Intelligent monitoring method and system based on unmanned aerial vehicle

Abstract

The embodiment of the invention provides an intelligent monitoring method and system based on an unmanned aerial vehicle, and the method comprises the steps: judging whether the spectral data of a previous pixel point and the spectral data of a current pixel point of each line of pixels in second spectral image data meet a replacement condition or not, and if yes, carrying out the replacement of the current pixel point; replacing the spectral data of the current pixel point with the spectral data of the previous pixel point; if not, the spectral data of the current pixel point is kept unchanged, all the pixel points are traversed to obtain third spectral image data, the third spectral image data are analyzed and processed to obtain water quality parameters in the monitored water area, and due to the fact that a large amount of same spectral data exists in the spectral image data, the spectral data are subjected to subsequent processing, and the spectral data can be subjected to subsequent processing to obtain the water quality parameters in the monitored water area. The data processing amount can be reduced, and the data processing efficiency is improved. There is no need to select several wavebands from the data of the multiple wavebands for analysis and processing in order to reduce the data volume, and the accuracy of data analysis and processing can be improved.

Description

Technical Field

[0001] The present application relates to the field of environmental monitoring technology, and in particular to an intelligent monitoring method and system based on drones. Background Art

[0002] Due to the limitations of traditional ground monitoring methods, such as limited field of view and low efficiency, drone technology has been introduced into the field of environmental protection due to its advantages in high-altitude operations and used for monitoring illegal sewage discharge.

[0003] More specifically, by carrying various sensors on drones, the sensors collect river data and transmit the river data back to the ground in real time, and the ground data processing center processes the data. Since the amount of data collected by drones is relatively large, how to improve the data processing capacity of the ground data processing center is an urgent problem to be solved. Summary of the invention

[0004] The embodiments of the present application provide an intelligent monitoring method and system based on a drone, so as to achieve the effect of improving the data processing efficiency of a background server.

[0005] Some embodiments of the present application provide an intelligent monitoring method based on a drone, the method is applied to a background server, and the method includes: The UAV is scheduled based on the flight mission and the flight capability of the UAV, and a corresponding flight path is assigned to the UAV; so that the UAV flies along the flight path during the flight time, and controls the carried hyperspectral detector to collect the first spectral image data; the flight mission includes at least one flight path and the flight time of the flight path; Receiving first spectral image data returned by the UAV, preprocessing the first spectral image data, and obtaining second spectral image data; For the current pixel point of each row of pixels in the second spectral image data, determine whether the spectral data of the previous pixel point and the spectral data of the current pixel point meet the replacement condition, and if so, use the spectral data of the previous pixel point to replace the spectral data of the current pixel point; if not, keep the spectral data of the current pixel point unchanged, traverse all the pixel points of each row of pixels in the second spectral image data, and obtain the third spectral image data; Extracting features from the third spectral image data, and classifying the extracted features to obtain water quality parameters of the water body corresponding to the third spectral image; It is determined whether the sewage discharged by the monitored factory meets the water quality standard according to the water quality parameters of the water area corresponding to the third spectral image.

[0006] In the above technical solution, the drone collects data along the flight path to obtain the first spectral image data, and the background server first pre-processes the first spectral image data to obtain the second spectral image data. Subsequently, when the spectral data of the two previous pixel points in the second spectral image data meet the replacement conditions, the background server replaces the spectral data so that the point spectral data of the two adjacent pixels are the same. When the spectral data is subsequently processed, the amount of data processing can be reduced and the data processing efficiency can be improved. In addition, there is no need to select one or several bands from the data of multiple bands for analysis and processing in order to reduce the amount of data, which can improve the accuracy of subsequent data analysis and processing.

[0007] In a possible implementation, replacing the spectral data of the current pixel point with the spectral data of the previous pixel point specifically includes: Obtaining the spectral data identifier associated with the previous pixel, and establishing an association relationship between the current pixel and the spectral data identifier associated with the previous pixel; wherein there is a mapping relationship between the spectral data identifier and the shared spectral data, and the shared spectral data is stored in a shared storage area; Accordingly, the spectrum data of the current pixel point is maintained unchanged, specifically including: A new spectral data identifier is randomly generated, the spectral data of the current pixel point is used as the new shared spectral data, the new shared spectral data is stored in the shared storage area, and an association relationship between the current pixel point and the new spectral data identifier is established.

[0008] In the above technical solution, if the spectral data of two adjacent pixels are similar, the spectral data are replaced, so there is a large amount of identical spectral data. In order to reduce the amount of data storage, a shared storage area is set in the background server, the shared storage area stores shared spectral data, a corresponding spectral data identifier is configured for each shared spectral data, and a spectral data identifier is associated with each pixel, so that the amount of spectral data storage can be reduced. In addition, when the spectral data is subsequently processed, there is no need to repeatedly calculate the features of the same spectral data, thereby reducing the amount of data calculation.

[0009] In a possible implementation, feature extraction is performed on the third spectral image data, and the extracted features are classified to obtain water quality parameters of the water body corresponding to the third spectral image, specifically including: Extracting features from each spectral data in the shared storage area, and classifying and processing the extracted features to obtain water quality parameters corresponding to each spectral data; The water quality parameter of the water area corresponding to each pixel point is obtained according to the spectral data identifier associated with each pixel point and the water quality parameter of the spectral data associated with each spectral data identifier.

[0010] In the above technical solution, the water quality parameters reflected by the spectral data are obtained by analyzing and processing the spectral data in the shared storage area, and then the water quality parameters reflected by the spectral data are associated with each pixel point through the spectral data identifier, so that the water quality parameters of the water area corresponding to each pixel point can be obtained. Since there is a large amount of identical data in the third spectral image data after the replacement process, it is not necessary to process the spectral data of each pixel, and only the spectral data in the shared storage area is processed, which can reduce the amount of data processing and improve data processing efficiency.

[0011] In a possible implementation, the spectral data includes light intensities of multiple bands, and determining whether the spectral data of the previous pixel point and the spectral data of the current pixel point meet the replacement condition specifically includes: Calculate the light intensity difference between the light intensity of each band of the previous pixel and the light intensity of the corresponding band of the current pixel to obtain the light intensity difference of multiple bands; Calculate the average value of the light intensity difference of all bands, and calculate the variance of the light intensity difference of all bands; If the average value of the light intensity difference is less than the preset average value threshold, and the variance of the light intensity difference is less than the preset variance threshold, it is determined that the replacement condition is met; If the average value of the light intensity difference is greater than or equal to the preset average value threshold, or the variance of the light intensity difference is greater than or equal to the preset variance threshold, it is determined that the replacement condition is not met.

[0012] In the above technical solution, the spectral data of the current pixel and the spectral data of the previous pixel both include the intensities of multiple bands. The light intensity difference between the light intensity of each band of the previous pixel and the light intensity of the corresponding band of the current pixel is calculated. By performing statistical analysis on the light intensity difference, the similarity between the spectral data of the current pixel and the spectral data of the previous pixel can be obtained. Based on the similarity, it is determined whether to replace the spectral data. In this way, it can be ensured that the information can be retained after the spectral data is replaced, and no information loss will occur, thereby improving the data processing efficiency and the accuracy of data processing.

[0013] In a possible implementation, preprocessing the first spectral image data to obtain the second spectral image data specifically includes: De-noising the first spectral image data to obtain denoised spectral image data; Performing baseline correction on the denoised spectral image data to obtain baseline-corrected spectral image data; The baseline-corrected spectral image data is subjected to black-and-white correction to obtain third spectral image data.

[0014] In the above technical solution, the image quality of the third spectral image data can be improved by successively performing denoising, baseline correction processing and black-and-white correction processing on the first spectral image data.

[0015] In a possible implementation, before scheduling the drones based on the flight missions and the flight capabilities of the drones and assigning corresponding flight paths to the drones, the method further includes: Obtain the pollution discharge standards of the factories to be monitored, the real-time pollution discharge data of the factories to be monitored, and the terrain data of the areas to be monitored; The flight mission is generated according to the pollution discharge standards of the factories to be monitored, the real-time pollution discharge data of the factories to be monitored and the terrain data of the areas to be monitored.

[0016] In the above technical solution, flight missions are generated based on obtaining the pollution discharge standards of the factories to be monitored, the real-time pollution discharge data of the factories to be monitored, and the terrain data of the areas to be monitored. The tasks can be executed with real-time reference to the pollution discharge conditions of the factories to be monitored, and targeted monitoring can be carried out to improve monitoring efficiency and accuracy.

[0017] In a possible implementation, the real-time sewage discharge data includes the sewage discharge data of the day and the historical sewage discharge data, and the sewage discharge data of the day and the historical sewage discharge data both include the sewage discharge time, sewage discharge amount and sewage quality; Accordingly, a flight mission is generated according to the pollution discharge standards of the factories to be monitored, the real-time pollution discharge data of the factories to be monitored, and the terrain data of the areas to be monitored, including: For each factory to be monitored, the discharge time coefficient is set according to the discharge time of the factory to be monitored and the required discharge time; the discharge water quality coefficient is set according to the discharge water quality and water quality requirements of the factory to be monitored; the discharge volume coefficient is set according to the discharge volume and maximum discharge volume of the factory to be monitored; For each factory to be monitored, the trained pollution emission prediction model is used to obtain the predicted pollution emission of the day; and the emission prediction coefficient is set according to the predicted pollution emission of the day and the actual pollution emission in the pollution emission data of the day; For each factory to be monitored, the monitoring frequency weight of each factory to be monitored is generated according to the discharge time coefficient, discharge water quality coefficient, discharge volume coefficient and discharge prediction coefficient; The terrain data of the area to be monitored and the weight of the monitoring times of each factory to be monitored are input into the task generation model to obtain the flight mission generated by the task generation model.

[0018] In the above technical scheme, the discharge time system, discharge water quality coefficient, discharge volume coefficient and discharge prediction coefficient are calculated respectively according to the discharge time, discharge water quality, discharge volume and predicted discharge volume of the factory to be monitored, and the monitoring times weight of the factory to be monitored is calculated based on the above four coefficients. Compared with increasing the monitoring times for all factories to be monitored, increasing the monitoring times weight of the factories to be monitored in a targeted manner can reduce the flight distance of the drone and the amount of data collection.

[0019] Some embodiments of the present application provide an intelligent monitoring system based on a drone, including a drone and a background server, the drone is equipped with a hyperspectral detector and an image sensor, and the background server is used to execute the intelligent monitoring method involved in the above embodiments.

[0020] Some embodiments of the present application provide a backend server, including: a memory, a processor; Memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above-mentioned embodiments and various possible implementations.

[0021] An embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the above-mentioned embodiment and various possible implementation methods.

[0022] An embodiment of the present application provides a computer program product, including a computer program, which implements the above embodiment and various possible implementation modes when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments satisfying the present application, and together with the description, are used to explain the principles of the present application.

[0024] Figure 1 A schematic diagram of a scene of an area to be monitored provided in some embodiments of the present application; Figure 2 A schematic diagram of the process of the intelligent monitoring method based on drones provided in this application; Figure 3A Schematic diagram of the replacement of spectral image data provided in this application Figure 1 ; Figure 3B Schematic diagram of the replacement of spectral image data provided in this application Figure 2 ; Figure 4 This is a schematic diagram of the spectral data of the previous pixel and the spectral data of the current pixel provided in this application.

[0025] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0026] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0027] In order to solve the above problems, in the embodiment provided in this application, the drone is equipped with a hyperspectral detector and an image sensor to perform flight inspections in the area to be monitored, and collect spectral image data and two-dimensional image data near the river and the sewage outlet. The collected spectral image data is pre-processed by denoising, baseline correction, and black and white correction to improve the image quality. At the same time, the two-dimensional image data is used to identify suspended matter and oil pollution to preliminarily judge the water quality.

[0028] For the pre-processed spectral image data, traverse each row of pixels to determine whether the spectral data of adjacent pixels meet the replacement conditions. If the conditions are met, the spectral data of the previous pixel is used to replace the spectral data of the current pixel to reduce the amount of data processing and improve processing efficiency. This step provides a more concise and efficient data basis for subsequent feature extraction and classification by reducing the redundant information in the spectral image data. Feature extraction is performed on the optimized spectral image data, and the extracted features are classified and processed using machine learning or deep learning algorithms to obtain water quality parameters. According to the water quality parameters, it is determined whether the sewage discharge behavior of the monitored factory meets the water quality standards. If the standards are not met, the early warning mechanism is triggered to notify the relevant departments for further investigation and processing. In addition, in the embodiment provided in the present application, the system includes two parts: a drone and a background server. The drone is responsible for data collection and preliminary processing, and the background server is responsible for tasks such as in-depth analysis, feature extraction, classification, and monitoring and early warning of the data. Data transmission between the drone and the background server is carried out through wireless communication to ensure the real-time and accuracy of the monitoring task.

[0029] In summary, the embodiment of the present application significantly reduces the redundant information in the spectral image data and improves the data processing efficiency through the spectral data replacement algorithm. Combining the data of the hyperspectral detector and the image sensor, accurate judgment of the water quality status is achieved, and the accuracy of monitoring and early warning is effectively improved. The system can adjust the flight path and monitoring frequency of the drone according to actual needs, and has strong flexibility and scalability. The entire monitoring process is intelligent and automated, reducing manual intervention and improving monitoring efficiency.

[0030] Figure 1 A schematic diagram of a scene of an area to be monitored provided in some embodiments of the present application, such as Figure 1 As shown, the specific application scenario of the present application is to monitor sewage discharge from factories in a certain monitoring area. The circle represents the factory, which is distributed along the river, and the triangle represents the sewage outlet of the factory.

[0031] In the existing technology, drone technology has been introduced into the field of environmental protection due to its advantages of high-altitude operation, and is used to monitor the illegal discharge of sewage. More specifically, by carrying various sensors on drones, the sensors collect river data and transmit the river data back to the ground in real time, and the data is processed by the ground data processing center. Since the amount of data collected by drones is relatively large, how to improve the data processing capacity of the ground data processing center is an urgent problem to be solved.

[0032] The intelligent monitoring method and system based on drone provided in the present application, for spectral image data collected by drone, by using the spectral data of the previous pixel point to replace the spectral data of the current pixel point when the spectral data of the previous pixel point and the spectral data of the current pixel point meet the replacement condition, so that the point spectral data of two adjacent pixels are the same, and then a large amount of identical spectral data in the processed spectral image data can reduce the data processing amount and improve the data processing efficiency when the spectral data is subsequently processed.

[0033] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0034] Some embodiments of the present application provide an intelligent monitoring system based on a drone, which includes a drone and a backend server. When the drone conducts an inspection in the monitored area, it collects river data of the monitored area, for example, it collects river data of each factory sewage outlet, and transmits the river data of the monitored area back to the backend server. The backend server uses an algorithm to analyze and process the river data to determine whether the sewage discharged from the sewage outlet of each factory to be monitored meets the discharge standard.

[0035] Drones are equipped with various sensors for data collection, such as image sensors and hyperspectral detectors.

[0036] Image sensors are divided into infrared image sensors and visible light image sensors. Visible light image sensors can take river images when visibility is high. Infrared image sensors can take river images when visibility is low. The water quality of each sewage outlet is determined based on the river image. For example: whether there is floating garbage, foam, oil, etc. in the water of the sewage outlet.

[0037] In addition, due to the different components in the river water, the absorption rate of light in different bands is also different. The hyperspectral detector is used to collect spectral image data at different wavelengths, and the water components at the sewage outlet are determined based on the collected spectral image data, and then it is determined whether the sewage discharged from the sewage outlet meets the discharge standards.

[0038] like Figure 2 As shown, some embodiments of the present application provide an intelligent monitoring method based on a drone, and the method specifically includes the following steps: S101. The backend server dispatches the drone based on the flight mission and the flight capability of the drone, and assigns the drone a corresponding flight path.

[0039] Among them, the flight mission includes at least one flight path and the flight time of each flight path. The flight capability of the drone refers to the maximum distance the drone can fly and the charging time of the drone. The background server dispatches the drone based on the flight time of each flight path, the path length of the flight path and the flight capability of the drone, and assigns the flight path to the drone.

[0040] Specifically, the backend server first schedules the flight according to the preset flight mission and the flight capability of the drone. The flight mission includes at least one flight path and the flight time of each flight path. The flight capability of the drone includes the maximum flight distance, flight speed, battery life, etc. The backend server comprehensively considers these factors and allocates the optimal flight path for the drone to ensure that the drone can fly along the specified path within the specified time and complete the data collection task.

[0041] For example, if the flight times of two flight paths differ by more than 4 hours, the drone's battery can be fully charged in 3 hours, and the maximum distance the drone can fly is greater than the distance of the flight path, two flight paths can be assigned to the drone.

[0042] S102: The UAV flies along the flight path during the flight time, and controls the carried hyperspectral detector to collect first spectral image data.

[0043] The UAV is equipped with a hyperspectral detector, and the UAV is turned on when flying along the flight path during the flight time. The hyperspectral detector collects spectral image data near the river channel, which is recorded as the first spectral image data. The first spectral image data includes spectral data of multiple pixel points. The spectral data includes light intensity under multiple bands.

[0044] Specifically, after receiving the flight mission, the drone flies according to the assigned flight path and flight time. During the flight, the hyperspectral detector carried by the drone starts working to collect spectral image data near the river and the sewage outlet, that is, the first spectral image data. Optionally, these data can include light intensity information in different bands, which can reflect the composition and concentration in the water body.

[0045] S103: The backend server receives the first spectral image data returned by the drone, and pre-processes the first spectral image data to obtain second spectral image data.

[0046] More specifically, the preprocessing includes denoising, baseline correction, and black-and-white correction, thus improving the image quality.

[0047] De-noising specifically includes smoothing algorithm or inverse method. Among them, the smoothing algorithm includes moving window average method or least squares fitting method. Baseline correction includes multivariate scattering correction or standard normal variable transformation. Black and white correction includes dark current correction and reflection correction.

[0048] In some embodiments, the first spectral image data is denoised to obtain denoised spectral image data, the denoised spectral image data is baseline corrected to obtain baseline corrected spectral image data, and the baseline corrected spectral image data is black-white corrected to obtain third spectral image data.

[0049] Specifically, after the backend server receives the first spectral image data returned by the drone, it first performs preprocessing operations. Preprocessing includes steps such as denoising, baseline correction, and black-and-white correction. Denoising removes noise signals in the image through a filtering algorithm; baseline correction is used to eliminate baseline drift in the spectral image; and black-and-white correction ensures that the brightness and contrast of the image are moderate, which is convenient for subsequent processing. After preprocessing, the second spectral image data is obtained.

[0050] In the above technical solution, the image quality of the third spectral image data can be improved by successively performing denoising, baseline correction processing and black-and-white correction processing on the first spectral image data.

[0051] It is worth noting that the above solution has at least the following technical effects: First, improve the quality of spectral image data: De-noising the first spectral image data can effectively remove noise and interference signals in the image, making the spectral data purer. The subsequent baseline correction process can eliminate the baseline drift phenomenon in the spectral data and ensure the accuracy and stability of the spectral data. Finally, through the black and white correction process, the brightness and contrast of the spectral image can be further adjusted to make the image clearer and easier to read. These preprocessing steps jointly improve the quality of the spectral image data and provide a reliable foundation for subsequent data analysis and processing.

[0052] Second, enhance the accuracy of data analysis: high-quality spectral image data is the prerequisite for accurate extraction of water quality parameters. By performing pre-processing steps such as denoising, baseline correction, and black and white correction on the first spectral image data, the noise and error in the data can be significantly reduced, and the accuracy of data analysis can be improved. This helps to more accurately determine the types and concentrations of pollutants in water bodies, providing a more reliable basis for environmental protection and supervision.

[0053] Third, improve the robustness of the system: In practical applications, the spectral image data collected by drones are often affected by many factors, such as lighting conditions, atmospheric conditions, sensor performance, etc. These factors may cause fluctuations and errors in the spectral data. By preprocessing the first spectral image data, the impact of these external factors on data analysis can be effectively reduced, and the robustness and stability of the system can be improved. This enables the system to maintain stable performance in various complex environments and ensure the smooth progress of monitoring tasks.

[0054] Fourth, optimize system resource utilization: high-quality spectral image data can reduce the time and computing resources required for subsequent data analysis and processing. By preprocessing the first spectral image data, the data can be made easier to process and analyze, thereby reducing system resource consumption. This helps to achieve higher system performance and longer battery life under limited hardware conditions, providing strong support for long-term and continuous monitoring of illegal sewage discharge.

[0055] To sum up, in the above scheme, the preprocessing steps such as denoising, baseline correction and black and white correction are performed on the first spectral image data, which has multiple technical effects such as improving the quality of spectral image data, enhancing data analysis accuracy, improving system robustness and optimizing system resource utilization, thereby improving the overall performance and monitoring efficiency of the system.

[0056] S104: for the current pixel point of each row of pixels in the second spectral image data, the background server determines whether the spectral data of the previous pixel point and the spectral data of the current pixel point meet the replacement condition, and if so, the spectral data of the current pixel point is replaced with the spectral data of the previous pixel point. If not, the spectral data of the current pixel point is maintained unchanged, and all the pixels of each row of pixels in the second spectral image data are traversed to obtain the third spectral image data.

[0057] Among them, the previous pixel and the current pixel are adjacent pixels. If the difference between the spectral data of the previous pixel and the spectral data of the current pixel is relatively large, the replacement condition is not met, and the spectral data of the current pixel is maintained unchanged. If the difference between the spectral data of the previous pixel and the spectral data of the current pixel is relatively small, the replacement condition is met, and the spectral data of the adjacent pixel is used to replace the spectral data of the current pixel. In this way, the amount of data processing can be reduced when extracting features. The third spectral image data is obtained by traversing all the pixels of each row of pixels in the second spectral image data.

[0058] Specifically, for each row of pixels in the second spectral image data, the background server performs traversal processing. For the current pixel, determine whether its spectral data meets the replacement condition with the previous pixel. The replacement condition is usually determined based on the similarity between the spectral data, for example, calculating the difference between the light intensity of two pixels in each band, and counting the average and variance of the difference. If the average and variance of the difference are both less than the preset threshold, it is considered that the spectral data are highly similar and meet the replacement condition, and the spectral data of the previous pixel is used to replace the spectral data of the current pixel; if the condition is not met, the spectral data of the current pixel is maintained unchanged. After traversing all pixels, the optimized third spectral image data is obtained.

[0059] Figure 3A and Figure 3B is a schematic diagram of the replacement of spectral image data, such as Figure 3A and Figure 3B As shown, for example, the second spectral image data includes 10 rows of pixels. For the first row of pixels, the first row and first column pixel point does not have a previous pixel point, so the spectral data of the first row and first column pixel point is maintained unchanged. The first row and second column pixel point is updated as the current pixel point, and it is determined whether the difference between the first row and first column pixel point and the first row and second column pixel point is relatively large. If so, the spectral data of the first row and second column pixel point is maintained unchanged. If the difference is relatively small, the spectral data of the first row and first column pixel point is used to replace the spectral data of the first row and second column pixel point.

[0060] Update the pixel in the 3rd column of the 1st row as the current pixel, and determine whether the difference between the pixel in the 2nd column of the 1st row and the pixel in the 3rd column of the 1st row is large. If so, keep the spectral data of the pixel in the 3rd column of the 1st row unchanged. If the difference is small, use the spectral data of the pixel in the 2nd column of the 1st row to replace the spectral data of the pixel in the 3rd column of the 1st row.

[0061] And so on, until all pixels in the first row are traversed.

[0062] For the pixel in the second row, the pixel in the first column of the second row does not have the previous pixel, so the spectral data of the pixel in the first column of the second row is maintained unchanged. The pixel in the second column of the second row is updated as the current pixel, and it is determined whether the difference between the pixel in the first column of the second row and the pixel in the second column of the second row is relatively large. If so, the spectral data of the pixel in the second column of the second row is maintained unchanged. If the difference is relatively small, the spectral data of the pixel in the first column of the second row is used to replace the spectral data of the pixel in the second column of the second row.

[0063] Update the pixel at row 2, column 3 as the current pixel, and determine whether the difference between the pixel at row 2, column 2 and the pixel at row 2, column 3 is large. If so, keep the spectral data of the pixel at row 2, column 3 unchanged. If the difference is small, use the spectral data of the pixel at row 2, column 2 to replace the spectral data of the pixel at row 2, column 3.

[0064] And so on, until all the pixels in the second row are traversed.

[0065] Through the above method, the traversal of all rows of pixels is completed.

[0066] S105: The backend server extracts features from the third spectral image data, and classifies the extracted features to obtain water quality parameters of the water body corresponding to the third spectral image.

[0067] Among them, the existing feature extraction algorithm can be used to extract features from the third spectral image data to obtain feature data of the third spectral image data, and the existing classification algorithm can be used to classify the feature data of the third spectral image data to obtain water quality parameters of the water area corresponding to the third spectral image.

[0068] Since the spectral image data is the data collected by the drone when flying along the flight path, the drone can collect multiple frames of first spectral image data, and multiple frames of second spectral image data can be obtained by processing the multiple frames of first spectral image data in the above manner. Multiple frames of third spectral image data are obtained by processing the multiple frames of second spectral image data. The water quality parameters of the water body corresponding to the third spectral image data can reflect the water quality parameters of the water body in the river where the flight path is located.

[0069] Specifically, feature extraction is performed on the third spectral image data to extract key features that can reflect the water quality. These features may include light intensity values ​​in a specific band, the shape and slope of the spectral curve, etc. Then, the extracted features are classified and processed using machine learning or deep learning algorithms to obtain water quality parameters of the water body corresponding to the third spectral image. These parameters may include key water quality indicators such as dissolved oxygen content, chemical oxygen demand, and ammonia nitrogen content.

[0070] S106. The backend server determines whether the sewage discharged by the monitored factory meets the water quality standard according to the water quality parameters of the water area corresponding to the third spectral image.

[0071] Among them, if the water quality parameters of a certain area in the river do not meet the water quality standards, it is determined that the sewage discharge of at least one factory to be monitored in the area does not meet the water quality standards. If the water quality parameters of a certain area in the river meet the water quality standards, it is determined that the sewage discharge of the factory to be monitored in the area meets the water quality standards.

[0072] Specifically, based on the water quality parameters obtained, the backend server determines whether the pollution discharge behavior of the monitored factory meets the water quality standards. This step usually involves comparative analysis with the preset water quality standards. If the water quality parameters exceed the standard range, it is considered that the factory's pollution discharge does not meet the water quality standards, and the early warning mechanism is triggered. The early warning mechanism may include sending alarm information to relevant departments, displaying abnormal prompts on the monitoring interface, etc., so that timely measures can be taken to intervene and deal with it.

[0073] In the above technical solution, the drone collects data along the flight path to obtain the first spectral image data, and the background server pre-processes the first spectral image data to obtain the second spectral image data. Subsequently, when the spectral data of two adjacent pixels in the second spectral image data meet the replacement condition, the background server replaces the spectral data so that the spectral data of the two adjacent pixels are the same. When the spectral data is subsequently processed, the amount of data processing can be reduced and the data processing efficiency can be improved. In addition, there is no need to select one or several bands from the data of multiple bands for analysis and processing in order to reduce the amount of data, which can improve the accuracy of subsequent data analysis and processing.

[0074] In a possible implementation, the spectral data includes light intensities of multiple bands, and determining whether the spectral data of the previous pixel and the spectral data of the current pixel meet a replacement condition specifically includes: S21, calculating the light intensity difference between the light intensity of each band of the previous pixel and the light intensity of the corresponding band of the current pixel.

[0075] Figure 4 A schematic diagram of the spectrum data of the previous pixel point and the spectrum data of the current pixel point provided in this application, such as Figure 4As shown, for example: the spectrum data of the previous pixel point includes light intensity data of 10 bands, namely, the light intensity In10λ1 of band λ1, the light intensity In11λ2 of band λ2, ..., the light intensity In19λ10 of band λ10. The spectrum data of the current pixel point includes light intensity data of 10 bands, namely, the light intensity In20λ1 of band λ1, the light intensity In21λ2 of band λ2, ..., the light intensity In29λ10 of band λ10.

[0076] S22. Calculate the light intensity difference of band λ1 as (In10λ1-In20λ1), calculate the light intensity difference of band λ2 as (In11λ2-In21λ2), ..., calculate the light intensity difference of band λ10 as (In19λ10-In29λ10), and obtain the light intensity differences of 10 bands.

[0077] S23, calculating the average value of the light intensity difference of all the bands, and calculating the variance of the light intensity difference of all the bands.

[0078] The average value of the light intensity difference between the wavelength band λ1 and the wavelength band λ10 is calculated, and the variance of the light intensity difference between the wavelength band λ1 and the wavelength band λ10 is calculated.

[0079] S24: If the average value of the light intensity difference is greater than or equal to a preset average value threshold, or the variance of the light intensity difference is greater than or equal to a preset variance threshold, it is determined that the replacement condition is not met.

[0080] The variance and average of the intensity difference can reflect the difference between the spectrum data of the current pixel and the spectrum data of the previous pixel. If the average value and variance of the intensity difference are both relatively large, it means that the spectrum data of the current pixel and the spectrum data of the previous pixel are quite different, and the spectrum data of the previous pixel cannot be used to replace the spectrum data of the current pixel.

[0081] S25. If the average value of the light intensity difference is less than a preset average value threshold, and the variance of the light intensity difference is less than a preset variance threshold, it is determined that the replacement condition is met.

[0082] If the average value and variance of the light intensity difference are relatively small, it means that the spectral data of the current pixel point is very similar to the spectral data of the previous pixel point. The spectral data of the current pixel point can be replaced by the spectral data of the previous pixel point, thereby reducing the data processing amount of subsequent feature extraction.

[0083] In the above technical solution, the spectral data of the current pixel and the spectral data of the previous pixel both include the intensities of multiple bands. The light intensity difference between the light intensity of each band of the previous pixel and the light intensity of the corresponding band of the current pixel is calculated. By performing statistical analysis on the light intensity difference, the similarity between the spectral data of the current pixel and the spectral data of the previous pixel can be obtained. Based on the similarity, it is determined whether to replace the spectral data. In this way, it can be ensured that the information can be retained after the spectral data is replaced, and no information loss will occur, thereby improving the data processing efficiency and the accuracy of data processing.

[0084] It is worth noting that the above solution has at least the following technical effects: First, ensure the accuracy of spectral data: by calculating the intensity difference between the intensity of each band of the previous pixel and the intensity of the corresponding band of the current pixel, and counting the average and variance of these differences, the similarity of the spectral data of the two pixels can be accurately evaluated. Only when the average and variance of the intensity difference are less than the preset threshold, the spectral data is considered similar enough to meet the replacement conditions. This method ensures that the replaced spectral data can accurately reflect the information of the original data and avoids data distortion caused by replacement.

[0085] Second, improve data processing efficiency: In spectral image data, the spectral data of adjacent pixels often have high similarity. By setting reasonable mean and variance thresholds, pixels that meet the replacement conditions can be quickly screened out, thereby reducing unnecessary data processing. This method significantly improves data processing efficiency, allowing the system to complete the optimization and analysis of spectral image data more quickly.

[0086] Third, enhance the adaptability and robustness of the system: Different monitoring scenarios and lighting conditions may cause fluctuations in spectral data. By calculating the mean and variance of the light intensity difference and judging the replacement conditions accordingly, the system can automatically adapt to these changes. When the spectral data fluctuates slightly due to external factors, the system can still accurately determine which pixel spectral data can be replaced, thereby maintaining the stability and accuracy of monitoring. This adaptability and robustness enables the system to operate stably in various complex environments.

[0087] Fourth, support for more refined monitoring and analysis: By calculating and analyzing the multi-band light intensity difference of spectral data, the system can capture more subtle changes in spectral characteristics. These characteristic changes may reflect changes in the concentration of different pollutants in the water body or slight fluctuations in water quality parameters. By accurately judging whether the replacement conditions are met, the system can retain these important characteristic information and provide more accurate and comprehensive data support for subsequent water quality parameter extraction and classification processing. This helps to achieve more refined monitoring and analysis and improve the accuracy and reliability of monitoring.

[0088] To sum up, in the above scheme, the technical measures taken to determine whether the spectral data of the previous pixel and the spectral data of the current pixel meet the replacement conditions have multiple technical effects such as ensuring the accuracy of spectral data, improving data processing efficiency, enhancing system adaptability and robustness, and supporting more refined monitoring and analysis, thereby improving the overall performance and monitoring accuracy of the system.

[0089] In some possible implementations, the spectrum data of the current pixel point is replaced with the spectrum data of the previous pixel point, specifically including: S31, obtaining the spectral data identifier associated with the previous pixel, and establishing an association relationship between the current pixel and the spectral data identifier associated with the previous pixel; there is a mapping relationship between the spectral data identifier and the shared spectral data, and the shared spectral data is stored in a shared storage area.

[0090] A shared storage area is reserved in the background server, and the shared storage area is used to store shared spectral data. A mapping relationship exists between the spectral data identifier and the shared spectral data, and a mapping relationship exists between the spectral data identifier and each pixel point.

[0091] If the spectral data of the current pixel point is highly similar to the spectral data of the previous pixel point, the replacement condition is met. The spectral data identifier associated with the previous pixel point is obtained, and an association relationship between the spectral data identifier associated with the current pixel point and the previous pixel point is established.

[0092] Figure 3A Schematic diagram of the replacement of spectral image data Figure 1 ,like Figure 3A As shown, the spectral image data 100 includes 10 rows and 6 columns of pixels. For example, for the first row of pixels, the first row and first column of pixels do not have a previous pixel, so the spectral data is retained. The first spectral data identifier (identifier 1 in the figure) is randomly generated, and the spectral data of the first row and first column of pixels is used as the first common spectral data (data 1 in the figure). The first spectral data identifier is associated with the first common spectral data, and the first common spectral data is stored in the common storage area 200. The first row and first column of pixels are associated with the first spectral data identifier.

[0093] Update the pixel point in the first row and the second column as the current pixel point, read the first common spectrum data corresponding to the first spectrum data identifier from the common storage area, and determine whether the first common spectrum data and the spectrum data of the pixel point in the first row and the second column meet the replacement condition. If the difference between the pixel point in the first row and the first column and the pixel point in the first row and the second column is relatively small, associate the pixel point in the first row and the second column with the first spectrum data identifier. In this way, there is no need to store multiple identical spectrum data, which can reduce the amount of data storage.

[0094] In some possible implementations, the spectral data of the current pixel point is maintained unchanged, specifically including: S32, randomly generate a new spectral data identifier, use the spectral data of the current pixel as new shared spectral data, store the new shared spectral data in a shared storage area, and establish an association relationship between the current pixel and the new spectral data identifier.

[0095] If the spectral data of the current pixel point is less similar to the spectral data of the previous pixel point, and the replacement condition is not met, new spectral data needs to be stored in the shared storage area. A new spectral data identifier is randomly generated, and the spectral data of the current pixel point is used as the new shared spectral data, and the new shared spectral data is stored in the shared storage area. An association relationship is established between the new spectral data identifier and the new shared spectral data, and an association relationship is established between the current pixel point and the new spectral data identifier.

[0096] Figure 3B Schematic diagram of the replacement of spectral image data Figure 2 ,like Figure 3B As shown, for example: for the first row of pixels, the pixel point in the first row and the second column is updated as the current pixel point, the first common spectral data corresponding to the first spectral data identifier is read from the common storage area, and it is determined whether the first common spectral data and the spectral data of the pixel point in the first row and the second column meet the replacement condition. If the difference between the pixel point in the first row and the first column and the pixel point in the first row and the second column is relatively large, a second spectral data identifier (identifier 2 in the figure) is generated, and the spectral data of the pixel point in the first row and the second column is used as the second common spectral data (data 2 in the figure), a mapping relationship between the second spectral data identifier and the second common spectral data is established, and a mapping relationship between the second spectral data identifier and the pixel point in the first row and the second column is established.

[0097] In the above technical solution, if the spectral data of two adjacent pixels are similar, the spectral data are replaced, so there is a large amount of identical spectral data. In order to reduce the amount of data storage, a shared storage area is set in the background server, the shared storage area stores shared spectral data, a corresponding spectral data identifier is configured for each shared spectral data, and a spectral data identifier is associated with each pixel, so that the amount of spectral data storage can be reduced. In addition, when the spectral data is subsequently processed, there is no need to repeatedly calculate the features of the same spectral data, thereby reducing the amount of data calculation.

[0098] It is worth noting that the above solution has at least the following technical effects: First, improve the consistency of spectral image data: In spectral image data, the spectral data of adjacent pixels are often highly similar, especially when the water is stable and the light is uniform. By obtaining the spectral data identifier associated with the previous pixel and using its spectral data to replace the spectral data of the current pixel, the redundant information in the spectral image can be effectively reduced and the consistency of the data can be improved. This consistency not only helps with subsequent feature extraction and classification processing, but also reduces the amount of data processing calculations to a certain extent, improving the overall monitoring efficiency.

[0099] Second, optimize spectral data storage and access: by randomly generating new spectral data identifiers while maintaining the spectral data of the current pixel unchanged, and storing the spectral data of the current pixel as new shared spectral data in the shared storage area, centralized management and efficient access to spectral data can be achieved. This storage method avoids duplicate storage of data and saves storage space. At the same time, by establishing an association between the pixel and the spectral data identifier, the corresponding spectral data can be quickly located, improving the speed and efficiency of data access.

[0100] Third, enhance the flexibility and scalability of the system: The above scheme enables the system to flexibly handle changes in spectral image data. Whether it is replacing the spectral data of the current pixel with the spectral data of the previous pixel, or maintaining the spectral data of the current pixel unchanged and generating a new spectral data identifier, the system can be adjusted and optimized according to actual needs. This flexibility helps the system adapt to different monitoring scenarios and changes in demand, and also facilitates the expansion and upgrade of the system.

[0101] Fourth, improve the accuracy and reliability of monitoring: By optimizing the processing method and storage structure of spectral image data, it helps to improve the accuracy and reliability of monitoring. Consistent and optimized spectral data provides a more accurate data basis for subsequent feature extraction and classification processing, so as to more accurately judge whether the pollution discharge behavior of the monitored factory meets the water quality standards. At the same time, the centralized management and efficient access to spectral data also ensures the continuity and stability of the monitoring process and improves the reliability of the system.

[0102] In summary, the technical measures taken in replacing the spectral data of the current pixel with the spectral data of the previous pixel and maintaining the spectral data of the current pixel unchanged not only improve the consistency and storage efficiency of the spectral image data, but also enhance the flexibility and scalability of the system, thereby improving the accuracy and reliability of monitoring.

[0103] In some possible implementations, feature extraction is performed on the third spectral image data, and the extracted features are classified to obtain water quality parameters of the water body corresponding to the third spectral image, specifically including: S41, extracting features from each spectral data in the shared storage area, and classifying the extracted features to obtain water quality parameters corresponding to each spectral data.

[0104] Among them, for the monitored substance, the absorption of light at different wavelengths by the substance in different concentration ranges is obtained. The characteristic wavelength is selected from the absorption of light at different wavelengths, and the absorption of the characteristic wavelength is used to characterize the concentration of the monitored substance. That is, a mapping relationship between the absorption of the characteristic wavelength and the concentration of the monitored substance is established.

[0105] For each spectral data, the wavelength corresponding to the absorption peak in the spectral data is extracted, and the wavelength corresponding to the absorption peak is compared with the characteristic wavelength of each monitored substance. If the wavelength corresponding to the absorption peak is the same as the characteristic wavelength of each monitored substance, it means that the water body contains the substance, and the substance content can be determined based on the mapping relationship between the intensity corresponding to the absorption peak and the absorption amount of the characteristic wavelength and the monitored substance.

[0106] For example, if substance A absorbs more at wavelength λm, and other monitored substances do not absorb wavelength λm, then wavelength λm is used as the characteristic wavelength of substance A, and the absorption rate of substance A at wavelength λm at different concentrations is obtained. By analyzing the data collected by the hyperspectral detector and determining that the absorption peak wavelength is near wavelength λm, it can be determined that substance A is contained in the water, and the concentration of substance A can be determined based on the light intensity at the absorption peak wavelength.

[0107] S42: Obtain the water quality parameter of the water area corresponding to each pixel point according to the spectral data identifier associated with each pixel point and the water quality parameter of the spectral data associated with each spectral data identifier.

[0108] The water quality parameters include the content of each monitored substance. By performing feature extraction and classification processing on each spectral data in the shared storage area, the content of the monitored substance corresponding to each spectral data is obtained, and then the water quality parameters corresponding to the spectral data are obtained.

[0109] The spectral data of each pixel point can be obtained from the common storage area through the spectral data identifier. The water quality parameters of the spectral data are also stored in the common storage area. Then, the water quality parameters of the water area corresponding to each pixel point can be obtained from the common storage area.

[0110] In the above technical solution, the water quality parameters reflected by the spectral data are obtained by analyzing and processing the spectral data in the shared storage area, and then the water quality parameters reflected by the spectral data are associated with each pixel point through the spectral data identifier, so that the water quality parameters of the water area corresponding to each pixel point can be obtained. Since there is a large amount of identical data in the third spectral image data after the replacement process, it is not necessary to process the spectral data of each pixel, and only the spectral data in the shared storage area is processed, which can reduce the amount of data processing and improve data processing efficiency.

[0111] It is worth noting that the above solution has at least the following technical effects: First, improve data processing efficiency: By extracting features and classifying each spectral data in the shared storage area, rather than processing the spectral data of each pixel separately, the amount of data processing is significantly reduced. Since the spectral data of adjacent pixels are often similar, there will be a large amount of identical spectral data in the third spectral image data after replacement processing. This method avoids repeated calculation of the features of the same spectral data, thereby improving data processing efficiency and enabling the system to respond to monitoring needs more quickly.

[0112] Second, enhance the accuracy of data processing: Feature extraction and classification processing are based on the entire spectral data set, which helps to capture more comprehensive spectral feature information. By centrally processing spectral data in a shared storage area, more abundant data samples can be used for feature extraction and model training, thereby improving classification accuracy. This improvement in accuracy helps to more accurately determine water quality parameters and reduce the probability of false alarms and missed reports.

[0113] Third, optimize resource utilization: spectral data is stored in a shared storage area, and an association is established between spectral data identifiers and pixel points to achieve centralized management and efficient access to data. This storage method avoids repeated storage and redundant processing of data and optimizes the utilization of system resources. At the same time, by reducing the amount of data processing, the demand for computing resources is also reduced, allowing the system to achieve higher performance under limited hardware conditions.

[0114] Fourth, support real-time monitoring and early warning: efficient feature extraction and classification processing enable the system to obtain water quality parameters more quickly, thus supporting real-time monitoring and early warning functions. When abnormal water quality parameters are detected, the system can quickly trigger the early warning mechanism and notify relevant departments to take countermeasures. This real-time monitoring and early warning capability is of great significance for timely detection and prevention of illegal sewage discharge.

[0115] To sum up, through the above scheme, the technical measures taken in feature extraction and classification processing of the third spectral image data not only improve the data processing efficiency and accuracy, but also optimize resource utilization and support real-time monitoring and early warning functions, thereby jointly improving the overall performance and monitoring effect of the system.

[0116] In some embodiments, before receiving the first spectral image data returned by the drone, the method further includes: S51. The backend server receives the two-dimensional image data returned by the drone, and performs suspended matter recognition and oil pollution recognition on the two-dimensional image data.

[0117] Among them, the drone is equipped with a hyperspectral detector and an image sensor. When the drone monitors a sewage outlet, it first turns on the image sensor to collect two-dimensional image data with less data volume. The existing image recognition method is used to identify suspended matter and oil pollution in the two-dimensional image data.

[0118] S52: If no suspended matter or oil pollution is identified, the backend server sends a start instruction of the hyperspectral detector to the drone, so that the hyperspectral detector carried by the drone collects the first spectral image data.

[0119] Among them, if suspended matter and oil pollution are not identified, it is necessary to analyze the composition of the water body at the sewage outlet, collect the first spectral image data by the hyperspectral detector, and the background server analyzes the first spectral image data to obtain the water quality parameters of the water body at the sewage outlet.

[0120] S53: If suspended matter and oil pollution are identified, the background server controls the drone to continue to fly along the flight path to the next sewage outlet.

[0121] In the above technical solution, since the amount of data collected by the hyperspectral detector is relatively large, in order to further reduce the amount of data processing of the background server, an image sensor is also mounted on the drone, and the image sensor collects image data, and the image data includes the grayscale values ​​of multiple pixels. The image data is identified and analyzed by the existing image processing method to determine whether there are visible pollutants in the monitored waters. After no visible pollutants are monitored, the hyperspectral detector is then turned on to reduce the amount of data collected, reduce the amount of data processing of the background server, and improve monitoring efficiency.

[0122] It is worth noting that the above solution has at least the following technical effects: First, reduce unnecessary data collection: Before receiving the first spectral image data returned by the drone, identify suspended matter and oil pollution in the image data collected by the drone. If no suspended matter and oil pollution are identified in the image, it means that the water quality in the area may be relatively clear and there are no obvious pollutants visible to the naked eye. At this time, instruct the drone to turn on the hyperspectral detector to collect fine spectral image data, which can effectively avoid unnecessary hyperspectral data collection in areas without obvious pollution, thereby reducing the amount of data collection and alleviating the processing burden of the background server.

[0123] Second, improve monitoring efficiency: By first identifying suspended matter and oil pollution in image data, areas that may be polluted can be quickly screened out. For areas without obvious pollution, the monitoring frequency can be reduced or the hyperspectral data collection step can be skipped to focus limited monitoring resources on areas where problems are more likely to be found. This targeted monitoring strategy significantly improves monitoring efficiency, allowing the system to respond to and handle real pollution incidents more quickly.

[0124] Third, optimize resource utilization: The amount of data collected by the hyperspectral detector is usually large, and processing this data requires more computing resources and time. By preprocessing and identifying the image data first, it is possible to avoid wasting resources in areas where hyperspectral data is not needed. This resource optimization strategy enables the system to achieve higher performance and longer battery life under limited hardware conditions.

[0125] Fourth, improve monitoring accuracy: Although the identification of suspended matter and oil pollution by image data is a relatively rough monitoring method, it can reflect the initial status of water quality to a certain extent. By combining this preliminary identification with the detailed analysis of hyperspectral data, a complementary monitoring system can be formed. If no obvious pollution is found in the preliminary identification, the collection and analysis of hyperspectral data can more accurately judge the water quality status and reduce the possibility of false alarms and missed reports.

[0126] To sum up, in the above scheme, adding the step of identifying suspended matter and oil pollution on the image data before receiving the first spectral image data returned by the drone has multiple technical effects such as reducing unnecessary data collection, improving monitoring efficiency, optimizing resource utilization, and improving monitoring accuracy, thereby jointly improving the overall performance and monitoring effectiveness of the system.

[0127] Some embodiments of the present application provide an intelligent monitoring method based on a drone, which specifically includes the following steps: S601. The backend server obtains the pollution discharge standard of the factory to be monitored, the real-time pollution discharge data of the factory to be monitored, and the terrain data of the area to be monitored.

[0128] The pollution discharge standards of the factory to be monitored include the required pollution discharge time, the maximum pollution discharge amount and the water quality standard. The pollution discharge standards are extracted from the pollution discharge specification file by reading the pollution discharge specification file.

[0129] The real-time sewage discharge data of the factory to be monitored includes the discharge time, discharge volume and sewage quality. The sewage outlet of the factory to be monitored is equipped with detection equipment, for example: a flow detector is provided to detect the discharge time and discharge volume of the sewage outlet. Another example: a water quality detector is provided to detect the sewage quality of the sewage outlet.

[0130] The topographic data of the area to be monitored includes the location of the factory to be monitored and the flow path of the river. The topographic data is obtained by collecting data on the area to be monitored through map surveying and mapping equipment.

[0131] S602: The backend server generates a flight mission according to the pollution discharge standard of the factory to be monitored, the real-time pollution discharge data of the factory to be monitored, and the terrain data of the area to be monitored.

[0132] The flight mission includes at least one flight path and the flight time of each flight path.

[0133] By analyzing and processing the real-time sewage discharge data of the monitored factory, it is determined whether the monitored factory discharges sewage in accordance with the regulations. For example: determine whether the monitored factory discharges sewage at the required discharge time, whether the water quality of the sewage discharged by the monitored factory meets the water quality standards, and whether the sewage discharge volume of the monitored factory is less than the maximum discharge volume.

[0134] If the factory to be monitored discharges pollutants in accordance with the regulations, the number of flights in the area can be reduced when formulating flight missions. If the factory to be monitored does not discharge pollutants in accordance with the regulations, the number of flights in the area can be increased when formulating flight missions.

[0135] In the above technical scheme, by obtaining the pollution discharge standards of the factory to be monitored, the real-time pollution discharge data of the factory to be monitored and the terrain data of the area to be monitored, a flight mission is generated based on the pollution discharge standards of the factory to be monitored, the real-time pollution discharge data of the factory to be monitored and the terrain data of the area to be monitored. The task can be executed with real-time reference to the pollution discharge situation of the factory to be monitored, and targeted monitoring can be carried out to improve the monitoring efficiency and accuracy.

[0136] It is worth noting that the above solution has at least the following technical effects: First, improve the pertinence and effectiveness of monitoring: By obtaining the pollution discharge standards, real-time pollution discharge data of the factories to be monitored, and the terrain data of the areas to be monitored, we can fully understand the pollution discharge situation of the factories and the environmental characteristics of the monitored areas. The flight missions generated based on this information can more accurately locate factories and areas where illegal discharge may occur, thereby improving the pertinence and effectiveness of monitoring. This targeted monitoring strategy helps reduce ineffective monitoring and waste of resources, and improves overall monitoring efficiency.

[0137] Second, optimize the flight path and task allocation of drones: When generating flight tasks, a more reasonable and efficient flight path can be developed by comprehensively considering the pollution discharge standards, real-time pollution discharge data and terrain data of the factories to be monitored. This can not only reduce the flight distance and time of drones, reduce energy consumption and costs, but also ensure that drones can cover all key areas that need to be monitored. At the same time, according to the pollution discharge conditions and monitoring needs of each factory, the monitoring tasks of drones can be reasonably allocated to avoid duplication of work and monitoring blind spots, and improve the overall monitoring quality.

[0138] Third, improve the intelligence and automation level of the system: By introducing a data-driven task generation mechanism, the scheduling and flight path allocation of drones are made more intelligent and automated. The system can automatically adjust flight tasks and paths based on real-time sewage discharge data and terrain data without manual intervention or frequent adjustments. This intelligent and automated scheduling method not only improves the response speed and flexibility of the system, but also reduces errors and risks caused by human factors.

[0139] Fourth, enhance the adaptability and scalability of the system: the flight missions and paths can be flexibly adjusted to meet new monitoring needs. This adaptability and scalability enables the system to operate stably for a long time and continuously optimize and upgrade as the monitoring area expands and the monitoring needs increase. At the same time, the system can also add new functional modules or optimize existing algorithms according to actual needs to further improve the system's performance and monitoring effect.

[0140] To sum up, in the above scheme, before scheduling the UAV based on the flight mission and the flight capability of the UAV, adding the step of obtaining the pollution discharge standards, real-time pollution discharge data and terrain data of the factory to be monitored, and generating the flight mission based on these data, has multiple technical effects such as improving the targetedness and effectiveness of monitoring, optimizing the flight path and task allocation of the UAV, improving the intelligence and automation level of the system, and enhancing the adaptability and scalability of the system.

[0141] In a possible implementation, the real-time pollution data of the factory to be monitored includes historical pollution data and current pollution data, and both current pollution data and historical pollution data include pollution time, pollution volume, and sewage quality. Accordingly, S602, the backend server generates a flight mission according to the pollution standard of the factory to be monitored, the real-time pollution data of the factory to be monitored, and the terrain data of the area to be monitored, specifically including: S71. For any factory to be monitored, the backend server determines whether the pollution discharge of the factory to be monitored meets the emission standard according to the pollution discharge standard of the factory to be monitored and the pollution discharge data of the day. If yes, enter S72; if not, increase the monitoring times weight of the factory to be monitored to the default value.

[0142] Among them, determine whether the pollution discharged by the monitored factory meets the emission standards, including: Determine whether the pollution discharge time of the monitored factory is within the required discharge time.

[0143] Determine whether the wastewater quality of the monitored factory meets the water quality requirements.

[0144] Determine whether the pollutant discharge of the monitored factory is less than or equal to the maximum pollutant discharge.

[0145] If any of the above items does not meet the requirements, it is determined that the pollutant discharge of the monitored factory does not meet the emission standards. If all three of the above items meet the requirements, it is determined that the pollutant discharge of the monitored factory meets the emission standards.

[0146] If the pollution discharge of the monitored factory meets the emission standards, it is further judged whether the monitored factory has the possibility of illegal discharge. If the pollution discharge of the monitored factory does not meet the emission standards, the monitoring frequency weight of the monitored factory is increased.

[0147] S72: If the pollution discharge of the monitored factory meets the emission standard, the untrained pollution discharge prediction model is trained with the historical pollution discharge data to obtain a trained pollution discharge prediction model. The trained pollution discharge prediction model is used to obtain the predicted pollution discharge amount of the day.

[0148] Among them, the historical pollution discharge data of each day in the past years are obtained in units of days, and the pollution discharge prediction model is trained with the historical pollution discharge data of each day in the past years. After receiving the date information, the trained pollution discharge prediction model can predict the pollution discharge of the day.

[0149] S73. Calculate the difference between the predicted pollution discharge volume for the day and the actual pollution discharge volume in the pollution discharge data for the day, and determine whether the difference is greater than the preset difference threshold. If so, increase the monitoring times weight of the factory to be monitored; if not, maintain the monitoring times weight of the factory to be monitored at the default value.

[0150] Among them, if the difference between the current predicted pollutant discharge and the actual pollutant discharge is relatively large, the possibility of the monitored factory secretly discharging is relatively high, and the monitoring of the monitored factory needs to be strengthened. If the difference between the current predicted pollutant discharge and the actual pollutant discharge is relatively small, the risk of the monitored factory secretly discharging is relatively small, and the monitoring of the monitored factory can be reduced.

[0151] For any factory to be monitored, through step S71, step S72 and step S73, it is determined whether the monitoring times weight of the factory to be monitored needs to be updated, so that the monitoring times weight of each factory to be monitored can be obtained.

[0152] S74, inputting the terrain data of the area to be monitored and the weight of the monitoring times of each factory to be monitored into the task generation model to obtain the flight mission generated by the task generation model.

[0153] Among them, the mission generation model can be obtained after training the machine learning model. The input parameters of the mission generation model include the terrain data of the area to be monitored and the weight of the monitoring times of each factory to be monitored. By giving the input parameters of the mission generation model, the mission generation model can output the flight mission.

[0154] If the weight of the monitoring times of the factory to be monitored is larger, the monitoring times of the factory to be monitored are more, and the flight paths including the factory to be monitored are more. If the weight of the monitoring times of the factory to be monitored is smaller, the monitoring times of the factory to be monitored are smaller, and the flight paths including the factory to be monitored are fewer.

[0155] For example, the monitored areas include Factory A, Factory B, and Factory C. The monitoring times of Factory A have the highest weight, while the monitoring times of Factory B and Factory C have the lowest weight. The flight mission contains two flight paths. The first flight path passes through Factory A and Factory B, and the second flight path passes through Factory A and Factory C.

[0156] In the above technical scheme, it is first determined whether the pollution discharge data of a certain factory to be monitored on the day meets the pollution discharge standard. If not, the weight of the monitoring times of the factory to be monitored is increased. If the pollution discharge standard is met, the pollution discharge volume of the day is further predicted based on the historical pollution discharge data. It is determined whether the difference between the actual pollution discharge volume and the predicted volume on the day is large, and the weight of the monitoring times of the factory to be monitored is increased. On the contrary, if the difference is relatively small, the weight of the monitoring times of the factory to be monitored is maintained unchanged. By determining whether to maintain the monitoring times weight as the default value through two-level judgment conditions, more accurate monitoring can be achieved, thereby reducing the risk of the factory to be monitored controlling the pollution discharge data within the standard data through illegal discharge. Compared with increasing the monitoring times for all factories to be monitored, increasing the monitoring times weight of the factory to be monitored in a targeted manner can reduce the flight distance of the drone and the amount of data collected.

[0157] It is worth noting that the above solution has at least the following technical effects: First, improve the pertinence and effectiveness of monitoring: The system first directly determines whether the factory's pollution discharge meets the regulatory requirements based on the pollution discharge standards of the factory to be monitored and the pollution discharge data of the day. For factories that do not meet the regulations, the monitoring frequency weight is immediately increased to ensure that these high-risk areas receive more attention. This immediate response mechanism improves the pertinence of monitoring, allowing resources to quickly tilt toward problem areas, effectively curbing the illegal discharge of sewage.

[0158] Second, optimize the allocation of monitoring resources and improve monitoring efficiency: For factories that meet the pollution discharge regulations for the day, the system does not immediately relax its vigilance, but further uses historical pollution discharge data to train the pollution discharge prediction model and predict the pollution discharge volume for the day. By comparing the difference between the predicted pollution discharge volume and the actual pollution discharge volume, the system can identify those factories that are currently compliant but may have potential risks. This risk assessment method based on data prediction allows monitoring resources to be more reasonably allocated to those factories that really need attention, avoiding waste of resources and improving overall monitoring efficiency.

[0159] Third, enhance the intelligence and automation level of the system: The entire flight mission generation process is highly dependent on data analysis and model prediction, without excessive human intervention. The system can automatically collect, process and analyze data, dynamically adjust the monitoring strategy based on the analysis results, and generate corresponding flight missions. This intelligent and automated operation mode not only reduces the errors caused by human factors, but also greatly improves the response speed and flexibility of the system, making the monitoring work more efficient and accurate.

[0160] Fourth, improve data utilization efficiency and decision-making support capabilities: By making full use of the current day's pollution data and historical pollution data, the system can not only monitor the factory's pollution behavior in real time, but also provide strong support for future monitoring work through data analysis and model prediction. These data not only provide a basis for current monitoring tasks, but also provide valuable information resources for decision makers to formulate long-term environmental protection policies and regulatory measures. This data-driven decision-making support capability makes the system's monitoring work more scientific, reasonable and effective.

[0161] To sum up, in the above scheme, the flight mission is generated by comprehensively considering the pollution discharge standards of the factories to be monitored, the real-time pollution discharge data and the terrain data of the areas to be monitored. This not only improves the pertinence and effectiveness of monitoring, optimizes the allocation of monitoring resources, but also enhances the intelligence and automation level of the system, improves data utilization efficiency and decision-making support capabilities, and thus provides a strong guarantee for effectively combating the illegal discharge of sewage.

[0162] In another possible implementation, S602, the backend server generates a flight mission according to the pollution discharge standard of the factory to be monitored, the real-time pollution discharge data of the factory to be monitored, and the terrain data of the area to be monitored, specifically including: S81. For each factory to be monitored, a discharge time coefficient is set according to the discharge time of the factory to be monitored and the required discharge time.

[0163] More specifically, it is determined whether the discharge time of the monitored factory is within the required discharge time. If yes, the discharge time coefficient is set to a first value, and if no, the discharge time coefficient is set to a second value, wherein the first value is smaller than the second value.

[0164] S82. For each factory to be monitored, set the discharge water quality coefficient according to the discharge water quality and water quality requirements of the factory to be monitored.

[0165] More specifically, it is determined whether the quality of the discharged water of the monitored factory meets the water quality standard. If yes, the discharged water quality coefficient is set to a third value, and if no, the discharged water quality coefficient is set to a fourth value. The third value is less than the fourth value.

[0166] S83. For each factory to be monitored, a pollutant discharge coefficient is set according to the pollutant discharge amount and the maximum pollutant discharge amount of the factory to be monitored.

[0167] More specifically, it is determined whether the pollutant discharge of the factory to be monitored is less than or equal to the maximum pollutant discharge. If so, the pollutant discharge coefficient is set to the fifth value; if not, the pollutant discharge coefficient is set to the sixth value.

[0168] Among them, the fifth value is smaller than the sixth value.

[0169] S84. For each factory to be monitored, the trained pollution discharge prediction model is used to obtain the predicted pollution discharge of the day, and the emission prediction coefficient is set according to the predicted pollution discharge of the day and the actual pollution discharge in the pollution discharge data of the day.

[0170] More specifically, the difference between the predicted pollutant discharge of the day and the actual pollutant discharge in the pollutant discharge data of the day is calculated, and it is determined whether the difference is greater than a preset difference threshold. If so, the emission prediction coefficient is set to the seventh value, and if not, the emission prediction coefficient is set to the eighth value. The seventh value is less than the eighth value.

[0171] S85. For each factory to be monitored, generate a monitoring times weight for the factory to be monitored according to the discharge time coefficient, the discharge water quality coefficient, the discharge volume coefficient and the discharge prediction coefficient.

[0172] More specifically, the weighted average of the discharge time coefficient, the discharge water quality coefficient, the discharge volume coefficient and the discharge prediction coefficient is performed to calculate the weight of the monitoring times of the factory to be monitored.

[0173] For any factory to be monitored, through steps S81 to S85, the monitoring times weight of the factory to be monitored is calculated, so that the monitoring times weight of each factory to be monitored can be obtained.

[0174] S86. Input the terrain data of the area to be monitored and the weight of the monitoring times of each factory to be monitored into the task generation model to obtain the flight mission generated by the task generation model.

[0175] This step has been described in detail in the above embodiment and will not be repeated here.

[0176] In the above technical scheme, the discharge time system, discharge water quality coefficient, discharge volume coefficient and discharge prediction coefficient are calculated respectively according to the discharge time, discharge water quality, discharge volume and predicted discharge volume of the factory to be monitored, and the monitoring times weight of the factory to be monitored is calculated based on the above four coefficients. Compared with increasing the monitoring times for all factories to be monitored, increasing the monitoring times weight of the factories to be monitored in a targeted manner can reduce the flight distance of the drone and the amount of data collection.

[0177] It is worth noting that the above solution has at least the following technical effects: First, improve the level of refinement and personalization of monitoring: For each factory to be monitored, the system sets corresponding coefficients (discharge time coefficient, discharge water quality coefficient, discharge volume coefficient) based on multiple dimensions such as discharge time, discharge volume, and discharge water quality. These coefficients reflect multiple key aspects of the factory's discharge behavior. By comprehensively considering these coefficients, the system can more comprehensively evaluate the factory's discharge situation and generate personalized monitoring tasks based on the evaluation results. This refined and personalized monitoring strategy enables the system to more effectively identify potential illegal discharge of sewage.

[0178] Second, enhance prediction capabilities and respond to potential risks in advance: The system uses the trained pollution prediction model, combined with the factory's real-time pollution data and historical data, to predict the pollution discharge volume of the day and set the emission prediction coefficient accordingly. This step enables the system to identify in advance those factories that are currently compliant with pollution discharge but may have potential risks. By increasing the weight of the number of monitoring times for these factories, the system can respond to potential risks in advance and prevent the occurrence of illegal sewage discharge.

[0179] Third, optimize flight mission generation and improve monitoring efficiency: When generating flight missions, the system comprehensively considers the terrain data of the area to be monitored and the monitoring frequency weight of each factory. The terrain data provides an important reference for the flight path planning of the drone, while the monitoring frequency weight ensures that high-risk areas receive more attention. By optimizing flight mission generation, the system can ensure that the drone covers as many high-risk areas as possible within a limited time, thereby improving overall monitoring efficiency.

[0180] Fourth, improve data utilization efficiency and decision-making support capabilities: The system analyzes real-time pollution data in multiple dimensions, which not only improves the level of refinement and personalization of monitoring, but also provides decision makers with richer and more accurate information support. Decision makers can formulate more scientific and reasonable environmental protection policies and regulatory measures based on the multi-dimensional pollution data and monitoring task execution provided by the system. This data-driven decision-making support capability makes the system's monitoring work more in line with actual needs and more effective.

[0181] In summary, in the above scheme, by analyzing the real-time sewage discharge data in multiple dimensions and generating flight missions based on it, not only the level of monitoring refinement and personalization is improved, the prediction ability of the system is enhanced, but also the flight mission generation process is optimized and the monitoring efficiency is improved. At the same time, this strategy also improves the data utilization efficiency and decision-making support capabilities, providing a strong guarantee for effectively combating the illegal discharge of sewage.

[0182] The background server provided in this embodiment includes: at least one processor and a memory. Optionally, the device also includes a communication component. The processor, the memory and the communication component are connected via a bus.

[0183] In a specific implementation process, at least one processor executes computer-executable instructions stored in a memory, so that at least one processor executes the above method.

[0184] The specific implementation process of the processor can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0185] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0186] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0187] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0188] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0189] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0190] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0191] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0192] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0193] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0194] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0195] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0196] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0197] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. An intelligent monitoring method based on drones, characterized in that: Applied to a backend server, the method comprises: The UAV is scheduled based on the flight mission and the flight capability of the UAV, and a corresponding flight path is assigned to the UAV; so that the UAV flies along the flight path during the flight time, and controls the carried hyperspectral detector to collect first spectral image data; the flight mission includes at least one flight path and the flight time of the flight path; Receiving the first spectral image data returned by the drone, preprocessing the first spectral image data, and obtaining second spectral image data; For the current pixel point of each row of pixels in the second spectral image data, determine whether the spectral data of the previous pixel point and the spectral data of the current pixel point meet the replacement condition, and if so, use the spectral data of the previous pixel point to replace the spectral data of the current pixel point; if not, keep the spectral data of the current pixel point unchanged, traverse all the pixel points of each row of pixels in the second spectral image data, and obtain the third spectral image data; Extracting features from the third spectral image data, and classifying the extracted features to obtain water quality parameters of the water area corresponding to the third spectral image; It is determined whether the sewage discharged by the monitored factory meets the water quality standard according to the water quality parameters of the water area corresponding to the third spectral image.

2. The method according to claim 1, characterized in that Replacing the spectral data of the current pixel point with the spectral data of the previous pixel point specifically includes: Acquire the spectral data identifier associated with the previous pixel point, and establish an association relationship between the current pixel point and the spectral data identifier associated with the previous pixel point; wherein there is a mapping relationship between the spectral data identifier and the common spectral data, and the common spectral data is stored in a common storage area; Accordingly, the spectrum data of the current pixel point is maintained unchanged, specifically including: A new spectral data identifier is randomly generated, the spectral data of the current pixel point is used as new common spectral data, the new common spectral data is stored in a common storage area, and an association relationship between the current pixel point and the new spectral data identifier is established.

3. The method according to claim 2, characterized in that Extracting features from the third spectral image data and classifying the extracted features to obtain water quality parameters of the water body corresponding to the third spectral image specifically includes: Extracting features from each spectral data in the shared storage area, and classifying the extracted features to obtain water quality parameters corresponding to each spectral data; The water quality parameter of the water area corresponding to each pixel point is obtained according to the spectral data identifier associated with each pixel point and the water quality parameter of the spectral data associated with each spectral data identifier.

4. The method according to any one of claims 1 to 3, characterized in that The spectral data includes light intensities of multiple bands. The determination of whether the spectral data of the previous pixel and the spectral data of the current pixel meet the replacement condition specifically includes: Calculate the light intensity difference between the light intensity of each band of the previous pixel and the light intensity of the corresponding band of the current pixel to obtain the light intensity difference of multiple bands; Calculate the average value of the light intensity difference of all bands, and calculate the variance of the light intensity difference of all bands; If the average value of the light intensity difference is less than a preset average value threshold, and the variance of the light intensity difference is less than a preset variance threshold, it is determined that the replacement condition is met; If the average value of the light intensity difference is greater than or equal to a preset average value threshold, or the variance of the light intensity difference is greater than or equal to a preset variance threshold, it is determined that the replacement condition is not met.

5. The method according to any one of claims 1 to 3, characterized in that: Preprocessing the first spectral image data to obtain second spectral image data specifically includes: De-noising the first spectral image data to obtain denoised spectral image data; Performing baseline correction on the denoised spectral image data to obtain baseline-corrected spectral image data; The baseline-corrected spectral image data is subjected to black-and-white correction to obtain the third spectral image data.

6. The method according to any one of claims 1 to 3, characterized in that: Before scheduling the drone based on the flight mission and the flight capability of the drone and assigning the corresponding flight path to the drone, the method further includes: Obtain the pollution discharge standards of the factories to be monitored, the real-time pollution discharge data of the factories to be monitored, and the terrain data of the areas to be monitored; The flight mission is generated according to the pollution discharge standard of the factory to be monitored, the real-time pollution discharge data of the factory to be monitored, and the terrain data of the area to be monitored.

7. The method according to claim 6, characterized in that The real-time sewage discharge data includes the sewage discharge data of the day and the historical sewage discharge data, and the sewage discharge data includes the sewage discharge time, sewage discharge amount and sewage quality; Accordingly, generating the flight mission according to the pollution discharge standard of the factory to be monitored, the real-time pollution discharge data of the factory to be monitored and the terrain data of the area to be monitored specifically includes: For each factory to be monitored, the discharge time coefficient is set according to the discharge time of the factory to be monitored and the required discharge time; the discharge water quality coefficient is set according to the discharge water quality and water quality requirements of the factory to be monitored; the discharge volume coefficient is set according to the discharge volume and maximum discharge volume of the factory to be monitored; For each factory to be monitored, the trained pollution emission prediction model is used to obtain the predicted pollution emission of the day; and the emission prediction coefficient is set according to the predicted pollution emission of the day and the actual pollution emission in the pollution emission data of the day; For each factory to be monitored, a monitoring times weight of each factory to be monitored is generated according to the discharge time coefficient, the discharge water quality coefficient, the discharge volume coefficient and the discharge prediction coefficient; The terrain data of the area to be monitored and the weight of the monitoring times of each factory to be monitored are input into the task generation model to obtain the flight task generated by the task generation model.

8. An intelligent monitoring system based on drones, characterized in that: The method comprises a drone and a background server, wherein the drone is equipped with a hyperspectral detector and an image sensor, and the background server is used to execute the method as claimed in any one of claims 1 to 7.

9. An electronic device, characterized in that: include: processor; as well as, A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images