An evaluation and early warning method for marine disaster-bearing bodies based on drones and geographical grids

Abstract

The present invention discloses a method for evaluating and warning marine disaster-bearing bodies based on unmanned aerial vehicles and geographical grids, belonging to the technical field of marine disaster-bearing body evaluation, and comprising the following steps: Step S1. Determining the evaluation area and establishing a monitoring network: determining the range of the disaster-bearing body area to be evaluated, burying a plurality of first sensors within the disaster-bearing body area, dividing geographical grids based on the positions of the first sensors, connecting the first sensors to a preset data processing system to form a monitoring network, and realizing real-time collection and transmission of data; Step S2. Receiving monitoring data and preprocessing the data: receiving and monitoring marine disaster data, when the marine disaster data reaches a first preset threshold, enabling the first sensors to collect corresponding data of the disaster-bearing body area at a preset frequency, collecting the data of the first sensors, and performing data preprocessing. The invention improves the real-time performance and accuracy of the evaluation, and enhances the monitoring and warning capabilities for marine disasters.

Description

Technical Field

[0001] The present invention belongs to the technical field of marine disaster-bearing body evaluation, and particularly relates to a method for evaluating and warning marine disaster-bearing bodies based on unmanned aerial vehicles and geographical grids. Background Art

[0002] A geographical grid is a grid system that divides the Earth's surface into regular grids, and each grid unit represents a specific geographical area. This grid system can be used for the organization, storage, and query of spatial data. Marine disaster-bearing bodies refer to various entities in the marine environment that may be affected by natural disasters (such as storm surges, tsunamis, typhoons, etc.), including but not limited to coastal cities, infrastructure, ecosystems, fishery resources, etc.

[0003] The impacts of marine disasters on marine disaster-bearing bodies in different regions are different. In order to effectively manage and mitigate the impacts brought by marine disasters, it is crucial to scientifically evaluate and compare the impacts suffered by marine disaster-bearing bodies in different regions. This not only helps to formulate targeted disaster prevention and mitigation measures but also provides an important basis for resource allocation, emergency response, and long-term planning. Therefore, how to evaluate the impacts on marine disaster-bearing bodies in different regions is an urgent problem to be solved. Summary of the Invention

[0004] Aiming at the problems existing in the prior art, the present invention provides a method for evaluating and warning marine disaster-bearing bodies based on unmanned aerial vehicles and geographical grids, which has the advantage of being able to evaluate the impacts on marine disaster-bearing bodies in different regions and solves the problems of the prior art.

[0005] The present invention is implemented as follows. A method for evaluating and warning marine disaster-bearing bodies based on unmanned aerial vehicles and geographical grids includes the following steps:

[0006] Step S1. Determine the evaluation area and establish a monitoring network: Determine the range of the disaster-bearing body area to be evaluated, bury a number of first sensors within the disaster-bearing body area, divide the geographical grid based on the positions of the first sensors, and connect the first sensors to a preset data processing system to form a monitoring network to achieve real-time data collection and transmission;

[0007] Step S2. Receive monitoring data and preprocess the data: Receive and monitor marine disaster data (such as typhoons, heavy rains, tsunamis, etc.). When the marine disaster data reaches the first preset threshold, make the first sensors collect the corresponding data of the disaster-bearing body area at a preset frequency, collect the data of the first sensors, and then preprocess the data;

[0008] Step S3. Construct a virtual grid and conduct early warning simulation: Construct a virtual grid, simulate the actual disaster-bearing body area, and conduct early warning on the virtual grid according to the preprocessed data;

[0009] Step S4. The drone collects image data: The drone flies along the virtual grid while taking photos to obtain the images within the virtual grid.

[0010] Step S5. Image processing and impact analysis: Use the SETR technology to process the images and compare the images to quantitatively evaluate the impact of marine disasters on the disaster-bearing bodies.

[0011] Preferably, step S1 of the present invention includes the following steps:

[0012] Step S11. Determine the range of the disaster-bearing body area: Determine the disaster-bearing body area to be evaluated on the map and preliminarily set the preset positions of the first sensors.

[0013] Step S12. Bury the first sensors: Set a number of concentric rings with the preset positions of the first sensors as the centers, and bury the first sensors at the center or in a certain concentric ring. The closer to the center, the higher the priority.

[0014] Step S13. Conduct geographical grid division: Connect the actual positions of adjacent first sensors to form a geographical grid.

[0015] Step S14. Establish a monitoring network: Connect all the first sensors to the data processing system to form a monitoring network to ensure that data can be collected and transmitted in real time.

[0016] Preferably, step S2 of the present invention includes the following sub-steps:

[0017] Step S21. Connect the data source: Establish a connection with the marine disaster data source to ensure real-time monitoring data.

[0018] Step S22. Set the monitoring data threshold: Set the first preset threshold as the standard for triggering the sensor to collect data.

[0019] Step S23. Judge whether the data reaches the threshold: Real-time monitor the marine disaster data. When the data reaches the first preset threshold, trigger the acquisition mechanism of the first sensor.

[0020] Step S24. Start the sensor: Start the first sensor to collect the corresponding data of the disaster-bearing body area at a preset frequency.

[0021] Step S25. Collect the data of the first sensor: Collect the data collected by the first sensor.

[0022] Step S26. Feature extraction: Extract the features of the collected data.

[0023] Step S27. Data preprocessing: Perform data preprocessing on the extracted feature data.

[0024] Preferably, in step S3 of the present invention, the steps of establishing a virtual grid are as follows:

[0025] Set a number of parallel vertical virtual grid lines and a number of parallel horizontal virtual grid lines;

[0026] Number the first sensors as Q ij , where i is the horizontal number and j is the vertical number;

[0027] Measure the distance from the first sensor Q ij to the corresponding vertical virtual grid line as L ij , and adjust the corresponding vertical virtual grid line left and right until the sum of L ij is minimized;

[0028] Measure the distance from the first sensor Q ij to the corresponding horizontal virtual grid line as M ij , and adjust the corresponding horizontal virtual grid line up and down until the sum of M ij is minimized.

[0029] Preferably, the steps of the early warning are as follows:

[0030] Construct an early warning circle with the actual position of the first sensor as the center and a multiple of the value collected by the first sensor as the radius;

[0031] When the area of the early warning circle is greater than the second preset threshold, perform a first early warning on the area inside the early warning circle;

[0032] When adjacent early warning circles overlap, perform a second early warning on at least part of the virtual grid area containing the overlapping area;

[0033] If the diameter of a certain early warning circle is greater than 80% of the distance between adjacent first sensors and the first early warning is not triggered, perform a third early warning, where the third early warning includes alarming the virtual grid area containing at least part of the early warning circle and warning of damage to the first sensor.

[0034] Preferably, it further includes a fourth early warning, and the steps are as follows:

[0035] Calculate the total length of a certain virtual grid line included by the corresponding early warning circle. When the ratio of the total length of the virtual grid line included by the corresponding early warning circle to the length of the virtual grid line is greater than the third preset threshold, perform early warnings on the virtual grids on both sides of the virtual grid line.

[0036] Preferably, it further includes setting a second sensor. The second sensor is set in the virtual grid, and a number of second sensors are set in each virtual grid; when the early warning circle wraps the second sensor, the second sensor is triggered to perform detection.

[0037] Preferably, step S4 of the present invention includes the following steps:

[0038] Step S41. Fly the UAV along the grid: Make the UAV fly along the path of the virtual grid. During the flight, take pictures of the specified area according to the grid division.

[0039] Step S42. Image data collection: Store the taken photos in the built-in storage device of the UAV or wirelessly transmit them to the ground receiving device.

[0040] Step S43. Acquisition adjustment: Adjust the flight speed of the UAV and the image acquisition of the UAV.

[0041] Preferably, the photographing frequency is controlled by the ratio of the total length of the virtual grid line included in the corresponding warning circle to the length of the virtual grid line, and the photographing frequency is directly proportional to the ratio of the total length of the virtual grid line included in the corresponding warning circle to the length of the virtual grid line.

[0042] The flight speed is controlled by the ratio of the total length of the virtual grid line included in the corresponding warning circle to the length of the virtual grid line, and the flight speed is inversely proportional to the ratio of the total length of the virtual grid line included in the corresponding warning circle to the length of the virtual grid line.

[0043] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0044] 1. Clearly define the evaluation area range, set the first sensor, construct the geographical grid and the monitoring network, and realize real-time data collection and transmission.

[0045] 2. When the marine disaster data reaches the first preset threshold, automatically trigger data collection, and perform feature extraction and preprocessing through the SETR technology to improve the data quality.

[0046] 3. Construct a virtual grid for early warning simulation, use the UAV to collect image data, and perform image processing and impact analysis through the SETR technology to realize the quantitative evaluation of the marine disaster on the disaster-bearing body. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flowchart of the method for evaluating and warning marine disaster-bearing bodies based on UAVs and geographical grids provided by an embodiment of the present invention;

[0048] Figure 2 is a flowchart of determining the evaluation area and establishing the monitoring network provided by an embodiment of the present invention;

[0049] Figure 3 is a flowchart of receiving monitoring data and data preprocessing provided by an embodiment of the present invention;

[0050] Figure 4 is a flowchart for constructing a virtual grid and early warning simulation provided by an embodiment of the present invention;

[0051] Figure 5 is a flowchart for a drone to collect image data provided by an embodiment of the present invention;

[0052] Figure 6 is a schematic diagram of a virtual grid provided by an embodiment of the present invention;

[0053] Figure 7 is a schematic diagram of an early warning circle of a virtual grid provided by an embodiment of the present invention;

[0054] Figure 8 is the first sensor Q provided by an embodiment of the present invention 22 corresponding enlarged schematic diagram of the early warning circle;

[0055] Figure 9 is a schematic diagram of a virtual grid with a second sensor provided by an embodiment of the present invention. Detailed implementation manners

[0056] To further understand the content, features and effects of the present invention, the following embodiments are exemplified and described in detail in conjunction with the accompanying drawings.

[0057] The structure of the present invention will be described in detail below with reference to the accompanying drawings.

[0058] As Figures 1 to 9 shown, a method for evaluating and warning marine disaster-bearing bodies based on drones and geographical grids provided by an embodiment of the present invention includes the following steps:

[0059] Step S1. Determine the evaluation area and establish a monitoring network: Determine the range of the disaster-bearing body area to be evaluated (for example, the following areas: coastal cities, infrastructure, ecosystems, fishery resources), bury a number of first sensors within the disaster-bearing body area, and divide the geographical grid based on the positions of the first sensors to ensure that the grid size is suitable for the burial of the first sensors and subsequent drone flights. Connect the first sensors to a preset data processing system to form a monitoring network to achieve real-time data collection and transmission;

[0060] Step S2. Receive monitoring data and preprocess the data: Receive and monitor marine disaster data (such as typhoons, heavy rains, tsunamis, etc.). When the marine disaster data reaches the first preset threshold, make the first sensors collect the corresponding data of the disaster-bearing body area at a preset frequency, and adjust the preset time according to the actual situation to ensure the timeliness of the data. After collecting the first sensor data, perform data preprocessing, including filtering, denoising, etc., to improve the data quality.

[0061] Step S3. Construct virtual grid and early warning simulation: Construct a virtual grid to simulate the actual disaster-bearing body area, and conduct early warning on the virtual grid according to the preprocessed data;

[0062] Step S4. UAV image data collection: Use a UAV to fly along the virtual grid while taking photos to obtain images within the virtual grid;

[0063] Step S5. Image processing and impact analysis: Use the SETR technology to process the images, and compare the images to quantitatively evaluate the impact of marine disasters on the disaster-bearing bodies.

[0064] In the above settings, it is first necessary to clarify the evaluation area range, such as key areas including coastal cities, infrastructure, ecosystems, and fishery resources, or any area as needed. Then, set the first sensors within the area, and divide the geographical grid with the positions of these first sensors as nodes. Connect the first sensors to the data processing system to form a monitoring network (specifically, it can be connected through wireless signals) to achieve real-time data collection and transmission, ensuring the immediacy and accuracy of information.

[0065] When data of marine disasters such as typhoons, heavy rains, or tsunamis reach the first preset threshold, the system will automatically trigger the first sensors to collect data at a preset frequency. As the disaster data increases, the collection frequency will also increase accordingly to ensure the timeliness and accuracy of the data. Extract features from the data collected by the first sensors, and perform necessary data preprocessing, including steps such as filtering and denoising, to improve the quality and reliability of the data.

[0066] Next, construct a virtual grid to simulate the disaster situation of the disaster-bearing body area based on the preprocessed data. This virtual model can conduct more accurate preliminary early warning to ensure that measures can be taken in a timely manner before the disaster occurs. In addition, use a UAV to fly along the virtual grid while taking high-definition photos to record the image data of the actual disaster-bearing body area, and these image data will provide visual information for subsequent analysis.

[0067] Use the SETR technology to process the collected images, and deeply analyze the impact of marine disasters on the disaster-bearing bodies by comparing the image data, including multiple aspects such as terrain, vegetation, and buildings. Conduct a quantitative evaluation of the impact of marine disasters on the disaster-bearing bodies based on the results of image analysis to provide a scientific basis for disaster prevention and control.

[0068] This method for evaluating and early warning marine disaster-bearing bodies based on UAVs and geographical grids not only improves the real-time performance and accuracy of the evaluation, but also enhances the monitoring and early warning capabilities of marine disasters through the application of high-tech means. This not only helps to reduce the losses caused by disasters, but also provides strong technical support for marine environmental protection and sustainable development.

[0069] In the image analysis stage, the SETR technology can play its advantages in image recognition, segmentation, etc. The photos taken by the drone contain rich image information, but directly analyzing this information may be time-consuming and laborious. The SETR technology can automatically process the images, identify key elements in the images, such as damaged buildings, vegetation coverage, terrain changes, etc. At the same time, it can accurately segment and classify these elements, providing more detailed analysis results of the disaster impact.

[0070] Furthermore, step S1 includes the following steps:

[0071] Step S11. Determine the scope of the disaster-bearing body area: Determine the disaster-bearing body area to be evaluated on the map and initially set the preset position of the first sensor; the disaster-bearing body area can be a coastal city, infrastructure, ecosystem, fishery resources, etc. Determining the area scope is the basis of the entire evaluation process, which will directly affect the implementation of subsequent steps and the accuracy of the evaluation results.

[0072] Step S12. Install the first sensor: Set several concentric rings with the preset position of the first sensor as the center. Considering the specific geographical situation, bury the first sensor at the center or in a certain concentric ring, and the closer to the center, the higher the priority; due to reasons such as the preset position being occupied, it is generally impossible to bury the first sensor exactly at the preset position. Through this setting, the first sensor can be installed as close as possible to the preset position.

[0073] Step S13. Conduct geographical grid division: Connect the actual positions of adjacent first sensors to form a geographical grid;

[0074] Step S14. Establish a monitoring network: Connect all the first sensors to the data processing system to form a monitoring network to ensure real-time data collection and transmission.

[0075] Furthermore, step S2 includes the following sub-steps:

[0076] Step S21. Connect to the data source: Establish a connection with the marine disaster data source to ensure real-time monitoring data;

[0077] Step S22. Set the data monitoring threshold: Set the first preset threshold as the standard for triggering the sensor to collect data;

[0078] Step S23. Judge whether the data reaches the threshold: Real-time monitor the marine disaster data. When the data reaches the first preset threshold, trigger the data collection mechanism of the first sensor;

[0079] Step S24. Sensor startup: Start the first sensor and collect corresponding data of the disaster-bearing body area at a preset frequency;

[0080] Step S25. Collection of data from the first sensor: Collect the data collected by the first sensor;

[0081] Step S26. Feature extraction: Extract features from the collected data;

[0082] Step S27. Data preprocessing: Perform data preprocessing on the extracted feature data, including:

[0083] Step S27a. Filtering process: Use a filtering algorithm to remove noise and interference in the data;

[0084] Step S27b. Denoising process: Eliminate outliers and interference signals in the data through denoising techniques.

[0085] Exemplarily, the specific implementation of the above solution is as follows:

[0086] Connect to the data source: Establish a connection with the ocean disaster data source to ensure real-time monitoring of data.

[0087] Set the monitoring data threshold: Set the first preset threshold. For example, when the typhoon wind speed reaches 100 kilometers per hour, trigger data collection.

[0088] Judge whether the data reaches the threshold: Monitor the ocean disaster data in real time. For example, when the typhoon wind speed reaches 100 kilometers per hour, trigger the acquisition mechanism.

[0089] Sensor startup: Start the first sensor and collect corresponding data of the disaster-bearing body area at a preset frequency (for example, once every 5 minutes). According to the actual situation, such as the intensification of the storm intensity, adjust the preset time to collect data once every 3 minutes to ensure the timeliness of the data.

[0090] Collection of data from the first sensor: Collect the data collected by the first sensor, such as wind speed, wind direction, air pressure, etc.

[0091] Feature extraction: Extract features from the collected data to obtain key features such as wind speed, wind direction, air pressure, etc.

[0092] Data preprocessing: Perform data preprocessing on the extracted feature data, including:

[0093] a. Filtering process: For example, perform low-pass filtering on the wind speed data to remove high-frequency noise.

[0094] b. Denoising process: For example, perform median filtering on the air pressure data to eliminate outliers.

[0095] Examples are as follows:

[0096] Wind speed data: [10, 12, 11, 13, 10, 14, 11, 13, 10, 12, 15, 14, 11, 13, 10, 14, 11, 12, 13, 10]

[0097] After filtering: [11, 12, 11, 12, 11, 13, 11, 12, 11, 12, 13, 12, 11, 12, 11, 12, 11, 12, 12, 11]

[0098] Atmospheric pressure data: [1013, 1012, 1011, 1010, 1013, 1012, 1011, 1010, 1013, 1012, 1011, 1010, 1013, 1012, 1011, 1010, 1013, 1012, 1011, 1010]

[0099] After denoising: [1013, 1012, 1011, 1010, 1013, 1012, 1011, 1010, 1013, 1012, 1011, 1010, 1013, 1012, 1011, 1010, 1013, 1012, 1011, 1010]

[0100] It should be noted that the first sensor can also be set as a rain sensor, an air pollution sensor, etc. An air pollution sensor is a device used to detect and monitor the concentration of pollutants in the air. It can monitor pollutants such as PM2.5, PM10, sulfur dioxide, nitrogen oxides, ozone, etc. in real time. Common types of air pollution sensors include optical sensors, electrochemical sensors, semiconductor sensors, etc.

[0101] Further, in one embodiment, step S3 includes the following steps:

[0102] Step S31. Determine the simulation target: Clearly define the simulation target (such as predicting the impact of a certain natural disaster, such as a typhoon or heavy rain), and screen the required sensor data, and perform data cleaning and formatting on the required sensor data to ensure the accuracy and consistency of the data for subsequent analysis and simulation work.

[0103] Step S32. Virtual grid division: Divide the simulation area into several virtual grids, and each grid represents a specific geographical location, which helps to more finely simulate the impact of disasters on different regions.

[0104] Step S33. Determine the properties of disaster-bearing bodies: Assign corresponding properties to the disaster-bearing bodies within each virtual grid, such as building type, population density, infrastructure conditions, etc. These properties will directly affect the degree of impact of the disaster.

[0105] Step S34. Simulate the impact of disasters: Using the existing data and models, simulate the specific impacts on the disaster-bearing bodies in each grid during the occurrence of disasters, including the losses and casualties caused.

[0106] Step S35. Set warning parameters: According to the simulation results, set the warning parameters, including warning levels, warning times, and warning ranges, to ensure the timeliness and accuracy of warning information.

[0107] Step S36. Output warning results: Output the warning information to the preset population in various forms such as electronic maps, text messages, and broadcasts, to ensure that the information can be quickly conveyed to the people in need.

[0108] The following is an exemplary description:

[0109] Determine the simulation target: Predict the impact of Typhoon Alpha in City H, screen the data of weather stations and water level sensors, and perform data cleaning and formatting.

[0110] Virtual grid division: Divide City H into 100 virtual grids, with each grid having a side length of 1 kilometer.

[0111] Determine the attributes of disaster-bearing bodies: Count the building types (residential, commercial, industrial), population density (number of people per square kilometer), and infrastructure conditions (roads, bridges, power facilities) in each grid.

[0112] Simulate the impact of disasters: It is estimated that Typhoon Alpha will cause damage to buildings in 30 of these grids and casualties in 50 grids, with an economic loss of approximately 500 million yuan.

[0113] Set warning parameters: The warning levels are dark red and light red, the warning time is 6 hours before the typhoon makes landfall, and the warning range covers all areas of City H. Among them, the grids with expected building damage and casualties are warned in dark red, and the rest are in light red.

[0114] Output warning results: Release warning information to the citizens of City H through electronic maps, text messages, and broadcasts to ensure coverage of 100% of the target population.

[0115] It should be noted that the following steps may also be included:

[0116] Step S37. Evaluate the warning effect: Evaluate the actual effect of the warning system, including the timeliness and accuracy of the warning and the public's response, to provide a basis for subsequent improvement.

[0117] Step S38. Result analysis and optimization: Conduct in-depth analysis of the simulation and warning results, identify existing problems and deficiencies, and propose optimization plans to improve the accuracy and effectiveness of future warnings.

[0118] Step S39. Simulation and warning iteration: Apply the optimized warning plan to new simulations and continuously iterate and update to adapt to the changing environment and disaster situations, ensuring the continuous improvement and upgrade of the warning system.

[0119] Furthermore, in another embodiment, since it is not suitable to install the first sensor in all places, the installation position of the first sensor is inaccurate. In this case, the following settings are made:

[0120] In step S3, the steps for establishing the virtual grid are as follows:

[0121] Set a number of parallel vertical virtual grid lines and a number of parallel horizontal virtual grid lines;

[0122] Number the first sensors as Q ij , where i is the horizontal number and j is the vertical number; for example, Q 12 is the second one in the first row;

[0123] Measure the distance from the first sensor Q ij to the corresponding vertical virtual grid line as L ij , for example, they are respectively L 1j , L 2j , L 3j ... Adjust the corresponding vertical virtual grid line left and right until the sum of L ij is the smallest. Exemplarily, the distance from the first sensor Q i1 in the first column to the first vertical virtual grid line is L 11 , L 21 , L 31 .

[0124] Measure the distance from the first sensor Q ij to the corresponding horizontal virtual grid line as M ij , for example, they are respectively M i1 , M i2 , M i3 ... Adjust the corresponding horizontal virtual grid line up and down until the sum of M ij is the smallest. Exemplarily, the distance from the first sensor Q 1j in the first row to the first horizontal virtual grid line is M 11 , M 12 , M 13 .

[0125] Through the above solution, the positions of the virtual grid and the first sensor can be closer, which can improve the correlation between the two. It should be noted that geographical grids are usually irregular. For example, if there is a deviation between the actual installation position and the preset position of the first sensor, each geographical grid area is an irregular quadrilateral. However, through the above settings, each grid area of the virtual grid is a standard rectangle or square. Even if the overall position of the first sensor deviates, the position correlation between the virtual grid and the first sensor can be ensured.

[0126] Further, the steps of the early warning are as follows:

[0127] Taking the actual position of the first sensor as the center and a multiple of the value collected by the first sensor as the radius, an early warning circle is constructed;

[0128] When the area of the early warning circle is greater than the second preset threshold, a first early warning is given to the area inside the early warning circle;

[0129] When adjacent early warning circles overlap, a second early warning is given to at least part of the virtual grid area containing the overlapping area;

[0130] If the diameter of a certain early warning circle is greater than 80% of the distance between adjacent first sensors and the first early warning is not triggered, a third early warning is given. The third early warning includes giving an alarm to the virtual grid area containing at least part of the early warning circle and giving an early warning of damage to the first sensor.

[0131] In the above settings, for example, the value collected by the first sensor is rainfall data, and the rainfall data is 120 mm. Then the multiple of the value collected by the first sensor is 120k, where k is the multiple and can be set artificially. The greater the rainfall, the larger the area of the early warning circle. The rainfall increases linearly, and the area of the early warning circle increases exponentially. When the area of the early warning circle is greater than the second preset threshold, a first early warning is given to the area inside the early warning circle.

[0132] The second early warning indicates that adjacent early warning circles are both large. Giving a second early warning to the virtual grid area where the overlapping area is located can prevent omissions. Generally, the expansion amplitude of adjacent early warning circles is similar. Therefore, the numerical difference between adjacent sensors checked will not be too large. Therefore, the third early warning not only represents that the disaster-bearing body is severely damaged but also represents that the first sensor may be damaged.

[0133] Further, it also includes a fourth early warning, and the steps are as follows: Calculate the total length of a certain virtual grid line included by the corresponding early warning circle. When the ratio of the total length of the virtual grid line included by the corresponding early warning circle to the length of the virtual grid line is greater than the third preset threshold (for example, 60%), early warnings are given to the virtual grids on both sides of the virtual grid line.

[0134] Exemplarily, the middle vertical virtual grid line is covered by the first sensor Q12 The length included in the corresponding warning circle is

[0135] The middle vertical virtual grid line is detected by the first sensor Q 22 The length included in the corresponding warning circle is

[0136] The middle vertical virtual grid line is detected by the first sensor Q 32 The length included in the corresponding warning circle is

[0137] The middle vertical virtual grid line is detected by the first sensor Q 12 The total length included in the corresponding warning circle is

[0138] wherein, R ij is the radius of the warning circle corresponding to the first sensor Q ij corresponding warning circle.

[0139] Furthermore, a second sensor is also included. The second sensor is arranged in the virtual grid, and several second sensors are arranged in each virtual grid; when the warning circle wraps the second sensor, the second sensor is triggered to perform detection.

[0140] In the above setting, the first sensor is used for the large framework, and the second sensor is used for small details; the second sensor is usually in the off state and only starts to work when triggered.

[0141] It should be noted that the disaster-bearing body area can be irregular. The first sensor can be arranged in the entire disaster-bearing body area or only in part of the disaster-bearing body area. Even if the first sensor is only arranged in part of the disaster-bearing body area, a second sensor can be set in the area where the first sensor is not arranged for monitoring. For example, for an area with an outward convex edge, a second sensor can be set in this convex area for early warning.

[0142] It should be noted that the types of the second sensor and the first sensor can be the same or different. For example, the first sensor is a rain sensor and the second sensor is a wind speed sensor.

[0143] It should be noted that the second sensors are not necessarily evenly arranged and can be specifically set according to needs. It has the following effects: First, improve the monitoring accuracy. The data collection in key areas is more intensive, which helps to accurately evaluate the condition of the disaster-bearing body. Second, optimize resource allocation. More first sensors are deployed in key areas, effectively reducing costs and improving the overall monitoring efficiency. Third, speed up the response speed. The unevenly distributed first sensors can quickly locate problems when anomalies are found, shortening the emergency response time.

[0144] Further, step S4 includes the following steps:

[0145] Step S41. Fly the UAV along the grid: Make the UAV fly along the path of the virtual grid. During the flight, take pictures of the designated area according to the grid division.

[0146] Step S42. Image data collection: Store the taken pictures in the built-in storage device of the UAV or wirelessly transmit them to the ground receiving device.

[0147] Step S43. Acquisition adjustment: Adjust the flight speed of the UAV and the image acquisition of the UAV.

[0148] It should be noted that the parameters can be adjusted manually or automatically. For example:

[0149] Further, the method of controlling the UAV's photographing frequency is as follows:

[0150] Control the photographing frequency with the ratio of the total length of the virtual grid line included in the corresponding warning circle to the length of the virtual grid line, and the photographing frequency is directly proportional to the ratio of the total length of the virtual grid line included in the corresponding warning circle to the length of the virtual grid line.

[0151] Control the flight speed with the ratio of the total length of the virtual grid line included in the corresponding warning circle to the length of the virtual grid line, and the flight speed is inversely proportional to the ratio of the total length of the virtual grid line included in the corresponding warning circle to the length of the virtual grid line.

[0152] The larger the ratio of the total length of the virtual grid line included in the corresponding warning circle to the length of the virtual grid line, the more serious the disaster, then the photographing frequency is correspondingly increased and the flight speed is correspondingly decreased, so as to collect more data.

[0153] Further, step S5. Image processing and impact analysis: Use the SETR technology to process the image, and compare the images to quantitatively evaluate the impact of the marine disaster on the disaster-bearing body.

[0154] The proportion of the affected image can be used to quantitatively evaluate the impact of the marine disaster on the disaster-bearing body. The corresponding warning area in the first warning, second warning, third warning, and fourth warning can also be used as the affected area, and calculate the ratio of the affected area to the range of the disaster-bearing body area to be evaluated.

[0155] The working principle of the present invention:

[0156] Step S1. Determine the evaluation area and establish a monitoring network: Determine the scope of the disaster-bearing body area to be evaluated, bury a number of first sensors within the disaster-bearing body area, conduct geographical grid division based on the positions of the first sensors, connect the first sensors to a preset data processing system to form a monitoring network, and achieve real-time data collection and transmission;

[0157] Step S2. Receive monitoring data and preprocess the data: Receive and monitor marine disaster data (such as typhoons, heavy rains, tsunamis, etc.). When the marine disaster data reaches the first preset threshold, make the first sensors collect the corresponding data of the disaster-bearing body area at a preset frequency. After collecting the data of the first sensors, perform data preprocessing;

[0158] Step S3. Construct a virtual grid and conduct early warning simulation: Construct a virtual grid, simulate the actual disaster-bearing body area, and conduct early warning on the virtual grid according to the preprocessed data;

[0159] Step S4. UAV collects image data: Use a UAV to fly along the virtual grid while taking pictures to obtain images within the virtual grid;

[0160] Step S5. Image processing and impact analysis: Use the SETR technology to process the images, and compare the images to quantitatively evaluate the impact of marine disasters on the disaster-bearing body.

[0161] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0162] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for evaluating and warning marine disaster-bearing bodies based on drones and geographical grids, characterized in that, Including the following steps: Step S1. Determine the evaluation area and establish a monitoring network: Determine the scope of the disaster-bearing body area to be evaluated, bury a number of first sensors within the disaster-bearing body area, perform geographical grid division based on the positions of the first sensors, connect the first sensors to a preset data processing system to form a monitoring network, and realize real-time data collection and transmission; Step S2. Receive monitoring data and perform data preprocessing: Receive and monitor marine disaster data. When the marine disaster data reaches the first preset threshold, make the first sensors collect the corresponding data of the disaster-bearing body area at a preset frequency. After collecting the data of the first sensors, perform data preprocessing; Step S3. Construct a virtual grid and perform early warning simulation: Construct a virtual grid, simulate the actual disaster-bearing body area, and perform early warning on the virtual grid according to the preprocessed data; Step S4. UAV collects image data: Use a UAV to fly along the virtual grid and take photos simultaneously to obtain images within the virtual grid; Step S5. Image processing and impact analysis: Use the SETR technology to process the images, and compare the images to quantitatively evaluate the impact of marine disasters on the disaster-bearing body.

2. The method for evaluating and warning marine disaster-bearing bodies based on UAVs and geographical grids according to claim 1, wherein: Step S1 includes the following steps: Step S11. Determine the scope of the disaster-bearing body area: Determine the disaster-bearing body area to be evaluated on the map and preliminarily set the preset positions of the first sensors; Step S12. Bury the first sensors: Set a number of concentric rings with the preset positions of the first sensors as the centers, bury the first sensors at the center or a certain concentric ring, and the closer to the center, the higher the priority; Step S13. Perform geographical grid division: Connect the actual positions of adjacent first sensors to form a geographical grid; Step S14. Establish a monitoring network: Connect all the first sensors to the data processing system to form a monitoring network to ensure real-time data collection and transmission.

3. The method for evaluating and warning marine disaster-bearing bodies based on UAVs and geographical grids according to claim 1, wherein: Step S2 includes the following sub-steps: Step S21. Connect the data source: Establish a connection with the marine disaster data source to ensure real-time monitoring data; Step S22. Set the monitoring data threshold: Set the first preset threshold as the standard for triggering the sensors to collect data; Step S23. Judge whether the data reaches the threshold: Monitor the marine disaster data in real time. When the data reaches the first preset threshold, trigger the acquisition mechanism of the first sensors; Step S24. Start the sensors: Start the first sensors to collect the corresponding data of the disaster-bearing body area at a preset frequency; Step S25. Collect the data of the first sensors: Collect the data collected by the first sensors; Step S26. Feature extraction: Extract features from the collected data; Step S27. Data preprocessing: Perform data preprocessing on the extracted feature data.

4. The method for evaluating and warning marine disaster-bearing bodies based on UAVs and geographical grids according to claim 1, wherein: Step S3 includes the following steps: Step S31. Determine the simulation target: Clearly define the simulation target, screen the required sensor data, and perform data cleaning and formatting on the required sensor data; Step S32. Virtual grid division: Divide the simulation area into several virtual grids, and each grid represents a specific geographical location; Step S33. Determine the properties of disaster-bearing bodies: Assign corresponding properties to the disaster-bearing bodies within each virtual grid; Step S34. Simulate the disaster impact: Utilize the existing data and models to simulate the specific impact on the disaster-bearing bodies within each grid when the disaster occurs; Step S35. Set warning parameters: According to the simulation results, set the warning parameters, including warning levels, warning times, and warning ranges; Step S36. Output warning results: Output the warning information to the preset population.

5. A method for evaluating and warning ocean disaster-bearing bodies based on unmanned aerial vehicles and geographical grids as claimed in claim 1, wherein: In step S3, the steps for establishing virtual grids are as follows: Set a number of parallel vertical virtual grid lines and a number of parallel horizontal virtual grid lines; is the first sensor number, which are Q respectively ij , where i is the horizontal number and j is the vertical number; Measure the first sensor Q ij The distance to the corresponding vertical virtual grid line is L ij , adjust the corresponding vertical virtual grid line left and right until the sum of L ij is minimized; Measure the first sensor Q ij The distance to the corresponding horizontal virtual grid line is M ij , adjust the corresponding horizontal virtual grid line up and down until M ij is minimized 6. A method for evaluating and warning ocean disaster-bearing bodies based on unmanned aerial vehicles and geographical grids as claimed in claim 5, wherein: The steps of the warning are as follows: Taking the actual position of the first sensor as the center and a multiple of the value collected by the first sensor as the radius, construct a warning circle; When the area of the warning circle is greater than the second preset threshold, conduct a first warning on the area inside the warning circle; When adjacent warning circles overlap, conduct a second warning on at least part of the virtual grid area containing the overlapping area; If the diameter of a certain warning circle is greater than 80% of the distance between adjacent first sensors and the first warning is not triggered, conduct a third warning, where the third warning includes warning the virtual grid area containing at least part of the warning circle and warning of damage to the first sensor.

7. A method for evaluating and warning ocean disaster-bearing bodies based on unmanned aerial vehicles and geographical grids as claimed in claim 6, wherein: It further includes a fourth warning, and the steps are as follows: Calculate the total length of a certain virtual grid line included by the corresponding warning circle. When the ratio of the total length of the virtual grid line included by the corresponding warning circle to the length of the virtual grid line is greater than the third preset threshold, conduct a warning on the virtual grids on both sides of the virtual grid line.

8. A method for evaluating and warning ocean disaster-bearing bodies based on unmanned aerial vehicles and geographical grids as claimed in claim 7, wherein: It further includes setting a second sensor. The second sensor is set in the virtual grid, and several second sensors are set in each virtual grid; when the warning circle encloses the second sensor, the second sensor is triggered to perform detection.

9. A method for evaluating and warning ocean disaster-bearing bodies based on unmanned aerial vehicles and geographical grids as claimed in claim 8, wherein: Step S4 includes the following steps: Step S41. Fly the unmanned aerial vehicle along the grid: Make the unmanned aerial vehicle fly along the path of the virtual grid. During the flight, take pictures of the specified area according to the grid division; Step S42. Collect image data: Store the taken pictures in the built-in storage device of the unmanned aerial vehicle or transmit them wirelessly to the ground receiving device; Step S43. Acquisition adjustment: Adjust the flight speed of the drone and the image acquisition of the drone.

10. A method for evaluating and warning marine disaster-bearing bodies based on drones and geographical grids according to claim 9, characterized in that: The photographing frequency is controlled by the ratio of the total length of the virtual grid line contained in the corresponding warning circle to the length of the virtual grid line, and the photographing frequency is directly proportional to the ratio of the total length of the virtual grid line contained in the corresponding warning circle to the length of the virtual grid line; The flight speed is controlled by the ratio of the total length of the virtual grid line contained in the corresponding warning circle to the length of the virtual grid line, and the flight speed is inversely proportional to the ratio of the total length of the virtual grid line contained in the corresponding warning circle to the length of the virtual grid line.

Images