A photoelectric detector system based on environmental perception and adjustment

Abstract

The present invention discloses a photoelectric detector system based on environmental perception and adjustment, which relates to the field of photoelectric detector adjustment technology. The system collects light illuminance L, air humidity S and soil moisture content H in real time through a first environmental perception module, constructs a perception condition coefficient Gzx, and when Gzx reaches a preset condition threshold Q, the system automatically switches the working mode of the photoelectric detector (the first mode uses a visible light filter, and the second mode uses an infrared filter) to ensure that accurate monitoring data can be obtained under different environmental conditions. By measuring the first disease index Bhzs 1 and the second disease index Bhzs 2 Through precise evaluation and multiple calibrations, the system can effectively reduce errors and improve the accuracy and reliability of pest monitoring. The temperature gradient calibration mechanism ensures that the monitoring data remains accurate in environments with large temperature changes, effectively improving the environmental adaptability and monitoring accuracy of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of photoelectric detector adjustment, and in particular to a photoelectric detector system based on environmental perception and adjustment. Background Art

[0002] The application of photoelectric detectors in the agricultural field has gradually become one of the important means of modern agricultural management and monitoring. Traditional agricultural monitoring methods usually rely on manual inspections and empirical judgments, which are not only time-consuming and laborious, but also often difficult to ensure the accuracy and consistency of data due to the influence of human factors. With the advancement of science and technology, the use of photoelectric detectors for real-time monitoring and data collection of crops has become an effective way to improve agricultural production efficiency and management level. However, traditional photoelectric detector systems still have some significant defects and limitations in practical applications.

[0003] First, traditional photoelectric detectors are not adaptable to the environment. The agricultural environment is complex and changeable, and conditions such as light, temperature, and humidity are often in dynamic change. Traditional photoelectric detector systems usually use fixed parameter settings, which are difficult to adapt to environmental changes in real time, resulting in the accuracy of monitoring results being affected. For example, in high or low temperature environments, the performance of photoelectric detectors may drop significantly, thus affecting the reliability of the data.

[0004] Secondly, traditional photoelectric detectors have certain limitations in pest and disease monitoring and crop growth status assessment. Crops will show different spectral characteristics at different growth stages, and the invasion of pests and diseases often causes changes in the spectral response of crops in different bands. Traditional photoelectric detector systems can usually only monitor light signals in specific bands and lack the ability to detect and analyze in multiple bands. Therefore, there are great challenges in the early detection and accurate assessment of pests and diseases. Summary of the invention

[0005] In view of the deficiencies of the prior art, the present invention provides a photoelectric detector system based on environmental perception and adjustment to solve the problems mentioned in the background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a photoelectric detector system based on environmental perception and adjustment, including a preselected calibration environment module, a first environmental perception module, a second data acquisition module, a third perception module, a first calibration module, a second calibration module and an error verification module;

[0007] The preselected calibration environment module is used to divide the preselected crop planting area into a plurality of monitoring areas, each monitoring area being planted with the same crop or crops at the same growth stage;

[0008] The first environment perception module is used to collect the light brightness L, air humidity S and soil moisture content H of the monitoring area in real time to construct a perception condition coefficient Gzx; and preset a condition threshold Q. When the perception condition coefficient Gzx ≥ the condition threshold Q, it triggers the switching of the photoelectric detector to the first mode and uses a visible light filter; when the perception condition coefficient Gzx < the condition threshold Q, it triggers the switching of the photoelectric detector to the second mode and uses an infrared filter;

[0009] The second data acquisition module is used to, when the photoelectric detector switches to the first mode, indicate that when the relative fluctuation of the environmental condition index HJ is normal, obtain the first thermal imaging data of the crops in the monitoring area through the photoelectric detector monitoring, and extract the crop pests and damage characteristics in the first thermal imaging data through image recognition technology, and obtain the following through deep calculation and analysis: the first temperature signal value xhz1, the hot spot area index Rb and the first disease index Bhzs1. When the first disease index Bhzs1 exceeds the first defect threshold value X, it triggers the switching of the photoelectric detector to the third mode, and uses the ultraviolet filter;

[0010] The third sensing module is used to switch the photoelectric detector to the third mode, re-monitor the same monitoring area to obtain the second ultraviolet imaging data, extract the fluorescence characteristics of the second ultraviolet imaging data, and perform in-depth calculation and analysis to obtain: the second fluorescence signal value xhz2, the water shortage distribution index Qs and the second disease index Bhzs2;

[0011] The first calibration module is used to calculate the difference between the second disease index Bhzs2 and the first disease index Bhzs1 to obtain the first error index wczs, and compare and analyze the first error index wczs with the error threshold W. When the first error index wczs is greater than the error threshold W, the second fluorescence signal value xhz2 is subjected to a first calibration;

[0012] The second calibration module is used to collect the temperature gradient characteristics of the monitoring area through the temperature sensor and construct the temperature gradient index Wd zs , when the temperature gradient index Wd zs If the value xhz1 is greater than the temperature threshold WD, a second calibration is performed on the first temperature signal value xhz1;

[0013] The error verification module recalculates the first error index wczs. When the first error index wczs still exceeds the error threshold W, the process of the second data acquisition module, the third perception module, the first calibration module and the second calibration module is repeated until the first error index wczs is lower than the error threshold W.

[0014] Preferably, the first environment perception module includes a first acquisition unit and a first calculation unit;

[0015] The first acquisition unit is used to connect a photodetector to a brightness sensor, an air humidity sensor, and a soil humidity sensor in the monitoring area, and collect in real time the illumination brightness L, air humidity S, and soil moisture content H of the monitoring area, establish a first environmental condition data set, and perform preprocessing on the first environmental condition data set, where the preprocessing includes data cleaning, data smoothing, and data standardization;

[0016] The first calculation unit is used to perform linear normalization on the illumination brightness L, air humidity S, and soil moisture content H, map the corresponding data values to the interval [0, 1], and construct a perception condition coefficient Gzx according to the following method:

[0017]

[0018] where i = 1, 2,..., n, n is the number of sampling frequencies, set to collect once per second, L i represents the illumination brightness of the i-th sampling node, S i represents the air humidity of the i-th sampling node, H i represents the soil moisture content of the i-th sampling node, L is the illumination brightness qualified threshold, is the brightness qualified threshold; is the soil moisture content qualified threshold; F1, F2, and F3 are weight coefficients: 0 < F1 < 1, 0 < F2 < 1, 0 < F3 < 1, and F1 + F2 + F3 = 1.

[0019] Preferably, the first environmental perception module further includes a first evaluation unit and a first adjustment unit;

[0020] The first evaluation unit is used to preset a condition threshold Q, and compare and analyze the perception condition coefficient Gzx with the condition threshold Q to obtain a first environmental perception evaluation result, including:

[0021] When the perception condition coefficient Gzx ≥ the condition threshold Q, it indicates that the environmental conditions of illumination, humidity, and soil moisture in the current monitoring area are normal, then trigger the switch to the first mode, and control the photodetector to use a visible light filter through the first adjustment unit;

[0022] When the perception condition coefficient Gzx < the condition threshold Q, it indicates that the environmental conditions of illumination, humidity, and soil moisture in the current monitoring area are abnormal, then trigger the switch to the second mode, and control the photodetector to use an infrared filter through the first adjustment unit.

[0023] Preferably, the second data acquisition module includes a second acquisition unit, a second extraction unit, and a second calculation unit;

[0024] The second acquisition unit is used to acquire first thermal imaging data of crops in the monitoring area through the photoelectric detector when the photoelectric detector switches to the first mode;

[0025] The second extraction unit is used to first perform denoising, contrast enhancement and image segmentation on the first thermal imaging data, apply a convolutional neural network to establish a recognition model and train it, extract the crop pests and diseases and damaged features in the first thermal imaging data by using a temperature threshold WD method or a K-means clustering algorithm, match the extracted features with the features in the trained recognition model, identify specific pests and diseases and damaged features, obtain a first matching result and classify and label it;

[0026] The second calculation unit is used to perform in-depth analysis on the first matching result, and obtain the first temperature signal value xhz1 and the hot spot area index Rb by calculating through the following formula:

[0027]

[0028] Where M is the total number of sampling points, S i (T) represents the response signal intensity of the crop surface temperature T of the photodetector at the i-th sampling point;

[0029]

[0030] In the formula, A hot is the total area of ​​the hot spot region, A total is the total area of ​​crop leaves in the monitoring area, N hot is the total number of sampling points in the hot spot area; S j (T) is the temperature T response signal of the photodetector at the sampling point of the jth hot spot area;

[0031] The first temperature signal value xhz1 is associated with the hot spot area index Rb, and the defect characteristics of crop leaves are collected to obtain the first disease index Bhzs1 through the following associated formula:

[0032]

[0033] In the formula, Yd i Indicates the roundness value of the i-th sampling point, A i represents the area of ​​the i-th leaf, p i represents the perimeter of the i-th leaf. If Yd i <1, it means there is a missing part, Yd avg Indicates the roundness value threshold of healthy crops; a1, a2 and a3 are weight coefficients, which are adjusted and set by the user.

[0034] Preferably, the second data acquisition module further includes a second evaluation unit and a second adjustment unit;

[0035] The second evaluation unit is used to preset a first defect threshold value X, and compare the first disease index Bhzs1 with the first defect threshold value X to obtain a second defect evaluation result, including:

[0036] When the first disease index Bhzs1> the first defect threshold X, indicating that the current crop diseases and insect pests and defects are abnormal, the third mode is triggered to switch, and the photoelectric detector is controlled to use an ultraviolet filter through the second adjustment unit;

[0037] When the first disease index Bhzs1 ≤ the first defect threshold X, it means that the current crops are free of diseases, pests and damage defects, and no adjustment is performed.

[0038] Preferably, the third perception module includes a third acquisition unit, a third extraction unit and a third calculation unit;

[0039] The third acquisition unit is used to repeatedly acquire the second ultraviolet imaging data from the same monitoring area after the photoelectric detector switches to the third mode, and perform Gaussian filtering to remove noise, contrast stretching image enhancement and image segmentation processing on the second ultraviolet imaging data;

[0040] The third extraction unit is used to detect the fluorescence signal area in the second ultraviolet imaging data by image processing technology, and calculate each fluorescence intensity to generate a fluorescence intensity map;

[0041] The third calculation unit is used to perform in-depth calculation and analysis according to the fluorescence intensity map to obtain the second fluorescence signal value xhz2 and the water shortage distribution index Qs. The second fluorescence signal value xhz2 is calculated and obtained by the following formula:

[0042]

[0043] Where M is the total number of sampling points, Y i represents the average fluorescence intensity of the photodetector in the ith fluorescence signal area, I ig represents the fluorescence intensity of the g-th pixel in the i-th fluorescence signal area, E i Indicates the total number of pixels in the area;

[0044] The method for obtaining the water shortage distribution index Qs is to set the fluorescence intensity water shortage threshold Y f , below the fluorescence intensity water shortage threshold Y f Marked as water-scarce area B i , B i The identification formula is:

[0045] B i ={i|Yi <Y f |};

[0046]

[0047] In the formula, B i represents the area of ​​the i-th water-deficient region, D represents the set of all identified water-deficient regions, and Y dry is the total area of ​​water-scarce regions, A total is the total area of ​​crop leaves in the monitoring area;

[0048] The second fluorescence signal value xhz2 is associated with the water shortage distribution index Qs, and the second disease index Bhzs2 is calculated by the following formula:

[0049]

[0050] Where Y normal It represents the normal fluorescence intensity threshold of healthy crops; a4, a5 and a6 are weight coefficients, which are adjusted by the user.

[0051] Preferably, the first calibration module includes a difference calculation unit and a first calibration unit, and the difference calculation unit is used to calculate and obtain the first error index wczs by the following formula:

[0052] wczs=Bhzs2-Bhzs1;

[0053] The error threshold W is preset, and the error threshold W is compared and analyzed with the first error index wczs to obtain the following error evaluation results, including:

[0054] When the first error index wczs>error threshold W, it indicates that the error of the detection index of pests and diseases is abnormal in the same detection area, and the second fluorescence signal value xhz2 is calibrated by the first calibration unit, including: increasing the gain of the front-end amplifier of the current photodetector by 5% and increasing the exposure time of the photosensitive element of the photodetector by 5%;

[0055] When the first error index wczs≤error threshold W, it means that the error of the detection pest index in the same detection area is normal and no calibration is required.

[0056] Preferably, the second calibration module includes a fourth acquisition unit, a fourth temperature impact calculation unit and a fourth evaluation unit, wherein the fourth acquisition unit is used to use a temperature sensor to collect air temperature data of the detection area in real time, and collect the air temperature Wd of the i-th sampling point. i The temperature gradient index Wd is calculated by the fourth calculation unit using the following formula: zs :

[0057]

[0058] Where Wd i is the air temperature at the i-th sampling point, Wd i-1 is the air temperature of the adjacent previous sampling point, d is the distance between sampling points, and M is the total number of sampling points;

[0059] The fourth evaluation unit is used to preset a temperature threshold WD and compare the temperature threshold WD with the temperature gradient index Wd zs Compare and obtain the air temperature impact results, including:

[0060] When the temperature gradient index Wd zs > Temperature threshold WD, indicating that the current ambient air temperature gradient changes abnormally and needs to trigger the second calibration instruction;

[0061] When the temperature gradient index Wd zs ≤ temperature threshold WD, indicating that the current ambient air temperature gradient changes normally and no calibration is required.

[0062] Preferably, the second calibration module also includes a second calibration unit, which is used to adjust the parameters of the photodetector after receiving the second calibration instruction, including increasing the gain of the current photodetector front-end amplifier by 3% and increasing the exposure time of the photodetector photosensitive element by 3%, and adjusting the black level of the photodetector so that the black level offset = 0.1.

[0063] The present invention provides a photoelectric detector system based on environmental perception and adjustment. It has the following beneficial effects:

[0064] (1) This is a photoelectric detector system based on environmental perception and adjustment. The present invention collects light brightness L, air humidity S and soil moisture content H in real time through the first environmental perception module, and constructs the perception condition coefficient Gzx. When Gzx reaches the preset condition threshold Q, the system automatically switches the working mode of the photoelectric detector (the first mode uses a visible light filter, and the second mode uses an infrared filter) to ensure that accurate monitoring data can be obtained under different environmental conditions. This dynamic adaptation mechanism effectively improves the adaptability and data reliability of the system under different environmental conditions, especially in high or low temperature environments. It can still maintain stable performance.

[0065] (2) This is a photoelectric detector system based on environmental perception and adjustment. The present invention realizes multi-band photoelectric detection by switching different filters (visible light, infrared, ultraviolet). This multi-band monitoring method can more comprehensively capture the changes in the spectral response of crops at different growth stages and when attacked by pests and diseases. Multi-band detection improves the accuracy of early detection of pests and diseases and the comprehensiveness of crop growth status assessment, enabling the monitoring system to provide richer and more accurate data to support agricultural decision-making.

[0066] (3) Based on the environmental perception and adjustment photoelectric detector system, the present invention obtains the first thermal imaging data and the second ultraviolet imaging data respectively through the second data acquisition module and the third perception module, and extracts relevant features. Through the first calibration module and the second calibration module, the disease index is differentially analyzed and calibrated to ensure the accuracy of the monitoring results. Through the accurate evaluation and multiple calibration of the first disease index Bhzs1 and the second disease index Bhzs2, the system can effectively reduce errors and improve the accuracy and reliability of pest and disease monitoring.

[0067] (4) Based on the environmental perception and adjustment photoelectric detector system, the present invention collects the temperature gradient characteristics of the monitoring area through the temperature sensor, constructs the temperature gradient index, and zs When the temperature threshold WD is exceeded, the first temperature signal value xhz1 is subjected to a second calibration. This temperature gradient calibration mechanism ensures that the monitoring data remains accurate in an environment with large temperature changes, effectively improving the environmental adaptability and monitoring accuracy of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 The present invention is a schematic diagram of a block diagram of a photoelectric detector system based on environmental perception and adjustment. DETAILED DESCRIPTION

[0069] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0070] Example 1

[0071] The present invention provides a photoelectric detector system based on environmental perception and adjustment, please refer to Figure 1 , including a preselected calibration environment module, a first environment perception module, a second data acquisition module, a third perception module, a first calibration module, a second calibration module and an error verification module;

[0072] The preselected calibration environment module is used to divide the preselected crop planting area into a plurality of monitoring areas, each monitoring area being planted with the same crop or crops at the same growth stage;

[0073] The first environment perception module is used to collect the light brightness L, air humidity S and soil moisture content H of the monitoring area in real time to construct a perception condition coefficient Gzx; and preset a condition threshold Q. When the perception condition coefficient Gzx ≥ the condition threshold Q, it triggers the switching of the photoelectric detector to the first mode and uses a visible light filter; when the perception condition coefficient Gzx < the condition threshold Q, it triggers the switching of the photoelectric detector to the second mode and uses an infrared filter;

[0074] The second data acquisition module is used to, when the photoelectric detector switches to the first mode, indicate that when the relative fluctuation of the environmental condition index HJ is normal, obtain the first thermal imaging data of the crops in the monitoring area through the photoelectric detector monitoring, and extract the crop pests and damage characteristics in the first thermal imaging data through image recognition technology, and obtain the following through deep calculation and analysis: the first temperature signal value xhz1, the hot spot area index Rb and the first disease index Bhzs1. When the first disease index Bhzs1 exceeds the first defect threshold value X, it triggers the switching of the photoelectric detector to the third mode, and uses the ultraviolet filter;

[0075] The third sensing module is used to switch the photoelectric detector to the third mode, re-monitor the same monitoring area to obtain the second ultraviolet imaging data, extract the fluorescence characteristics of the second ultraviolet imaging data, and perform in-depth calculation and analysis to obtain: the second fluorescence signal value xhz2, the water shortage distribution index Qs and the second disease index Bhzs2;

[0076] The first calibration module is used to calculate the difference between the second disease index Bhzs2 and the first disease index Bhzs1 to obtain the first error index wczs, and compare and analyze the first error index wczs with the error threshold W. When the first error index wczs is greater than the error threshold W, the second fluorescence signal value xhz2 is subjected to a first calibration;

[0077] The second calibration module is used to collect the temperature gradient characteristics of the monitoring area through the temperature sensor and construct the temperature gradient index Wd zs , when the temperature gradient index Wd zs If the value xhz1 is greater than the temperature threshold WD, a second calibration is performed on the first temperature signal value xhz1;

[0078] The error verification module recalculates the first error index wczs. When the first error index wczs still exceeds the error threshold W, the process of the second data acquisition module, the third perception module, the first calibration module and the second calibration module is repeated until the first error index wczs is lower than the error threshold W.

[0079] In this embodiment, traditional photoelectric detectors perform poorly in the face of dynamic changes in agricultural environments, especially when environmental conditions such as light, temperature, and humidity change. The fixed parameter settings of traditional systems limit their adaptability. The present invention collects light brightness L, air humidity S, and soil moisture content H in real time through the first environmental perception module, and constructs a perception condition coefficient Gzx. When Gzx reaches the preset condition threshold Q, the system automatically switches the working mode of the photoelectric detector (the first mode uses a visible light filter, and the second mode uses an infrared filter) to ensure that accurate monitoring data can be obtained under different environmental conditions. This dynamic adaptation mechanism effectively improves the adaptability and data reliability of the system under different environmental conditions, especially in high or low temperature environments. It can still maintain stable performance.

[0080] Traditional photodetectors can usually only monitor light signals in a specific band and lack the ability of multi-band detection and analysis. Therefore, they are limited in early detection of pests and diseases and assessment of crop growth status. The present invention achieves multi-band photodetection by switching different filters (visible light, infrared, ultraviolet). This multi-band monitoring method can more comprehensively capture the changes in the spectral response of crops at different growth stages and when pests and diseases invade. Multi-band detection improves the accuracy of early detection of pests and diseases and the comprehensiveness of crop growth status assessment, enabling the monitoring system to provide richer and more accurate data to support agricultural decision-making.

[0081] Traditional photoelectric detector systems may have errors in pest and disease monitoring, affecting the reliability of data. The present invention obtains the first thermal imaging data and the second ultraviolet imaging data through the second data acquisition module and the third perception module, respectively, and extracts relevant features. The disease index is differentially analyzed and calibrated through the first calibration module and the second calibration module to ensure the accuracy of the monitoring results. Through accurate evaluation and multiple calibration of the disease index, the system can effectively reduce errors and improve the accuracy and reliability of pest and disease monitoring.

[0082] The spectral response of crops in different temperature environments will be different. Traditional systems are difficult to deal with monitoring errors caused by temperature gradient changes. The present invention collects the temperature gradient characteristics of the monitoring area through a temperature sensor, constructs a temperature gradient index, and generates a temperature gradient index Wd. zs When the temperature threshold WD is exceeded, the first temperature signal value xhz1 is subjected to a second calibration. This temperature gradient calibration mechanism ensures that the monitoring data remains accurate in an environment with large temperature changes, effectively improving the environmental adaptability and monitoring accuracy of the system.

[0083] Example 2: This example is an explanation of Example 1. Figure 1 ,Specifically, the first environment perception module includes a first acquisition unit and a first calculation unit;

[0084] The first acquisition unit is used to connect a photodetector to a brightness sensor, an air humidity sensor, and a soil humidity sensor in the monitoring area, and to acquire in real time the illumination brightness L, air humidity S, and soil moisture content H of the monitoring area, establish a first environmental condition data set, and perform preprocessing on the first environmental condition data set, where the preprocessing includes data cleaning, data smoothing, and data standardization;

[0085] The first calculation unit is used to perform linear normalization on the illumination brightness L, air humidity S, and soil moisture content H, and map the corresponding data values to the interval [0, 1], and construct a perception condition coefficient Gzx according to the following method:

[0086]

[0087] where i = 1, 2,..., n, n is the number of sampling frequencies, set to be sampled once per second, L i represents the illumination brightness of the i-th sampling node, S i represents the air humidity of the i-th sampling node, H i represents the soil moisture content of the i-th sampling node, is the illumination brightness qualification threshold, is the brightness qualification threshold; is the soil moisture content qualification threshold; F1, F2, and F3 are weight coefficients: 0 < F1 < 1, 0 < F2 < 1, 0 < F3 < 1, and F1 + F2 + F3 = 1.

[0088] The first environmental perception module further includes a first evaluation unit and a first adjustment unit;

[0089] The first evaluation unit is used to preset a condition threshold Q, and compare and analyze the perception condition coefficient Gzx with the condition threshold Q to obtain a first environmental perception evaluation result, including:

[0090] When the perception condition coefficient Gzx ≥ the condition threshold Q, it indicates that the environmental conditions of illumination, humidity, and soil moisture in the current monitoring area are normal, then trigger to switch to the first mode, and control the photodetector to use a visible light filter through the first adjustment unit; it indicates that the current brightness meets the standard, and in the case of natural light source or stable light source, the relative brightness fluctuation is small.

[0091] When the perception condition coefficient Gzx < the condition threshold Q, it indicates that the environmental conditions of illumination, humidity, and soil moisture in the current monitoring area are abnormal, then trigger to switch to the second mode, and control the photodetector to use an infrared filter through the first adjustment unit.

[0092] In this embodiment, the present invention realizes real-time environmental monitoring and adaptive adjustment through the first environmental perception module. The first acquisition unit collects the light brightness L, air humidity S and soil moisture content H of the monitoring area in real time through the brightness sensor, air humidity sensor and soil humidity sensor, and establishes a first environmental condition data set. Real-time environmental data is collected to ensure the immediacy of monitoring results. Data cleaning, smoothing and standardization are performed to improve data quality and reliability. The environmental parameter data values ​​are mapped to a unified interval to improve the efficiency and accuracy of data processing and analysis.

[0093] The comparative analysis of the perception condition coefficient Gzx and the condition threshold Q can accurately evaluate the current environmental status. According to the environmental assessment results, the photoelectric detector working mode is automatically switched to ensure the best monitoring effect under different environmental conditions. Through the automatic switching of visible light filters and infrared filters, the monitoring needs under different environmental conditions are met, and the flexibility and adaptability of the system are improved.

[0094] Example 3, this example is explained in Example 1, please refer to Figure 1 ,Specifically, the second data acquisition module includes a second acquisition unit, a second extraction unit and a second calculation unit;

[0095] The second acquisition unit is used to acquire first thermal imaging data of crops in the monitoring area through the photoelectric detector when the photoelectric detector switches to the first mode;

[0096] The second extraction unit is used to first perform denoising, contrast enhancement and image segmentation on the first thermal imaging data, apply a convolutional neural network to establish a recognition model and train it, extract the crop pests and diseases and damaged features in the first thermal imaging data by using a temperature threshold WD method or a K-means clustering algorithm, match the extracted features with the features in the trained recognition model, identify specific pests and diseases and damaged features, obtain a first matching result and classify and label it;

[0097] The second calculation unit is used to perform in-depth analysis on the first matching result, and obtain the first temperature signal value xhz1 and the hot spot area index Rb by calculating through the following formula:

[0098]

[0099] Where M is the total number of sampling points, S i (T) represents the response signal intensity of the crop surface temperature T of the photodetector at the i-th sampling point;

[0100]

[0101] In the formula, A hot is the total area of ​​the hot spot region, Atotal is the total area of the crop leaves in the monitoring area, N hot is the total number of sampling points within the hotspot area; S j (T) is the temperature T response signal of the photodetector at the j-th sampling point in the hotspot area;

[0102] Correlate the first temperature signal value xhz1 with the hotspot area index Rb, and collect the characteristics of crop leaf defects. Calculate and obtain the first disease index Bhzs1 through the following correlation formula:

[0103]

[0104] In the formula, Yd i represents the roundness value of the i-th sampling point, A i represents the area of the i-th leaf, p i represents the perimeter of the i-th leaf. If Yd i < 1, it indicates that there is a defective part. Yd avg represents the roundness value threshold of healthy crops; a1, a2, and a3 represent weight coefficients, which are adjusted and set by the user, 0 < a1 < 1, 0 < a2 < 1, 0 < a3 < 1, and a1 + a2 + a3 = 1..

[0105] The second data acquisition module further includes a second evaluation unit and a second adjustment unit;

[0106] The second evaluation unit is used to preset a first defect threshold X, and compare the first disease index Bhzs1 with the first defect threshold X to obtain a second defect evaluation result, including:

[0107] When the first disease index Bhzs1 > the first defect threshold X, it indicates that there are current crop pests and diseases and defect abnormalities, then trigger the switch to the third mode, and control the photodetector to use an ultraviolet filter through the second adjustment unit;

[0108] When the first disease index Bhzs1 ≤ the first defect threshold X, it indicates that there are no pests, diseases, and damage defects in the current crop, then no adjustment is made.

[0109] In this embodiment, the traditional photoelectric detector has limited data processing capabilities in crop monitoring and is difficult to cope with complex pest and disease and growth status monitoring requirements. The present invention realizes efficient data acquisition and processing through a second data acquisition module. When the photoelectric detector switches to the first mode, the second acquisition unit obtains the first thermal imaging data of the crops in the monitoring area through the photoelectric detector monitoring. Detailed temperature distribution information of the crops is obtained through thermal imaging data to improve the comprehensiveness and accuracy of monitoring. The second extraction unit performs denoising, contrast enhancement and image segmentation on the data to improve data quality and ensure the accuracy of subsequent analysis. The second extraction unit applies a convolutional neural network to establish a recognition model to extract and identify crop pests and diseases and damaged features in the first thermal imaging data. The second calculation unit performs a deep analysis on the recognition results and calculates the first temperature signal value xhz1, the hot spot area index Rb and the first disease index Bhzs1. The second evaluation unit compares and analyzes the first disease index Bhzs1 with the first defect threshold value X. If Bhzs1 exceeds the first defect threshold value X, it triggers the switching of the third mode and controls the photoelectric detector to use an ultraviolet filter through the second adjustment unit. According to the real-time monitoring results, the working mode is automatically switched to ensure timely response to pests and diseases and changes in growth status. Through the use of UV filters, more accurate monitoring of pests and diseases and defects can be achieved, providing more reliable data support.

[0110] Example 4: This example is an explanation of Example 1. Figure 1 ,Specifically, the third perception module includes a third acquisition unit, a third extraction unit and a third calculation unit;

[0111] The third acquisition unit is used to repeatedly acquire the second ultraviolet imaging data from the same monitoring area after the photoelectric detector switches to the third mode, and perform Gaussian filtering to remove noise, contrast stretching image enhancement and image segmentation processing on the second ultraviolet imaging data;

[0112] The third extraction unit is used to detect the fluorescence signal area in the second ultraviolet imaging data by image processing technology, and calculate each fluorescence intensity to generate a fluorescence intensity map;

[0113] The third calculation unit is used to perform in-depth calculation and analysis according to the fluorescence intensity map to obtain the second fluorescence signal value xhz2 and the water shortage distribution index Qs. The second fluorescence signal value xhz2 is calculated and obtained by the following formula:

[0114]

[0115]

[0116] Where M is the total number of sampling points, Y iRepresents the average fluorescence intensity of the photodetector in the i-th fluorescence signal region, I ig Represents the fluorescence intensity of the g-th pixel in the i-th fluorescence signal region, E i Represents the total number of pixels in this region;

[0117] The method for obtaining the water shortage distribution index Qs is to set the water shortage threshold Y of fluorescence intensity f , regions with fluorescence intensity lower than the water shortage threshold Y f Are marked as water shortage regions B i , B i The recognition formula is:

[0118] B i ={i|Y i <Y f |};

[0119]

[0120] In the formula, B i Represents the area of the i-th water shortage region, D represents the set of all regions recognized as water shortage regions, Y dry Is the total area of the water shortage regions, A total Is the total area of the crop leaves in the monitoring region;

[0121] And correlate the second fluorescence signal value xhz2 with the water shortage distribution index Qs, and calculate and obtain the second disease index Bhzs2 through the following formula:

[0122]

[0123] In the formula, Y normal Represents the normal fluorescence intensity threshold of healthy crops; a4, a5, and a6 represent weight coefficients, which are adjusted and set by the user, 0 < a4 < 1, 0 < a5 < 1, 0 < a6 < 1, and a4 + a5 + a6 = 1.

[0124] The first calibration module includes a difference calculation unit and a first calibration unit. The difference calculation unit is used to calculate and obtain the first error index wczs through the following formula:

[0125] wczs = Bhzs2 - Bhzs1;

[0126] And preset an error threshold W, and compare and analyze the error threshold W with the first error index wczs to obtain the following error evaluation results, including:

[0127] When the first error index wczs>error threshold W, it indicates that the error of the detection index of pests and diseases is abnormal in the same detection area, and the second fluorescence signal value xhz2 is calibrated by the first calibration unit, including: increasing the gain of the front-end amplifier of the current photodetector by 5% and increasing the exposure time of the photosensitive element of the photodetector by 5%;

[0128] When the first error index wczs≤error threshold W, it means that the error of the detection pest index in the same detection area is normal and no calibration is required.

[0129] In this embodiment, the present invention realizes accurate ultraviolet imaging analysis through the third perception module. After the photoelectric detector switches to the third mode, the third acquisition unit re-collects the second ultraviolet imaging data of the monitoring area, and removes noise, contrast stretching image enhancement and image segmentation processing through Gaussian filtering. The third extraction unit detects the fluorescence signal area in the second ultraviolet imaging data through image processing technology, calculates each fluorescence intensity, and generates a fluorescence intensity map. The third calculation unit performs in-depth calculation and analysis based on the fluorescence intensity map to obtain the second fluorescence signal value xhz2 and the water shortage distribution index Qs. The disease index evaluation is dynamically adjusted according to the real-time fluorescence signal and the water shortage state, providing a more comprehensive and accurate crop health status monitoring result, and improving the flexibility and adaptability of the monitoring system. The present invention realizes accurate error calibration through the first calibration module. The detection error can be analyzed and calibrated according to the set error threshold. By accurately calculating the first error index wczs, the error in the detection process can be discovered in time. By comparing and analyzing the error threshold W with the first error index wczs, it can effectively determine whether the current detection error is within an acceptable range. When the detection error is abnormal, the gain and exposure time of the photodetector are dynamically adjusted through the first calibration unit to ensure the accuracy of the detection result. When the first error index wczs> error threshold W, the first calibration unit automatically increases the gain of the front-end amplifier of the photodetector by 5% and increases the exposure time by 5%. Through automated adjustment, the sensitivity and response time of the detection equipment are improved, thereby improving the accuracy and reliability of crop pest and disease detection.

[0130] Example 5: This example is explained in Example 1. Figure 1 Specifically, the second calibration module includes a fourth acquisition unit, a fourth temperature impact calculation unit and a fourth evaluation unit. The fourth acquisition unit is used to use a temperature sensor to collect air temperature data of the detection area in real time, and collect the air temperature Wd of the i-th sampling point. i The temperature gradient index Wd is calculated by the fourth calculation unit using the following formula: zs :

[0131]

[0132] Where Wd i is the air temperature at the i-th sampling point, Wd i-1 is the air temperature of the adjacent previous sampling point, d is the distance between sampling points, and M is the total number of sampling points;

[0133] The fourth evaluation unit is used to preset a temperature threshold WD and compare the temperature threshold WD with the temperature gradient index Wd zs Compare and obtain the air temperature impact results, including:

[0134] When the temperature gradient index Wd zs >Temperature threshold WD, indicating that the current ambient air temperature gradient changes abnormally and needs to trigger the second calibration instruction;

[0135] When the temperature gradient index Wd zs ≤ temperature threshold WD, indicating that the current ambient air temperature gradient changes normally and no calibration is required.

[0136] The second calibration module also includes a second calibration unit, which is used to adjust the parameters of the photodetector after receiving the second calibration instruction, including increasing the gain of the current photodetector front-end amplifier by 3% and increasing the exposure time of the photodetector photosensitive element by 3%, and adjusting the black level of the photodetector so that the black level offset = 0.1.

[0137] In this embodiment, the air temperature data of the detection area is collected in real time by the temperature sensor to ensure the timeliness and accuracy of the data. The temperature gradient index is calculated to monitor the temperature change in real time to ensure dynamic monitoring of the temperature change.

[0138] By comparing the temperature gradient index with the preset temperature threshold, abnormal temperature changes can be detected in time, reducing the impact of ambient temperature on the detection results of the photodetector. When the temperature gradient index exceeds the preset threshold, the second calibration instruction is triggered, and the detection parameters are automatically calibrated by adjusting the gain, exposure time and black level offset of the photodetector to improve the detection accuracy. By evaluating the changes in the air temperature gradient, calibration can be performed in time when the ambient temperature changes greatly, ensuring the stable operation of the system in different temperature environments. The automatic calibration mechanism can effectively reduce the detection errors caused by ambient temperature changes and improve the overall stability and reliability of the system.

[0139] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0140] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and the inventive concept of the present invention, make equivalent replacement or change, which should be covered within the protection scope of the present invention.

Claims

1. A photoelectric detector system based on environmental perception and adjustment, characterized in that: It includes a preselected calibration environment module, a first environment perception module, a second data acquisition module, a third perception module, a first calibration module, a second calibration module and an error verification module; The preselected calibration environment module is used to divide the preselected crop planting area into a plurality of monitoring areas, each monitoring area being planted with the same crop or crops at the same growth stage; The first environment perception module is used to collect the light brightness L, air humidity S and soil moisture content H of the monitoring area in real time to construct the perception condition coefficient Gzx; A condition threshold Q is preset, and when the perception condition coefficient Gzx ≥ the condition threshold Q, the photoelectric detector is triggered to switch to the first mode, and a visible light filter is used; when the perception condition coefficient Gzx < the condition threshold Q, the photoelectric detector is triggered to switch to the second mode, and an infrared filter is used; The first environment perception module includes a first acquisition unit and a first calculation unit; The first acquisition unit is used to connect the photoelectric detector to the brightness sensor, air humidity sensor and soil moisture sensor in the monitoring area, collect and obtain the light brightness L, air humidity S and soil moisture content H of the monitoring area in real time, establish a first environmental condition data set, and preprocess the first environmental condition data set, the preprocessing includes data cleaning, data smoothing and data standardization; The first calculation unit is used to perform linear normalization processing on the light illuminance L, air humidity S and soil moisture content H, and map the corresponding data values ​​to the interval [0, 1], and construct the perception condition coefficient Gzx according to the following method: where \(i = 1, 2, \ldots, n\), \(n\) is the number of sampling frequencies, set to be collected once per second, \(L\) i represents the illumination brightness of the \(i\)-th sampling node, \(S\) i represents the air humidity of the \(i\)-th sampling node, \(H\) i represents the soil moisture content of the \(i\)-th sampling node, is the qualified threshold of illumination brightness, is the qualified threshold of brightness; is the qualified threshold of soil moisture content; \(F1\), \(F2\) and \(F3\) are weight coefficients: \(0 \lt F1 \lt 1\), \(0 \lt F2 \lt 1\), \(0 \lt F3 \lt 1\), and \(F1 + F2 + F3 = 1\); The second data acquisition module is used to, when the photoelectric detector switches to the first mode, indicate that when the relative fluctuation of the environmental condition index HJ is normal, obtain the first thermal imaging data of the crops in the monitoring area through the photoelectric detector monitoring, and extract the crop pests and damage characteristics in the first thermal imaging data through image recognition technology, and obtain the following through deep calculation and analysis: the first temperature signal value xhz1, the hot spot area index Rb and the first disease index Bhzs1. When the first disease index Bhzs1 exceeds the first defect threshold value X, it triggers the switching of the photoelectric detector to the third mode, and uses the ultraviolet filter; The second data acquisition module includes a second acquisition unit, a second extraction unit and a second calculation unit; The second acquisition unit is used to acquire first thermal imaging data of crops in the monitoring area through the photoelectric detector when the photoelectric detector switches to the first mode; The second extraction unit is used to first perform denoising, contrast enhancement and image segmentation on the first thermal imaging data, apply a convolutional neural network to establish a recognition model and train it, extract the crop pests and diseases and damaged features in the first thermal imaging data by using a temperature threshold WD method or a K-means clustering algorithm, match the extracted features with the features in the trained recognition model, identify specific pests and diseases and damaged features, obtain a first matching result and classify and label it; The second calculation unit is used to perform in-depth analysis on the first matching result, and obtain the first temperature signal value xhz1 and the hot spot area index Rb by calculating through the following formula: Where M is the total number of sampling points, S i (T) represents the response signal intensity of the crop surface temperature T of the photodetector at the i-th sampling point; In the formula, A hot is the total area of ​​the hot spot region, A total is the total area of ​​crop leaves in the monitoring area, N hot is the total number of sampling points in the hot spot area; S j (T) is the temperature T response signal of the photodetector at the sampling point of the jth hot spot area; The first temperature signal value xhz1 is associated with the hot spot area index Rb, and the defect characteristics of crop leaves are collected to obtain the first disease index Bhzs1 through the following associated formula: In the formula, Yd i Indicates the roundness value of the i-th sampling point, A i represents the area of ​​the i-th leaf, p i represents the perimeter of the i-th leaf. If Yd i <1, it means there is a missing part, Yd avg Indicates the roundness value threshold of healthy crops; a1, a2 and a3 are weight coefficients, which are adjusted and set by the user; The third sensing module is used to switch the photoelectric detector to the third mode, re-monitor the same monitoring area to obtain the second ultraviolet imaging data, extract the fluorescence characteristics of the second ultraviolet imaging data, and perform in-depth calculation and analysis to obtain: the second fluorescence signal value xhz2, the water shortage distribution index Qs and the second disease index Bhzs2; The third perception module includes a third acquisition unit, a third extraction unit and a third calculation unit; The third acquisition unit is used to repeatedly acquire the second ultraviolet imaging data from the same monitoring area after the photoelectric detector switches to the third mode, and perform Gaussian filtering to remove noise, contrast stretching image enhancement and image segmentation processing on the second ultraviolet imaging data; The third extraction unit is used to detect the fluorescence signal area in the second ultraviolet imaging data by image processing technology, and calculate each fluorescence intensity to generate a fluorescence intensity map; The third calculation unit is used to perform in-depth calculation and analysis according to the fluorescence intensity map to obtain the second fluorescence signal value xhz2 and the water shortage distribution index Qs. The second fluorescence signal value xhz2 is calculated and obtained by the following formula: Where M is the total number of sampling points, Y i represents the average fluorescence intensity of the photodetector in the ith fluorescence signal area, I ig represents the fluorescence intensity of the g-th pixel in the i-th fluorescence signal area, E i Indicates the total number of pixels in the area; The method for obtaining the water shortage distribution index Qs is to set the fluorescence intensity water shortage threshold Y f , below the fluorescence intensity water shortage threshold Y f Marked as water-scarce area B i , B i The identification formula is: B i ={i|Y i <Y f |}; In the formula, B i represents the area of ​​the i-th water-deficient region, D represents the set of all identified water-deficient regions, and Y dry is the total area of ​​water-scarce regions, A total is the total area of ​​crop leaves in the monitoring area; The second fluorescence signal value xhz2 is associated with the water shortage distribution index Qs, and the second disease index Bhzs2 is calculated by the following formula: Where Y normal Indicates the normal fluorescence intensity threshold of healthy crops; a4, a5 and a6 are weight coefficients, which are adjusted and set by the user; The first calibration module is used to calculate the difference between the second disease index Bhzs2 and the first disease index Bhzs1 to obtain the first error index wczs, and compare and analyze the first error index wczs with the error threshold W. When the first error index wczs is greater than the error threshold W, the second fluorescence signal value xhz2 is subjected to a first calibration, including: increasing the gain of the current photodetector front-end amplifier by 5% and increasing the exposure time of the photodetector photosensitive element by 5%; The second calibration module is used to collect the temperature gradient characteristics of the monitoring area through the temperature sensor and construct the temperature gradient index Wd zs , when the temperature gradient index Wd zs If the temperature signal value xhz1 is greater than the temperature threshold WD, a second calibration is performed on the first temperature signal value xhz1 to adjust the parameters of the photodetector, including increasing the gain of the current photodetector front-end amplifier by 3% and increasing the exposure time of the photodetector photosensitive element by 3%, and adjusting the black level of the photodetector so that the black level offset = 0.1; The error verification module recalculates the first error index wczs. When the first error index wczs still exceeds the error threshold W, the process of the second data acquisition module, the third perception module, the first calibration module and the second calibration module is repeated until the first error index wczs is lower than the error threshold W.

2. The photoelectric detector system based on environmental perception and adjustment according to claim 1, characterized in that: The first environment perception module also includes a first evaluation unit and a first adjustment unit; The first evaluation unit is used to preset a condition threshold Q, and compare and analyze the perception condition coefficient Gzx with the condition threshold Q to obtain a first environmental perception evaluation result, including: When the perception condition coefficient Gzx ≥ the condition threshold Q, indicating that the current monitoring area environmental conditions of light, humidity and soil moisture are normal, the first mode is switched, and the photoelectric detector is controlled to use a visible light filter through the first adjustment unit; When the perception condition coefficient Gzx is less than the condition threshold Q, indicating that the current monitoring area environmental conditions of light, humidity and soil moisture are abnormal, the second mode is triggered to switch, and the photoelectric detector is controlled to use an infrared filter through the first adjustment unit.

3. The photoelectric detector system based on environmental perception and adjustment according to claim 1, characterized in that: The second data acquisition module also includes a second evaluation unit and a second adjustment unit; The second evaluation unit is used to preset a first defect threshold value X, and compare the first disease index Bhzs1 with the first defect threshold value X to obtain a second defect evaluation result, including: When the first disease index Bhzs1> the first defect threshold X, indicating that the current crop diseases and insect pests and defects are abnormal, the third mode is triggered to switch, and the photoelectric detector is controlled to use an ultraviolet filter through the second adjustment unit; When the first disease index Bhzs1 ≤ the first defect threshold X, it means that the current crops are free from diseases, pests and damage defects, and no adjustment is performed.

4. The photoelectric detector system based on environmental perception and adjustment according to claim 1, characterized in that: The first calibration module includes a difference calculation unit and a first calibration unit, and the difference calculation unit is used to calculate and obtain the first error index wczs by the following formula: wczs=Bhzs2-Bhzs1; The error threshold W is preset, and the error threshold W is compared and analyzed with the first error index wczs to obtain the following error evaluation results, including: When the first error index wczs>error threshold W, it indicates that the error of the detection index of pests and diseases is abnormal in the same detection area, and the second fluorescence signal value xhz2 is calibrated by the first calibration unit, including: increasing the gain of the front-end amplifier of the current photodetector by 5% and increasing the exposure time of the photosensitive element of the photodetector by 5%; When the first error index wczs≤error threshold W, it means that the error of the detection index of pests and diseases in the same detection area is normal and no calibration is required.

5. The photoelectric detector system based on environmental perception and adjustment according to claim 4, characterized in that: The second calibration module includes a fourth acquisition unit, a fourth temperature impact calculation unit and a fourth evaluation unit. The fourth acquisition unit is used to use a temperature sensor to collect air temperature data of the detection area in real time, and collect the air temperature Wd of the i-th sampling point. i The temperature gradient index Wd is calculated by the fourth calculation unit using the following formula: zs : Where Wd i is the air temperature at the i-th sampling point, Wd i-1 is the air temperature of the adjacent previous sampling point, d is the distance between sampling points, and M is the total number of sampling points; The fourth evaluation unit is used to preset a temperature threshold WD and compare the temperature threshold WD with the temperature gradient index Wd zs Compare and obtain the air temperature impact results, including: When the temperature gradient index Wd zs >Temperature threshold WD, indicating that the current ambient air temperature gradient changes abnormally and needs to trigger the second calibration instruction; When the temperature gradient index Wd zs ≤ temperature threshold WD, indicating that the current ambient air temperature gradient changes normally and no calibration is required.

6. The photoelectric detector system based on environmental perception and adjustment according to claim 5, characterized in that: The second calibration module also includes a second calibration unit, which is used to adjust the parameters of the photodetector after receiving the second calibration instruction, including increasing the gain of the current photodetector front-end amplifier by 3% and increasing the exposure time of the photodetector photosensitive element by 3%, and adjusting the black level of the photodetector so that the black level offset = 0.1.

Images