A method, apparatus, equipment, and medium for coastal information assessment based on big data.

Abstract

This application relates to a method, apparatus, device, and medium for coastal information assessment based on big data. The method includes acquiring historical remote sensing images corresponding to multiple vegetation blocks within a preset coastal area; determining the area change curve and a first soil color value change map for each vegetation block based on the historical remote sensing images; acquiring multiple aerial images of each vegetation block within a preset historical time period; determining a second soil color value change map, garbage characteristics, and human activity intensity within each aerial image of each vegetation block based on the multiple aerial images; determining the pollution level of each vegetation block based on the first soil color value change map, the second soil color value change map, garbage characteristics, and human activity intensity; and determining the pollution level of a preset coastal area based on the area change curve and pollution level of each vegetation block. This application offers a more convenient and accurate assessment of the pollution level of coastal tidal flat soil.

Description

Technical Field

[0001] This application relates to the field of coastal assessment, and in particular to a method, apparatus, equipment and medium for coastal information assessment based on big data. Background Technology

[0002] In recent years, invasive alien plants affecting my country's coastal mudflats, such as Spartina alterniflora, have expanded rapidly in coastal areas due to the lack of natural enemies and other constraints, seriously threatening the safety of coastal wetland ecosystems. The rampant growth of these coastal invasive plants pollutes the soil and weakens the scouring effect of seawater on coastal mudflats. In addition, human activities such as production operations and garbage dumping on the mudflats have led to soil pollution, and the inability of seawater to effectively scour the mudflats has exacerbated coastal pollution.

[0003] Currently, the assessment of the pollution level of coastal invasive plants on coastal tidal flat soils is mainly conducted by relevant personnel through remote sensing images or field investigations. Assessing the pollution level of invasive plants on soil through remote sensing images requires the analysis of a large amount of data, which is time-consuming, labor-intensive, and not very accurate. Summary of the Invention

[0004] To more conveniently and accurately assess the pollution level of coastal tidal flat soil, this application provides a coastal information assessment method, apparatus, equipment, and medium based on big data.

[0005] Firstly, this application provides a coastal information assessment method based on big data, employing the following technical solution:

[0006] A big data-based method for coastal information assessment includes:

[0007] Acquire historical remote sensing images of multiple vegetation blocks within a preset coastal area;

[0008] Based on the historical remote sensing images, determine the area change curve of each vegetation block and the first soil color value change map;

[0009] Multiple aerial images of each vegetation block within a preset historical time period are acquired. Based on the multiple aerial images, a second soil color value change map of each vegetation block, garbage characteristics in each aerial image of each vegetation block, and human activity heat map are determined.

[0010] The pollution level of each vegetation block is determined based on the first soil color value change map, the second soil color value change map, garbage characteristics, and human activity heat.

[0011] The pollution level of the preset coastal area is determined based on the area change curve of each vegetation block and the pollution level of each vegetation block.

[0012] By employing the above technical solutions, historical remote sensing images are acquired. These images record specific changes in the coastline. Therefore, based on these images, the area change curves and first soil color value change maps for each vegetation block can be determined. The vegetation block area change map represents the expansion or reduction of invasive plants. Soil color changes when polluted; therefore, the first soil color value change map represents changes in soil pollution levels. Aerial images are then acquired. Aerial images are closer than remote sensing images, allowing for the capture of more details. Therefore, a second soil color value change map for each vegetation block is determined based on the aerial images. Due to the difference in altitude between the remote sensing images and the aerial images, the second soil color value change map... There are differences between the color value change map and the first soil color value change map. Combining the first and second soil color value change maps can more accurately assess the soil pollution status, determine the garbage characteristics and human activity intensity of each vegetation block. Garbage characteristics also pollute the soil, and the higher the human activity intensity, the greater the damage and pollution to the soil. Therefore, determining the pollution level of each vegetation block based on the sum of the first and second soil color value change maps, garbage characteristics, and human activity intensity is more accurate. Finally, combining the area change curve of each vegetation block and the pollution level to comprehensively determine the pollution level of the entire preset coastal area is more accurate and convenient than manual assessment.

[0013] In another possible implementation, determining the pollution level of each vegetation block based on the first soil color value change map, the second soil color value change map, waste characteristics, and human activity heat map includes:

[0014] Based on the first soil color value change map and the second soil color value change map, a fitted soil color value change map for each vegetation block is determined.

[0015] The first average value of the soil color value is determined from the fitted soil color value variation graph;

[0016] The characteristics of the waste in each vegetation block are counted to obtain the amount of waste in each vegetation block;

[0017] The difficulty score for waste purification in each vegetation block is determined based on the characteristics of the waste within each vegetation block.

[0018] The pollution level of each vegetation block is determined based on the first average value, the amount of garbage, the difficulty score of garbage purification, and the activity level of people.

[0019] In another possible implementation, the pollution level of the preset coastal area is determined based on the area change curve of each vegetation block and the pollution level of each vegetation block, including:

[0020] The area change trend of each vegetation block is determined from the area change curve of each vegetation block, and the first vegetation block with an area change trend of decreasing or remaining unchanged, and the second vegetation block with an area change trend of increasing are obtained.

[0021] Determine a first ratio between the number of the second vegetation blocks and the number of the first vegetation blocks;

[0022] Determine the first total area of ​​all first vegetation blocks and the second total area of ​​all second vegetation blocks;

[0023] Determine a second ratio between the second total area and the first total area;

[0024] The pollution level of the preset coastal area is determined based on the pollution level of each vegetation block, the first ratio, the second ratio, and their respective coefficients.

[0025] In another possible implementation, determining the waste purification difficulty score for each vegetated block based on the waste characteristics within each vegetated block includes:

[0026] The outline of each vegetation block is determined, and a Cartesian coordinate system is drawn with the center point of the outline as the origin. The two coordinate axes of the Cartesian coordinate system make an angle of 45° with the coastline.

[0027] Determine the coordinates of the waste features in each quadrant of the Cartesian coordinate system, and determine the coordinates of the center point representing the distribution of waste features in each quadrant based on the coordinates;

[0028] Determine the distance from the center point coordinates to the origin of the Cartesian coordinate system;

[0029] Determine the number of waste features in each quadrant of the Cartesian coordinate system;

[0030] The waste purification difficulty score for each quadrant is determined based on the distance, quantity, and waste purification difficulty coefficient corresponding to each quadrant.

[0031] The waste purification difficulty score within each vegetation block is determined based on the waste purification difficulty score corresponding to each quadrant.

[0032] In another possible implementation, determining the fitted soil color value change map for each vegetation block based on the first soil color value change map and the second soil color value change map includes:

[0033] Determine the first time point corresponding to each color value in the first soil color value change graph, and determine the second time point corresponding to each color value in the second soil color value change graph;

[0034] A target color value group is determined from the first soil color value change map and the second soil color value change map. The target color value group is two color values ​​whose time interval between the first time point and the second time point is less than a preset interval.

[0035] Calculate the average of the color values ​​of the target color value group;

[0036] The obtained average value is mapped to the first time point within the target color value group to obtain the candidate soil color value change map in the first soil color value change map.

[0037] Identify the remaining color values ​​in the second soil color value variation map, excluding those located in the target color value group;

[0038] The associated color values ​​are determined from the first soil color value change map based on the second time point of each remaining color value. The first time points of the associated color values ​​are the two color values ​​closest to the remaining color values, and the first time points of the associated color values ​​are located before and after the second time points of the remaining color values, respectively.

[0039] Calculate the average color value of the associated color values, and calculate the difference between the remaining color values ​​and the average color value;

[0040] The remaining color values ​​whose difference does not reach the preset difference threshold are mapped to the candidate soil color value change map according to the second time point of the remaining color values, so as to obtain the fitted soil color value change map for each vegetation block.

[0041] In another possible implementation, determining the human activity heat map of each vegetation block based on the multiple aerial images includes:

[0042] Determine the number of people in each aerial image;

[0043] Determine the average number of personnel and the total number of personnel based on the aforementioned number of personnel;

[0044] The score representing the activity intensity of the personnel is determined based on the average number of personnel, the total number of personnel, and their respective coefficients.

[0045] In another possible implementation, the method further includes:

[0046] The location and time of the third vegetation block are determined by the most recent remote sensing image. The third vegetation block is a vegetation block whose pollution level has reached a preset threshold and whose area is increasing.

[0047] Output the location and time of the most recent remote sensing image of the third vegetation block.

[0048] Secondly, this application provides a coastal information assessment device based on big data, which adopts the following technical solution:

[0049] A big data-based coastal information assessment device includes:

[0050] The image acquisition module is used to acquire historical remote sensing images of multiple vegetation blocks within a preset coastal area.

[0051] The first determining module is used to determine the area change curve of each vegetation block and the first soil color value change map based on the historical remote sensing image.

[0052] The second determining module is used to acquire multiple aerial images of each vegetation block within a preset historical time period, and to determine the second soil color value change map of each vegetation block, garbage characteristics in each aerial image of each vegetation block, and human activity heat based on the multiple aerial images.

[0053] The third determining module is used to determine the pollution level of each vegetation block based on the first soil color value change map, the second soil color value change map, garbage characteristics, and human activity heat.

[0054] The fourth determining module is used to determine the pollution level of the preset coastal area based on the area change curve of each vegetation block and the pollution level of each vegetation block.

[0055] By employing the above technical solution, the image acquisition module acquires historical remote sensing images, which record specific changes in the coastline. Therefore, the first determination module can determine the area change curve and the first soil color value change map for each vegetation block based on the historical remote sensing images. The vegetation block area change map represents the expansion or reduction of invasive plants. Soil color changes when polluted; therefore, the first soil color value change map represents changes in soil pollution. The second determination module acquires aerial images. Aerial images are closer than remote sensing images and can capture more details. Therefore, the second determination module determines the second soil color value change map for each vegetation block based on the aerial images. Since the remote sensing images and aerial images have different altitudes... Therefore, there is a difference between the second soil color value change map and the first soil color value change map. Combining the first and second soil color value change maps can more accurately assess the soil pollution situation, determine the garbage characteristics and human activity intensity of each vegetation block. Garbage characteristics also pollute the soil, and the higher the human activity intensity, the greater the damage and pollution to the soil. Therefore, the third determination module determines the pollution level of each vegetation block more accurately based on the sum of the first and second soil color value change maps, garbage characteristics, and human activity intensity. Finally, the fourth determination module combines the area change curve of each vegetation block and the pollution level to comprehensively determine the pollution level of the entire preset coastal area, which is more accurate and convenient than manual assessment.

[0056] In another possible implementation, when the third determining module determines the pollution level of each vegetation block based on the first soil color value change map, the second soil color value change map, garbage characteristics, and human activity heat map, it is specifically used for:

[0057] Based on the first soil color value change map and the second soil color value change map, a fitted soil color value change map for each vegetation block is determined.

[0058] The first average value of the soil color value is determined from the fitted soil color value variation graph;

[0059] The characteristics of the waste in each vegetation block are counted to obtain the amount of waste in each vegetation block;

[0060] The difficulty score for waste purification in each vegetation block is determined based on the characteristics of the waste within each vegetation block.

[0061] The pollution level of each vegetation block is determined based on the first average value, the amount of garbage, the difficulty score of garbage purification, and the activity level of people.

[0062] In another possible implementation, when the fourth determining module determines the pollution level of the preset coastal area based on the area change curve of each vegetation block and the pollution level of each vegetation block, it is specifically used for:

[0063] The area change trend of each vegetation block is determined from the area change curve of each vegetation block, and the first vegetation block with an area change trend of decreasing or unchanged and the second vegetation block with an area change trend of increasing are obtained.

[0064] Determine a first ratio between the number of the second vegetation blocks and the number of the first vegetation blocks;

[0065] Determine the first total area of ​​all first vegetation blocks and the second total area of ​​all second vegetation blocks;

[0066] Determine a second ratio between the second total area and the first total area;

[0067] The pollution level of the preset coastal area is determined based on the pollution level of each vegetation block, the first ratio, the second ratio, and their respective coefficients.

[0068] In another possible implementation, when the third determining module determines the waste purification difficulty score for each vegetated block based on the waste characteristics within each vegetated block, it is specifically used for:

[0069] The outline of each vegetation block is determined, and a Cartesian coordinate system is drawn with the center point of the outline as the origin. The two coordinate axes of the Cartesian coordinate system make an angle of 45° with the coastline.

[0070] Determine the coordinates of the waste features in each quadrant of the Cartesian coordinate system, and determine the coordinates of the center point representing the distribution of waste features in each quadrant based on the coordinates;

[0071] Determine the distance from the center point coordinates to the origin of the Cartesian coordinate system;

[0072] Determine the number of waste features in each quadrant of the Cartesian coordinate system;

[0073] The waste purification difficulty score for each quadrant is determined based on the distance, quantity, and waste purification difficulty coefficient corresponding to each quadrant.

[0074] The waste purification difficulty score within each vegetation block is determined based on the waste purification difficulty score corresponding to each quadrant.

[0075] In another possible implementation, when the third determining module determines the fitted soil color value change map for each vegetation block based on the first soil color value change map and the second soil color value change map, it is specifically used for:

[0076] Determine the first time point corresponding to each color value in the first soil color value change graph, and determine the second time point corresponding to each color value in the second soil color value change graph;

[0077] A target color value group is determined from the first soil color value change map and the second soil color value change map. The target color value group is two color values ​​whose time interval between the first time point and the second time point is less than a preset interval.

[0078] Calculate the average of the color values ​​of the target color value group;

[0079] The obtained average value is mapped to the first time point within the target color value group to obtain the candidate soil color value change map in the first soil color value change map.

[0080] Identify the remaining color values ​​in the second soil color value variation map, excluding those located in the target color value group;

[0081] The associated color values ​​are determined from the first soil color value change map based on the second time point of each remaining color value. The first time points of the associated color values ​​are the two color values ​​closest to the remaining color values, and the first time points of the associated color values ​​are located before and after the second time points of the remaining color values, respectively.

[0082] Calculate the average color value of the associated color values, and calculate the difference between the remaining color values ​​and the average color value;

[0083] The remaining color values ​​whose difference does not reach the preset difference threshold are mapped to the candidate soil color value change map according to the second time point of the remaining color values, so as to obtain the fitted soil color value change map for each vegetation block.

[0084] In another possible implementation, when determining the human activity heat map of each vegetation block based on the multiple aerial images, the second determining module is specifically used for:

[0085] Determine the number of people in each aerial image;

[0086] Determine the average number of personnel and the total number of personnel based on the aforementioned number of personnel;

[0087] The score representing the activity intensity of the personnel is determined based on the average number of personnel, the total number of personnel, and their respective coefficients.

[0088] In another possible implementation, the device further includes:

[0089] The fifth determination module is used to determine the location and time of the third vegetation block from the most recent remote sensing image. The third vegetation block is a vegetation block whose pollution level has reached a preset threshold and whose area is increasing.

[0090] The output module is used to output the location and time of the most recent remote sensing image of the third vegetation block.

[0091] Thirdly, this application provides an electronic device that adopts the following technical solution:

[0092] An electronic device comprising:

[0093] At least one processor;

[0094] Memory;

[0095] At least one application, wherein the application is stored in memory and configured to be executed by at least one processor, the at least one configuration being for: executing a big data-based coastal information assessment method as shown in any possible implementation of the first aspect.

[0096] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution:

[0097] A computer-readable storage medium that, when the computer program is executed in a computer, causes the computer to perform a big data-based coastal information assessment method as described in any one of the first aspects.

[0098] In summary, this application includes at least one of the following beneficial technical effects:

[0099] Historical remote sensing imagery is acquired, which records specific changes in the coastline. Therefore, based on this imagery, the area change curve and the first soil color value change map for each vegetation block can be determined. The vegetation block area change map represents the expansion or reduction of invasive plants. Soil color changes when polluted; therefore, the first soil color value change map represents changes in soil pollution levels. Aerial images are also acquired. Aerial images are closer than remote sensing imagery, allowing for the capture of more details. Therefore, the second soil color value change map for each vegetation block is determined based on aerial images. Due to the difference in altitude between the remote sensing imagery and the aerial imagery, the second soil color value change... There are differences between the first and second soil color value change maps. Combining the first and second soil color value change maps allows for a more accurate assessment of soil pollution, determining the characteristics of waste and the intensity of human activity in each vegetation block. Waste characteristics also pollute the soil, and higher levels of human activity lead to greater soil damage and pollution. Therefore, determining the pollution level of each vegetation block based on the sum of the first and second soil color value change maps, waste characteristics, and human activity intensity is more accurate. Finally, combining the area change curves of each vegetation block with the pollution level to comprehensively determine the pollution level of the entire preset coastal area is more accurate and convenient than manual assessment. Attached Figure Description

[0100] Figure 1 This is a flowchart illustrating a big data-based coastal information assessment method according to an embodiment of this application.

[0101] Figure 2 This is an example diagram of the coastline, vegetation blocks, garbage features, and the establishment of a plane rectangular coordinate system in the embodiments of this application.

[0102] Figure 3 This is a schematic diagram of the structure of a coastal information assessment device based on big data, according to an embodiment of this application.

[0103] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application.

[0104] Reference numerals: 21, coastline; 22, vegetation block; 23, garbage characteristics; 30, a big data-based coastal information assessment device; 301, image acquisition module; 302, first determination module; 303, second determination module; 304, third determination module; 305, fourth determination module; 40, electronic device; 401, processor; 402, bus; 403, memory; 404, transceiver. Detailed Implementation

[0105] The present application will be further described in detail below with reference to the accompanying drawings.

[0106] After reading this specification, those skilled in the art may make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

[0107] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0108] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0109] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0110] This application provides a big data-based coastal information assessment method executed by an electronic device, which can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication. This application does not impose any limitations on this. Figure 1 As shown, the method includes steps S101, S102, S103, S104, and S105, wherein,

[0111] S101, acquire historical remote sensing images of multiple vegetation blocks within a preset coastal area.

[0112] In this embodiment, the preset coastal area can be a coastal area manually set through a visual operation interface, such as delineating the preset coastal area based on latitude and longitude, or selecting the preset coastal area using an input device such as a mouse. The electronic device can obtain historical remote sensing images of multiple vegetation blocks within the preset coastal area from relevant mapping websites, or obtain historical remote sensing images corresponding to each of the multiple vegetation blocks through relevant remote sensing mapping database API interfaces, or directly obtain historical remote sensing images from remote sensing satellites. The historical remote sensing images can be multiple remote sensing images from different historical points in time. A vegetation block is a block formed by the reproduction and growth of invasive species or other plants that damage the coastal ecological environment, such as Spartina alterniflora. A vegetation block also includes the surrounding preset area outside the outline formed by the vegetation.

[0113] S102, determine the area change curve of each vegetation block and the first soil color value change map based on historical remote sensing images.

[0114] In this embodiment of the application, since historical remote sensing images record the area size of each vegetation block, after acquiring the historical remote sensing images, the electronic device can obtain coordinate points based on the time point of each historical remote sensing image and the corresponding area size of the vegetation block. By mapping the coordinate points corresponding to each historical remote sensing image onto a preset coordinate system showing area changes over time and connecting them sequentially, the area change curve of each vegetation block can be obtained. The area change curve allows for a more intuitive and convenient observation of the area changes of each vegetation block.

[0115] Historical remote sensing images record the color of vegetated areas and the soil in pre-defined areas near these areas. The greater the deviation between the color value and the soil's color value when it is uncontaminated, the more severe the soil contamination. Therefore, electronic devices can perform grayscale transformation on historical remote sensing images to obtain their grayscale values. That is, grayscale values ​​are used to represent color values. By mapping the coordinate points corresponding to each historical remote sensing image onto a pre-defined coordinate system showing grayscale value changes over time and connecting them sequentially, a first soil color value change curve for each vegetated area can be obtained. This first soil color value change curve allows for a more intuitive and convenient observation of the soil color changes in each vegetated area, i.e., the degree of soil contamination.

[0116] Specifically, taking Spartina alterniflora as an example, the rampant growth of Spartina alterniflora hinders the scouring of coastal mudflats by seawater, causing soil, garbage, and animal and plant carcasses on the coastal mudflats to be unable to be carried back into the ocean by the water flow. This results in a reduction in the seawater exchange capacity, and the accumulation and fermentation of garbage and other pollutants on the soil causes changes in soil color, indicating that the soil pollution is more serious.

[0117] S103, acquire multiple aerial images of each vegetation block within a preset historical time period, and determine the second soil color value change map of each vegetation block, garbage characteristics in each aerial image of each vegetation block, and human activity heat map based on the multiple aerial images.

[0118] In this embodiment of the application, the aerial images are images of vegetation blocks taken by drones. These are aerial images collected at multiple different points in history. Compared to remote sensing images, aerial images are closer to the vegetation blocks, allowing for the collection of more detailed features of the vegetation blocks and surrounding areas. Furthermore, the soil color values ​​of each vegetation block and its surrounding area can be determined based on the aerial images, and a second soil color value change map can be determined using the method described in step S102. The second soil color value change map differs from the first soil color value change map because they are determined from images collected at different altitudes. Therefore, the two color value change maps differ, but both can characterize the soil color value changes of the vegetation blocks to a certain extent.

[0119] The electronic device inputs each aerial image into a trained network model for feature recognition, thereby identifying garbage features in each image. These garbage features can also characterize soil pollution to some extent. Specifically, the network model can be a convolutional neural network, a recurrent neural network, or other types of network models. The electronic device also analyzes each aerial image to determine the level of human activity in each vegetation block. Since human activities such as production on coastal mudflats also pollute the soil, higher activity levels indicate greater soil pollution, and vice versa.

[0120] S104. The pollution level of each vegetation block is determined based on the first soil color value change map, the second soil color value change map, garbage characteristics, and human activity heat.

[0121] In summary, for the embodiments of this application, the first soil color value change map, the second soil color value change map, garbage characteristics, and human activity heat are all important factors affecting the assessment of the pollution level of each vegetation block. Therefore, the electronic device can more accurately determine the pollution level of each vegetation block by combining the above four factors.

[0122] S105, determine the pollution level of the preset coastal area based on the area change curve of each vegetation block and the pollution level of each vegetation block.

[0123] In this embodiment of the application, the pollution level of the entire preset coastal area can be determined by the electronic device after determining the pollution level of each vegetation block. Determining the pollution level of each vegetation block first and then the pollution level of the entire preset coastal area is more convenient and accurate than manually assessing the pollution level of the coastal area.

[0124] One possible implementation of this application embodiment involves determining the pollution level of each vegetation block in step S104 based on a first soil color value change map, a second soil color value change map, garbage characteristics, and human activity heat. Specifically, this includes steps S1041 (not shown in the figure), S1042 (not shown in the figure), S1043 (not shown in the figure), S1044 (not shown in the figure), and S1045 (not shown in the figure).

[0125] S1041, Based on the first soil color value change map and the second soil color value change map, determine the fitted soil color value change map for each vegetation block.

[0126] In the embodiments of this application, since the first soil color value change map and the second soil color value change map are determined based on images collected at different heights, although both can characterize the changes in soil color values ​​and the soil pollution status, there are still differences. Therefore, the electronic device comprehensively analyzes the first soil color value change map and the second soil color value change map to determine the fitted soil color value change map for each vegetation block. The determined fitted soil color value change map more accurately characterizes the soil pollution status.

[0127] S1042, determine the first average value of the soil color value from the fitted soil color value variation map.

[0128] In the embodiments of this application, after the electronic device determines the fitted soil color value change map, it calculates the first average value of the soil gray value based on the gray value of each coordinate point in the change map using the average value calculation formula. The first average value is used to more accurately represent the specific color depth of the soil as a whole within the historical time period corresponding to the historical remote sensing image, that is, the first average value is used to more accurately represent the soil pollution situation.

[0129] S1043, count the characteristics of the waste in each vegetation block to obtain the amount of waste in each vegetation block.

[0130] In the embodiments of this application, after the electronic device identifies the garbage characteristics in each vegetation block, it accumulates and counts the garbage characteristics to obtain the garbage quantity. The more garbage in a certain vegetation block, the more serious the soil pollution in that vegetation block is.

[0131] S1044, Determine the waste purification difficulty score for each vegetation block based on the waste characteristics within each vegetation block.

[0132] In the embodiments of this application, after the electronic device identifies the garbage characteristics in each vegetation block, it can further analyze the garbage characteristics, such as determining the location of the garbage characteristics, and analyze the garbage purification difficulty score in each vegetation block. The garbage purification difficulty can characterize the difficulty of seawater scouring to purify garbage on the soil, that is, the difficulty of seawater carrying garbage back into the ocean. The higher the score, the more serious the soil pollution in the vegetation block.

[0133] S1045, the pollution level of each vegetation block is determined based on the first average value, the amount of garbage, the difficulty score of garbage purification, and the activity intensity of people.

[0134] In summary, for the embodiments of this application, the first average value, the amount of waste, the difficulty score of waste purification, and the activity level of personnel are all important factors affecting the degree of pollution in vegetation blocks. After the electronic device determines the first average value, it can calculate the difference between the first average value and the preset gray value. The preset gray value represents the gray value of the soil when it is not polluted; the larger the difference, the more severe the soil pollution. Therefore, staff can set different coefficients for the four elements mentioned above, including the first average value, and then perform a weighted calculation on the difference, the amount of waste, the difficulty score of waste purification, and the activity level of personnel, combining their respective coefficients, to obtain a score representing the degree of pollution of each vegetation block. This score more accurately represents the degree of pollution of each vegetation block. Furthermore, calculating the score representing the degree of pollution by comprehensively considering important parameters such as the first average value and the amount of waste is more accurate and convenient.

[0135] One possible implementation of this application embodiment is that step S105 determines the pollution level of a preset coastal area based on the area change curve of each vegetation block and the pollution level of each vegetation block. Specifically, this includes steps S1051 (not shown in the figure), S1052 (not shown in the figure), S1053 (not shown in the figure), S1054 (not shown in the figure), and S1055 (not shown in the figure).

[0136] S1051, determine the area change trend of each vegetation block from the area change curve of each vegetation block, and obtain the first vegetation block whose area change trend is decreasing or unchanged, and the second vegetation block whose area change trend is increasing.

[0137] In this embodiment of the application, the electronic device performs linear fitting on the area change curve of each vegetation block to obtain an approximate linear function. Then, the electronic device determines the slope of the linear function. If the slope is positive, it indicates that the area change trend is increasing; if the slope is negative, it indicates that the area change trend is decreasing; and if the slope is 0, it indicates that the area change trend is unchanged. The electronic device determines the first vegetation block and the second vegetation block using the above method.

[0138] S1052, determine a first ratio of the number of second vegetation blocks to the number of first vegetation blocks.

[0139] In this embodiment of the application, the electronic device determines the number of second vegetation blocks whose area change trend is increasing, and the number of first vegetation blocks whose area change trend is decreasing or unchanged. Then, the electronic device calculates a first ratio between these two numbers, with the number of second vegetation blocks as the numerator and the number of first vegetation blocks as the denominator. The larger the first ratio, the more vegetation blocks in the preset coastal area are in the state of increasing area, and the preset coastal area as a whole is in the state of invasive plant expansion. Furthermore, since there are a large number of vegetation blocks in the state of increasing area, it indicates that the faster the plant expansion rate in the preset coastal area, the more serious the pollution.

[0140] S1053, determine the first total area of ​​all first vegetation blocks and the second total area of ​​all second vegetation blocks.

[0141] In this embodiment of the application, the electronic device sums the areas of all first vegetation blocks to obtain a first total area, and sums the areas of all second vegetation blocks to obtain a second total area.

[0142] S1054, determine the second ratio of the second total area to the first total area.

[0143] In the embodiments of this application, the electronic device calculates a second ratio of the two total areas, with the second total area as the numerator and the first total area as the denominator. The larger the second ratio, the larger the proportion of vegetation blocks with increasing area in the preset coastal area. The preset coastal area as a whole is in a state of invasive plant expansion and the expansion trend is serious, which in turn indicates that the pollution in the preset coastal area is more serious.

[0144] S1055, based on the pollution level of each vegetation block, the first ratio, the second ratio, and their respective coefficients, a score characterizing the pollution level of the preset coastal area is determined.

[0145] In summary, for the embodiments of this application, the pollution level, first ratio, and second ratio of each vegetation block are all key factors affecting the overall pollution level of the preset coastal area, and their influence varies. Therefore, staff can set their respective coefficients through a visual interface, and then the electronic device can use these coefficients to perform a weighted calculation on the pollution level, first ratio, and second ratio of each block to obtain a score representing the pollution level of the preset coastal area. A more accurate assessment of the pollution level of the preset coastal area is achieved by combining the pollution level, first ratio, and second ratio of each vegetation block.

[0146] One possible implementation of this application embodiment is that step S1044 determines the garbage purification difficulty score of each vegetation block based on the garbage characteristics within each vegetation block, specifically including steps S1 (not shown in the figure), S2 (not shown in the figure), S3 (not shown in the figure), S4 (not shown in the figure), S5 (not shown in the figure), and S6 (not shown in the figure), wherein...

[0147] S1, determine the outline of each vegetation block, and draw a plane rectangular coordinate system with the center point of the outline as the origin.

[0148] The two coordinate axes of the plane rectangular coordinate system form an angle of 45° with the coastline.

[0149] In this embodiment, the electronic device determines the outline of each vegetation block based on the most recent aerial image. The electronic device performs denoising on the most recent aerial image and then grayscale transformation on the denoised image. It then identifies locations where grayscale values ​​change abruptly to determine the outline of the vegetation block. Next, the electronic device determines the smallest circumscribed rectangle of the outline and its center coordinates, which are the center point of the outline. The electronic device then draws a Cartesian coordinate system with this center point as the origin.

[0150] The electronic device determines the coastline of a preset coastal area, approximating it as a straight line, with the direction of seawater erosion perpendicular to the coastline. After determining the approximate straight line of the coastline, the electronic device draws a Cartesian coordinate system with both coordinate axes making a 45° angle with the coastline, resulting in four quadrants, as shown below. Figure 2 As shown, the electronic device draws a coordinate system based on the direction of the coastline 21 and the position of the vegetation block 22. Seawater washes over the area on the coast in a direction perpendicular to the coastline 21. The vegetation on the vegetation block 22 blocks the seawater from flowing and washing further, and the invasive plants also block garbage, making it difficult for soil and garbage features 23 to move back into the ocean, thus aggravating soil pollution.

[0151] S2 determines the coordinates of the waste features in each quadrant of the Cartesian coordinate system, and determines the coordinates of the center point representing the distribution of waste features in each quadrant based on the coordinates.

[0152] In this embodiment, after identifying waste features, the electronic device defines the waste features as coordinate points on a Cartesian coordinate system and determines the coordinates of each waste feature, thereby determining the coordinates of the waste features in each quadrant. Then, the electronic device calculates the arithmetic mean of the X and Y coordinates of all scattered points. These two averages are used as the coordinates of the center point of the waste feature distribution in each quadrant. Specifically, the electronic device first adds all X coordinates and divides by the total number of scattered points to obtain the average X coordinate, and then adds all Y coordinates and divides by the total number of scattered points to obtain the average Y coordinate.

[0153] S3, determine the distance from the center point coordinates to the origin of the Cartesian coordinate system.

[0154] In this embodiment, after determining the coordinates of the center point of the garbage feature distribution in each quadrant, the electronic device calculates the distance from the center point to the origin. This distance is obtained using the formula for the distance between two points. The closer to the origin, i.e., the smaller the distance, the closer the garbage is to the center of the vegetation block, the greater the obstruction from the vegetation, and the more difficult it is for the garbage to be washed away by seawater. For the quadrant furthest from the coastline, due to the separation of seawater and garbage by the vegetation block, the farther the center point of the garbage feature distribution is from the coastline, the less likely it is to be washed away by seawater. However, since this is relatively obvious and its position may shift under external factors such as windy weather, the analysis also follows the principle that the smaller the distance, the greater the difficulty of being washed away by seawater.

[0155] S4 determines the number of waste features in each quadrant of the Cartesian coordinate system.

[0156] In the embodiments of this application, the electronic device can count the number of waste features in each quadrant to obtain the number of waste features in each quadrant. The more waste features there are, the greater the difficulty of purification, and vice versa.

[0157] S5 determines the waste purification difficulty score for each quadrant based on distance, quantity, and the waste purification difficulty coefficient corresponding to each quadrant.

[0158] In summary, for the embodiments of this application, distance and quantity are both key factors regarding the difficulty of waste purification in each quadrant, and their influence varies. Therefore, the staff sets corresponding coefficients for distance and quantity, takes the reciprocal of the distance, and uses the reciprocal of the distance and the quantity to call the corresponding coefficients to calculate an intermediate score. Since the location of each quadrant is different, the corresponding waste purification difficulty is also different. Therefore, the staff sets different waste purification difficulty coefficients for each quadrant. The electronic device calls the waste purification difficulty coefficient corresponding to each quadrant and multiplies it by the above intermediate score to obtain the waste purification difficulty score corresponding to each quadrant.

[0159] In other embodiments, the electronic device can also determine the grayscale value of the soil color in each quadrant from the aerial image, then calculate the difference between the grayscale value of the soil color in each quadrant and the preset grayscale value, and combine the distance, quantity and the difference of grayscale value to comprehensively calculate the garbage purification difficulty score in each quadrant.

[0160] S6. Determine the waste purification difficulty score within each vegetation block based on the waste purification difficulty score corresponding to each quadrant.

[0161] In this embodiment of the application, after the electronic device determines the waste purification difficulty score corresponding to each quadrant, the waste purification scores of the four quadrants are summed to obtain the waste purification difficulty score of each vegetation block. By analyzing the waste distribution and quantity in each quadrant, and combining the location of each quadrant, the waste purification difficulty score of each vegetation block is determined more accurately.

[0162] In other embodiments, the electronic device may also calculate the garbage purification difficulty score of each vegetation area for each aerial image in the manner described above, and then average the garbage purification difficulty scores of all aerial images, and determine the average value as the garbage purification difficulty score of each vegetation block.

[0163] One possible implementation of this application embodiment is that step S1041 determines the fitted soil color value change map for each vegetation block based on the first soil color value change map and the second soil color value change map, specifically including steps one, two, three, four, five, six, seven, and eight, wherein...

[0164] Step 1: Determine the first time point corresponding to each color value in the first soil color value change graph, and determine the second time point corresponding to each color value in the second soil color value change graph.

[0165] In this embodiment of the application, the electronic device retrieves the time point of each color value on the horizontal time axis of the first soil color value change graph, i.e., the first time point, and determines the second time point in the same way.

[0166] Step 2: Determine the target color value group from the first soil color value change map and the second soil color value change map.

[0167] The target color value group consists of two color values ​​whose time interval between the first time point and the second time point is less than a preset interval.

[0168] In this embodiment, historical remote sensing images can be acquired at specified time intervals, and aerial images can also be acquired at specified time intervals or not. The preset interval is much smaller than the time interval for acquiring remote sensing images. The preset interval serves as a boundary point for determining whether the first time point and the second time point are relatively close in time. The electronic device calculates the difference between the first time point and each second time point for each color value, thereby obtaining two color values ​​with a time interval less than the preset interval, i.e., the target color value group. The two color values ​​within the target color value group are close in time, thus representing the soil color value at the same time. The color values ​​within the target color value group facilitate subsequent correction to obtain more realistic and accurate color values.

[0169] Step 3: Calculate the average of the color values ​​in the target color value group.

[0170] In the embodiments of this application, the electronic device calculates the average value of each target color value group using an average value calculation formula. Using this average value to characterize the soil color value corresponding to the first time point and the second time point (the same time point) is more accurate.

[0171] Step 4: Map the obtained average value to the first time point within the target color value group in the first soil color value change map to obtain the candidate soil color value change map.

[0172] In the embodiments of this application, after the electronic device determines the average value in step three, since the target color value group represents the soil color value at the same time point, the electronic device maps the average value to the first time point of the target color value group and deletes the original soil color value corresponding to the first time point of the target color value group, thereby obtaining the candidate soil color value change map.

[0173] Step 5: Determine the remaining color values ​​in the second soil color value change graph, excluding the color values ​​located in the target color value group.

[0174] In this embodiment of the application, the electronic device removes the color values ​​that are in the target color value group from the second soil color value change map, thereby obtaining the remaining color values.

[0175] Step 6: Determine the associated color value from the first soil color value change graph based on the second time point of each remaining color value.

[0176] Among them, the first time point of the associated color value is the two color values ​​closest to the remaining color value, and the first time point of the associated color value is located before and after the second time point of the remaining color value, respectively.

[0177] In this embodiment of the application, the electronic device determines the associated color value from the first soil color value change map according to the second time point of the remaining color value. The associated color value is the color value that has a time progression relationship with the remaining color value.

[0178] Step 7: Calculate the average color value of the associated color values, and calculate the difference between the remaining color values ​​and the average color value.

[0179] In this embodiment of the application, to improve the richness and accuracy of color value data, the electronic device calculates the average color value of the associated color values ​​after determining the associated color values, and uses this average color value to represent the overall level of the associated color values. Then, the difference between the remaining color values ​​and the average color value is calculated. The magnitude of this difference represents the reliability of the remaining color values.

[0180] Step 8: Map the remaining color values ​​that do not reach the preset difference threshold onto the candidate soil color value change map according to the second time point of the remaining color values, to obtain the fitted soil color value change map for each vegetation block.

[0181] In this embodiment, a preset difference threshold serves as a dividing point for whether the difference is too large. If the difference reaches the preset difference threshold, it indicates that the gap between the remaining color value and the associated color value is too large, and the data is unreliable. If the difference does not reach the preset difference threshold, it indicates that the gap between the remaining color value and the associated color value is small, and the data is reliable. Therefore, the electronic device maps the remaining color values ​​whose difference does not reach the preset difference threshold onto the above-mentioned candidate soil color value change map according to the second time point of the remaining color value, thereby obtaining a fitted soil color value change map. The fitted soil color value change map integrates the first soil color value change map and the second soil color value change map, improving the richness of the data and retaining data with higher accuracy and reliability, thereby making the first average value determined subsequently based on the fitted soil color value change map more accurate.

[0182] One possible implementation of this application embodiment is that step S103, which determines the human activity heat map of each vegetation block based on multiple aerial images, specifically includes steps S1031 (not shown in the figure), S1032 (not shown in the figure), and S1033 (not shown in the figure), wherein...

[0183] S1031, Determine the number of people in each aerial image.

[0184] In this embodiment of the application, the electronic device inputs each aerial image into a trained network model to identify people and obtain their features in each image. Then, by counting these features, the number of people in each aerial image can be determined. A higher number of people indicates greater activity.

[0185] S1032, determine the average number of personnel and the total number of personnel based on the number of personnel.

[0186] In this embodiment of the application, after the electronic device determines the number of people in each aerial image, it sums the number of people in all aerial images to obtain a total number, and then calculates the average number of people using an average value calculation formula. A larger average number of people indicates a higher sustained human activity level within the time period corresponding to all aerial images; a larger total number of people indicates a higher level of human activity; and higher human activity indicates more severe soil pollution.

[0187] S1033, based on the average number of people, the total number of people, and their respective coefficients, determines the score characterizing the activity intensity of people.

[0188] In summary, for the embodiments of this application, both the average number of people and the total number of people are key factors in determining the activity level of people. Therefore, staff pre-set coefficients for the average number of people and the total number of people. Then, the electronic device uses these coefficients to perform a weighted calculation on the average number of people and the total number of people to obtain a score, which can represent the activity level of people. Determining the activity level of people by combining the average number of people and the total number of people is more accurate.

[0189] In one possible implementation of this application embodiment, step S105 is followed by steps S106 (not shown in the figure) and S107 (not shown in the figure), wherein...

[0190] S106, the location and time of the third vegetation block were determined by the most recent remote sensing image.

[0191] The third vegetation block is a vegetation block whose pollution level has reached a preset threshold and whose area is increasing.

[0192] S107 outputs the location and time of the most recent remote sensing image of the third vegetation block.

[0193] In this embodiment, if the pollution level of the third vegetation block reaches a preset level, it indicates severe pollution, and the area is showing an increasing trend. Therefore, the third vegetation block is a priority area for remediation. The electronic device identifies the location and time of the most recent remote sensing image of the third vegetation block and sends it to the staff's terminal device. This allows staff to promptly understand and grasp the specific situation of the third vegetation block and make corresponding preparations. For example, based on the most recent remote sensing image, staff can determine the size of the third vegetation block and prepare an appropriate amount of materials.

[0194] The above embodiments introduce a big data-based coastal information assessment method from the perspective of process flow. The following embodiments introduce a big data-based coastal information assessment device from the perspective of virtual modules or virtual units. For details, please refer to the following embodiments.

[0195] This application provides a coastal information assessment device 20 based on big data, such as... Figure 3 As shown, the coastal information assessment device 30 based on big data may specifically include:

[0196] The image acquisition module 301 is used to acquire historical remote sensing images of multiple vegetation blocks within a preset coastal area.

[0197] The first determining module 302 is used to determine the area change curve of each vegetation block and the first soil color value change map based on historical remote sensing images.

[0198] The second determining module 303 is used to acquire multiple aerial images of each vegetation block within a preset historical time period, and to determine the second soil color value change map of each vegetation block, garbage characteristics in each aerial image of each vegetation block, and human activity heat based on the multiple aerial images.

[0199] The third determining module 304 is used to determine the pollution level of each vegetation block based on the first soil color value change map, the second soil color value change map, garbage characteristics, and human activity heat.

[0200] The fourth determining module 305 is used to determine the pollution level of the preset coastal area based on the area change curve of each vegetation block and the pollution level of each vegetation block.

[0201] This application discloses a coastal information assessment device 20 based on big data. The image acquisition module 301 acquires historical remote sensing images, which record specific changes in the coastline. Therefore, the first determination module 302 can determine the area change curve and the first soil color value change map for each vegetation block based on the historical remote sensing images. The vegetation block area change map represents the expansion or reduction of invasive plants. Soil color changes when polluted; therefore, the first soil color value change map represents changes in soil pollution. The second determination module 303 acquires aerial images. Aerial images are closer than remote sensing images and can capture more details. Therefore, the second determination module 303 determines the second soil color value change map for each vegetation block based on the aerial images. Because remote sensing... The different altitudes of the aerial images and the photographic images result in differences between the second and first soil color value change maps. Combining the first and second soil color value change maps allows for a more accurate assessment of soil pollution, identifying the characteristics of litter and the intensity of human activity in each vegetation block. Litter also pollutes the soil, and higher levels of human activity contribute to greater soil damage and pollution. Therefore, the third determining module 304 uses the sum of the first and second soil color value change maps, litter characteristics, and human activity intensity to more accurately determine the pollution level of each vegetation block. Finally, the fourth determining module 305 combines the area change curve of each vegetation block with the pollution level to comprehensively determine the pollution level of the entire preset coastal area, which is more accurate and convenient than manual assessment.

[0202] In one possible implementation of this application embodiment, when the third determining module 304 determines the pollution level of each vegetation block based on the first soil color value change map, the second soil color value change map, garbage characteristics, and human activity heat, it is specifically used for:

[0203] Based on the first and second soil color value change maps, a fitted soil color value change map for each vegetation block is determined.

[0204] The first average value of the soil color value was determined from the fitted soil color value variation graph;

[0205] The characteristics of the waste in each vegetation block are counted to obtain the amount of waste in each vegetation block;

[0206] The difficulty score for waste purification in each vegetated block is determined based on the characteristics of the waste within that block.

[0207] The pollution level of each vegetation block is determined based on the first average value, the amount of garbage, the difficulty score of garbage purification, and the activity level of people.

[0208] In one possible implementation of this application embodiment, when the fourth determining module 305 determines the pollution level of a preset coastal area based on the area change curve of each vegetation block and the pollution level of each vegetation block, it is specifically used for:

[0209] The area change trend of each vegetation block is determined from the area change curve of each vegetation block, and the first vegetation block with the area change trend of decreasing or remaining unchanged and the second vegetation block with the area change trend of increasing are obtained.

[0210] Determine a first ratio of the number of second vegetation blocks to the number of first vegetation blocks;

[0211] Determine the first total area of ​​all first vegetation blocks and the second total area of ​​all second vegetation blocks;

[0212] Determine a second ratio between the second total area and the first total area;

[0213] The score characterizing the pollution level of the preset coastal area is determined based on the pollution level of each vegetation block, the first ratio, the second ratio, and their respective coefficients.

[0214] In one possible implementation of this application embodiment, when the third determining module 304 determines the waste purification difficulty score for each vegetated block based on the waste characteristics within each vegetated block, it is specifically used for:

[0215] Determine the outline of each vegetation block and draw a Cartesian coordinate system with the center point of the outline as the origin. The two coordinate axes of the Cartesian coordinate system make an angle of 45° with the coastline.

[0216] Determine the coordinates of waste features in each quadrant of a Cartesian coordinate system, and determine the coordinates of the center point representing the distribution of waste features in each quadrant based on the coordinates;

[0217] Determine the distance from the center point to the origin of the Cartesian coordinate system;

[0218] Determine the number of waste features in each quadrant of a Cartesian coordinate system;

[0219] The waste purification difficulty score for each quadrant is determined based on distance, quantity, and the waste purification difficulty coefficient corresponding to each quadrant.

[0220] The waste purification difficulty score for each vegetation block is determined based on the waste purification difficulty score corresponding to each quadrant.

[0221] In one possible implementation of this application embodiment, when the third determining module 304 determines the fitted soil color value change map for each vegetation block based on the first soil color value change map and the second soil color value change map, it is specifically used for:

[0222] Determine the first time point corresponding to each color value in the first soil color value change graph, and determine the second time point corresponding to each color value in the second soil color value change graph;

[0223] The target color value group is determined from the first soil color value change map and the second soil color value change map. The target color value group is two color values ​​whose time interval between the first time point and the second time point is less than a preset interval.

[0224] Calculate the average of the color values ​​for the target color value group;

[0225] The obtained average value is mapped to the first time point within the target color value group in the first soil color value change map to obtain the candidate soil color value change map.

[0226] Identify the remaining color values ​​in the second soil color value variation map, excluding those located in the target color value group;

[0227] The associated color values ​​are determined from the first soil color value change map based on the second time point of each remaining color value. The first time points of the associated color values ​​are the two color values ​​closest to the remaining color values, and the first time points of the associated color values ​​are located before and after the second time points of the remaining color values, respectively.

[0228] Calculate the average color value of the associated color values, and calculate the difference between the remaining color values ​​and the average color value;

[0229] The remaining color values ​​whose difference does not reach the preset difference threshold are mapped onto the candidate soil color value change map according to the second time point of the remaining color values, so as to obtain the fitted soil color value change map for each vegetation block.

[0230] In one possible implementation of this application embodiment, when determining the human activity heat map of each vegetation block based on multiple aerial images, the second determining module 303 is specifically used for:

[0231] Determine the number of people in each aerial image;

[0232] Determine the average number of personnel and the total number of personnel based on the number of personnel;

[0233] The score representing the activity intensity of personnel is determined based on the average number of personnel, the total number of personnel, and their respective coefficients.

[0234] In one possible implementation of this application embodiment, the device 30 further includes:

[0235] The fifth determination module is used to determine the location and time of the third vegetation block from the most recent remote sensing image. The third vegetation block is a vegetation block whose pollution level has reached a preset threshold and whose area is increasing.

[0236] The output module is used to output the location and time of the most recent remote sensing image of the third vegetation block.

[0237] In the embodiments of this application, the first determining module 302, the second determining module 303, the third determining module 304, the fourth determining module 305 and the fifth determining module may be the same determining module, different determining modules, or partially the same determining modules, which is not limited here.

[0238] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the big data-based coastal information assessment device 30 described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0239] This application provides an electronic device, such as... Figure 4 As shown, Figure 4 The illustrated electronic device 40 includes a processor 401 and a memory 403. The processor 401 and the memory 403 are connected, for example, via a bus 402. Optionally, the electronic device 40 may also include a transceiver 404. It should be noted that in practical applications, the transceiver 404 is not limited to one type, and the structure of this electronic device 40 does not constitute a limitation on the embodiments of this application.

[0240] Processor 401 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 401 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0241] Bus 402 may include a pathway for transmitting information between the aforementioned components. Bus 402 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 402 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0242] The memory 403 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0243] The memory 403 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 401. The processor 401 is used to execute the application code stored in the memory 403 to implement the content shown in the foregoing method embodiments.

[0244] Electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Servers can also be included. Figure 4 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0245] This application provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the corresponding content in the aforementioned method embodiments. Compared with related technologies, this application acquires historical remote sensing images, which record specific changes in the coastline. Therefore, based on the historical remote sensing images, the area change curve of each vegetation block and a first soil color value change map can be determined. The vegetation block area change map represents the expansion or reduction of invasive plants. Soil color changes when polluted; therefore, the first soil color value change map represents changes in soil pollution. Aerial images are acquired, as they are closer than remote sensing images and can capture more details. Therefore, a second soil color value change map for each vegetation block is determined based on the aerial images. Since the remote sensing images and aerial images have different altitudes, the second... There are differences between the soil color value change map and the first soil color value change map. Combining the first and second soil color value change maps can more accurately assess the soil pollution status, determine the garbage characteristics and human activity intensity of each vegetation block. Garbage characteristics also pollute the soil, and the higher the human activity intensity, the greater the damage and pollution to the soil. Therefore, determining the pollution level of each vegetation block based on the sum of the first and second soil color value change maps, garbage characteristics, and human activity intensity is more accurate. Finally, combining the area change curve of each vegetation block and the pollution level to comprehensively determine the pollution level of the entire preset coastal area is more accurate and convenient than manual assessment.

[0246] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0247] The above description is only a partial embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for assessing coastal information based on big data, characterized in that, include: Acquire historical remote sensing images of multiple vegetation blocks within a preset coastal area; Based on the historical remote sensing images, determine the area change curve of each vegetation block and the first soil color value change map; Multiple aerial images of each vegetation block within a preset historical time period are acquired. Based on the multiple aerial images, a second soil color value change map of each vegetation block, garbage characteristics in each aerial image of each vegetation block, and human activity heat map are determined. The pollution level of each vegetation block is determined based on the first soil color value change map, the second soil color value change map, garbage characteristics, and human activity heat. The pollution level of the preset coastal area is determined based on the area change curve of each vegetation block and the pollution level of each vegetation block.

2. The coastal information assessment method based on big data according to claim 1, characterized in that, The determination of the pollution level of each vegetation block based on the first soil color value change map, the second soil color value change map, garbage characteristics, and human activity heat map includes: Based on the first soil color value change map and the second soil color value change map, a fitted soil color value change map for each vegetation block is determined. The first average value of the soil color value is determined from the fitted soil color value variation graph; The characteristics of the waste in each vegetation block are counted to obtain the amount of waste in each vegetation block; The difficulty score for waste purification in each vegetation block is determined based on the characteristics of the waste within each vegetation block. The pollution level of each vegetation block is determined based on the first average value, the amount of garbage, the difficulty score of garbage purification, and the activity level of people.

3. The coastal information assessment method based on big data according to claim 2, characterized in that, The pollution level of the preset coastal area is determined based on the area change curve of each vegetation block and the pollution level of each vegetation block, including: The area change trend of each vegetation block is determined from the area change curve of each vegetation block, and the first vegetation block with an area change trend of decreasing or unchanged and the second vegetation block with an area change trend of increasing are obtained. Determine a first ratio between the number of the second vegetation blocks and the number of the first vegetation blocks; Determine the first total area of ​​all first vegetation blocks and the second total area of ​​all second vegetation blocks; Determine a second ratio between the second total area and the first total area; The pollution level of the preset coastal area is determined based on the pollution level of each vegetation block, the first ratio, the second ratio, and their respective coefficients.

4. The coastal information assessment method based on big data according to claim 2, characterized in that, The determination of the waste purification difficulty score for each vegetation block based on the waste characteristics within each vegetation block includes: The outline of each vegetation block is determined, and a Cartesian coordinate system is drawn with the center point of the outline as the origin. The two coordinate axes of the Cartesian coordinate system make an angle of 45° with the coastline. Determine the coordinates of the waste features in each quadrant of the Cartesian coordinate system, and determine the coordinates of the center point representing the distribution of waste features in each quadrant based on the coordinates; Determine the distance from the center point coordinates to the origin of the Cartesian coordinate system; Determine the number of waste features in each quadrant of the Cartesian coordinate system; The waste purification difficulty score for each quadrant is determined based on the distance, quantity, and waste purification difficulty coefficient corresponding to each quadrant. The waste purification difficulty score within each vegetation block is determined based on the waste purification difficulty score corresponding to each quadrant.

5. The coastal information assessment method based on big data according to claim 2, characterized in that, The process of determining the fitted soil color value change map for each vegetation block based on the first soil color value change map and the second soil color value change map includes: Determine the first time point corresponding to each color value in the first soil color value change graph, and determine the second time point corresponding to each color value in the second soil color value change graph; A target color value group is determined from the first soil color value change map and the second soil color value change map. The target color value group is two color values ​​whose time interval between the first time point and the second time point is less than a preset interval. Calculate the average of the color values ​​of the target color value group; The obtained average value is mapped to the first time point within the target color value group to obtain the candidate soil color value change map in the first soil color value change map. Identify the remaining color values ​​in the second soil color value variation map, excluding those located in the target color value group; The associated color values ​​are determined from the first soil color value change map based on the second time point of each remaining color value. The first time points of the associated color values ​​are the two color values ​​closest to the remaining color values, and the first time points of the associated color values ​​are located before and after the second time points of the remaining color values, respectively. Calculate the average color value of the associated color values, and calculate the difference between the remaining color values ​​and the average color value; The remaining color values ​​whose differences do not reach the preset difference threshold are mapped to the candidate soil color value change map according to the second time point of the remaining color values, so as to obtain the fitted soil color value change map for each vegetation block.

6. The coastal information assessment method based on big data according to claim 1, characterized in that, The determination of human activity intensity in each vegetation block based on the multiple aerial images includes: Determine the number of people in each aerial image; Determine the average number of personnel and the total number of personnel based on the aforementioned number of personnel; The score representing the activity intensity of the personnel is determined based on the average number of personnel, the total number of personnel, and their respective coefficients.

7. The coastal information assessment method based on big data according to claim 2, characterized in that, The method further includes: The location and time of the third vegetation block are determined by the most recent remote sensing image. The third vegetation block is a vegetation block whose pollution level has reached a preset threshold and whose area is increasing. Output the location and time of the most recent remote sensing image of the third vegetation block.

8. A coastal information assessment device based on big data, characterized in that, include: The image acquisition module is used to acquire historical remote sensing images of multiple vegetation blocks within a preset coastal area. The first determining module is used to determine the area change curve of each vegetation block and the first soil color value change map based on the historical remote sensing image. The second determining module is used to acquire multiple aerial images of each vegetation block within a preset historical time period, and to determine the second soil color value change map of each vegetation block, garbage characteristics in each aerial image of each vegetation block, and human activity heat based on the multiple aerial images. The third determining module is used to determine the pollution level of each vegetation block based on the first soil color value change map, the second soil color value change map, garbage characteristics, and human activity heat. The fourth determining module is used to determine the pollution level of the preset coastal area based on the area change curve of each vegetation block and the pollution level of each vegetation block.

9. An electronic device, characterized in that, It includes: At least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and configured to be executed by the at least one processor, the at least one application being used to execute a big data-based coastal information assessment method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed in the computer, the computer is instructed to perform a big data-based coastal information assessment method as described in any one of claims 1 to 7.

Images