Marine carrier evaluation and early warning method based on unmanned aerial vehicle and geographic grid

Abstract

The invention discloses a marine carrier evaluation and early warning method based on an unmanned aerial vehicle and a geographic grid, and belongs to the technical field of marine disaster-bearing body evaluation, and the method comprises the following steps: S1, determining an evaluation region and building a monitoring network: determining a carrier region range to be evaluated, burying a plurality of first sensors in the carrier region range, performing geographic grid division on the basis of the position of the first sensor, and connecting the first sensor with a preset data processing system to form a monitoring network so as to realize real-time acquisition and transmission of data; and S2, receiving monitoring data and preprocessing data: receiving and monitoring marine disaster data, when the marine disaster data reaches a first preset threshold value, enabling a first sensor to collect corresponding data of a carrier region according to a preset frequency, and after collecting the data of the first sensor, carrying out data preprocessing. According to the invention, the real-time performance and accuracy of evaluation are improved, and the capability of monitoring and early warning marine disasters is enhanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of marine disaster-bearing body evaluation, and in particular relates to a marine disaster-bearing body evaluation and early warning method based on unmanned aerial vehicles and geographic grids. Background Art

[0002] A geographic grid is a system that divides the earth's surface into regular grids, with each grid cell representing a specific geographic area. This grid system can be used to organize, store, and query spatial data. Marine hazard-prone 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 impact of marine disasters on marine carriers in different regions is different. In order to effectively manage and mitigate the impact of marine disasters, it is crucial to scientifically evaluate and compare the impacts on marine carriers 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 impact on marine carriers in different regions is an urgent problem to be solved. Summary of the invention

[0004] In response to the problems existing in the prior art, the present invention provides an ocean carrier evaluation and early warning method based on drones and geographic grids, which has the advantage of being able to evaluate the impact on ocean carriers in different regions, thus solving the problems of the prior art.

[0005] The present invention is implemented as follows: a marine carrier evaluation and early warning method based on drones and geographic grids, comprising the following steps:

[0006] Step S1. Determine the evaluation area and establish a monitoring network: determine the area of ​​the carrier body to be evaluated, bury a number of first sensors within the area of ​​the carrier body, divide the geographic grid based on the location of the first sensors, connect the first sensors and the preset data processing system to form a monitoring network, and realize real-time data collection and transmission;

[0007] Step S2. Receiving monitoring data and data preprocessing: receiving and monitoring marine disaster data (such as typhoons, rainstorms, tsunamis, etc.). When the marine disaster data reaches a first preset threshold, the first sensor collects corresponding data of the carrier area at a preset frequency. After collecting the first sensor data, data preprocessing is performed;

[0008] Step S3. Constructing a virtual grid and early warning simulation: constructing a virtual grid, simulating the actual disaster-prone area, and issuing an early warning to the virtual grid based on the preprocessed data;

[0009] Step S4. Collecting image data using a drone: Using a drone to fly along the virtual grid and take photos to obtain images within the virtual grid;

[0010] Step S5. Image processing and impact analysis: Use SETR technology to process the image, compare the images, and conduct a quantitative evaluation of the impact of the marine disaster on the disaster-sustaining body.

[0011] As preferred embodiment of the present invention, step S1 includes the following steps:

[0012] Step S11. Determine the area of ​​the carrier: determine the area of ​​the carrier to be evaluated on the map, and preliminarily set the preset position of the first sensor;

[0013] Step S12. burying the first sensor: setting a plurality of concentric rings with the preset position of the first sensor as the center, burying the first sensor at the center or in one of the concentric rings, and the closer to the center, the higher the priority;

[0014] Step S13. Performing geographic grid division: connecting the actual positions of the adjacent first sensors to form a geographic grid;

[0015] Step S14. Establishing a monitoring network: connecting all 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] As preferred embodiment of the present invention, step S2 includes the following sub-steps:

[0017] Step S21. Connecting to the data source: establishing a connection with the marine disaster data source to ensure real-time monitoring of data;

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

[0019] Step S23. Data reaches a threshold value judgment: real-time monitoring of marine disaster data, when the data reaches a first preset threshold, triggering the collection mechanism of the first sensor;

[0020] Step S24. Sensor start: start the first sensor to collect corresponding data of the carrier area according to a preset frequency;

[0021] Step S25. First sensor data collection: collecting data collected by the first sensor;

[0022] Step S26. Feature extraction: extracting features from the collected data;

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

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

[0025] Setting a plurality of parallel vertical virtual grid lines and a plurality of parallel horizontal virtual grid lines;

[0026] is the first sensor number, respectively Q ij , where i is the horizontal number and j is the vertical number;

[0027] 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 L ij Until the sum is the smallest;

[0028] 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 Until the sum is minimum.

[0029] As preferred embodiment of the present invention, the steps of early warning are as follows:

[0030] A warning circle is constructed with the actual position of the first sensor as the center and the multiple of the value collected by the first sensor as the radius;

[0031] When the area of ​​the warning circle is greater than the second preset threshold, a first warning is issued to the area inside the warning circle;

[0032] When adjacent warning circles overlap, a second warning is issued to a virtual grid area that at least partially includes the overlapping area;

[0033] If the diameter of a warning circle is greater than 80% of the distance between adjacent first sensors and the first warning is not triggered, a third warning is issued, wherein the third warning includes an alarm for a virtual grid area containing at least part of the warning circle and a warning for damage to the first sensor.

[0034] As a preferred embodiment of the present invention, a fourth warning is also included, and the steps are as follows:

[0035] The total length of a virtual grid line included in the corresponding warning circle is calculated. When 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 is greater than a third preset threshold, the virtual grids on both sides of the virtual grid line are warned.

[0036] As a preferred embodiment of the present invention, a second sensor is further provided, the second sensor is provided in a virtual grid, and a plurality of second sensors are provided in each virtual grid; when the warning circle wraps around the second sensor, the second sensor is triggered to perform detection.

[0037] As preferred embodiment of the present invention, step S4 comprises the following steps:

[0038] Step S41. Make the drone fly along the grid: Make the drone fly along the path of the virtual grid, and take pictures of the designated area according to the division of the grid during the flight;

[0039] Step S42. Image data collection: storing the captured photos in the drone's built-in storage device or transmitting them wirelessly to a ground receiving device;

[0040] Step S43. Collection adjustment: adjust the flight speed of the drone and the image collection of the drone.

[0041] As a preferred embodiment of the present invention, the photographing frequency is controlled by the ratio of the total length of the virtual grid lines included in the corresponding warning circle to the length of the virtual grid lines, and the photographing frequency is proportional to the ratio of the total length of the virtual grid lines included in the corresponding warning circle to the length of the virtual grid lines;

[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 present invention has the following beneficial effects:

[0044] 1. Define the scope of the evaluation area, set up the first sensor, build a geographic grid and monitoring network, and realize real-time data collection and transmission.

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

[0046] 3. Construct a virtual grid for early warning simulation, use drones to collect image data, and use SETR technology to perform image processing and impact analysis to achieve quantitative evaluation of the impact of marine disasters on disaster-prone objects. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flowchart of a method for evaluating and warning an ocean carrier based on a drone and a geographic grid provided by an embodiment of the present invention;

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

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

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

[0051] Figure 5 is a flowchart of collecting image data by a drone 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 a warning circle of a virtual grid provided by an embodiment of the present invention;

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

[0055] Fig. 9 is a schematic diagram of a virtual grid with a second sensor provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to further understand the content, features and effects of the present invention, the following embodiments are given as examples and described in detail with reference to the accompanying drawings.

[0057] The structure of the present invention is described in detail below in conjunction with the accompanying drawings.

[0058] like Figures 1 to 9 As shown, an embodiment of the present invention provides a marine carrier evaluation and early warning method based on a drone and a geographic grid, comprising the following steps:

[0059] Step S1. Determine the evaluation area and establish a monitoring network: determine the area of ​​the carrier body to be evaluated (for example, the following areas: coastal cities, infrastructure, ecosystems, fishery resources), bury a number of first sensors within the area of ​​the carrier body, divide the geographic grid based on the location of the first sensor, ensure that the grid size is suitable for the burial of the first sensor and the subsequent UAV flight, connect the first sensor and the preset data processing system to form a monitoring network, and realize real-time data collection and transmission;

[0060] Step S2. Receiving monitoring data and data preprocessing: receiving and monitoring marine disaster data (such as typhoons, rainstorms, tsunamis, etc.), when the marine disaster data reaches a first preset threshold, the first sensor collects the corresponding data of the carrier area at a preset frequency, and adjusts the preset time according to the actual situation to ensure the timeliness of the data. After collecting the first sensor data, data preprocessing is performed, including filtering, denoising, etc., to improve data quality.

[0061] Step S3. Constructing a virtual grid and early warning simulation: constructing a virtual grid, simulating the actual disaster-prone area, and issuing an early warning to the virtual grid based on the preprocessed data;

[0062] Step S4. Collecting image data using a drone: Using a drone to fly along the virtual grid and take photos to obtain images within the virtual grid;

[0063] Step S5. Image processing and impact analysis: Use SETR technology to process the image, compare the images, and conduct a quantitative evaluation of the impact of the marine disaster on the disaster-sustaining body.

[0064] In the above settings, it is first necessary to clearly define the scope of the evaluation area, such as key areas such as coastal cities, infrastructure, ecosystems, and fishery resources, or any other areas as needed. Then, first sensors are set up in the area, and the locations of these first sensors are used as nodes to divide the geographical grid. The first sensors are connected to the data processing system to form a monitoring network (specifically, they can be connected via wireless signals) to achieve real-time data collection and transmission, ensuring the timeliness and accuracy of information.

[0065] When the data of marine disasters such as typhoons, rainstorms or tsunamis reaches the first preset threshold, the system will automatically trigger the first sensor to collect data at the preset frequency. As the amount of disaster data increases, the collection frequency will also increase accordingly to ensure the timeliness and accuracy of the data. The collected first sensor data is feature extracted and necessary data preprocessing is performed, including filtering and denoising steps, to improve the quality and reliability of the data.

[0066] Next, a virtual grid is constructed to simulate the disaster situation in the disaster-prone area based on the preprocessed data. This virtual model can provide more accurate preliminary warnings and ensure that timely measures can be taken before a disaster occurs. In addition, drones are used to fly along the virtual grid while taking high-definition photos to record image data of the actual disaster-prone area, which will provide visual information for subsequent analysis.

[0067] The collected images are processed using SETR technology, and the impact of marine disasters on disaster-prone objects is deeply analyzed by comparing image data, including terrain, vegetation, buildings, etc. The impact of marine disasters on disaster-prone objects is quantitatively evaluated through the results of image analysis, providing a scientific basis for disaster prevention and control.

[0068] This marine carrier assessment and early warning method based on drones and geographic grids not only improves the real-time and accuracy of the assessment, 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, SETR technology can play its advantages in image recognition and segmentation. Photos taken by drones contain rich image information, but directly analyzing this information may be time-consuming and laborious. SETR technology can automatically process images and identify key elements in the images, such as damaged buildings, vegetation coverage, terrain changes, etc. At the same time, it can also accurately segment and classify these elements, providing more detailed disaster impact analysis results.

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

[0071] Step S11. Determine the scope of the carrier area: Determine the carrier area to be evaluated on the map and preliminarily set the preset position of the first sensor; the carrier area can be a coastal city, infrastructure, ecosystem or 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. burying the first sensor: setting a number of concentric rings with the preset position of the first sensor as the center, and burying the first sensor at the center or in a concentric ring in combination with the specific geographical conditions, 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 completely and accurately at the preset position. Through this setting, the first sensor can be set as close to the preset position as possible.

[0073] Step S13. Performing geographic grid division: connecting the actual positions of the adjacent first sensors to form a geographic grid;

[0074] Step S14. Establishing a monitoring network: connecting all first sensors to the data processing system to form a monitoring network to ensure that data can be collected and transmitted in real time.

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

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

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

[0078] Step S23. Data reaches a threshold value judgment: real-time monitoring of marine disaster data, when the data reaches a first preset threshold, triggering the collection mechanism of the first sensor;

[0079] Step S24. Sensor start: start the first sensor to collect corresponding data of the carrier area according to a preset frequency;

[0080] Step S25. First sensor data collection: collecting data collected by the first sensor;

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

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

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

[0084] Step S27b. De-noising: Eliminate outliers and interference signals in the data through denoising technology.

[0085] Exemplarily, the above solution is specifically implemented as follows:

[0086] Connect to data sources: Establish connections with marine hazard data sources to ensure real-time monitoring of data.

[0087] Monitoring data threshold setting: Set the first preset threshold, for example, when the typhoon wind speed reaches 100 kilometers per hour, data collection is triggered.

[0088] Judgment when data reaches threshold value: Real-time monitoring of marine disaster data, such as when typhoon wind speed reaches 100 kilometers per hour, the collection mechanism is triggered.

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

[0090] First sensor data collection: collects 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, and air pressure.

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

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

[0094] b. De-noising: For example, median filtering is performed on the air pressure data to eliminate outliers.

[0095] The following are examples:

[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: [11,12,11,12,11,13,11,12,11,12,13,12,11,12,11,12,11,12,11,12,11]

[0098] Air 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 rainfall sensor, an air pollution sensor, etc. The air pollution sensor is a device used to detect and monitor the concentration of pollutants in the air. It can monitor PM2.5, PM10, sulfur dioxide, nitrogen oxides, ozone and other pollutants in real time. Common air pollution sensors include optical sensors, electrochemical sensors, semiconductor sensors and other types.

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

[0102] Step S31. Determine the simulation goal: clarify the simulation goal (for example, to predict the impact of a natural disaster, such as a typhoon or rainstorm), screen the required sensor data, and clean and format 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, each grid representing a specific geographical location, which helps to simulate the impact of disasters on different areas more finely.

[0104] Step S33. Determine the attributes of the disaster-prone body: assign corresponding attributes to the disaster-prone body in each virtual grid, such as building type, population density, infrastructure status, etc. These attributes will directly affect the impact of the disaster.

[0105] Step S34. Simulate the impact of disasters: Use existing data and models to simulate the specific impact of disasters on the disaster-bearing objects in each grid, including the losses and casualties caused.

[0106] Step S35. Warning parameter setting: According to the simulation results, set the warning parameters, including warning level, warning time, and warning range, to ensure the timeliness and accuracy of the warning information.

[0107] Step S36. Output of warning results: Output the warning information to a preset group of people, such as electronic maps, text messages, broadcasts and other forms, 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 objectives: predict the impact of Typhoon Alpha on H City, screen data from weather stations and water level sensors, and perform data cleaning and formatting.

[0110] Virtual grid division: City H is divided into 100 virtual grids, each with a side length of 1 km.

[0111] Determine the attributes of the disaster-prone body: count the building type (residential, commercial, industrial), population density (people per square kilometer), and infrastructure conditions (roads, bridges, power facilities) of each grid.

[0112] Simulated disaster impact: Typhoon Alpha is expected to cause damage to buildings in 30 grids, casualties in 50 grids, and economic losses of approximately RMB 500 million.

[0113] Warning parameter settings: The warning levels are deep red and light red, the warning time is 6 hours before the typhoon lands, and the warning range covers all areas of H City. Among them, the warning in the grid where building damage and casualties are expected is deep red, and the rest is light red.

[0114] Warning result output: Issue warning information to citizens of H City through electronic maps, text messages and broadcasts to ensure 100% coverage of the target population.

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

[0116] Step S37. Early warning effect evaluation: Evaluate the actual effect of the early warning system, including the timeliness and accuracy of the early warning and the public response, to provide a basis for subsequent improvements.

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

[0118] Step S39. Simulation and warning iteration: Apply the optimized warning scheme to new simulations and continuously iterate and update it to adapt to the ever-changing environment and disaster conditions, ensuring the continuous improvement and upgrading of the warning system.

[0119] Further, in another embodiment, not all places are suitable for installing the first sensor, so the installation position of the first sensor is not accurate. In this case, the following settings are performed:

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

[0121] Setting a plurality of parallel vertical virtual grid lines and a plurality of parallel horizontal virtual grid lines;

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

[0123] Measure the first sensor Q ij The distance to the corresponding vertical virtual grid line is L ij , for example, L 1j , L 2j , L 3j ...adjust the corresponding vertical virtual grid line left and right until L ij For example, the first sensor Q of the first vertical column i1 The distance to the first vertical virtual grid line is L 11 , L 21 , L 31 .

[0124] Measure the first sensor Q ij The distance to the corresponding horizontal virtual grid line is M ij , for example, M i1 、M i2 、M i3 ...adjust the corresponding horizontal virtual grid line up and down until M ij For example, the first sensor Q of the first row 1j The distance to the first horizontal virtual grid line is M 11 、M 12 、M 13 .

[0125] Through the above scheme, the virtual grid and the first sensor can be brought closer together, which can improve the correlation between the two. It should be noted that the geographic grid is usually irregular. For example, if the actual installation position of the first sensor deviates from the preset position, each geographic grid area is an irregular quadrilateral. However, through the above setting, each grid area of ​​the virtual grid is a standard rectangle or square. Even if the actual position of the first sensor deviates as a whole, the position correlation between the virtual grid and the first sensor can be guaranteed.

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

[0127] A warning circle is constructed with the actual position of the first sensor as the center and the multiple of the value collected by the first sensor as the radius;

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

[0129] When adjacent warning circles overlap, a second warning is issued to a virtual grid area that at least partially includes the overlapping area;

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

[0131] In the above settings, for example, if 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 a multiple and can be set manually. The larger the rainfall, the larger the area of ​​the warning circle, and the rainfall increases linearly, while the area of ​​the warning circle increases exponentially. When the area of ​​the warning circle is greater than the second preset threshold, the first warning is issued to the area inside the warning circle.

[0132] The second warning indicates that the adjacent warning circles are large, and issuing a second warning to the virtual grid area where the overlapping area is located can prevent omissions. Generally, the expansion range of adjacent warning circles is similar, so the difference in the values ​​checked by adjacent sensors will not be too large. Therefore, the third warning not only means that the carrier is seriously damaged, but also that the first sensor may be damaged.

[0133] Furthermore, it also includes a fourth warning, and the steps are as follows: calculate the total length of a virtual grid line included in the corresponding warning circle, and when 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 is greater than a third preset threshold (for example, 60%), issue a warning for the virtual grids on both sides of the virtual grid line.

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

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

[0136]

[0137] The middle vertical virtual grid line is represented by the first sensor Q 32 The length of the corresponding warning circle is

[0138]

[0139] The middle vertical virtual grid line is represented by the first sensor Q 12 The total length of the corresponding warning circle is

[0140]

[0141] Among them, R ij The first sensor Q ij The corresponding radius of the warning circle.

[0142] Furthermore, it also includes setting a second sensor, which is set in the virtual grid, and a plurality of second sensors are set in each virtual grid; when the warning circle wraps around the second sensor, the second sensor is triggered to perform detection.

[0143] In the above setting, the first sensor is used for the large frame, and the second sensor is used for small details; the second sensor is usually in a closed state and only starts working when it is triggered.

[0144] It should be noted that the carrier area may be irregular, and the first sensor may be arranged in the entire carrier area or only in part of the carrier area. Even if the first sensor is only arranged in part of the carrier area, a second sensor may be arranged in the area where the first sensor is not arranged for monitoring. For example, for an area with an edge protruding outward, a second sensor may be arranged in the protruding area for early warning.

[0145] It should be noted that the second sensor and the first sensor may be of the same or different types. For example, the first sensor is a rainfall sensor, and the second sensor is a wind speed sensor.

[0146] It should be noted that the second sensors are not necessarily evenly arranged and can be arranged specifically as needed. The following effects are achieved: First, the monitoring accuracy is improved. The data collection in key areas is more intensive, which helps to accurately assess the condition of the carrier. Second, resource allocation is optimized. More first sensors are deployed in key areas, which effectively reduces costs and improves overall monitoring efficiency. Third, the response speed is accelerated. The unevenly distributed first sensors can quickly locate the problem when an abnormality is found, shortening the emergency response time.

[0147] Further, step S4 includes the following steps:

[0148] Step S41. Make the drone fly along the grid: Make the drone fly along the path of the virtual grid, and take pictures of the designated area according to the division of the grid during the flight;

[0149] Step S42. Image data collection: storing the captured photos in the drone's built-in storage device or transmitting them wirelessly to a ground receiving device;

[0150] Step S43. Collection adjustment: adjust the flight speed of the drone and the image collection of the drone.

[0151] It should be noted that the parameters can be adjusted manually or automatically, for example:

[0152] Furthermore, the method of controlling the drone's photography frequency is as follows:

[0153] 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 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;

[0154] 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.

[0155] 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 is, and the frequency of taking pictures will increase accordingly, and the flight speed will decrease accordingly, so as to collect more data.

[0156] Furthermore, step S5. Image processing and impact analysis: the images are processed using SETR technology, and the images are compared to quantitatively evaluate the impact of the marine disaster on the disaster-prone body.

[0157] The proportion of disaster-affected images can be used to quantitatively evaluate the impact of marine disasters on disaster-bearing bodies. The warning area corresponding to the first warning, second warning, third warning and fourth warning can also be used as the disaster-affected area to calculate the ratio of the disaster-affected area to the area of ​​the bearing body to be evaluated.

[0158] Working principle of the present invention:

[0159] Step S1. Determine the evaluation area and establish a monitoring network: determine the area of ​​the carrier body to be evaluated, bury a number of first sensors within the area of ​​the carrier body, divide the geographic grid based on the location of the first sensors, connect the first sensors and the preset data processing system to form a monitoring network, and realize real-time data collection and transmission;

[0160] Step S2. Receiving monitoring data and data preprocessing: receiving and monitoring marine disaster data (such as typhoons, rainstorms, tsunamis, etc.), when the marine disaster data reaches a first preset threshold, the first sensor collects corresponding data of the carrier area at a preset frequency. After collecting the first sensor data, data preprocessing is performed;

[0161] Step S3. Constructing a virtual grid and early warning simulation: constructing a virtual grid, simulating the actual disaster-prone area, and issuing an early warning to the virtual grid based on the preprocessed data;

[0162] Step S4. Collecting image data using a drone: Using a drone to fly along the virtual grid and take photos to obtain images within the virtual grid;

[0163] Step S5. Image processing and impact analysis: Use SETR technology to process the image, compare the images, and conduct a quantitative evaluation of the impact of the marine disaster on the disaster-sustaining body.

[0164] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0165] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A marine carrier evaluation and early warning method based on drones and geographic grids, characterized in that: The following steps are involved: Step S1. Determine the evaluation area and establish a monitoring network: determine the area of ​​the carrier body to be evaluated, bury a number of first sensors within the area of ​​the carrier body, divide the geographic grid based on the location of the first sensors, connect the first sensors and the preset data processing system to form a monitoring network, and realize real-time data collection and transmission; Step S2. Receiving monitoring data and data preprocessing: receiving and monitoring marine disaster data, when the marine disaster data reaches a first preset threshold, enabling the first sensor to collect corresponding data of the carrier area at a preset frequency, and after collecting the first sensor data, performing data preprocessing; Step S3. Constructing a virtual grid and early warning simulation: constructing a virtual grid, simulating the actual disaster-prone area, and issuing an early warning to the virtual grid based on the preprocessed data; Step S4. Collecting image data using a drone: Using a drone to fly along the virtual grid and take photos to obtain images within the virtual grid; Step S5. Image processing and impact analysis: Use SETR technology to process the image, compare the images, and conduct a quantitative evaluation of the impact of the marine disaster on the disaster-sustaining body.

2. The marine carrier evaluation and early warning method based on drones and geographic grids as claimed in claim 1, characterized in that: Step S1 includes the following steps: Step S11. Determine the area of ​​the carrier: determine the area of ​​the carrier to be evaluated on the map, and preliminarily set the preset position of the first sensor; Step S12. burying the first sensor: setting a plurality of concentric rings with the preset position of the first sensor as the center, burying the first sensor at the center or in one of the concentric rings, and the closer to the center, the higher the priority; Step S13. Performing geographic grid division: connecting the actual positions of the adjacent first sensors to form a geographic grid; Step S14. Establishing a monitoring network: connecting all first sensors to the data processing system to form a monitoring network to ensure that data can be collected and transmitted in real time.

3. The marine carrier evaluation and early warning method based on drones and geographic grids as claimed in claim 1, characterized in that: Step S2 includes the following sub-steps: Step S21. Connecting to the data source: establishing a connection with the marine disaster data source to ensure real-time monitoring of data; Step S22. Setting the monitoring data threshold: Setting a first preset threshold as a standard for triggering the sensor to collect data; Step S23. Data reaches a threshold value judgment: real-time monitoring of marine disaster data, when the data reaches a first preset threshold, triggering the collection mechanism of the first sensor; Step S24. Sensor start: start the first sensor to collect corresponding data of the carrier area according to a preset frequency; Step S25. First sensor data collection: collecting data collected by the first sensor; Step S26. Feature extraction: extracting features from the collected data; Step S27. Data preprocessing: performing data preprocessing on the extracted feature data.

4. The marine carrier evaluation and early warning method based on drones and geographic grids as claimed in claim 1, characterized in that: Step S3 includes the following steps: Step S31. Determine the simulation target: clarify the simulation target, screen the required sensor data, and clean and format the required sensor data; Step S32. Virtual grid division: divide the simulation area into several virtual grids, each grid representing a specific geographical location; Step S33. Determine the disaster-prone body attributes: assign corresponding attributes to the disaster-prone body in each virtual grid; Step S34. Simulate the impact of disasters: Use existing data and models to simulate the specific impact of disasters on the disaster-bearing bodies in each grid; Step S35. Warning parameter setting: according to the simulation results, set the warning parameters, including warning level, warning time, and warning range; Step S36. Warning result output: output the warning information to a preset group of people.

5. The marine carrier evaluation and early warning method based on drones and geographic grids as claimed in claim 1, characterized in that: In step S3, the steps of establishing a virtual grid are as follows: Setting a plurality of parallel vertical virtual grid lines and a plurality of parallel horizontal virtual grid lines; is the first sensor number, respectively Q 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 L ij Until the sum is the smallest; 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 Until the sum is minimum.

6. The marine carrier evaluation and early warning method based on drones and geographic grids as claimed in claim 5, characterized in that: The steps of the early warning are as follows: A warning circle is constructed with the actual position of the first sensor as the center and the multiple of the value collected by the first sensor as the radius; When the area of ​​the warning circle is greater than the second preset threshold, a first warning is issued to the area inside the warning circle; When adjacent warning circles overlap, a second warning is issued to a virtual grid area that at least partially includes the overlapping area; If the diameter of a warning circle is greater than 80% of the distance between adjacent first sensors and the first warning is not triggered, a third warning is issued, wherein the third warning includes an alarm for a virtual grid area containing at least part of the warning circle and a warning for damage to the first sensor.

7. The marine carrier evaluation and early warning method based on drones and geographic grids as claimed in claim 6, characterized in that: It also includes a fourth warning, the steps are as follows: The total length of a virtual grid line included in the corresponding warning circle is calculated. When 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 is greater than a third preset threshold, the virtual grids on both sides of the virtual grid line are warned.

8. The marine carrier evaluation and early warning method based on drones and geographic grids as claimed in claim 7, characterized in that: It also includes setting a second sensor, which is set in the virtual grid, and a plurality of second sensors are set in each virtual grid; when the warning circle wraps around the second sensor, the second sensor is triggered to perform detection.

9. The marine carrier evaluation and early warning method based on drones and geographic grids as claimed in claim 8, characterized in that: Step S4 includes the following steps: Step S41. Make the drone fly along the grid: Make the drone fly along the path of the virtual grid, and take pictures of the designated area according to the division of the grid during the flight; Step S42. Image data collection: storing the captured photos in the drone's built-in storage device or transmitting them wirelessly to a ground receiving device; Step S43. Collection adjustment: adjust the flight speed of the drone and the image collection of the drone.

10. The marine carrier assessment and early warning method based on drones and geographic grids as claimed in claim 9, characterized in that: 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 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; 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.

Images