LED light source control method and system for inhibiting pests

Abstract

The invention discloses an LED light source control method and system for inhibiting pests, and relates to the field of light control, and the method comprises the steps: obtaining the current environment data and image data around a target plant, recognizing a hot spot region of the pests based on the data, and matching a proper initial light source parameter according to the region area and density, according to the method, the pest gathering area can be identified, response can be made in time when the environment changes by dynamically adjusting the light source parameters, effective control and repelling of the pests are kept, and the pest repelling effect is improved.

Description

Technical Field

[0001] The present application relates to the field of lighting control, and in particular to a method and system for controlling an LED light source for inhibiting pests. Background Art

[0002] With the development of agricultural production, pests are becoming more and more threatening to crops. Although traditional chemical pesticides are effective in controlling pests, long-term use will lead to increased resistance of pests and adverse effects on the environment and human health. Therefore, finding an environmentally friendly and efficient pest control method has become an important research direction in the agricultural field.

[0003] At present, technical solutions for controlling pests through physical means are gradually gaining attention. For example, the method of using light sources with specific wavelengths to repel pests has been applied in some agricultural production. These technical solutions usually set up LED light sources with specific wavelengths in the target area, and change the irradiation intensity and frequency of the light source to affect the behavior of pests, thereby achieving the purpose of controlling pests. However, this method cannot switch the LED light source parameters in time when the environment changes, resulting in poor pest repelling effect. Summary of the invention

[0004] The present application provides a method and system for controlling an LED light source for inhibiting pests, so as to improve the effect of pest control.

[0005] In a first aspect, the present application provides an LED light source control method for suppressing pests, which is applied to an LED light source control system, the method comprising: acquiring current environmental data and image data around a target plant; identifying a pest hotspot area based on the current environmental data and the image data; identifying the area and density of the pest hotspot area; matching corresponding initial light source parameters based on the area and the density; calculating current environmental parameters based on the current environmental data, and correcting the initial light source parameters based on the current environmental parameters to obtain preset light source parameters; and irradiating the pest hotspot area according to the preset light source parameters.

[0006] By adopting the above technical scheme, by acquiring the current environmental data and image data around the target plant, and identifying the hot spots of pests based on these data, and matching appropriate initial light source parameters according to the area and density of the area, and taking into account the influence of environmental factors, the initial light source parameters are corrected based on the basic environmental data to obtain preset light source parameters. This method can identify the area where pests gather, and by dynamically adjusting the light source parameters, it can respond in time to environmental changes, maintain effective control and expulsion of pests, and improve the effect of pest expulsion.

[0007] In combination with some embodiments of the first aspect, in some embodiments, the step of identifying the pest hotspot area based on the current environmental data and the image data specifically includes: extracting features from the image data to obtain the location of the pests; searching for pest activity patterns corresponding to the current environmental data in a preset pest database, and planning pest gathering areas based on the pest activity patterns; and performing image fusion of the pest location and the pest gathering area to obtain the pest hotspot area.

[0008] By adopting the above technical scheme, a method for identifying pest hotspots through image data feature extraction and the use of a preset pest database can accurately locate the position of pests by extracting features from image data, and plan out the gathering areas of pests in combination with preset pest activity patterns. By fusing the images of the pest locations and the pest gathering areas, more accurate hotspots can be obtained, which can improve recognition accuracy and efficiency and ensure accurate positioning of pest hotspots.

[0009] In combination with some embodiments of the first aspect, in some embodiments, the step of identifying the area and density of the pest hotspot area specifically includes: calculating the area of ​​the pest hotspot area based on the image data; analyzing the color distribution and texture complexity of the pest hotspot image, which is the pest part in the image data; and calculating the density of the pest hotspot area based on the color distribution and the texture complexity.

[0010] By adopting the above technical solution, by calculating the area of ​​the region in the image data, the specific size of the pest hotspot area can be accurately known, and by analyzing the color distribution and texture complexity of the pest hotspot image, the pest density can be evaluated, which is more comprehensive and accurate than the evaluation of a single indicator, and can better reflect the actual situation of the pest hotspot area, ensuring the pertinence and effectiveness of light source control and improving the effect of pest control.

[0011] In combination with some embodiments of the first aspect, in some embodiments, the step of calculating the current environmental parameters based on the current environmental data, and correcting the initial light source parameters based on the current environmental parameters to obtain preset light source parameters specifically includes: inputting the current environmental data into a preset environmental parameter calculation model to obtain the current environmental parameters, the current environmental data including temperature, humidity, light intensity and wind speed, and the current environmental parameters including temperature parameters, humidity parameters, light intensity parameters and wind speed parameters; correcting the irradiation time in the initial light source parameters according to the temperature parameters, correcting the light source wavelength parameters in the initial light source parameters according to the humidity parameters, correcting the light source intensity parameters in the initial light source parameters according to the light intensity parameters, and correcting the irradiation range parameters in the initial light source parameters according to the wind speed parameters to obtain preset light source parameters.

[0012] By adopting the above-mentioned technical scheme, the current environmental parameters are calculated according to the current environmental data, and the initial light source parameters are corrected according to these environmental parameters, and finally a method for obtaining preset light source parameters is obtained. By inputting environmental data such as temperature, humidity, light intensity and wind speed into the preset environmental parameter calculation model, more accurate current environmental parameters can be obtained, so that the light source control system can dynamically adjust the light source parameters according to the actual environmental conditions, thereby improving the accuracy and effectiveness of light source control.

[0013] In combination with some embodiments of the first aspect, in some embodiments, after the step of illuminating the pest hotspot area according to the preset light source parameters, the method also includes: acquiring the latest environmental data and the latest image around the target plant; identifying the latest pest area based on the latest environmental data and the latest image; calculating the pest distribution change index based on the latest pest area and the pest hotspot area; when the pest distribution change index is greater than a first change threshold, increasing the illumination range parameters to the first illumination range.

[0014] By adopting the above technical solution, the latest environmental data and images are obtained, the latest pest areas are identified, and the pest distribution change index is calculated. Through this real-time monitoring and feedback mechanism, the pest control effect can be dynamically adjusted. When the pest distribution change index is greater than the first change threshold, the irradiation range parameter is increased to the first irradiation range to cover a larger area, effectively compensating for the control blind spots that may be caused by a single adjustment, and ensuring the continuous and efficient suppression of pests by the light source control system.

[0015] In combination with some embodiments of the first aspect, in some embodiments, it is characterized in that after the step of calculating the pest distribution change index based on the latest pest area and the pest hotspot area, the method also includes: when the pest distribution change index is less than the second change threshold, increasing the light source intensity parameter to the first light source intensity.

[0016] By adopting the above technical solution, when the pest distribution change index is less than the second change threshold, the light source intensity parameter is increased to the first light source intensity. By continuously monitoring the pest hotspot area and dynamically adjusting the light source intensity, the illumination intensity of the light source can be enhanced when the pest distribution does not change much, so as to ensure effective control of the pests. This not only improves the flexibility and adaptability of the light source control, but also can further inhibit the growth of pests by increasing the light source intensity when the pest distribution changes little, so as to prevent the pests from re-aggregating and spreading.

[0017] In combination with some embodiments of the first aspect, in some embodiments, after the step of calculating the pest distribution change index based on the latest pest area and the pest hotspot area, the method also includes: when the pest distribution change index is not greater than the first change threshold and not less than the second change threshold, increasing the light source intensity parameter to the first light source intensity.

[0018] By adopting the above technical solution, when the pest distribution change index is not greater than the first change threshold and not less than the second change threshold, the light source intensity parameter is increased to the first light source intensity. By accurately monitoring the changes in pest distribution, when the pest distribution changes are not significant but there is still a certain degree of activity, the light source intensity is timely enhanced for more effective suppression. This allows for more flexible response to the actual situation of pest distribution, and by enhancing the light source intensity, a stronger interference and suppression effect can be produced on pests.

[0019] In a second aspect, an embodiment of the present application provides an LED light source control system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the LED light source control system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0020] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when executed on an LED light source control system, enables the LED light source control system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions. When the instructions are executed on an LED light source control system, the LED light source control system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0022] It can be understood that the LED light source control system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The present application obtains the current environmental data and image data around the target plant, identifies the pest hotspots based on these data, matches the appropriate initial light source parameters according to the area and density of the area, and corrects the initial light source parameters based on the environmental data in consideration of the influence of environmental factors to obtain preset light source parameters. This method can identify the pest gathering areas, and by dynamically adjusting the light source parameters, can respond in time to environmental changes, maintain effective control and expulsion of pests, and improve the effect of pest expulsion.

[0024] 2. The present application discloses a method for identifying pest hotspots through feature extraction of image data and use of a preset pest database. By extracting features from image data, the position of pests can be accurately located, and the gathering areas of pests can be planned out in combination with preset pest activity patterns. By fusing the images of pest locations and pest gathering areas, more accurate hotspots can be obtained, which can improve recognition accuracy and efficiency and ensure accurate positioning of pest hotspots.

[0025] 3. The present application calculates the current environmental parameters based on the current environmental data, and corrects the initial light source parameters based on these environmental parameters to finally obtain the method of preset light source parameters. By inputting environmental data such as temperature, humidity, light intensity and wind speed into the preset environmental parameter calculation model, more accurate current environmental parameters can be obtained, so that the light source control system can dynamically adjust the light source parameters according to the actual environmental conditions, thereby improving the accuracy and effectiveness of light source control. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of a method for controlling an LED light source for inhibiting pests in an embodiment of the present application; Figure 2 is another flow chart of the LED light source control method for inhibiting pests in an embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a physical device of the LED light source control system in the embodiment of the present application. DETAILED DESCRIPTION

[0027] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0028] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0029] For ease of understanding, the following is a description of the process of the method provided by this implementation. Figure 1 , is a flow chart of a method for controlling an LED light source for inhibiting pests in an embodiment of the present application.

[0030] S101, obtaining current environmental data and image data around a target plant.

[0031] Among them, the target plant refers to the specific plant or crop that needs pest control; the current environmental data refers to the environmental parameters around the target plant at the moment of acquisition, such as temperature, humidity, light intensity, etc.; the image data is used to represent the visual information of the target plant and its surrounding area, which can be a static picture or a dynamic video.

[0032] This step is usually performed when the pest control system is started or regularly at preset time intervals. Specifically, the system first determines the location of the target plant, and then uses various sensors to collect environmental data around the target plant, including but not limited to temperature, humidity, light intensity, wind speed, etc. At the same time, the system also collects image or video data of the target plant and its surrounding area through camera equipment. These data will provide the necessary information basis for the subsequent identification of pest hotspots.

[0033] In some embodiments, environmental data and image data can be acquired in a variety of ways: optionally, multiple environmental sensors and high-definition cameras can be arranged around the target plant, and these devices transmit data to the central processing unit in real time through a wireless network; multiple sensor nodes can be set up, each node contains a temperature and humidity sensor, a light sensor, and a micro camera, and these nodes form a sensor network that works together to collect data; drones equipped with multiple sensors can be used to cruise in the target area to collect environmental data and aerial images. It is understandable that other methods can also be used to acquire data, such as using satellite remote sensing technology or ground mobile robots, etc., which are not limited here.

[0034] S102: Identify pest hotspots according to the current environment data and the image data.

[0035] Among them, pest hotspots refer to areas where pests are densely distributed or active; identification refers to determining the location and scope of pest hotspots by analyzing and processing the acquired data.

[0036] This step is performed immediately after acquiring environmental data and image data. Specifically, the system first pre-processes the acquired image data, such as denoising and contrast enhancement. Then, the image recognition algorithm is used to analyze the processed image to identify areas where pests may exist. At the same time, the system will combine the current environmental data, such as temperature, humidity, etc., and through comprehensive analysis of the image recognition results and environmental data, the system will ultimately determine the location and range of the pest hotspot area.

[0037] In some embodiments, pest hotspots can be identified in a variety of ways: optionally, a deep learning model, such as a convolutional neural network (CNN), can be used to analyze image data, identify the location and number of pests, and then determine hotspots in combination with a density clustering algorithm; a knowledge base containing different pest species and living environment conditions can be established, and the acquired environmental data can be matched with the information in the knowledge base to predict areas where pests may exist, and then verified by image analysis; time series analysis can be used to compare image data at different time points to identify areas where the number of pests has increased significantly or the activity has increased significantly as hotspots. It is understandable that other methods can also be used to identify hotspots, such as using an expert system or combining field survey data, etc., which are not limited here.

[0038] S103, identifying the area and density of the pest hotspot area.

[0039] Among them, pest hotspots refer to areas where pests are concentrated or active; regional area refers to the spatial size of pest hotspots, usually measured in square meters or square centimeters; density is used to indicate the number or distribution density of pests per unit area, reflecting the degree of pest aggregation. The identification process refers to determining the specific values ​​of these parameters through analysis and calculation.

[0040] This step is usually performed immediately after the pest hotspot area is determined, and it is a key link in providing basic data for subsequent light source parameter matching. Specifically, the system first accurately locates and divides the boundaries of the identified pest hotspot area, and then uses image processing technology to calculate the actual area of ​​the area. Next, the system analyzes the image features in the hotspot area, such as color distribution, texture complexity, etc., and combines the morphological characteristics and behavior patterns of the pests to estimate the number and distribution of pests in the area. By combining the number of pests with the area of ​​the region, the system can calculate the density of pests, usually expressed as the number of pests per unit area.

[0041] In some embodiments, the area and density of pest hotspots can be identified in a variety of ways: Optionally, an image segmentation algorithm can be used to accurately divide the hotspot area, and then the pixel counting method can be used to calculate the area of ​​the area; then a target detection algorithm can be used to identify and count individual pests in the area; finally, the total number of pests is divided by the area of ​​the area to obtain the density. Optionally, a deep learning model, such as a fully convolutional network (FCN), can be used to directly learn and predict the distribution density map of pests from the image; then the total area and the total number of pests are calculated by an integral method; finally, the average density is calculated as the density. It is understandable that other methods can also be used to identify the area and density, such as using three-dimensional imaging technology combined with volume analysis, or combining multimodal information fusion methods such as pest sound detection, which are not limited here.

[0042] S104: Match corresponding initial light source parameters according to the area and the density.

[0043] Among them, the initial light source parameters refer to the initial settings used to control the LED light source, including the wavelength, intensity, irradiation time and irradiation range of the light source; matching means selecting appropriate light source parameters according to the characteristics of the pest hotspot area; correspondence means that there is a certain correlation between the initial light source parameters and the area and density of the area.

[0044] This step is performed after determining the area and density of the pest hotspot, and is a key link in achieving precise pest control. Specifically, the system first accesses a pre-established parameter matching database, which contains recommended light source parameters for different areas and densities. The system then inputs the identified area and density into the matching algorithm, which considers multiple factors, such as pest type, plant type, seasonal changes, etc., and selects the most suitable initial light source parameters after comprehensive analysis. These parameters typically include the wavelength range of the light source (affecting the attraction or repelling effect on pests), light intensity (affecting the effective range of action), irradiation time (affecting energy efficiency and plant growth), and irradiation range (ensuring coverage of the entire hotspot area).

[0045] In some embodiments, the matching of initial light source parameters can be achieved in a variety of ways: Optionally, a rule-based expert system can be used to directly derive initial parameters based on preset parameter matching rules, such as "If the area is greater than X square meters and the density is greater than Y / square meter, then select a wavelength of A-Bnm, an intensity of C lumens, and an irradiation time of D hours"; then fine-tune these parameters to suit the specific situation; and finally output the final initial light source parameters. Optionally, a machine learning method, such as a support vector machine (SVM) or a random forest, can be used to train a parameter prediction model; using features such as area and density as input to predict the optimal light source parameters; then optimizing the model performance through cross-validation; and finally using the optimized model for real-time parameter matching. It is understandable that other methods can also be used to achieve parameter matching, such as using a genetic algorithm to dynamically optimize parameter combinations, or combining reinforcement learning methods to continuously adjust and improve matching strategies, which are not limited here.

[0046] S105 , calculating current environment parameters according to the current environment data, and correcting the initial light source parameters according to the current environment parameters to obtain preset light source parameters.

[0047] Among them, current environmental data refers to the real-time environmental information around the target plants, such as temperature, humidity, light intensity, etc.; current environmental parameters refer to environmental indicators after processing and calculation, which are used to quantify the impact of environmental factors on pest behavior; initial light source parameters refer to the LED light source settings preliminarily determined based on the characteristics of the pest hotspot area; correction refers to the adjustment of light source parameters based on environmental factors; preset light source parameters refer to the final light source settings after adjustment for environmental factors, which are used to actually control the LED light source.

[0048] This step is performed after obtaining the initial light source parameters in order to make the light source parameters more adaptable to the actual environmental conditions and improve the effect of pest control. Specifically, the system first inputs the collected current environmental data into the preset environmental parameter calculation model. The model takes into account the comprehensive impact of factors such as temperature, humidity, light intensity and wind speed on pest activity, and outputs quantified environmental parameters. Then, the system corrects the initial light source parameters according to these environmental parameters. For example, the irradiation time is adjusted according to the temperature parameter, the light source wavelength is adjusted according to the humidity parameter, the light source intensity is adjusted according to the light intensity parameter, and the irradiation range is adjusted according to the wind speed parameter. This correction ensures that the light source parameters can better adapt to the current environmental conditions and improve the control effect of pests.

[0049] In some embodiments, environmental parameter calculation and light source parameter correction can be achieved in a variety of ways: Optionally, a multivariate linear regression model can be used to calculate environmental parameters, with environmental data such as temperature and humidity as independent variables and environmental parameters as dependent variables; then a mapping relationship between environmental parameters and light source parameters is established, such as the irradiation time increases by 5 minutes for every 1 degree increase in temperature; then the initial light source parameters are adjusted according to the mapping relationship; finally, the preset light source parameters are obtained by combining various adjustments. Optionally, a fuzzy logic control system can be used, first converting environmental data into fuzzy sets; then inferring the degree of influence of the environment on the light source parameters according to preset fuzzy rules; then using a defuzzification method to obtain specific correction values; finally, applying the correction values ​​to the initial light source parameters to obtain preset light source parameters. It is understandable that other methods can also be used to achieve environmental parameter calculation and light source parameter correction, such as using a neural network to directly learn the mapping of environmental data to light source parameters, or combining time series analysis to predict short-term environmental changes and adjust parameters in advance, which is not limited here.

[0050] S106, irradiating the pest hotspot area according to the preset light source parameters.

[0051] Among them, the preset light source parameters refer to the final LED light source control parameters after adjustment of environmental factors, including wavelength, intensity, irradiation time and range, etc.; the pest hotspot area refers to the area where the identified pests are densely distributed or active; irradiation refers to the use of LED light source to illuminate the target area according to preset parameters, with the aim of inhibiting or interfering with the growth and activity of pests.

[0052] This step is the final execution stage of the entire pest control process, and is usually performed immediately after all parameter calculations and adjustments are completed. Specifically, the system first sets the various parameters of the LED light source according to the preset light source parameters, including adjusting the wavelength range of the light source, setting the light intensity, planning the irradiation time, and determining the irradiation range. Then, the system controls the LED light source equipment to aim at the identified pest hotspot area. Then, the irradiation process starts according to the preset time plan. During the irradiation process, the system may monitor the lighting effects and environmental changes in real time and make fine adjustments when necessary. The entire irradiation process aims to interfere with the physiological rhythm, reproductive behavior or phototaxis of pests through light of specific wavelengths and intensities, thereby achieving the purpose of inhibiting pest growth and activity.

[0053] In some embodiments, irradiation of pest hotspots can be achieved in a variety of ways: Optionally, a programmable LED array can be used. First, the wavelength and intensity of each LED unit are configured according to the preset light source parameters; then the direction of the LED array is precisely adjusted through the motor control system to ensure that the entire pest hotspot area is covered; then the timer is started to control the switch of the LED according to the preset irradiation time; finally, during the irradiation process, the light intensity is monitored in real time using a light sensor, and a stable lighting effect is maintained through feedback control. Optionally, an intelligent lighting system can be used. First, the preset light source parameters are input into the central control unit; then the unit coordinates multiple distributed LED light sources, each of which is responsible for irradiating a specific area; then the system dynamically adjusts the irradiation angle and range of each light source according to the shape of the pest hotspot area; finally, the working status of each light source is monitored in real time through a wireless network to ensure continuous and effective irradiation.

[0054] The following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the LED light source control method for inhibiting pests in an embodiment of the present application.

[0055] S201, obtaining current environmental data and image data around a target plant.

[0056] It can be understood that this step is similar to step S101 and will not be described in detail here.

[0057] S202: Extract features from the image data to obtain the location of the pests.

[0058] Image data refers to the visual information of the target plant and its surrounding area collected by a camera, which can be a static picture or a dynamic video sequence. Feature extraction means identifying and extracting key visual features that can characterize the presence of pests from image data, such as shape, color, texture, etc. The location of the pest refers to the specific location or area where the pest appears in the image coordinate system.

[0059] When the LED light source control system performs this step, it first preprocesses the acquired image data, including operations such as denoising, contrast enhancement, and color correction to improve image quality. The system then applies a series of computer vision algorithms to extract features from the image. This may include using edge detection algorithms to identify the outline of pests, color segmentation algorithms to distinguish pests from the background, and texture analysis algorithms to capture surface features unique to pests. After feature extraction, the system uses object detection or instance segmentation algorithms to accurately locate the location of pests in the image. The specific implementation can use deep learning models such as YOLO (You Only Look Once) or Mask R-CNN, which have been trained with a large amount of pest image data and can quickly and accurately identify and locate pests in the image. Finally, the system converts the recognition results into actual spatial coordinates to provide precise location information for subsequent pest control.

[0060] S203: searching a preset pest database for pest activity patterns corresponding to the current environmental data, and planning pest gathering areas according to the pest activity patterns.

[0061] Among them, the preset pest database is a comprehensive data set containing various pest biological characteristics, behavior patterns and environmental response information. Current environmental data refers to the real-time environmental parameters of the target area, such as temperature, humidity, light intensity, etc. Pest activity patterns refer to the behavior patterns and distribution characteristics of pests under specific environmental conditions. Pest gathering areas refer to areas where pests are likely to gather in large numbers according to the activity patterns.

[0062] In this step, the LED light source control system will first use the currently collected environmental data as a query condition to access the preset pest database. This database is usually established based on long-term field observations and laboratory studies, and contains the activity patterns of various pests under different environmental conditions. The system will use data matching algorithms, such as nearest neighbor search or decision trees, to find the historical records most similar to the current environment and extract the corresponding pest activity patterns. These patterns may include information such as the daily activity cycle, phototropism, and temperature sensitivity of pests. Next, the system will combine these activity patterns with the pest location information obtained in the previous step and use spatial analysis algorithms to plan possible pest gathering areas. The specific implementation can use heat map generation technology to mark areas with high pest occurrence frequency as hotspots, or use clustering algorithms such as DBSCAN (density-based clustering algorithm) to identify areas with dense pest distribution. In addition, the system may also consider terrain features, plant distribution, and microclimate factors to optimize the prediction of gathering areas through a multi-factor weighted model. Finally, the system will generate a probability distribution map of pest gathering areas, providing an important basis for subsequent precise light source control.

[0063] S204: Fusing the images of the location of the pest and the pest gathering area to obtain the pest hotspot area.

[0064] Among them, the location of pests refers to the actual location of pests at the current moment determined by image analysis. Pest gathering areas refer to areas where pests are likely to gather in large numbers based on environmental data and activity patterns. Image fusion refers to the integration of image information from two or more different sources to form a more comprehensive and accurate image representation. Pest hotspots refer to the integrated areas obtained after fusion, which represent the actual distribution and predicted gathering of pests.

[0065] In this step, the LED light source control system first converts the pest location information and predicted pest gathering area information obtained in the previous step into a visual image representation. This usually involves converting discrete location points and probability distribution maps into pixel-level image data. The system then applies an image fusion algorithm to integrate the two types of information. The specific implementation can use multi-resolution analysis methods, such as wavelet transform fusion, to effectively combine information at different scales; or use a pixel-based weighted average method to assign weights according to the reliability of each source. Another feasible method is to use a deep learning model, such as a conditional generative adversarial network (cGAN), to learn how to best fuse the two types of information. During the fusion process, the system will consider the reliability of the actual observed pest location and the uncertainty of the predicted gathering area, and dynamically adjust the fusion weight. For example, in areas with good lighting conditions and clear observations, the actual observation results may be preferred; while in areas with limited field of view, the predicted results may be more relied on. The fused image will highlight the areas where pests actually exist and potentially gather, forming a comprehensive pest hotspot area map. This hotspot map not only reflects the current distribution of pests, but also includes short-term pest activity trends predicted based on environmental factors and behavioral patterns, providing a more comprehensive decision-making basis for subsequent precise light source control.

[0066] S205: Calculate the area of ​​the pest hotspot according to the image data.

[0067] The image data refers to the digital image representation of the pest hotspot area obtained after fusion. The pest hotspot area refers to the comprehensive area where pests actually exist and may gather, determined by image fusion. The area refers to the area covered by the pest hotspot area in actual space, usually in square meters or square centimeters.

[0068] In this step, the LED light source control system will perform quantitative analysis on the fused pest hotspot image to calculate the actual area of ​​the hotspot. First, the system will binarize the image to clearly separate the hotspot from the non-hotspot. This can be achieved by setting a threshold, such as marking pixels with a heat value higher than a certain threshold as hotspots. Then, the system will use the connected domain analysis algorithm to identify and mark all hotspots. For each identified hotspot, the system will calculate the number of pixels it contains. Next, the system needs to convert the number of pixels into the actual physical area. This requires knowing the resolution of the image and the actual physical size covered, which can usually be obtained from the parameters of the image acquisition device. The system will use a pre-calibrated conversion factor to multiply the number of pixels by the actual area represented by each pixel to obtain the actual physical area of ​​the hotspot. In practical applications, the system may also need to consider the effects of image distortion and projection transformation. For example, if the image is taken by an aerial device (such as a drone), geometric correction may be required to compensate for the error caused by the perspective. In addition, if the hotspot area spans different terrains (such as flat land and slopes), the system needs to use a digital elevation model (DEM) to correct the calculation results to obtain a more accurate three-dimensional surface area. Finally, the system will convert the calculated area and perform precision control to ensure that the result meets the requirements of subsequent processing. This accurately calculated hotspot area will provide an important basis for determining the appropriate light source parameters in the next step, which will help achieve more accurate and efficient pest control.

[0069] S206: Analyze the color distribution and texture complexity of the pest hotspot image, where the pest hotspot image is the pest part in the image data.

[0070] Among them, pest hotspot images refer to the image parts extracted from the original image data, which only contain pests and their immediate surroundings. Color distribution represents the frequency of occurrence and spatial arrangement of various colors in the image, usually described by histogram or color moment. Texture complexity refers to the degree and pattern of grayscale changes in local areas of the image, reflecting the richness of details and structural complexity of the image.

[0071] In this step, the LED light source control system first segments the pest hotspot area from the overall image data to form a pest hotspot image. The system uses an image processing library (such as OpenCV) to convert the hotspot image into a color space, usually into the HSV (hue, saturation, value) space, because the HSV space is more consistent with human perception of color. Subsequently, the system calculates the color histogram and counts the pixel distribution of each color channel. In order to more accurately describe the color distribution, the system also calculates the color moment, including the first-order moment (mean), second-order moment (standard deviation), and third-order moment (skewness). These statistics provide a comprehensive description of the color distribution. For the analysis of texture complexity, the system uses a variety of texture description algorithms. First, the gray level co-occurrence matrix (GLCM) is used to calculate statistical features such as contrast, correlation, energy, and homogeneity. Secondly, the local binary pattern (LBP) algorithm is applied to capture the local texture pattern of the image. In addition, the system uses a Gabor filter bank to extract texture information of different scales and directions. These methods are used in combination to fully describe the texture characteristics of the pest hotspot image. Finally, the system stores the analysis results of color distribution and texture complexity as feature vectors to prepare for subsequent density calculations. Through these detailed image analyses, the system can obtain fine feature descriptions of pest hotspots, laying the foundation for accurate assessment of pest distribution.

[0072] S207: Calculate the density of the pest hotspot area according to the color distribution and the texture complexity.

[0073] Among them, density refers to the number or distribution density of pests per unit area, reflecting the degree of pest aggregation. It is a quantitative indicator, usually expressed in terms of the number of pests per square meter or per square centimeter.

[0074] In this step, the LED light source control system uses the color distribution and texture complexity information obtained in the previous step to calculate the density of pest hotspots through a machine learning model. First, the system uses a pre-trained regression model, such as support vector regression (SVR) or random forest regression, to take color and texture features as input and output an estimated density. This model uses a large number of sample images with known density in the training phase to learn the mapping relationship between features and density. Secondly, the system considers the characteristics of different pest species and corrects the model output. For example, for larger pests, the same color and texture features may correspond to a lower density, while for smaller pests, it may indicate a higher density. The system uses a preset pest characteristic database for this correction. In addition, the system also integrates spatial analysis technology. Use spatial autocorrelation analysis methods, such as Moran's I index, to evaluate the degree of aggregation of pest distribution. At the same time, the kernel density estimation algorithm is applied to generate a density map of the hotspot area to intuitively display the spatial changes in pest distribution. In order to improve the calculation accuracy, the system also uses an ensemble learning method to combine the output results of multiple models. For example, the Adaboost algorithm is used to integrate multiple weak classifiers, or the prediction results of multiple regression models are combined through a voting mechanism. Finally, the system compares the calculated density value with the preset threshold to determine different levels of density, such as low density, medium density, and high density.

[0075] S208: Match corresponding initial light source parameters according to the area and the density.

[0076] The area refers to the actual physical area of ​​the pest hotspot calculated in the previous step, usually in square meters or square centimeters. The density refers to the number or distribution density of pests per unit area, reflecting the degree of pest aggregation. The initial light source parameters refer to the basic settings for controlling the LED light source, including the intensity, wavelength, irradiation angle and duration of the light source.

[0077] In this step, the LED light source control system first accesses the preset parameter matching database. This database contains the optimal light source parameter settings for different combinations of area and density. The construction of the database is based on a large amount of experimental data and expert knowledge, taking into account the sensitivity of different pest species to light sources and the impact of light on plants. The system uses a multidimensional lookup table algorithm to quickly locate the closest parameter combination. For exact matches, the parameter settings in the database are directly used. For inexact matches, the system uses an interpolation algorithm to calculate the appropriate parameter values. For example, bilinear interpolation is used to calculate the parameter values ​​suitable for the current situation between known parameter points. In addition, the system also takes into account the physical characteristics and energy consumption limitations of the light source. Use optimization algorithms, such as genetic algorithms or particle swarm optimization, to minimize energy consumption while satisfying the control effect. The system also integrates an adaptive control mechanism to dynamically adjust the parameter matching strategy based on historical control effect data. This mechanism uses reinforcement learning algorithms, such as Q-learning, to continuously optimize the parameter selection strategy. Finally, the system generates an initial light source parameter setting plan, including specific parameters of each LED light source, such as wavelength range (for example, 450-470nm blue light is particularly effective for certain pests), light intensity (expressed in lumens or watts per square meter), irradiation angle (usually 30°-60° to cover the entire target area), and irradiation duration (which may vary from a few minutes to a few hours, depending on the light sensitivity of the pests and the diurnal cycle). These parameters are encoded into control instructions and are ready to be sent to the LED light source control device for execution.

[0078] S209, inputting the current environmental data into a preset environmental parameter calculation model to obtain current environmental parameters, wherein the current environmental data includes temperature, humidity, light intensity and wind speed, and the current environmental parameters include temperature parameters, humidity parameters, light intensity parameters and wind speed parameters.

[0079] Among them, current environmental data refers to environmental information collected in real time by various sensors, including temperature (usually expressed in degrees Celsius), relative humidity (expressed in percentage), light intensity (expressed in lux or micromoles / square meter / second) and wind speed (expressed in meters / second). The preset environmental parameter calculation model is a mathematical model or algorithm used to convert raw environmental data into standardized or normalized parameter values. The current environmental parameters are processed and standardized environmental indicators to facilitate the system's subsequent decision-making and control.

[0080] When the LED light source control system performs this step, it first obtains real-time current environmental data from the connected environmental monitoring subsystem. These data are collected through multiple sensor networks distributed in the target area to ensure the comprehensiveness and representativeness of the data. The system uses data preprocessing algorithms to clean and calibrate the raw data, including removing outliers, supplementing missing values, and smoothing noise. For example, use median filtering to remove spikes in temperature data, or use moving average method to smooth wind speed data. Next, the system inputs the processed data into the preset environmental parameter calculation model. This model uses a multi-layer perceptron (MLP) neural network structure, which can effectively capture the complex nonlinear relationship between environmental factors after training with a large amount of historical data. The input layer of the model receives data of four environmental factors, the hidden layer uses the ReLU activation function for nonlinear transformation, and the output layer generates the corresponding four environmental parameters. The model also integrates time series analysis techniques, such as long short-term memory networks (LSTM), to consider the temporal dynamic characteristics of environmental factors. The system uses a sliding window method to consider not only the data at the current moment, but also the data over a period of time in the past (such as the past 24 hours) to capture environmental change trends. In addition, the model also takes into account seasonal factors and geographic location characteristics, using One-Hot Encoding to convert these categorical information into numerical forms that the model can process. Ultimately, the model outputs standardized environmental parameters, including temperature parameters (values ​​in the range of 0-1, indicating the location relative to the preset temperature range), humidity parameters (also in the range of 0-1, reflecting the relative humidity level), light intensity parameters (standardized to the range of 0-1, indicating the light level) and wind speed parameters (in the range of 0-1, indicating the wind speed intensity). These parameters are stored in the system's temporary database, providing an important basis for subsequent adjustments to light source parameters, ensuring that the lighting control strategy can adapt to current environmental conditions.

[0081] S210. Correct the irradiation time in the initial light source parameters according to the temperature parameter, correct the light source wavelength parameter in the initial light source parameters according to the humidity parameter, correct the light source intensity parameter in the initial light source parameters according to the light intensity parameter, and correct the irradiation range parameter in the initial light source parameters according to the wind speed parameter to obtain preset light source parameters.

[0082] Among them, the temperature parameter refers to the current ambient temperature index after standardization. The humidity parameter indicates the standardized relative humidity level. The light intensity parameter refers to the standardized ambient light level. The wind speed parameter reflects the standardized wind speed intensity. The initial light source parameters include basic settings such as irradiation time, light source wavelength, light source intensity and irradiation range. The preset light source parameters refer to the final light source control parameters after correction of environmental factors.

[0083] When the LED light source control system performs this step, it first calls the parameter correction module. This module uses a combination of rule-based expert systems and machine learning algorithms to fine-tune the initial light source parameters. For the correction of irradiation time, the system uses temperature parameters as input and applies a piecewise linear regression model. For example, when the temperature parameter is high, the system shortens the irradiation time to avoid overstimulating pests or affecting plant growth; when the temperature is low, the irradiation time is appropriately extended to ensure the control effect. The system sets multiple temperature threshold points and uses different linear functions for time adjustment in each interval. For the correction of light source wavelength, the system uses a lookup table (LUT) and an interpolation algorithm based on the humidity parameter. The LUT stores the most effective wavelength range at different humidity levels, and the system calculates the optimal wavelength at the current humidity through interpolation. For example, under high humidity conditions, the system may choose shorter wavelength light to enhance penetration. The correction of light source intensity is based on the light intensity parameter and uses a feedback control algorithm. The system calculates the difference between the target light intensity and the ambient light intensity, and then uses a proportional-integral-differential (PID) controller to dynamically adjust the output intensity of the LED light source. This ensures that the overall light intensity reaches the desired effect while avoiding over-illumination. For the correction of the illumination range, the system uses the wind speed parameter and applies a computational fluid dynamics (CFD) model to simulate the change of the illumination range of the light source. Under high wind speed conditions, the system increases the illumination angle or enables additional LED units to compensate for the light diffusion caused by the wind. During the entire correction process, the system also takes into account the interaction between the various parameters. Using multivariable optimization algorithms, such as genetic algorithms or particle swarm optimization, the best combination is found in the multidimensional space of all parameters. Finally, the system compares the corrected parameters with the preset safety thresholds to ensure that all parameters are within the safety range to avoid adverse effects on plants or the environment. After the correction is completed, the system generates a complete set of preset light source parameters, including the precise illumination time (accurate to seconds), the optimal wavelength range (in nanometers), the adjusted light source intensity (expressed in lumens or watts per square meter), and the optimized illumination range (expressed in angle and coverage area).

[0084] S211, irradiating the pest hotspot area according to the preset light source parameters S212: Acquire the latest environmental data and the latest image around the target plant.

[0085] Among them, target plants refer to specific plants or crops that require pest control. The latest environmental data refers to the environmental information around the target plants collected in real time by various sensors, including but not limited to temperature, humidity, light intensity, carbon dioxide concentration, etc. The latest image refers to the latest image data of the target plants and their surroundings taken by a high-resolution camera or a multispectral camera.

[0086] When the LED light source control system performs this step, it first activates the sensor network distributed around the target plant. This network consists of multiple types of sensors, including temperature and humidity sensors, light intensity sensors, carbon dioxide concentration sensors, etc. The system uses wireless sensor network (WSN) technology and adopts low-power wide area network protocols such as ZigBee or LoRa to ensure real-time data transmission and energy efficiency. In order to improve the accuracy and reliability of the data, the system adopts a redundant design, deploys multiple sensors of the same type at key locations, and integrates the readings of multiple sensors through a data fusion algorithm. For example, the final temperature value is calculated using a weighted average method, and the weight is dynamically adjusted based on the historical accuracy of each sensor. At the same time, the system starts the image acquisition subsystem. This subsystem includes high-resolution RGB cameras and multispectral cameras fixed at different angles and heights. The RGB camera is used to capture visible light images of plants with a resolution of 4K (3840x2160 pixels) to ensure the clarity of image details. The multispectral camera can simultaneously capture images in multiple bands such as visible light, near infrared and short-wave infrared, and the resolution of each band is not less than 1080p (1920x1080 pixels). The system uses computer vision algorithms to pre-process the captured images, including denoising, color correction, and image enhancement. For example, Gaussian filtering is used to remove image noise, and histogram equalization is applied to improve image contrast. In order to cope with different lighting conditions, the system also integrates an adaptive exposure control algorithm to ensure clear images in various environments.

[0087] S213: Identify the latest pest area according to the latest environmental data and the latest image.

[0088] The latest pest area refers to the specific area around the plant where pests are found at the current time point by analyzing the latest environmental data and image data. This area may include the location where pests are directly present, as well as plant parts that show abnormal characteristics due to pest activity.

[0089] When the LED light source control system performs this step, it first starts the data fusion module. This module uses a multi-source data fusion algorithm to comprehensively analyze environmental data and image data. The system uses a data fusion framework based on the Dempster-Shafer evidence theory to effectively integrate information from different sources. For environmental data, the system uses anomaly detection algorithms such as Isolation Forest or Local Outlier Factor (LOF) to identify abnormal environmental parameters that may be associated with pest activity. For example, sudden changes in temperature or humidity may suggest large-scale pest activity. For image data, the system deploys a multi-stage deep learning model. First, a semantic segmentation model such as U-Net or Mask R-CNN is used to perform a preliminary analysis of the image to segment the image into plants, background, and potential pest areas. Then, the system applies specially trained convolutional neural network (CNN) models such as ResNet or DenseNet to finely classify potential pest areas and identify specific pest species and quantities. In order to improve recognition accuracy, the system also integrates multispectral image analysis technology. Using image features in different bands, such as changes in near-infrared reflectivity, plant physiological changes caused by pest infestation can be detected early. The system uses algorithms such as principal component analysis (PCA) and independent component analysis (ICA) to extract key features from multispectral data. In addition, the system also applies time series analysis techniques, such as long short-term memory networks (LSTM), to dynamically analyze continuously collected images and capture the temporal patterns of pest activities. In order to cope with different lighting conditions and complex backgrounds, the system finally integrates the environmental data analysis results and image analysis results, and uses the Bayesian network model to comprehensively evaluate the pest risk level of each area. The system generates a detailed pest distribution heat map, annotating pest density and risk level with different colors, and marking specific pest types and estimated numbers.

[0090] S214. Calculate a pest distribution change index based on the latest pest area and the pest hotspot area.

[0091] Among them, the latest pest area refers to the current pest distribution area obtained through the latest environmental data and image analysis. The pest hotspot area refers to the area with a high concentration of pests previously identified. The pest distribution change index is a numerical indicator used to quantify the degree of change in pest distribution patterns, reflecting the dynamics of pest activities.

[0092] When the LED light source control system performs this step, it first starts the spatial analysis module. This module uses geographic information system (GIS) technology to spatially register the latest pest area with the previous pest hotspot area. The system uses an affine transformation algorithm to ensure that the two areas are compared under the same coordinate system. In order to accurately calculate the changes in pest distribution, the system uses a variety of spatial analysis methods. First, the raster analysis technology is applied to divide the entire monitoring area into high-resolution grids, with each grid cell size of 10cm×10cm. For each grid cell, the system calculates the pest density value to form a density grid map. Then, the system uses spatial autocorrelation analysis methods, such as Moran's I index, to evaluate the spatial aggregation degree of pest distribution. At the same time, the system applies the kernel density estimation (KDE) algorithm to generate a continuous pest density surface to better capture the gradual characteristics of the distribution. In order to quantify the distribution differences between two time points, the system calculates the Jaccard similarity coefficient and the Sørensen-Dice coefficient, which reflect the changes in the degree of overlap of pest areas. In addition, the system also uses the center of gravity drift analysis to calculate the displacement distance and direction of the center of gravity of the pest distribution, reflecting the changing trend of the overall distribution pattern. To capture local characteristics of change, the system applies local indicator spatial autocorrelation (LISA) analysis to identify hot and cold areas with significant changes. The system also takes into account the time factor, using a time-weighted function to give higher weights to recent changes. All of these analysis results are input into a multi-indicator evaluation model, which uses the analytic hierarchy process (AHP) to determine the weight of each indicator, and then the final pest distribution change index is obtained through weighted summation. This index is standardized to a range of 0 to 100, where 0 represents no change and 100 represents the maximum degree of change.

[0093] S215: When the pest distribution change index is greater than a first change threshold, increase the irradiation range parameter to a first irradiation range.

[0094] The first change threshold is a preset value used to determine whether the change in pest distribution is significant enough to require adjustment of the control strategy. The irradiation range parameter refers to the coverage area and angle setting of the LED light source. The first irradiation range is a predefined larger irradiation range used to respond to significant changes in pest distribution.

[0095] The system first compares the calculated pest distribution change index with the preset first change threshold. This threshold is usually set between 60-80, and the specific value is determined based on historical data and expert experience. The comparison process uses a fuzzy logic controller to allow a certain amount of error tolerance near the threshold. When the change index is significantly greater than the threshold, the system triggers the irradiation range adjustment process. The adjustment process first accesses the preset irradiation range database to extract the specific parameters of the first irradiation range. These parameters include the tilt angle, scattering angle and coverage area of ​​the LED array. The system uses an inverse ray tracing algorithm to accurately calculate the parameters of each LED unit that needs to be adjusted to ensure that the light evenly covers the expanded area. During the adjustment process, the system takes into account the three-dimensional structure of the plant and uses 3D modeling technology to optimize the light distribution and avoid dead spots. At the same time, the system starts the power management module, recalculates the energy consumption requirements after the irradiation range is increased, and adjusts the power output accordingly.

[0096] S216: When the pest distribution change index is less than the second change threshold, increase the light source intensity parameter to the first light source intensity.

[0097] The second change threshold is a preset lower value used to determine whether the change in pest distribution is small enough to require a different control strategy. The light intensity parameter refers to the output power or brightness setting of the LED light source. The first light intensity is a predefined higher light intensity value used to deal with small changes in pest distribution.

[0098] When the LED light source control system performs this step, it first activates the parameter evaluation module. This module uses a data-based dynamic threshold algorithm to calculate and update the second change threshold in real time based on historical data and current environmental conditions. Usually, this threshold is set between 20-40, and the specific value is dynamically determined by time series analysis and seasonal adjustment algorithms. The system uses a fuzzy comparator to compare the calculated pest distribution change index with the current second change threshold. When the change index is significantly less than the threshold, the system triggers the light source intensity adjustment process. The adjustment process first accesses the light source parameter database to extract the specific value of the first light source intensity. This intensity value is usually 20%-30% higher than the standard working intensity, but still within the safe range. The system uses a nonlinear optimization algorithm to calculate the optimal light intensity increase curve considering the light saturation point and light compensation point of the plant. In order to accurately control the light source output, the system uses pulse width modulation (PWM) technology to achieve fine adjustment of light intensity by adjusting the duty cycle of the LED. At the same time, the system starts the thermal management module, uses the computational fluid dynamics (CFD) model to predict the heat distribution after the light intensity is increased, and adjusts the working parameters of the heat dissipation system accordingly to ensure that the LED chip temperature remains within a safe range. In order to avoid light shock to plants caused by sudden changes in light intensity, the system implements a gradual adjustment strategy. Using an S-curve algorithm, the light intensity is gradually increased within 5 minutes to simulate the natural light change process. The system also starts the real-time spectral monitoring mode, uses a spectrum analyzer to continuously measure the adjusted spectral distribution, and uses a feedback control algorithm to make fine adjustments to ensure that the spectrum remains within the target range. In order to evaluate the effect of the adjustment, the system performs rapid photosynthesis efficiency measurements 10 minutes, 30 minutes and 1 hour after the light intensity changes, and uses chlorophyll fluorescence technology to evaluate the photosynthetic response of the plant. If the plant is found to have symptoms of photoinhibition, the system will immediately activate the protection mechanism and gradually reduce the light intensity. All adjustment processes and plant response data are recorded in the system database for long-term trend analysis and strategy optimization. At the same time, the system pushes notifications to the user interface to inform the operator of the changes in light intensity and the reasons for the adjustments.

[0099] S217: When the pest distribution change index is not greater than the first change threshold and not less than the second change threshold, increase the light source intensity parameter to the first light source intensity.

[0100] The first change threshold and the second change threshold are respectively the upper and lower thresholds preset to define the medium range of pest distribution changes. The light source intensity parameter refers to the output power or brightness setting of the LED light source. The first light source intensity is a predefined higher light source intensity value used to cope with medium changes in pest distribution.

[0101] When the LED light source control system performs this step, it first starts the multi-threshold judgment module. This module uses an interval judgment algorithm to determine whether the pest distribution change index falls between the first change threshold and the second change threshold. The system uses a fuzzy logic controller, which allows a certain amount of fault tolerance near the threshold to avoid frequent switching of control strategies due to small fluctuations. When it is confirmed that the change index is within this medium range, the system triggers the light source intensity adjustment process. The adjustment process first accesses the light source control strategy database to extract the preset strategy for medium change situations. This strategy usually includes increasing the light source intensity to the first light source intensity, and may involve fine-tuning of other parameters. The system uses an adaptive control algorithm to dynamically calculate the optimal light intensity increase curve based on the current environmental conditions and plant growth stage. In order to accurately control the light source output, the system uses the digital addressable lighting interface (DALI) protocol to achieve independent and fine control of each LED unit. At the same time, the system starts the spectrum optimization module and uses a genetic algorithm to adjust the output ratio of LEDs of different wavelengths in real time to ensure that the optimal spectral composition is maintained while increasing the overall light intensity. In order to prevent sudden changes in light intensity from causing stress to plants, the system implements a phased adjustment strategy. Using a piecewise linear function, the light intensity is gradually increased in 3-5 stages within 15 minutes, and a 2-minute pause is made after each stage to allow the plants time to adapt. The system also starts a real-time plant physiological monitoring mode, using infrared thermal imaging technology to monitor leaf temperature, and multispectral imaging technology to monitor chlorophyll content and moisture conditions. If an abnormal reaction is detected in the plant, the system will immediately activate the emergency response mechanism, suspend the adjustment and perform a diagnosis. In order to evaluate the long-term effect of the adjustment, the system conducts comprehensive plant growth parameter measurements, including leaf area index, stem diameter, etc., 1 hour, 4 hours and 24 hours after the light intensity is changed, and the measurement is automatically completed using machine vision technology.

[0102] The following describes the LED light source control system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of an LED light source control system in an embodiment of the present application.

[0103] It should be noted that Figure 3 The structure of the LED light source control system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0104] like Figure 3As shown, the LED light source control system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0105] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0106] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0107] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0108] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0109] Specifically, the LED light source control system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the LED light source control method for inhibiting pests provided in the above embodiment is implemented.

[0110] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the LED light source control system described in the above embodiment; or may exist independently without being assembled into the LED light source control system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the LED light source control system, the LED light source control system implements the LED light source control method for inhibiting pests provided in the above embodiment.

[0111] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0112] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0113] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for controlling an LED light source for inhibiting pests, characterized in that: Applied to an LED light source control system, the method comprises: Acquire current environmental data and image data around the target plant; Identifying pest hotspots based on the current environment data and the image data; Identify the area size and density of said pest hotspots; Matching corresponding initial light source parameters according to the area and the density; Calculating current environment parameters according to the current environment data, and correcting the initial light source parameters according to the current environment parameters to obtain preset light source parameters; The pest hotspot area is illuminated according to the preset light source parameters.

2. The method according to claim 1, characterized in that The step of identifying pest hotspots according to the current environment data and the image data specifically includes: Extracting features from the image data to obtain the location of the pests; Searching for pest activity patterns corresponding to the current environmental data in a preset pest database, and planning pest gathering areas according to the pest activity patterns; The pest location and the pest gathering area are image-fused to obtain the pest hotspot area.

3. The method according to claim 1, characterized in that The step of identifying the area and density of the pest hotspot area specifically includes: Calculate the area of ​​the pest hotspot region based on the image data; Analyzing the color distribution and texture complexity of a pest hotspot image, wherein the pest hotspot image is a pest portion in the image data; The density of the pest hotspot area is calculated according to the color distribution and the texture complexity.

4. The method according to claim 1, characterized in that: The step of calculating the current environment parameters according to the current environment data, and correcting the initial light source parameters according to the current environment parameters to obtain the preset light source parameters specifically includes: Inputting the current environmental data into a preset environmental parameter calculation model to obtain current environmental parameters, wherein the current environmental data includes temperature, humidity, light intensity and wind speed, and the current environmental parameters include temperature parameters, humidity parameters, light intensity parameters and wind speed parameters; The irradiation time in the initial light source parameters is corrected according to the temperature parameters, the light source wavelength parameters in the initial light source parameters are corrected according to the humidity parameters, the light source intensity parameters in the initial light source parameters are corrected according to the light intensity parameters, and the irradiation range parameters in the initial light source parameters are corrected according to the wind speed parameters to obtain preset light source parameters.

5. The method according to claim 4, characterized in that After the step of irradiating the pest hotspot area according to the preset light source parameters, the method further includes: Acquire the latest environmental data and latest images around the target plant; Identify the latest pest area based on the latest environmental data and the latest image; Calculate the pest distribution change index based on the latest pest area and the pest hotspot area; When the pest distribution change index is greater than a first change threshold, the irradiation range parameter is increased to a first irradiation range.

6. The method according to claim 5, characterized in that: After the step of calculating the pest distribution change index according to the latest pest area and the pest hotspot area, the method further includes: When the pest distribution change index is less than a second change threshold, the light source intensity parameter is increased to the first light source intensity.

7. The method according to claim 5, characterized in that After the step of calculating the pest distribution change index according to the latest pest area and the pest hotspot area, the method further includes: When the pest distribution change index is not greater than the first change threshold and not less than the second change threshold, the light source intensity parameter is increased to the first light source intensity.

8. An LED light source control system, characterized in that: The LED light source control system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the LED light source control system to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the LED light source control system, the LED light source control system executes the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product runs on an LED light source control system, the LED light source control system is enabled to execute the method according to any one of claims 1 to 7.

Images