle and canopy opening degree features, fruit / stem features; S12: Use a calibration model to calibrate the multispectral images, use an improved RANSAC algorithm to align the visible light and multispectral images to ensure pixel-level spatial consistency, extract features from the 710nm red edge image and 840nm near-infrared light image, calculate the vegetation index features, and combine the 660nm red light image to obtain the normalized vegetation index features; S13: Convert the gray value to the absolute temperature through blackbody radiation correction, apply adaptive threshold segmentation to extract the vegetation area, obtain the temperature thermal map and obtain the standard deviation feature of the canopy temperature.

[0010] Preferably, in step S2, calculate the plant morphological parameters of the crop through the visible light image features, calculate the vegetation index of the crop through the multi-spectral image features, and the specific process of obtaining the vegetation canopy temperature distribution by providing the thermal infrared image features is as follows: S21: Calculate the leaf area index, leaf length, leaf width, perimeter, shape factor, petiole length, leaf inclination, and canopy openness based on the leaf inclination and canopy openness features, plant leaf edge features, and leaf skeleton features, and obtain the fruit size and color based on the fruit / stem features; S22: Calculate the vegetation index NDRE based on the vegetation index features. The calculation formula of the vegetation index NDRE is as follows: NDRE = ( ρ 840 - ρ 710) / ( ρ 840 + ρ 710); Where, ρ 840 is the reflectance of the 840nm near-infrared band, ρ 710 is the reflectance of the 710nm red-edge band; S23: Calculate the normalized difference vegetation index NDVI based on the normalized difference vegetation index features. The calculation formula of the normalized difference vegetation index NDVI is as follows: NDVI = ( ρ 840 - ρ 660) / ( ρ 840 + ρ 660); Where, ρ 840 is the reflectance of the 840nm near-infrared band, ρ 660 is the reflectance of the 660nm red light band; Preferably, in step S4, create an image segmentation network model, input the visible light image, multi-spectral image, thermal infrared image, and three-dimensional physiological feature matrix into the image segmentation network model to segment the plant organs, and the specific process of quantifying the organ-level phenotypic parameters is as follows: S41: Establish the visible light image, multi-spectral image, and thermal infrared image in a unified spatial coordinate system, and perform registration based on the spatial coordinate system; S42: Resample the three-dimensional physiological feature matrix to the two-dimensional image resolution through bilinear interpolation to establish a voxel-pixel mapping relationship; S43: The image segmentation network model is set with 12 input channels, among which three channels input visible light images, three channels input the reflectance of the 840nm near-infrared band, the reflectance of the 710nm red-edge band, and the reflectance of the 660nm red-light band of the multispectral image, and the remaining channels input the eigenvalues of the three-dimensional physiological feature matrix; S44: The backbone network module of the image segmentation network model adopts a ConvNeXt-Tiny encoder, embeds a dilated spatial pyramid pooling module to expand the receptive field to 128×128 pixels, introduces an efficient channel attention module in the decoder to mark candidate regions, and outputs the overall plant region; S45: The secondary network module of the image segmentation network model performs fine segmentation of plant organs on the candidate regions; S46: Quantify the leaf area, leaf serration, and leaf curvature based on the Fourier descriptors analysis of the segmentation mask contour, quantify the stem height, curvature, and diameter based on three-dimensional skeletonization processing and thermal infrared temperature gradient mapping, and quantify the fruit volume and surface patches based on the three-dimensional point cloud convex hull algorithm and multispectral abnormal reflection analysis.

[0011] Preferably, the specific process of step S5 is as follows: S51: Establish the state space of the water and fertilizer decision-making model. The state space includes a three-dimensional physiological feature matrix, organ-level phenotypic parameters, and soil specified parameters. The soil specified parameters are collected in real time by a soil moisture sensor and include 8-dimensional data of pH value, organic matter content, nutrient content, heavy metal content, microbial biomass, enzyme activity, humidity, and conductivity, and are denoised by Kalman filtering; S52: Create the action space of the water and fertilizer decision-making model. The action space includes action ID, water and fertilizer plan, and the corresponding water and nitrogen, phosphorus, and potassium ratios of the water and fertilizer plan. The action ID includes 0, 1, 2; 0, 1, 2 correspond to the baseline plan, high-nitrogen plan, and water-saving plan respectively; S53: Create the reward function of the water and fertilizer decision-making model. The formula of the reward function is: R = α (△BI - BI target ) + β (WUE - WUE baseline ); Among them, R is the reward function value; α and βIt is a crop-related weight coefficient that balances the optimization priorities of biomass growth and resource efficiency. In the early growth stage: α > β (focusing on biomass accumulation), and in the mature stage: β > α (focusing on resource efficiency); △BI is the biomass increment, which reflects the growth rate of the plant biomass per unit time and is calculated as follows: dynamically estimated through the three-dimensional reconstruction data of the leaf area index (LAI) and the stem volume; BI target is the target biomass threshold, which is the expected biomass growth value preset according to the crop growth stage and is corrected in real time based on environmental factors (such as accumulated temperature and sunshine hours) through a sliding window algorithm; WUE is the water use efficiency, which is usually defined as the ratio of crop yield to irrigation water volume (kg / m³), and maximizes the biomass output per unit water volume by adjusting the irrigation strategy. WUE baseline is the baseline water use efficiency, representing the historical average or industry standard level, serving as the reference benchmark for reward calculation, and reflecting the improvement amplitude of the current strategy compared to the conventional plan; S54: The reward function drives strategy optimization through the following mechanism. When the actual biomass increment (△BI) exceeds the preset target BI target at that time, α item generates a positive reward, β item ensures that the water use efficiency is not lower than the baseline level, avoiding resource waste caused by over-irrigation, and the α / β ratio adjustment realizes the dynamic balance between increasing production and saving water, meeting the sustainable development needs of agricultural production.

[0012] Preferably, during the image acquisition process, the image acquisition module performs polarized light filtering and polarization angle adjustment, and the polarization angle adjustment formula is as follows: θ = arctan( n 2 / n 1) + k ·Δ φ ; Among them, θ is the polarization angle adjustment amount, n 1, n 2 are the refractive indices of the medium, Δ φ is the leaf surface curvature compensation amount, k is the proportional coefficient, which is used to describe the sensitivity of the polarization angle to the phase difference change.

[0013] Preferably, when the NDRE value is in the range of 0.35 - 0.42, the hierarchical fertilization strategy is triggered: First-level fertilization correction: Execute 80% of the baseline fertilization amount; Second-level fertilization correction: Dynamically adjust by superimposing the detection results of leaf stomatal aperture; Tertiary fertilization correction: Combine with soil pH value to compensate for acid-base balance.

[0014] Preferably, the hierarchical fertilization strategy is specifically as follows: The calculation formula for the benchmark fertilization amount is: Benchmark fertilization amount = (fertilizer requirement for target yield - soil fertilizer supply) / fertilizer utilization rate; Primary fertilization correction: Execute 80% of the benchmark fertilization amount; Secondary fertilization correction: Dynamically adjust by superimposing the detection results of leaf stomatal aperture. The leaf stomatal aperture is measured by an infrared thermal imager. When the leaf stomatal aperture is less than 150 mmol, increase the application of nitrate nitrogen fertilizer by 15%. When the leaf stomatal aperture is between 150 - 350 mmol, maintain the current amount at ±0%. When the leaf stomatal aperture is greater than 350 mmol, reduce the application of ammonium nitrogen fertilizer by 10%; Tertiary fertilization correction: When the soil pH is lower than 6.0, for every 0.5 pH unit decrease, increase the application of calcium magnesium phosphate fertilizer by 3 kg / mu. When the soil pH is higher than 7.5, for every 0.5 pH unit increase, increase the application of sulfur powder by 1.5 kg / mu.

[0015] The beneficial effects of the present invention include: The water and fertilizer management control method based on image data processing provided by the present invention collects visible light images, multispectral images, and thermal infrared images of crops and performs feature extraction, calculates the plant morphological parameters, vegetation indices, and vegetation canopy temperature distribution of crops, creates a three-dimensional physiological feature matrix, creates an image segmentation network model, inputs the visible light images, multispectral images, thermal infrared images, and three-dimensional physiological feature matrix into the image segmentation network model to segment plant organs, quantifies organ-level phenotypic parameters, establishes a water and fertilizer decision-making model based on reinforcement learning, uses the real-time data of the three-dimensional physiological feature matrix, organ-level phenotypic parameters, and soil specified parameters as state inputs, uses the water and fertilizer ratio scheme as the action space, and implements the water and fertilizer management scheme through dynamic optimization control strategies. It solves the technical problems of insufficient integration of single-sensor data, limited phenotypic analysis accuracy, and adaptability defects of the decision-making model existing in traditional water and fertilizer regulation schemes.

[0016] First, calculate the plant morphological parameters of crops through visible light image features, calculate the vegetation indices of crops through multispectral image features, obtain the vegetation canopy temperature distribution through thermal infrared image features, create a three-dimensional physiological feature matrix of crops, break through the information density limitation of traditional two-dimensional data, and realize the synchronous analysis of multi-scale physiological states of canopy-organ-cell.

[0017] Secondly, through the Q-learning reinforcement learning algorithm, the composite reward function of biomass increment and water use efficiency is used to drive policy optimization. Compared with the traditional PID control model, the response time of the water and fertilizer scheme adjustment is greatly shortened, and the resource waste rate is significantly reduced at the same time.

[0018] Finally, through the NDRE threshold to trigger the three-level joint control mechanism, the first-level correction avoids the risk of excessive fertilization; the second-level correction, the stomatal aperture is linked to the adjustment of nitrogen form to improve stress adaptability; the pH compensation of the third-level correction maintains the stability of the rhizosphere microenvironment, forming a full-chain optimization system of "macro-control - meso-compensation - micro-response". Brief Description of the Drawings

[0019] Figure 1 It is a schematic flow chart of the water and fertilizer management control method based on image data processing of the present invention.

[0020] Figure 2 It is a schematic flow chart of the image segmentation network model of the present invention for segmenting plant organs and quantifying organ-level phenotypic parameters. Detailed Description of the Invention

[0021] The following is a further detailed description of the present invention in conjunction with the attached Figures 1 - 2 drawings: Example 1 Refer to the attached Figure 1 As shown, a water and fertilizer management control method based on image data processing includes the following steps: S1: The visible light image, multispectral image and thermal infrared image of the corn crop are collected through the image acquisition module, and the features of the visible light image, multispectral image and thermal infrared image are extracted respectively to obtain the visible light image features, multispectral image features and thermal infrared image features. The visible light image, multispectral image and thermal infrared image are collected by a drone equipped with visible light, multi-light including 710nm, 840nm, 660nm bands and a thermal infrared camera. The images are collected along a preset route with a 70% overlap rate to ensure the integrity of the canopy coverage. The visible light image is collected through the 400 - 700nm band, with a resolution greater than 20 million pixels, capturing the details of the plant morphology. The multispectral image covers the 710nm red edge, 840nm near infrared and 660nm red light bands, quantifying chlorophyll fluorescence and photosynthetic activity. The thermal infrared image based on the 8 - 14μm wavelength range has a spatial resolution less than or equal to 0.1°C, detecting abnormal transpiration areas in the canopy.

[0022] S2: Calculate the plant morphological parameters of the corn crop through the visible light image features, calculate the vegetation index of the corn crop through the multispectral image features, and obtain the vegetation canopy temperature distribution by providing the thermal infrared image features; S3: Create a three-dimensional physiological feature matrix of maize crops based on the plant morphological parameters, vegetation indices, and canopy temperature distribution; S4: Create an image segmentation network model, input the visible light image, multispectral image, thermal infrared image, and three-dimensional physiological feature matrix into the image segmentation network model to segment plant organs, and quantify organ-level phenotypic parameters; S5: Establish a water and fertilizer decision-making model based on reinforcement learning. Use the real-time data of the three-dimensional physiological feature matrix, organ-level phenotypic parameters, and soil specified parameters as state inputs, use the water and fertilizer ratio scheme as the action space, and dynamically optimize the control strategy through the Q-learning algorithm; S6: Implement the water and fertilizer management plan based on the optimized control strategy.

[0023] In this embodiment, the visible light image of the maize crop in step S1 is collected by a visible light image acquisition module, the multispectral image is collected by a multispectral image acquisition module, and the thermal infrared image is collected by a thermal infrared image acquisition module.

[0024] The specific process of extracting features from the visible light image, multispectral image, and thermal infrared image in step S1 to obtain visible light image features, multispectral image features, and thermal infrared image features is as follows: S11: Standardize the visible light image, extract the plant leaf edge features and leaf skeleton features in the visible light image through an edge detection algorithm, generate a three-dimensional point cloud model by combining multi-view visible light images, and obtain leaf inclination angle and canopy openness features, fruit / stem features. The canopy openness feature measures the canopy porosity.

[0025] In the process of extracting the plant leaf edge features and leaf skeleton features in the visible light image through the edge detection algorithm, use σ A 5×5 Gaussian kernel with =1.5 to smooth the image and suppress noise interference. Calculate the gradient magnitude in the specified direction, retain the local maximum pixels in the gradient direction, refine the edge to a single-pixel width, set high and low thresholds, connect strong edges and eliminate weak responses. First, initialize the clustering space, select the center point in the image grid, adjust it to the position with the minimum gradient in the 3×3 neighborhood, then combine color similarity and spatial proximity, iteratively update the clustering within the specified search window, and finally perform forced connectivity processing to merge fragmented superpixels.

[0026] In the process of generating the three-dimensional point cloud model, match the superpixel feature points through the structure from motion algorithm to generate a dense point cloud, calculate the leaf inclination angle by fitting the included angle between the normal vector of the point cloud and the vertical axis, calculate the canopy porosity based on the voxelized model by statistically analyzing the light penetration rate, and canopy porosity = penetrated voxels / total canopy voxels × 100%.

[0027] S12: Use the calibration model to correct the multi-spectral image, eliminate the geometric distortion caused by the viewing angle difference, ensure pixel-level spatial consistency, use the improved RANSAC algorithm to align the visible light and multi-spectral images to ensure pixel-level spatial consistency, extract features from the 710nm red-edge image and 840nm near-infrared light image, calculate the vegetation index features, and combine with the 660nm red light image to obtain the normalized vegetation index features.

[0028] Extract scale-invariant feature points from the 710nm red-edge band image or 840nm near-infrared light image or 660nm red light image in the visible light and multi-spectral images, accelerate the nearest neighbor matching through KD-Tree, eliminate obvious outliers, dynamically adjust the inlier threshold, fit the affine transformation matrix for iterative optimization, and terminate the iteration when the root mean square error is less than 0.5 pixels. Resample the multi-spectral image to the visible light image coordinate system, maintain the integrity of the spectral information, and verify the registration accuracy through the maximization of mutual information (MI) to ensure the consistency of NDVI calculation.

[0029] S13: Convert the gray value to the absolute temperature through blackbody radiation correction, apply adaptive threshold segmentation to extract the vegetation area, obtain the temperature heat map and the standard deviation feature of the canopy temperature.

[0030] Use a blackbody reference source with a known temperature to establish a gray-temperature linear relationship. The specific formula is: T = a × DN + b , where T is the output absolute temperature value, in units of °C or K, obtained by reverse derivation through the blackbody radiation model; DN is the original gray value of the sensor, directly output by the thermal infrared camera without temperature conversion; a is the temperature conversion coefficient, the linear proportionality factor, which determines DN the temperature change when b increases by 1 unit, calibrated by two blackbody reference sources with known temperatures;

[0031] Example 2 On the basis of Example 1, in step S2, calculate the plant morphological parameters of the corn crop through the visible light image features, calculate the vegetation index of the corn crop through the multi-spectral image features, and provide the specific process of obtaining the vegetation canopy temperature distribution from the thermal infrared image features as follows: S21: Calculate the leaf area index, leaf length, leaf width, perimeter, shape factor, petiole length, leaf inclination angle, and canopy openness based on the leaf inclination angle, canopy openness characteristics, plant leaf edge characteristics, and leaf skeleton characteristics, and obtain the fruit size and color based on the fruit / stem characteristics; S22: Calculate the vegetation index NDRE based on the vegetation index characteristics. The calculation formula for the vegetation index NDRE is as follows: NDRE = ( ρ 840 - ρ 710) / ( ρ 840 + ρ 710); Where, ρ 840 is the reflectance of the 840 nm near-infrared band, ρ 710 is the reflectance of the 710 nm red-edge band; S23: Calculate the normalized difference vegetation index NDVI based on the normalized difference vegetation index characteristics. The calculation formula for the normalized difference vegetation index NDVI is as follows: NDVI = ( ρ 840 - ρ 660) / ( ρ 840 + ρ 660); Where, ρ 840 is the reflectance of the 840 nm near-infrared band, ρ 660 is the reflectance of the 660 nm red-light band.

[0032] In this embodiment, the angle between the leaf normal vector and the vertical axis is calculated by fitting the three-dimensional point cloud model of the leaf, and the least squares plane fitting is used to calculate the leaf inclination angle. The superpixel feature points are matched by the structure from motion algorithm to generate a dense point cloud, and the angle between the fitted point cloud normal vector and the vertical axis is calculated for the leaf inclination angle. The light penetration rate is statistically calculated based on the voxelized model to calculate the canopy porosity. Canopy porosity = penetrated voxels / total canopy voxels × 100%. Detect the leaf contour, calculate the leaf perimeter by chain code encoding, obtain the shape factor by the convex hull algorithm, extract the leaf vein skeleton by the medial axis transform, determine the petiole length by branch point detection, and combine the leaf inclination angle distribution and canopy porosity to calculate through the porosity inversion model. LAI = -ln(porosity / extinction coefficient).

[0033] Extract the fruit color by quantifying the fruit hue (H channel) and saturation (S channel) in the HSV space, and calculate the fruit volume by the three-dimensional point cloud convex hull algorithm. Align the 710 nm red-edge band and the 840 nm near-infrared band to the same coordinate system, eliminate the interference of cloud shadows and soil background, calculate the average value of effective pixels, based on NDRE = ( ρ 840 - ρ 710) / ( ρ 840 +ρ 710) Obtain the vegetation index NDRE. The 660nm band needs to be compensated for atmospheric scattering. Based on NDVI = ( ρ 840 - ρ 660) / ( ρ 840 + ρ 660), obtain the normalized difference vegetation index NDVI.

[0034] Example 3 Based on Example 1 or Example 2, refer to Figure 2 , in step S4, create an image segmentation network model, and input the visible light image, multispectral image, thermal infrared image, and three-dimensional physiological feature matrix into the image segmentation network model to segment plant organs, and the specific process of quantifying organ-level phenotypic parameters is as follows: S41: Establish the visible light image, multispectral image, and thermal infrared image in a unified spatial coordinate system, and perform registration based on the spatial coordinate system; S42: Resample the three-dimensional physiological feature matrix to the two-dimensional image resolution through bilinear interpolation, establish a voxel-pixel mapping relationship, and retain the spatial topological relationship; S43: The image segmentation network model is set with 12 input channels, where three channels input the visible light image, and three channels input the reflectance of the 840nm near-infrared band, 710nm red-edge band, and 660nm red-light band of the multispectral image, and the remaining channels input the eigenvalues of the three-dimensional physiological feature matrix; S44: The backbone network module of the image segmentation network model uses a ConvNeXt-Tiny encoder, embeds a dilated spatial pyramid pooling module to expand the receptive field to 128×128 pixels, introduces an efficient channel attention module in the decoder to optimize the feature weights, mark the candidate regions, and output the overall plant region; S45: The secondary network module of the image segmentation network model performs fine segmentation of plant organs at the organ level on the candidate regions, and realizes pixel-level segmentation of leaves, stems, and fruits through a lightweight U-Net++ structure; S46: Quantify the leaf area, leaf serration, and leaf curvature based on the Fourier descriptors of the segmentation mask contour, quantify the stem height, curvature, and diameter based on three-dimensional skeletonization processing and thermal infrared temperature gradient mapping, and quantify the fruit volume and surface patches based on the three-dimensional point cloud convex hull algorithm and multispectral abnormal reflection analysis.

[0035] Analyze the contour based on Fourier descriptors, calculate the area based on pixel statistics, calculate the serration degree based on the variance of curvature, calculate the curvature based on Fourier coefficients, extract the centerline by three-dimensional skeletonization, combine the thermal infrared temperature gradient to map the stem diameter and curvature, calculate the volume by the convex hull algorithm, and identify the surface patches by multi-spectral abnormal reflection. Through multi-modal data fusion and hierarchical segmentation, the above process realizes the accurate phenotypic analysis from the canopy to the organ level.

[0036] Example 4 Based on Example 1 or Example 2 or Example 3, the specific process of step S5 is as follows: S51: Establish the state space of the water and fertilizer decision model. The state space includes a three-dimensional physiological feature matrix, organ-level phenotypic parameters, and soil specified parameters. The soil specified parameters are collected in real time by a soil moisture sensor. The soil specified parameters include 8-dimensional data of pH value, organic matter content, nutrient content, heavy metal content, microbial biomass, enzyme activity, humidity, and conductivity, and are denoised by Kalman filtering. S52: Create the action space of the water and fertilizer decision model. The action space includes an action ID, a water and fertilizer plan, and the corresponding water and nitrogen, phosphorus, and potassium ratios of the water and fertilizer plan. The action ID includes 0, 1, 2; 0, 1, 2 correspond to the baseline plan, the high-nitrogen plan, and the water-saving plan, respectively. S53: Create the reward function of the water and fertilizer decision model. The formula of the reward function is: R = α (△BI - BI target ) + β (WUE - WUE baseline ); where R is the reward function value; α and β are the weight coefficients related to corn crops, balancing the optimization priorities of biomass growth and resource efficiency. In the early growth stage: α > β (focusing on biomass accumulation), in the mature stage: β > α (focusing on resource efficiency); △BI is the biomass increment, reflecting the growth rate of plant biomass per unit time, and the calculation method is: dynamically estimated through the three-dimensional reconstruction data of the leaf area index (LAI) and the stem volume; BI target is the target biomass threshold, which is the expected biomass growth value preset according to the growth stage of corn crops and is corrected in real time by the sliding window algorithm based on environmental factors (such as accumulated temperature, sunshine hours); WUE is the water use efficiency, usually defined as the ratio of the corn crop yield to the irrigation water volume (kg / m³), and maximizes the biomass output per unit water volume by adjusting the irrigation strategy. WUE baselineis the reference water use efficiency, representing the historical average or industry standard level, serving as the reference benchmark for reward calculation, and reflecting the improvement amplitude of the current strategy relative to the conventional plan; S54: The reward function drives strategy optimization through the following mechanism. When the actual biomass increment (△BI) exceeds the preset target BI target at that time, α item generates a positive reward, β item ensures that the water use efficiency is not lower than the baseline level, avoiding resource waste caused by over-irrigation. The α / β ratio adjustment realizes the dynamic balance between increasing production and saving water, meeting the sustainable development needs of agricultural production.

[0037] During the image acquisition process, the image acquisition module performs polarized light filtering and polarization angle adjustment. The polarization angle adjustment formula is as follows: θ =arctan( n 2 / n 1) + k ·Δ φ ; Where, θ is the polarization angle adjustment amount, n 1, n 2 are the refractive indices of the media, and Δ φ is the leaf surface curvature compensation amount, k is the proportionality coefficient, used to describe the sensitivity of the polarization angle to the phase difference change.

[0038] During the polarization angle adjustment process, it is necessary to first calculate the basic polarization angle. According to the refractive index of the incident medium n 1 and the refractive index of the transmitted medium n 2, calculate the basic polarization angle θ 0, θ 0=arctan( n 2 / n 1).

[0039] Then, obtain the leaf surface curvature radius through laser scanning or structured light three-dimensional reconstruction. The compensation amount is defined by the following formula: Δ φ = d / R , d is the empirical coefficient, related to the optical properties of the material, R is the leaf surface curvature radius. If the surface curvature changes in real time, such as the movement of the leaf, it is necessary to feedback the R value through the optoelectronic sensor and update the compensation amount.

[0040] The comprehensive polarization angle adjustment formula is θ =arctan( n 2 / n 1) + k ·Δ φ, rotate the analyzer to the target angle θ by a stepper motor, with a positioning accuracy of ±0.1°. The polarizer is fixed at the light source end to generate linearly polarized light, and the analyzer is dynamically adjusted to the θ direction to suppress interference in a specific polarization direction. For different wavelength bands, such as visible light and near-infrared, it is necessary to synchronously adjust the material of the polarizer, such as quartz or polymer polarizer, to match the transmittance characteristics. This process realizes adaptive polarization light control in complex surface scenarios through refractive index matching and dynamic curvature compensation.

[0041] A water and fertilizer management control method based on image data processing of the present invention further includes the following process. When the NDRE value is in the range of 0.35 - 0.42, a hierarchical fertilization strategy is triggered: First-level fertilization correction: Execute 80% of the benchmark fertilization amount; Second-level fertilization correction: Dynamically adjust by superimposing the detection result of leaf stomatal aperture; Third-level fertilization correction: Perform acid-base balance compensation in combination with the soil pH value.

[0042] The hierarchical fertilization strategy is specifically as follows: The calculation formula for the benchmark fertilization amount is: Benchmark fertilization amount = (fertilizer requirement for target yield - soil fertilizer supply) / fertilizer utilization rate; First-level fertilization correction: Execute 80% of the benchmark fertilization amount; Second-level fertilization correction: Dynamically adjust by superimposing the detection result of leaf stomatal aperture. The leaf stomatal aperture is measured by an infrared thermal imager. When the leaf stomatal aperture is less than 150 mmol, increase the application of nitrate nitrogen fertilizer by 15%. When the leaf stomatal aperture is between 150 - 350 mmol, maintain the current amount at ±0%. When the leaf stomatal aperture is greater than 350 mmol, reduce the application of ammonium nitrogen fertilizer by 10%; Third-level fertilization correction: When the soil pH is lower than 6.0, for every 0.5 pH unit lower, increase the application of calcium magnesium phosphate fertilizer by 3 kg / mu. When the soil pH is higher than 7.5, for every 0.5 pH unit higher, increase the application of sulfur powder by 1.5 kg / mu.

[0043] In summary, the water and fertilizer management control method based on image data processing provided by the present invention collects visible light images, multispectral images, and thermal infrared images of corn crops and performs feature extraction, calculates the plant morphological parameters, vegetation indices, and vegetation canopy temperature distribution of corn crops, creates a three-dimensional physiological feature matrix, creates an image segmentation network model, inputs the visible light images, multispectral images, thermal infrared images, and three-dimensional physiological feature matrix into the image segmentation network model to segment plant organs, quantifies organ-level phenotypic parameters, establishes a water and fertilizer decision-making model based on reinforcement learning, uses the real-time data of the three-dimensional physiological feature matrix, organ-level phenotypic parameters, and specified soil parameters as state inputs, uses the water and fertilizer ratio scheme as the action space, and implements the water and fertilizer management scheme through dynamic optimization control strategies. It solves the technical problems of insufficient integration of single-sensor data, limited phenotypic analysis accuracy, and adaptive defects of decision-making models existing in traditional water and fertilizer regulation schemes.

[0044] The present invention calculates the plant morphological parameters of corn crops through visible light image features, calculates the vegetation indices of corn crops through multispectral image features, obtains the vegetation canopy temperature distribution by providing thermal infrared image features, creates a three-dimensional physiological feature matrix of corn crops, breaks through the information density limitation of traditional two-dimensional data, and realizes the synchronous analysis of multi-scale physiological states of canopy-organ-cell. Through the Q-learning reinforcement learning algorithm, the policy optimization is driven by a composite reward function of biomass increment and water use efficiency. Compared with the traditional PID control model, the response time of water and fertilizer scheme adjustment is greatly shortened, and the resource waste rate is significantly reduced at the same time. Through the NDRE threshold trigger three-level linkage mechanism, the first-level correction avoids the risk of excessive fertilization; the second-level correction, the stomatal aperture is linked with the adjustment of nitrogen form to improve stress adaptability; the pH compensation of the third-level correction maintains the stability of the rhizosphere microenvironment, forming a full-chain optimization system of "macro-control-mesoscopic compensation-microscopic response".

Claims

1. A water and fertilizer management control method based on image data processing, characterized in that, Including the following steps: S1: Collect the visible light image, multispectral image, and thermal infrared image of the crop through the image acquisition module, extract features from the visible light image, multispectral image, and thermal infrared image respectively, and obtain the visible light image features, multispectral image features, and thermal infrared image features; S2: Calculate the plant morphological parameters of the crop through the visible light image features, calculate the vegetation index through the multispectral image features, and obtain the vegetation canopy temperature distribution by providing the thermal infrared image features; S3: Create a three-dimensional physiological feature matrix of the crop based on the plant morphological parameters, vegetation index, and canopy temperature distribution; S4: Create an image segmentation network model, input the visible light image, multispectral image, thermal infrared image, and three-dimensional physiological feature matrix into the image segmentation network model to segment the plant organs, and quantify the organ-level phenotypic parameters; S5: Establish a water and fertilizer decision-making model based on reinforcement learning, use the real-time data of the three-dimensional physiological feature matrix, organ-level phenotypic parameters, and soil specified parameters as the state input, use the water and fertilizer ratio scheme as the action space, and dynamically optimize the control strategy through the Q-learning algorithm; S6: Implement the water and fertilizer management plan based on the optimized control strategy.

2. The water and fertilizer management control method based on image data processing according to claim 1, wherein In step S1, the visible light image of the crop is collected through the visible light image acquisition module, the multispectral image is collected through the multispectral image acquisition module, and the thermal infrared image is collected through the thermal infrared image acquisition module.

3. The water and fertilizer management control method based on image data processing according to claim 2, characterized in that, The specific process of extracting features from the visible light image, multispectral image, and thermal infrared image in step S1 to obtain the visible light image features, multispectral image features, and thermal infrared image features is as follows: S11: Standardize the visible light image, extract the plant leaf edge features and leaf skeleton features in the visible light image through the edge detection algorithm, generate a point cloud model by combining multi-view visible light images, and obtain the leaf inclination angle and canopy opening degree features, fruit / stem features; S12: Use the calibration model to calibrate the multispectral image, use the improved RANSAC algorithm to align the visible light and multispectral images, extract features from the 710nm red edge image and 840nm near-infrared light image, calculate the vegetation index features, and obtain the normalized vegetation index features by combining the 660nm red light image; S13: Convert the gray value to the absolute temperature through blackbody radiation correction, apply adaptive threshold segmentation to extract the vegetation area, and obtain the temperature heat map and the canopy temperature standard deviation feature.

4. A water and fertilizer management control method based on image data processing according to claim 1, characterized in that, The specific process of calculating the plant morphological parameters of the crop through the visible light image features, calculating the vegetation index through the multispectral image features, and obtaining the vegetation canopy temperature distribution by providing the thermal infrared image features in step S2 is as follows: S21: Calculate the leaf area index, leaf length, leaf width, perimeter, shape factor, petiole length, leaf inclination angle, and canopy opening degree based on the leaf inclination angle and canopy opening degree features, plant leaf edge features, and leaf skeleton features, and obtain the fruit size and color based on the fruit / stem features; S22: Calculate the vegetation index NDRE based on the vegetation index features; S23: Calculate the Normalized Difference Vegetation Index (NDVI) based on the Normalized Difference Vegetation Index feature.

5. A water and fertilizer management control method based on image data processing according to claim 4, characterized in that, In step S4, an image segmentation network model is created. The process of inputting the visible light image, multispectral image, thermal infrared image, and three-dimensional physiological feature matrix into the image segmentation network model to segment plant organs and quantify organ-level phenotypic parameters is as follows: S41: Establish the visible light image, multispectral image, and thermal infrared image in a unified spatial coordinate system and perform registration based on the spatial coordinate system. S42: Resample the three-dimensional physiological feature matrix to the two-dimensional image resolution through bilinear interpolation to establish a voxel-pixel mapping relationship. S43: The image segmentation network model is set with 12 input channels. Among them, three channels input the visible light image, and three channels input the reflectance of the 840nm near-infrared band, 710nm red-edge band, and 660nm red-light band of the multispectral image. The remaining channels input the eigenvalues of the three-dimensional physiological feature matrix. S44: The backbone network module of the image segmentation network model adopts a specified encoder, embeds a dilated spatial pyramid pooling module to expand the receptive field to the specified pixels, introduces an efficient channel attention module in the decoder to mark candidate regions, and outputs the overall plant region. S45: The secondary network module of the image segmentation network model performs plant organ-level segmentation on the candidate regions. S46: Quantify the leaf area, leaf serration, and leaf curvature based on the Fourier descriptors of the segmentation mask contour. Quantify the stem height, curvature, and diameter based on three-dimensional skeletonization processing and thermal infrared temperature gradient mapping. Quantify the fruit volume and surface patches based on the three-dimensional point cloud convex hull algorithm and multispectral abnormal reflection analysis.

6. The water and fertilizer management control method based on image data processing according to claim 5, characterized in that The specific process of step S5 is as follows: S51: Establish the state space of the water and fertilizer decision-making model. The state space includes the three-dimensional physiological feature matrix, organ-level phenotypic parameters, and specified soil parameters. The specified soil parameters are collected in real time by a soil moisture sensor. The specified soil parameters include 8-dimensional data of pH value, organic matter content, nutrient content, heavy metal content, microbial biomass, enzyme activity, humidity, and conductivity, and are denoised by Kalman filtering. S52: Create the action space of the water and fertilizer decision-making model. The action space includes action ID, water and fertilizer plan, and the corresponding water and nitrogen, phosphorus, and potassium ratios of the water and fertilizer plan. The action ID includes 0, 1, 2; 0, 1, 2 correspond to the benchmark plan, high-nitrogen plan, and water-saving plan respectively. S53: Create the reward function of the water and fertilizer decision-making model. The formula of the reward function is: R= α ( △ BI - BI target ) + β (WUE - WUE baseline ); Among them, R is the reward function value; α and β are crop-related weight coefficients that balance the optimization priorities of biomass growth and resource efficiency; △BI is the biomass increment, which reflects the growth rate of plant biomass per unit time and is calculated as follows: dynamically estimated through the three-dimensional reconstruction data of leaf area index and stem volume; BI target is the target biomass threshold, which is the expected biomass growth value preset according to the crop growth stage and is corrected in real time based on environmental factors through a sliding window algorithm; WUE is the water use efficiency, which is defined as the ratio of crop yield to irrigation water volume, and maximizes the biomass output per unit water volume by adjusting the irrigation strategy. WUE baseline is the baseline water use efficiency, representing the historical average or industry standard level, serving as the reference benchmark for reward calculation, and reflecting the improvement amplitude of the current strategy relative to the conventional plan; S54: The reward function drives policy optimization through the following mechanism. When the actual biomass increment (△BI) exceeds the preset target BI target at this time, α a positive reward is generated for the item, β the item ensures that the water use efficiency is not lower than the baseline level, avoiding resource waste caused by over-irrigation. The α / β ratio adjustment realizes the dynamic balance between increasing production and saving water, meeting the sustainable development needs of agricultural production.

7. A water and fertilizer management control method based on image data processing according to claim 1, characterized in that During the image acquisition process by the image acquisition module, polarization light filtering and polarization angle adjustment are performed. The polarization angle adjustment formula is as follows: θ = arctan( n 2 / n 1) + k ·Δ φ ; Among them, θ is the polarization angle adjustment amount, n 1, n 2 is the refractive index of the medium, Δ φ is the curvature compensation amount of the blade surface, k is the proportionality coefficient, which is used to describe the sensitivity of the polarization angle to the phase difference change.

8. A method for controlling water and fertilizer management based on image data processing according to claim 6, characterized in that When the NDRE value is in the range of 0.35 - 0.42, trigger the hierarchical fertilization strategy: First-level fertilization correction: Execute at 80% of the benchmark fertilization amount. Second-level fertilization correction: Dynamically adjust by superimposing the detection results of leaf stomatal aperture. Third-level fertilization correction: Perform acid-base balance compensation in combination with the soil pH value.

9. The water and fertilizer management control method based on image data processing according to claim 8, characterized in that, The specific hierarchical fertilization strategy is as follows: The calculation formula of the benchmark fertilization amount is: Base fertilization rate = (fertilizer requirement for target yield - soil fertilizer supply) / fertilizer utilization rate; Primary fertilization correction: Implement 80% of the base fertilization rate; Secondary fertilization correction: Dynamically adjust by superimposing the detection results of leaf stomatal aperture. The leaf stomatal aperture is measured by an infrared thermal imager. When the leaf stomatal aperture is less than 150 mmol, increase the application of nitrate nitrogen fertilizer by 15%. When the leaf stomatal aperture is between 150 - 350 mmol, maintain the current amount at ±0%. When the leaf stomatal aperture is greater than 350 mmol, reduce the application of ammonium nitrogen fertilizer by 10%; Tertiary fertilization correction: When the soil pH is lower than 6.0, for every 0.5 pH unit decrease, increase the application of calcium magnesium phosphate fertilizer by 3 kg / mu. When the soil pH is higher than 7.5, for every 0.5 pH unit increase, increase the application of sulfur powder by 1.5 kg / mu.

Images