Agricultural greenhouse spatial distribution information extraction method, system, equipment and medium

Abstract

The invention relates to an agricultural greenhouse spatial distribution information extraction method, system and device and a medium, and belongs to the technical field of agricultural remote sensing image monitoring, and the extraction method comprises the steps: receiving spaceflight hyperspectral remote sensing image data, and carrying out the preprocessing of the data, and obtaining the surface reflectance data; extracting a spectrum subset of the first wave band interval, performing secondary fitting to obtain a reflectivity fitting coefficient, determining an area of which the spectral response accords with the first absorption characteristic, and generating a first mask; extracting a spectrum subset of the second wave band interval, calculating a reflectivity difference value of the two ends and carrying out threshold value comparison to generate a second mask; extracting a spectrum subset of the third wave band interval, performing cubic fitting calculation to obtain a reflectivity fitting coefficient, determining an area of which the spectral response accords with the second absorption characteristic, and generating a third mask; and performing logic fusion according to the first mask, the second mask and the third mask to obtain an extraction result of agricultural greenhouse spatial distribution information. The spatial distribution information of the agricultural greenhouse can be efficiently and accurately extracted.

Description

Technical Field

[0001] The present application relates to the technical field of agricultural remote sensing image monitoring, and in particular to a method, system, equipment and medium for extracting spatial distribution information of agricultural greenhouses. Background Art

[0002] With the rapid development of agricultural modernization, the management and monitoring of agricultural resources have become increasingly important. Especially in the fields of farmland management, environmental protection, precision agriculture, etc., it has become a core demand to quickly and accurately obtain the spatial distribution information of agricultural facilities. As an important part of modern agriculture, the accurate extraction of spatial distribution information of agricultural greenhouses is of great significance to the optimal utilization of land resources, agricultural planning and management, disaster assessment, etc.

[0003] Remote sensing technology, especially optical remote sensing technology, has been widely used in agricultural monitoring. However, the resolution of traditional remote sensing image data is relatively low, and the band range is relatively single. Existing remote sensing technology generally uses remote sensing data based on fewer bands for analysis, which makes the accuracy and timeliness of spatial distribution information extraction of agricultural greenhouses poor, and cannot fully utilize the rich spectral information in spectral remote sensing data.

[0004] In recent years, with the advancement of hyperspectral remote sensing technology, hyperspectral images provide higher spectral resolution and can cover a wider range of bands, making it possible to distinguish the spectral characteristics of different ground objects in more detail. However, although hyperspectral remote sensing technology has obvious advantages in theory, in practical applications, due to the high processing complexity of hyperspectral images and the huge amount of data, how to efficiently and accurately extract the spatial distribution information of agricultural greenhouses is still a problem that needs to be solved. Summary of the invention

[0005] In order to efficiently and accurately extract the spatial distribution information of agricultural greenhouses, the present application provides a method, system, equipment and medium for extracting the spatial distribution information of agricultural greenhouses.

[0006] In the first aspect, the present application provides a method for extracting spatial distribution information of agricultural greenhouses, which adopts the following technical solution: A method for extracting spatial distribution information of agricultural greenhouses, the extraction method comprising: Receive real-time aerospace hyperspectral remote sensing image data and pre-process it to obtain surface reflectance data; Extracting a spectral subset of a first band interval from the surface reflectance data, performing quadratic fitting to obtain a reflectance fitting coefficient, combining logical judgment to determine an area where the spectral response meets the first absorption feature, and generating a first mask; Extracting a spectral subset of a second band interval from the surface reflectance data, calculating a reflectance difference between two ends of the second band interval and performing a threshold comparison to generate a second mask; Extracting a spectral subset of a third band interval from the surface reflectance data, performing three fitting calculations to obtain a reflectance fitting coefficient, combining logical judgment to determine an area where the spectral response meets the second absorption feature, and generating a third mask; The first mask, the second mask and the third mask are logically fused to obtain the extraction result of the spatial distribution information of the agricultural greenhouse.

[0007] By adopting the above technical solutions, comprehensively applying multi-band hyperspectral remote sensing data, and combining quadratic and cubic fitting algorithms, the accuracy and efficiency of extracting spatial distribution information of agricultural greenhouses are effectively improved. Through logical judgment combined with the reflectance fitting model, the accurate capture of different band characteristics is ensured, minimizing misjudgment and redundant processing. Finally, through mask fusion technology, multiple mask information is integrated to obtain a more accurate and comprehensive spatial distribution map of agricultural greenhouses, realizing efficient and accurate extraction of spatial distribution information of agricultural greenhouses, which is especially suitable for large-scale agricultural monitoring and real-time data processing, and provides strong support for agricultural resource management, disaster assessment and monitoring and other fields.

[0008] Optionally, extracting a spectral subset of the first band interval from the surface reflectance data, performing quadratic fitting to obtain a reflectance fitting coefficient, and combining logical judgment to determine an area where the spectral response meets the first absorption feature, the step of generating a first mask includes: Extracting a spectral subset of pixels in a first band interval from the surface reflectance data to obtain a wavelength sequence and a reflectance sequence; Constructing a quadratic fitting coefficient matrix according to the wavelength sequence and the reflectivity sequence, calculating the reflectivity fitting coefficients by the least squares method, and obtaining the quadratic fitting coefficients; Performing logical judgment based on the quadratic fitting coefficient to obtain a first logical judgment result; A region whose spectral response conforms to a first absorption characteristic is determined according to the first logical judgment result, and a first mask is generated.

[0009] By adopting the above technical solution, the spectral features of a specific band are extracted from the aerospace hyperspectral remote sensing image data, and a mathematical model between wavelength and reflectivity is established through quadratic fitting, and the position of the first absorption feature is accurately determined by combining logical judgment. This technical solution not only improves the accuracy of absorption feature extraction, but also reduces noise and misjudgment through mask generation and logical judgment, and can provide reliable remote sensing data support for applications such as greenhouse spatial distribution and crop health monitoring.

[0010] Optionally, the step of extracting a spectral subset of a second band interval from the surface reflectance data, calculating a reflectance difference between two ends of the second band interval and performing a threshold comparison to generate a second mask includes: Extracting a spectral subset of a second wavelength band from the surface reflectance data; Calculating the reflectivity difference between the two ends of the second waveband interval; The reflectivity difference is compared with a preset threshold, and a second mask is generated according to the position of the area where the reflectivity difference is greater than the preset threshold.

[0011] By adopting the above technical solution, the second mask identifies the areas with significant reflectance changes, which can effectively reflect the changes in surface features, especially the spectral response of plants, provide clear regional calibration for subsequent image processing and spatial analysis, and improve the accuracy of feature extraction and analysis.

[0012] Optionally, extracting a spectral subset of a third band interval from the surface reflectance data, performing three fitting calculations to obtain reflectance fitting coefficients, and combining logical judgment to determine an area where the spectral response meets the second absorption feature, the step of generating a third mask includes: Extracting a spectral subset of pixels in a third band from the surface reflectance data to obtain a wavelength sequence and a reflectance sequence; Constructing a cubic fitting coefficient matrix according to the wavelength sequence and the reflectivity sequence, calculating the reflectivity fitting coefficients, and obtaining the cubic fitting coefficients; Performing logical judgment based on the cubic fitting coefficients to obtain a second logical judgment result; The region whose spectral response conforms to the second absorption characteristic is determined according to the second logic judgment result, and a third mask is generated.

[0013] By adopting the above technical solution, spectral data in the 1700-1745 nanometer band are extracted from the hyperspectral remote sensing image, and the relationship between reflectivity and wavelength is accurately fitted using the cubic fitting model, and the areas whose spectral response meets the 1730 nanometer absorption characteristics are screened out through complex logical judgment. These areas that meet the characteristics are marked by the third mask, providing clear data support for subsequent spatial analysis and feature extraction.

[0014] Optionally, the spectral range of the aerospace hyperspectral remote sensing image data is 400 nanometers to 2500 nanometers, the spectral resolution is less than 8 nanometers, and the spatial resolution is less than 30 meters.

[0015] Optionally, the first wavelength band range is selected from 2290 nanometers to 2325 nanometers; the second wavelength band range is selected from 680 nanometers to 750 nanometers; and the third wavelength band range is selected from 1700 nanometers to 1745 nanometers.

[0016] Optionally, the first mask, the second mask and the third mask are all logical matrices and are consistent with the spatial dimension of the aerospace hyperspectral remote sensing image data.

[0017] By adopting the above technical solution, it is possible to effectively extract areas that meet specific spectral characteristics on the basis of high precision and high efficiency. The logical matrix form of the mask facilitates subsequent logical fusion operations and ensures the precise correspondence between the mask and the image data, ultimately improving the accuracy and processing speed of extracting spatial distribution information of agricultural greenhouses.

[0018] In the second aspect, the present application provides an agricultural greenhouse spatial distribution information extraction system, which adopts the following technical solution: A system for extracting spatial distribution information of agricultural greenhouses, the extraction system comprising: A data receiving module is used to receive aerospace hyperspectral remote sensing image data collected in real time; A preprocessing module, used for preprocessing the aerospace hyperspectral remote sensing image data to obtain surface reflectance data; A first mask generation module is used to extract a spectral subset of a first band interval from the surface reflectance data, perform quadratic fitting to obtain a reflectance fitting coefficient, determine an area where the spectral response meets the first absorption feature by combining logical judgment, and generate a first mask; A second mask generating module, used for extracting a spectral subset of a second band interval from the surface reflectance data, calculating a reflectance difference between two ends of the second band interval and performing a threshold comparison to generate a second mask; A third mask generation module is used to extract a spectral subset of a third band interval from the surface reflectance data, perform three fitting calculations to obtain a reflectance fitting coefficient, and combine logical judgment to determine an area where the spectral response meets the second absorption feature to generate a third mask; The logic fusion module is used to perform logic fusion according to the first mask, the second mask and the third mask to obtain the extraction result of the spatial distribution information of the agricultural greenhouse.

[0019] In a third aspect, the present application provides a computer device, which adopts the following technical solution: A computer device comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method as described in the first aspect.

[0020] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any one of the methods in the first aspect.

[0021] In summary, the present application includes at least one of the following beneficial technical effects: Through multi-band hyperspectral data analysis, the characteristics of plastic greenhouses can be effectively extracted and identified. By extracting reflectance data of different bands from aerospace hyperspectral remote sensing images and performing quadratic and cubic fitting, and combining logical judgment to generate multiple masks, the absorption and reflection characteristics of the greenhouse can be accurately captured. By logically fusing these masks, the spatial distribution information of agricultural greenhouses can be efficiently and accurately extracted, reducing the impact of natural surfaces and other interferences, and improving the accuracy and efficiency of agricultural greenhouse detection. This technical solution has important practical application value in the fields of precision agriculture, land use monitoring, and environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a first flow chart of a method for extracting spatial distribution information of agricultural greenhouses according to one of the embodiments of the present application.

[0023] Figure 2 It is a second flow chart of the method for extracting spatial distribution information of agricultural greenhouses in one of the embodiments of the present application.

[0024] Figure 3 It is a third flow chart of the method for extracting spatial distribution information of agricultural greenhouses in one of the embodiments of the present application.

[0025] Figure 4 It is the fourth process diagram of the method for extracting spatial distribution information of agricultural greenhouses in one of the embodiments of the present application. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-4 It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0027] At present, the existing low- to medium-resolution remote sensing images pose great challenges to the identification of agricultural greenhouses. Since the materials of agricultural greenhouses (such as transparent or translucent plastic films) often have similar spectral characteristics to the surrounding ground objects (such as bare soil, crops, etc.), it is difficult to effectively distinguish them from other ground objects in the image. In addition, existing remote sensing technologies generally use remote sensing data based on fewer bands for analysis, which makes the accuracy and timeliness of spatial distribution information extraction of agricultural greenhouses poor. Especially in terms of spectral data processing and feature extraction, the shortcomings of traditional methods have led to the inability to fully utilize the rich spectral information in hyperspectral data.

[0028] Based on this, an embodiment of the present application discloses a method for extracting spatial distribution information of agricultural greenhouses.

[0029] Reference Figure 1 , a method for extracting spatial distribution information of agricultural greenhouses, the extraction method comprising: Step S101, receiving aerospace hyperspectral remote sensing image data collected in real time and preprocessing it to obtain surface reflectance data; Among them, aerospace hyperspectral remote sensing images are usually obtained through satellite sensors, covering multiple bands (from 400 nanometers to 2500 nanometers). These image data contain the reflectance spectrum information of surface objects. In practical applications, due to the influence of the atmosphere, sensor characteristics and other environmental factors, the original remote sensing image data often contains noise, radiation errors and atmospheric interference. Therefore, before analyzing remote sensing images, these data need to be preprocessed first.

[0030] Specifically, the preprocessing steps include bad line correction, radiation calibration and atmospheric correction. Bad line correction is to remove bad pixels or bad lines in the image, which may affect subsequent analysis; radiation calibration is to convert the radiation received by the sensor into the reflectance value of the surface, which is crucial to ensure data consistency and accuracy; atmospheric correction is used to remove the influence of the atmosphere on the spectral signal and obtain the true surface reflectance value.

[0031] Step S102, extracting a spectral subset of a first band interval from the surface reflectance data, performing quadratic fitting to obtain a reflectance fitting coefficient, combining logical judgment to determine an area where the spectral response meets the first absorption feature, and generating a first mask; Among them, in the hyperspectral remote sensing data, the reflectivity values ​​in different bands reflect the characteristics of surface objects. Agricultural greenhouse materials (such as plastic films) have obvious absorption characteristics in specific bands (for example, 2310 nanometers). The first absorption feature is the absorption feature of 2310 nanometers.

[0032] In some embodiments, in order to accurately extract these features, a specific band interval (e.g., 2290 nm to 2325 nm) is selected from the surface reflectance data for analysis. The reflectance fitting coefficient helps to identify the absorption characteristics within a specific band range, and the area whose spectral response meets the first absorption characteristic can be determined by a logical judgment formula (such as judging whether the reflectance fitting coefficient meets a specific condition). If the condition is met, it means that the area belongs to an agricultural greenhouse, that is, the area whose spectral response meets the first absorption characteristic is used to locate the agricultural greenhouse area.

[0033] In remote sensing image processing, a mask is a binary image or data matrix that is used to mark or distinguish specific areas or pixels. Each pixel in the mask is usually marked as 1 (indicating that the pixel belongs to the area of ​​interest) or 0 (indicating that the pixel does not belong to the area of ​​interest). In the embodiment of the present application, the pixels marked as 1 in the first mask correspond to the area whose spectral response conforms to the absorption characteristics of 2310 nanometers.

[0034] It can be understood that the position of a specific absorption band is identified through the mathematical model of reflectivity. Due to the absorption characteristics of agricultural greenhouses in a specific band, the reflectivity value of this band will change significantly. The occurrence location of this feature is determined through logical judgment, thereby accurately identifying the agricultural greenhouse, avoiding the situation in which it is difficult to distinguish between agricultural greenhouses and other ground objects in traditional methods, and improving the accuracy of the extraction results.

[0035] Step S103, extracting a spectral subset of a second band interval from the surface reflectance data, calculating a reflectance difference between two ends of the second band interval and performing a threshold comparison to generate a second mask; Among them, the difference in reflectivity between agricultural greenhouses and the surrounding environment can often be more obvious in certain band ranges. For example, the second band range of 680 nanometers to 750 nanometers can be selected. This band range is usually related to the reflectivity characteristics of vegetation and soil. By analyzing the reflectivity of this band, the distinction between greenhouses and other ground objects (such as soil, crops, etc.) can be further improved.

[0036] Specifically, by calculating the difference between the reflectances at both ends of the second band (680 nanometers and 750 nanometers), the change in the reflectance slope can be revealed. Usually, the reflectance of agricultural greenhouses changes more slowly in this band, so the reflectance difference can be used as a feature, and the location of the greenhouse can be determined by presetting an appropriate threshold for comparison. In this embodiment, the second mask is used to identify the location of the reflectance slope feature from 680 nanometers to 750 nanometers, which is mainly used to identify the boundaries of the agricultural greenhouse area, further enhancing the distinction between greenhouses and other crops.

[0037] Step S104, extracting a spectral subset of the third band interval from the surface reflectance data, performing three fitting calculations to obtain reflectance fitting coefficients, combining logical judgment to determine the area where the spectral response meets the second absorption feature, and generating a third mask; In some embodiments, the third wavelength range may be a wavelength range near the 1730 nm wavelength range (eg, 1700 nm to 1745 nm), which is generally associated with the absorption characteristics of agricultural greenhouse materials.

[0038] Specifically, since the spectral response of the agricultural greenhouse shows a more complex nonlinear relationship in this band range, fitting the reflectance data by three-dimensional fitting (using a, b, c, d coefficients) can more accurately reflect the spectral characteristics of the area. Through logical judgment of the fitting results, it is determined whether the spectral response meets the second absorption feature (for example, the peak position is near 1730 nanometers). If it meets, the pixel position is marked as 1 and a third mask is generated. Therefore, in the embodiment of the present application, the pixels marked as 1 in the third mask correspond to the area where the spectral response meets the 1730 nanometer absorption feature, which is used to locate the agricultural greenhouse area.

[0039] It should be noted that the first mask, the second mask and the third mask are all logical matrices, and are consistent with the spatial dimensions of aerospace hyperspectral remote sensing image data, so that they can effectively extract areas that meet specific spectral characteristics on the basis of high precision and high efficiency. The logical matrix form of the mask facilitates subsequent logical fusion operations and ensures the precise correspondence between the mask and the image data, ultimately improving the accuracy and processing speed of extracting spatial distribution information of agricultural greenhouses.

[0040] Step S105, performing logical fusion according to the first mask, the second mask and the third mask to obtain the extraction result of the spatial distribution information of the agricultural greenhouse.

[0041] Among them, the first mask, the second mask and the third mask are logically fused. The first mask identifies the area whose spectral response conforms to the 2310-nanometer absorption characteristic, the second mask identifies the 680-750-nanometer reflectivity slope characteristic, and the third mask identifies the area whose spectral response conforms to the 1730-nanometer absorption characteristic. The multi-mask information is integrated through logical operations (such as A AND (B OR C)) to generate a greenhouse spatial distribution map, and finally the spatial distribution information of the agricultural greenhouse is extracted.

[0042] In one of the embodiments of the present application, the logical fusion of A AND (B OR C) represents "first mask AND (second mask OR third mask)", and by screening the results of the first mask, it is ensured that only those areas that meet the characteristics of plastic greenhouses are retained. At the same time, through the joint verification of the second mask and the third mask, the accuracy and reliability of the classification are improved.

[0043] Specifically, during the screening process, the role of the first mask is to capture the absorption characteristics of plastic greenhouse materials in the short-wave infrared region. Only when the reflectivity response of a pixel meets the requirements at the absorption peak position of 2310 nanometers, it is considered to meet the conditions of the first mask; the second mask eliminates the interference between the natural surface (such as plants) and plastic by analyzing the differences in spectral reflectance in the 680-750 nanometer range, further confirms the area of ​​the plastic greenhouse and reduces misjudgment; the third mask further verifies the existence of the plastic greenhouse, especially eliminating other interference signals with similar absorption characteristics. When the secondary absorption peak at 1730 nanometers is detected, this band characteristic is the absorption signal of the plastic greenhouse material in the mid-infrared region.

[0044] It should be noted that the first mask (2290-2325 nanometers) and the third mask (1700-1745 nanometers) respectively target the absorption characteristics of plastic materials in different infrared sub-regions (short-wave infrared and mid-infrared), and achieve multi-feature cross-validation through the logical operation "A and (B orC)" to reduce single-band misjudgment. For example, the spectral response of bare soil or buildings in this band is usually flat and lacks sharp absorption peaks, while vegetation has high reflectivity in the short-wave infrared region (such as the first mask band), but has no obvious absorption characteristics in the mid-infrared region (the third mask band), thereby reducing the false detection rate.

[0045] It is understandable that through mask fusion, the advantages of data from different bands can be fully utilized to eliminate possible misidentification of a single band, ensuring that the extraction results are more accurate and comprehensive. The results after mask fusion can more accurately identify the distribution area of ​​agricultural greenhouses, providing reliable data support for applications such as agricultural resource management and disaster assessment.

[0046] In the above implementation, the comprehensive application of multi-band hyperspectral remote sensing data, combined with quadratic and cubic fitting algorithms, effectively improves the accuracy and efficiency of the extraction of spatial distribution information of agricultural greenhouses. Through logical judgment combined with the reflectivity fitting model, the accurate capture of different band characteristics is ensured, and misjudgment and redundant processing are minimized. Finally, through mask fusion technology, multiple mask information is integrated to obtain a more accurate and comprehensive spatial distribution map of agricultural greenhouses, realizing efficient and accurate extraction of spatial distribution information of agricultural greenhouses, which is especially suitable for large-scale agricultural monitoring and real-time data processing, and provides strong support for agricultural resource management, disaster assessment and monitoring and other fields.

[0047] In the embodiment of the present application, the spectral range of the aerospace hyperspectral remote sensing image data is 400 nanometers to 2500 nanometers, the spectral resolution is less than 8 nanometers, and the spatial resolution is less than 30 meters.

[0048] The spectral range of 400 nanometers to 2500 nanometers covers the spectrum from visible light to short-wave infrared (SWIR) and even part of the mid-infrared (MIR) region. This spectral range can fully capture the various spectral characteristics of surface materials and is suitable for remote sensing monitoring of various ground objects including greenhouse materials (such as plastics), vegetation, soil, irrigation water, etc.

[0049] Moreover, a spectral resolution of less than 8 nanometers means that the differences between each spectral band can be finely distinguished, and the spectral characteristics of objects can be accurately captured, especially in areas with denser bands. Such a resolution can effectively distinguish the spectral differences of objects at close wavelengths. For example, in the short-wave infrared and mid-infrared regions, the absorption peaks of materials are relatively narrow, and a resolution of 8 nanometers is sufficient to capture these absorption characteristics, thereby improving recognition accuracy. A spatial resolution of less than 30 meters means that the ground area represented by each pixel is small, and smaller ground features can be clearly distinguished. This is very important for the extraction of small-scale spatial targets such as agricultural greenhouses. Agricultural greenhouses usually have a certain area, but in larger remote sensing images, their spatial size is small, so a higher spatial resolution makes it possible to clearly distinguish the boundaries and morphology of the greenhouses.

[0050] Reference Figure 2 As an implementation method of step S102, extracting a spectral subset of the first band interval from the surface reflectance data, performing quadratic fitting to obtain a reflectance fitting coefficient, combining logical judgment to determine an area where the spectral response meets the first absorption feature, and generating a first mask includes: Step S201, extracting a spectral subset of pixels in a first band interval from the surface reflectance data to obtain a wavelength sequence and a reflectance sequence; In aerospace hyperspectral remote sensing images, the data of each pixel is composed of reflectance values ​​of multiple bands. For the spectral characteristics of target areas such as agricultural greenhouses, a specific band interval is usually selected for analysis. The goal of this step is to extract spectral data within the band (e.g., 2300-2325 nanometers) related to the first absorption feature from the hyperspectral data.

[0051] Specifically, by specifying a band interval (such as 2300-2325 nanometers), the reflectance values ​​of the corresponding band are extracted from the spectral data of the overall image. These reflectance values ​​correspond to the wavelength sequence of the band one by one, forming a reflectance sequence Y=[y 1 ,y 2 ,...,y n ] T and wavelength sequence X=[x 1 ,x 2 ,...,x n ] TThe reflectance sequence represents the surface reflectance value at each corresponding wavelength, and the wavelength sequence represents the wavelength value of each band in the band interval.

[0052] Step S202, constructing a quadratic fitting coefficient matrix according to the wavelength sequence and the reflectivity sequence, calculating the reflectivity fitting coefficients by the least square method, and obtaining the quadratic fitting coefficients; Among them, quadratic fitting is a common mathematical modeling method used to describe the relationship between data points. Since the spectral reflectance of agricultural greenhouses usually presents a specific curve shape, quadratic fitting (i.e., a quadratic polynomial) can better fit the trend of reflectance in this band changing with wavelength.

[0053] Specifically, the quadratic fitting method is used to establish a mathematical model between the wavelength sequence X and the reflectivity sequence Y. The quadratic fitting coefficient matrix is: , the shape of matrix A is a (n,3) matrix, where n is the length of the wavelength sequence.

[0054] In the above formula, Represents the element obtained by multiplying the element of wavelength sequence X by its own element by position, where X represents wavelength sequence X itself; 1 n T is a column vector of all ones, representing a constant term.

[0055] Furthermore, the best fitting coefficient is determined by minimizing the sum of squares of the errors between the reflectivity sequence Y and the fitting result through the least squares method. The specific calculation formula is: K=(A T A) -1 A T Y, the solved K contains the three coefficients a, b, c of the quadratic fit, that is, K=[a,b,c] T , these coefficients define a quadratic relationship between wavelength and reflectivity.

[0056] In the above formula, A T is the transpose of the matrix A, (A T A) -1 is the matrix A T The inverse matrix of A, A T Y is the product of the transpose of matrix A and the reflectivity sequence Y.

[0057] It can be understood that through quadratic fitting, the nonlinear relationship between the wavelength sequence and the reflectivity sequence can be accurately captured to obtain more detailed reflectivity characteristics, thereby providing a reliable mathematical model for further judging the absorption characteristics.

[0058] Step S203, performing logic judgment based on the quadratic fitting coefficient to obtain a first logic judgment result; Specifically, the formula for logical judgment is: sgn(-b / (2a)-2308)*sgn(2315+b / (2a))*a*k>threshold1; In the above formula, sgn represents the sign function of the returned value. If x is greater than zero, sgn(x)=1; if x is less than zero, sgn(x)=-1; if x is equal to zero, sgn(x)=0; -b / (2a)-2308 represents the vertex position of the fitting, through which it can be judged whether it is near 2310 nanometers (2310 nanometers is a typical wavelength of the absorption feature); 2315+b / (2a) is used to judge whether the fitting vertex is near 2315 nanometers; a and b are quadratic fitting coefficients; k is the normalization factor, which represents the ratio of the reflectance of the pixel in this band to the reflectance of the entire scene image, such as , M 2290-2325 is the average value of the pixel reflectance sequence Y, TM 2290-2325 It is the average reflectivity value of all pixels in the whole scene image in the range of 2290 nanometers to 2325 nanometers; threshold1 indicates whether the final judgment meets the specified threshold. If the condition is met, it means that the area meets the first absorption feature.

[0059] It should be noted that coefficients a and b play a decisive role in the shape and change of the signal curve, and coefficient c is a constant term that mainly affects the curve translation, so it is not directly used for logical judgment in subsequent steps.

[0060] Step S204: determining, according to the first logic judgment result, an area whose spectral response conforms to the first absorption characteristic, and generating a first mask.

[0061] Among them, through the logical judgment result, each pixel is judged whether it meets the first absorption feature. If the logical judgment result of a pixel is true (that is, the condition is met), the pixel position is marked as 1 in the first mask; otherwise, it is marked as 0. The first mask finally generated represents the positions of all pixels in the image that meet the first absorption feature.

[0062] It can be understood that the generation of the first mask is a calibration of the spatial area of ​​the agricultural greenhouse, marking the area in the image that meets the first absorption feature, and providing accurate basic data for subsequent spatial distribution analysis.

[0063] In the above implementation, the spectral features of a specific band are extracted from the aerospace hyperspectral remote sensing image data, and a mathematical model between wavelength and reflectivity is established through quadratic fitting, and the position of the first absorption feature is accurately determined in combination with logical judgment. This technical solution not only improves the accuracy of absorption feature extraction, but also reduces noise and misjudgment through mask generation and logical judgment, and can provide reliable remote sensing data support for applications such as greenhouse spatial distribution and crop health monitoring.

[0064] Reference Figure 3 As an implementation method of step S103, extracting a spectral subset of the second band interval from the surface reflectance data, calculating the reflectance difference between the two ends of the second band interval and performing a threshold comparison, the step of generating a second mask includes: Step S301, extracting a spectrum subset of a second band interval from the surface reflectance data; Among them, the second band ranges from 680 nanometers to 750 nanometers. This band is usually related to the chlorophyll absorption characteristics of plants. It can reflect the health status of plants or other surface characteristics, so as to further improve the distinction between greenhouses and other landforms.

[0065] Step S302, calculating the reflectivity difference between the two ends of the second waveband interval; Specifically, the reflectivity difference T is the difference between the reflectivity values ​​at both ends of the band (i.e., the 680 nm and 750 nm bands) By calculating the reflectance difference T, the change in reflectance at both ends of the band can be quantitatively reflected. If the reflectance difference is large, it may mean that the spectral response of the area has significant changes in this band, which may be related to specific ground features (such as vegetation type or health status).

[0066] Step S303, comparing the reflectivity difference with a preset threshold, and generating a second mask according to the position of the region where the reflectivity difference is greater than the preset threshold.

[0067] Among them, the preset threshold is determined based on experience or previous research, and is intended to distinguish areas with significant changes from areas without significant changes, so as to help filter out areas with smaller spectral changes, thereby focusing on areas that may have special landforms or environmental characteristics.

[0068] Specifically, the calculated reflectivity difference T is compared with a preset threshold value threshold2, and the second mask is a logical matrix, and the value of each pixel can be 0 or 1. If the reflectivity difference T is greater than the preset threshold value threshold2, the pixel is assigned a value of 1 at the corresponding position in the mask, indicating that the spectral response at the position meets the specific conditions; otherwise, it is assigned a value of 0.

[0069] In the above implementation, the second mask identifies the area where the reflectance changes significantly, which can effectively reflect the changes in surface features, especially the spectral response of plants, provides clear area calibration for subsequent image processing and spatial analysis, and improves the accuracy of feature extraction and analysis.

[0070] Reference Figure 4As an implementation method of step S104, extracting a spectral subset of the third band interval from the surface reflectance data, performing three fitting calculations to obtain the reflectance fitting coefficients, combining logical judgment to determine the area where the spectral response meets the second absorption feature, and generating the third mask includes: Step S401, extracting a spectral subset of pixels in a third band from the surface reflectance data to obtain a wavelength sequence and a reflectance sequence; Among them, since plastic greenhouse covering materials (such as polyethylene, polyvinyl chloride, etc.) exhibit significant spectral absorption characteristics near the wavelength of 1730 nanometers, the third band range selects spectral data in the band range near the 1730 nanometer band (1700 nanometers to 1745 nanometers) to form a high contrast for accurate detection.

[0071] Specifically, the reflectance values ​​of the corresponding band (1700 nm to 1745 nm) are extracted from the spectral data of the overall image. These reflectance values ​​correspond to the wavelength sequence of the band one by one, forming a reflectance sequence Y=[y 1 ,y 2 ,...,y n ] T and wavelength sequence X=[x 1 ,x 2 ,...,x n ] T The reflectance sequence represents the surface reflectance value at each corresponding wavelength, and the wavelength sequence represents the wavelength value of each band in the band interval.

[0072] Step S402, constructing a cubic fitting coefficient matrix according to the wavelength sequence and the reflectivity sequence, calculating the reflectivity fitting coefficients, and obtaining the cubic fitting coefficients; Among them, cubic fitting is used to accurately describe the trend of reflectivity changing with wavelength in this band. The fitting curve of the spectral data is obtained by fitting the extracted wavelength sequence and reflectivity sequence with a cubic polynomial.

[0073] Specifically, when fitting, the cubic fitting coefficient matrix A is constructed as: ; In the above formula, Represents the element obtained by multiplying the element of wavelength sequence X by its own element by position, where X represents the wavelength sequence X itself, 1 n T is a column vector of all 1s, representing a constant term.

[0074] Furthermore, the fitting coefficient is solved by the least square method, and the specific calculation formula is: K=(A T A) -1 A TY, the solved K contains the three coefficients a, b, c, d of the quadratic fit, that is, K=[a,b,c,d] T , these coefficients define the cubic relationship between wavelength and reflectivity.

[0075] In the above formula, A T is the transpose of the matrix A, (A T A) -1 is the matrix A T The inverse matrix of A, A T Y is the product of the transpose of matrix A and the reflectivity sequence Y.

[0076] It can be understood that the cubic fitting can accurately capture the complex nonlinear relationship between reflectivity and wavelength within the band range, and the fitting coefficients a, b, c, and d provide the basis for subsequent spectral response judgment.

[0077] Step S403, performing logic judgment based on the cubic fitting coefficients to obtain a second logic judgment result; Specifically, the formula for logical judgment is: sgn(b / a>100)*sgn( -1726)*sgn(1734- )*b*k>threshold3; In the above formula, sgn(b / a>100) is used to determine whether the fitting coefficient b / a is greater than 100 to ensure the significance of the reflectivity change; sgn( -1726) determines whether the inflection point of the reflectivity curve (i.e., the point where the second derivative is zero) is close to 1726 nanometers, which is related to the wavelength position of the second absorption feature; sgn (1734- ) is used to ensure that the inflection point of the reflectivity curve is near 1734 nanometers, which is also the wavelength range of the second absorption feature; a, b, c are cubic fitting coefficients, and k is the ratio of the reflectivity of the pixel in the range of 1700-1745 nanometers to the average reflectivity value of all pixels in the entire image in the same band, such as , M 1700-1745 is the average value of the pixel reflectance sequence Y, TM 1700-1745 It is the average reflectivity value of all pixels in the whole scene image in the range of 1700 nm-1745 nm. This ratio reflects the relative reflectivity level of the pixel, which helps to further screen out areas with significant absorption characteristics. Threshold3 indicates whether the final judgment meets the specified threshold. If the condition is met, it means that the area meets the second absorption feature.

[0078] It should be noted that the coefficients a, b and c have an important influence on the shape, inflection point and other characteristics of the signal curve, while the constant term d is mainly used to adjust the translation of the curve, so it is not directly used in subsequent logical judgments.

[0079] Step S404: determining the region whose spectral response conforms to the second absorption characteristic according to the second logic judgment result, and generating a third mask.

[0080] In combination with the result of the second logic judgment, the regions whose spectral response conforms to the 1730 nanometer absorption characteristic are determined, and these regions are marked as 1 to generate a third mask. The pixels marked as 1 in the third mask indicate that the spectral response of these pixels conforms to the second absorption characteristic (1730 nanometer absorption characteristic).

[0081] In the above implementation, spectral data in the 1700-1745 nm band is extracted from the hyperspectral remote sensing image, and the relationship between reflectivity and wavelength is accurately fitted using a cubic fitting model, and regions whose spectral response meets the 1730 nm absorption characteristics are screened out through complex logical judgment. These regions that meet the characteristics are marked by a third mask, providing clear data support for subsequent spatial analysis and feature extraction.

[0082] As the basis for selecting the first band range in the embodiment of the present application, plastic greenhouse covering materials (such as polyethylene, polyvinyl chloride) have significant spectral absorption characteristics in the short-wave infrared region (about 2000-2500 nanometers), and near 2310 nanometers is the typical position of the absorption peak caused by the stretching vibration of the CH bond in the plastic material. Therefore, the band range of 2290-2325 nanometers is selected to cover the complete profile of the absorption peak, ensuring that the center position (2310 nanometers) of the absorption signal and the changes on both sides can be accurately captured.

[0083] As the basis for selecting the third band interval in the embodiment of the present application, plastic materials also have secondary absorption peaks in the mid-infrared region (approximately 1700-1800 nanometers), which are mainly caused by the overtone vibration of the CH bond or material additives (such as stabilizers), and around 1730 nanometers is the typical position of such absorption. Therefore, the band range of 1700-1745 nanometers is selected to cover the complete range of the secondary absorption peak and avoid signal omission due to spectral drift or noise.

[0084] In summary, the first mask (2310 nanometers) and the third mask (1730 nanometers) respectively target the absorption characteristics of plastic materials in different infrared regions, forming a double verification, enhancing specificity through multi-band joint analysis, and reducing missed detections or false detections caused by misjudgment of a single band (such as interference from similar materials); and as the basis for selecting the second band interval in the embodiment of the present application, the second band interval (680-750 nanometers) uses the reflectivity difference between plastic and vegetation in the red edge interval to further eliminate natural surface interference and achieve high-precision and high-efficiency extraction of the spatial distribution of agricultural greenhouses.

[0085] In addition, in order to deal with the problem of false detection caused by weak spectral response in specific bands, the spectral images in specific bands can be enhanced and smoothing filtering can be used to reduce noise interference; at the same time, according to the actual reflection characteristics of agricultural greenhouses in the target band, the above preset thresholds can be dynamically adjusted to ensure more accurate mask generation and effectively improve the overall recognition effect. In addition, parallel computing architecture and efficient algorithm library can be introduced to make full use of the resources of multi-core processors in each step of preprocessing and mask generation to perform fragmentation processing of large-scale remote sensing image data, so as to significantly shorten the processing time and improve the speed and efficiency of data processing.

[0086] The embodiment of the present application also discloses a system for extracting spatial distribution information of agricultural greenhouses.

[0087] A system for extracting spatial distribution information of agricultural greenhouses, comprising: A data receiving module is used to receive aerospace hyperspectral remote sensing image data collected in real time; The preprocessing module is used to preprocess the aerospace hyperspectral remote sensing image data to obtain the surface reflectance data; A first mask generation module is used to extract a spectral subset of a first band interval from the surface reflectance data, perform quadratic fitting to obtain a reflectance fitting coefficient, and combine logical judgment to determine an area where the spectral response meets the first absorption feature to generate a first mask; A second mask generation module is used to extract a spectral subset of a second band interval from the surface reflectance data, calculate the reflectance difference between the two ends of the second band interval and perform threshold comparison to generate a second mask; A third mask generation module is used to extract a spectral subset of the third band interval from the surface reflectance data, perform three fitting calculations to obtain the reflectance fitting coefficient, combine logical judgment to determine the area where the spectral response meets the second absorption feature, and generate a third mask; The logic fusion module is used to perform logic fusion according to the first mask, the second mask and the third mask to obtain the extraction result of the spatial distribution information of the agricultural greenhouse.

[0088] An agricultural greenhouse spatial distribution information extraction system in an embodiment of the present application can implement any of the above-mentioned agricultural greenhouse spatial distribution information extraction methods, and the specific working process of each module in the distribution information extraction system can refer to the corresponding process in the above-mentioned method embodiment.

[0089] In the several embodiments provided in this application, it should be understood that the provided methods and systems can be implemented in other ways. For example, the system embodiments described above are only illustrative; for example, the division of a certain module is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0090] The embodiment of the present application also discloses a computer device.

[0091] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a method for extracting spatial distribution information of agricultural greenhouses as described above is implemented.

[0092] The embodiment of the present application also discloses a computer-readable storage medium.

[0093] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any one of the above-mentioned methods for extracting spatial distribution information of agricultural greenhouses.

[0094] Among them, computer-readable storage media can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus or device; the program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0095] It should be noted that in the above embodiments, the description of each embodiment has different emphases, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0096] The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims

1. A method for extracting spatial distribution information of agricultural greenhouses, characterized in that: The extraction method comprises: Receive real-time aerospace hyperspectral remote sensing image data and pre-process it to obtain surface reflectance data; Extracting a spectral subset of a first band interval from the surface reflectance data, performing quadratic fitting to obtain a reflectance fitting coefficient, combining logical judgment to determine an area where the spectral response meets the first absorption feature, and generating a first mask; Extracting a spectral subset of a second band interval from the surface reflectance data, calculating a reflectance difference between two ends of the second band interval and performing a threshold comparison to generate a second mask; Extracting a spectral subset of a third band interval from the surface reflectance data, performing three fitting calculations to obtain a reflectance fitting coefficient, combining logical judgment to determine an area where the spectral response meets the second absorption feature, and generating a third mask; The first mask, the second mask and the third mask are logically fused to obtain the extraction result of the spatial distribution information of the agricultural greenhouse.

2. The method for extracting spatial distribution information of agricultural greenhouses according to claim 1, characterized in that: The step of extracting a spectral subset of the first band interval from the surface reflectance data, performing quadratic fitting to obtain a reflectance fitting coefficient, and combining logical judgment to determine an area where the spectral response meets the first absorption feature, and generating a first mask includes: Extracting a spectral subset of pixels in a first band interval from the surface reflectance data to obtain a wavelength sequence and a reflectance sequence; Constructing a quadratic fitting coefficient matrix according to the wavelength sequence and the reflectivity sequence, calculating the reflectivity fitting coefficients by the least squares method, and obtaining the quadratic fitting coefficients; Performing logical judgment based on the quadratic fitting coefficient to obtain a first logical judgment result; A region whose spectral response conforms to the first absorption characteristic is determined according to the first logical judgment result, and a first mask is generated.

3. The method for extracting spatial distribution information of agricultural greenhouses according to claim 1, characterized in that: The steps of extracting a spectral subset of a second band interval from the surface reflectance data, calculating the reflectance difference between the two ends of the second band interval and performing threshold comparison, and generating a second mask include: Extracting a spectral subset of a second wavelength band from the surface reflectance data; Calculating the reflectivity difference between the two ends of the second waveband interval; The reflectivity difference is compared with a preset threshold, and a second mask is generated according to the position of the area where the reflectivity difference is greater than the preset threshold.

4. The method for extracting spatial distribution information of agricultural greenhouses according to claim 1, characterized in that: The steps of extracting a spectral subset of the third band interval from the surface reflectance data, performing three fitting calculations to obtain reflectance fitting coefficients, and combining logical judgment to determine the area where the spectral response meets the second absorption feature, and generating a third mask include: Extracting a spectral subset of pixels in a third band from the surface reflectance data to obtain a wavelength sequence and a reflectance sequence; Constructing a cubic fitting coefficient matrix according to the wavelength sequence and the reflectivity sequence, calculating the reflectivity fitting coefficients, and obtaining the cubic fitting coefficients; Performing logical judgment based on the cubic fitting coefficients to obtain a second logical judgment result; The region whose spectral response conforms to the second absorption characteristic is determined according to the second logic judgment result, and a third mask is generated.

5. The method for extracting spatial distribution information of agricultural greenhouses according to claim 1, characterized in that: The spectral range of the aerospace hyperspectral remote sensing image data is 400 nanometers to 2500 nanometers, the spectral resolution is less than 8 nanometers, and the spatial resolution is less than 30 meters.

6. A method for extracting spatial distribution information of agricultural greenhouses according to claim 5, characterized in that: The first waveband range is 2290 nanometers to 2325 nanometers; the second waveband range is 680 nanometers to 750 nanometers; and the third waveband range is 1700 nanometers to 1745 nanometers.

7. A method for extracting spatial distribution information of agricultural greenhouses according to any one of claims 1 to 6, characterized in that: The first mask, the second mask and the third mask are all logical matrices and are consistent with the spatial dimensions of the aerospace hyperspectral remote sensing image data.

8. An agricultural greenhouse spatial distribution information extraction system, characterized in that: The extraction system comprises: A data receiving module is used to receive aerospace hyperspectral remote sensing image data collected in real time; A preprocessing module, used for preprocessing the aerospace hyperspectral remote sensing image data to obtain surface reflectance data; A first mask generation module is used to extract a spectral subset of a first band interval from the surface reflectance data, perform quadratic fitting to obtain a reflectance fitting coefficient, determine an area where the spectral response meets the first absorption feature by combining logical judgment, and generate a first mask; A second mask generating module, used for extracting a spectral subset of a second band interval from the surface reflectance data, calculating a reflectance difference between two ends of the second band interval and performing a threshold comparison to generate a second mask; A third mask generation module is used to extract a spectral subset of a third band interval from the surface reflectance data, perform three fitting calculations to obtain a reflectance fitting coefficient, and combine logical judgment to determine an area where the spectral response meets the second absorption feature to generate a third mask; The logic fusion module is used to perform logic fusion according to the first mask, the second mask and the third mask to obtain the extraction result of the spatial distribution information of the agricultural greenhouse.

9. A computer device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the program.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 7.

Images