Method and device for adjusting layout of marine monitoring points

Abstract

The present application discloses a method and device for adjusting the layout of marine monitoring points, wherein the regional weight coefficient and pollution diffusion intensity of each pollution detection area are obtained; the estimated pollution concentration of each marine monitoring point is determined based on the regional center coordinates, regional weight coefficient, pollution diffusion intensity and monitoring point coordinates of each pollution detection area; the sampling frequency of each marine monitoring point is determined based on the estimated pollution concentration of the marine monitoring point; the target sea area is divided into multiple sub-areas, and the overall frequency average corresponding to each sub-area is calculated; the layout density of marine monitoring points is increased in the sub-area where the overall frequency average is higher than a first preset value, and the layout density of marine monitoring points is reduced in the sub-area where the overall frequency average is not higher than a second preset value. The present application can dynamically adjust the layout of marine monitoring points to improve the accuracy of marine monitoring.

Description

Technical Field

[0001] The present application relates to the field of ocean monitoring technology, and in particular to a method and device for adjusting the layout of ocean monitoring points. Background Art

[0002] Affected by many factors such as human activities, meteorology and hydrology, the change process of the marine water environment system is a complex nonlinear dynamic process with characteristics such as trend, seasonality and mutation. Timely and accurate evaluation of seawater quality is of great significance to marine environmental protection, marine development and management. Therefore, when dealing with many problems, especially the problem of seawater quality evaluation, once the evaluation is improper, the marine ecological environment security will be threatened and the sustainable development of the marine economy will be affected. Therefore, it is very important to scientifically evaluate the seawater quality of the target sea area, and the layout of the monitoring station as the basis of the evaluation is crucial. It is related to the success or failure of marine environmental monitoring and marine environmental evaluation. With the rise of the marine economic boom, marine environmental disasters have occurred more and more frequently, and the scale of occurrence has become larger and larger, and the losses to the marine economy and ecological environment have become more and more serious. The scientific and reasonable layout of marine environmental monitoring stations, but the layout of the existing marine monitoring points cannot be dynamically adjusted, resulting in the inability to adapt to the monitoring needs well, resulting in low accuracy of marine monitoring. Summary of the invention

[0003] The embodiments of the present application provide a method and device for adjusting the layout of ocean monitoring points, which can dynamically adjust the layout of ocean monitoring points and improve the accuracy of ocean monitoring.

[0004] In a first aspect, the layout adjustment method of the marine monitoring points provided in the present application includes:

[0005] Obtain the monitoring point coordinates of multiple ocean monitoring points in the target sea area;

[0006] Acquiring satellite remote sensing images of the target sea area;

[0007] Identify polluted areas based on the satellite remote sensing images to obtain multiple pollution detection areas;

[0008] Obtain the regional weight coefficient and pollution diffusion intensity of each pollution detection area;

[0009] Determine the estimated pollution concentration of each of the ocean monitoring points based on the regional center coordinates, regional weight coefficients, pollution diffusion intensity of each of the pollution detection areas and the monitoring point coordinates of each of the ocean monitoring points;

[0010] Determining the sampling frequency of each of the ocean monitoring points based on the estimated pollution concentration of the ocean monitoring point, wherein the higher the estimated pollution concentration, the higher the sampling frequency;

[0011] Obtaining an average sampling frequency of the sampling frequencies of each of the ocean monitoring points within a preset time period;

[0012] Divide the target sea area into multiple sub-areas, calculate the overall frequency average of the sampling frequency averages of all the ocean monitoring points in the sub-areas, and obtain the overall frequency average corresponding to each of the sub-areas;

[0013] In the sub-region where the overall frequency average value is higher than the first preset value, the layout density of the ocean monitoring points is increased, and in the sub-region where the overall frequency average value is not higher than the second preset value, the layout density of the ocean monitoring points is reduced.

[0014] Optionally, the obtaining of the regional weight coefficient and the pollution diffusion intensity of each pollution detection area includes:

[0015] Generate a sea surface area outside the pollution detection area, and generate a target pollution area inside the pollution detection area, wherein the sea surface area surrounds the pollution detection area, and the area of ​​the sea surface area is the same as the area of ​​the target pollution area;

[0016] Acquire a first image color parameter in the sea surface area and a second image color parameter in the target pollution area;

[0017] Calculating a color parameter ratio of the first image color parameter to the second image color parameter;

[0018] The regional weight coefficient of the pollution detection area is determined based on the color parameter ratio, wherein the larger the color parameter ratio is, the larger the regional weight coefficient of the pollution detection area is.

[0019] Optionally, the regional center coordinates, regional weight coefficient, pollution diffusion intensity of each of the pollution detection areas, the monitoring point coordinates of each of the ocean monitoring points, and the estimated pollution concentration of each of the ocean monitoring points satisfy the following formula:

[0020]

[0021] Where M represents the total number of pollution detection areas, Q i represents the estimated pollution concentration at the i-th marine monitoring point, k j represents the regional weight coefficient of the jth pollution detection area, (x ci ,y ci ) represents the monitoring point coordinates of the i-th ocean monitoring point, (x wi ,y wi ) represents the center coordinate of the jth pollution detection area, δ j Represents the pollution diffusion intensity of the jth pollution detection area.

[0022] Optionally, the acquiring the first image color parameter in the sea surface area and the second image color parameter in the target pollution area includes:

[0023] Obtain the average pixel value of the red channel, the average pixel value of the green channel and the average pixel value of the blue channel of the sea surface area on the three RGB channels;

[0024] Based on three preset channel weights, weighted summation is performed on the average value of sea surface red channel pixels, the average value of sea surface green channel pixels, and the average value of sea surface blue channel pixels to obtain a first image color parameter in the sea surface area;

[0025] Obtain the average value of polluted red channel pixels, the average value of polluted green channel pixels, and the average value of polluted blue channel pixels in the pollution detection area on the three RGB channels;

[0026] Based on three preset channel weights, a weighted sum is performed on an average value of polluted red channel pixels, an average value of polluted green channel pixels, and an average value of polluted blue channel pixels to obtain a second image color parameter in the target polluted area.

[0027] Optionally, generating a sea surface area outside the pollution detection area and generating a target pollution area inside the pollution detection area includes:

[0028] Obtaining the area boundary of the pollution detection area;

[0029] The region boundary is determined as the inner boundary of the sea surface area, and the enlarged boundary obtained by proportionally enlarging the region boundary is determined as the outer boundary of the sea surface area to obtain the sea surface area; the region boundary is determined as the outer boundary of the target pollution area, and the reduced boundary obtained by proportionally reducing the region boundary is determined as the inner boundary of the target pollution area to obtain the target pollution area.

[0030] Optionally, increasing the layout density of the ocean monitoring points in the sub-region where the overall frequency average value is higher than a first preset value includes:

[0031] In the sub-area where the overall frequency average value is higher than the first preset value, a plurality of candidate monitoring location points are randomly generated,

[0032] Determine a plurality of the ocean monitoring points within the sub-area whose distances to the candidate monitoring location point are less than a preset distance value as neighboring monitoring points of the candidate monitoring location point;

[0033] Establishing a polar coordinate system with the candidate monitoring position point as the origin, and obtaining the polar diameter and polar angle of each of the neighboring monitoring points of the candidate monitoring position point;

[0034] Calculate the polar diameter variance and polar angle variance of each of the neighboring monitoring points of the candidate monitoring location point;

[0035] Determine the layout uniformity parameters of the candidate monitoring location points based on the polar diameter variance and the polar angle variance, and obtain the layout uniformity parameters of each of the candidate monitoring location points, wherein the larger the polar diameter variance is, the smaller the uniformity parameter is, and the larger the polar angle variance is, the smaller the uniformity parameter is;

[0036] New detection location points are added at a preset number of the candidate monitoring location points that are ranked top in order of the uniformity parameters, so as to increase the layout density of the ocean monitoring points.

[0037] Optionally, the identifying of polluted areas based on the satellite remote sensing image to obtain multiple pollution detection areas includes:

[0038] Obtain a pre-trained contamination detection model, wherein the contamination detection model includes an MBConv1 (k3x3) module, an MBConv6 (k3x3) module, a fusion network module, and a detection network module;

[0039] Use the MBConv1(k3x3) module to extract features from the satellite remote sensing image to obtain a first feature map of 112×112×24; perform channel attention feature extraction on the first feature map to obtain a channel attention feature map; perform dot multiplication of the channel attention feature map and the first feature map to obtain a second feature map; perform spatial attention feature extraction on the second feature map to obtain a spatial attention feature map; perform dot multiplication of the spatial attention feature map and the second feature map to obtain a third feature map of 112×112×32, wherein the dimension of the convolution operation of the MBConv1(k3x3) module is 1-dimensional, and a 1-dimensional matrix convolution operation is performed;

[0040] Use the MBConv6 (k3x3) module to extract features from the third feature map to obtain a fourth feature map of 56×56×48, wherein the dimension of the convolution operation performed by the MBConv6 (k3x3) module is 6 dimensions, and a 6-dimensional matrix convolution operation is performed;

[0041] Using a fusion network module, upsampling the fourth feature map by a factor of 2 and fusing it with the third feature map to obtain an upsampled fused feature map; downsampling the upsampled fused feature map by a factor of 2 and fusing it with the fourth feature map to obtain a downsampled fused feature map;

[0042] The detection network module is used to identify the polluted areas of the satellite remote sensing image by using the downsampled fusion feature map to obtain multiple pollution detection areas.

[0043] In a second aspect, the layout adjustment device of the marine monitoring point provided by the present application comprises:

[0044] The first acquisition module is used to obtain the monitoring point coordinates of multiple ocean monitoring points in the target sea area;

[0045] A second acquisition module is used to acquire satellite remote sensing images of the target sea area;

[0046] An identification module, used to identify polluted areas based on the satellite remote sensing image to obtain multiple pollution detection areas;

[0047] The third acquisition module is used to obtain the regional weight coefficient and pollution diffusion intensity of each pollution detection area;

[0048] A first determination module is used to determine the estimated pollution concentration of each of the marine monitoring points based on the regional center coordinates, regional weight coefficients, pollution diffusion intensity and monitoring point coordinates of each of the marine monitoring points;

[0049] A second determination module is used to determine the sampling frequency of each of the ocean monitoring points based on the estimated pollution concentration of the ocean monitoring point, wherein the higher the estimated pollution concentration, the higher the sampling frequency;

[0050] A third acquisition module is used to obtain the average sampling frequency of the sampling frequencies of each of the ocean monitoring points within a preset time period;

[0051] A calculation module, used for dividing the target sea area into a plurality of sub-areas, calculating the overall frequency average of the sampling frequency averages of all the ocean monitoring points in the sub-areas, and obtaining the overall frequency average corresponding to each of the sub-areas;

[0052] The adjustment module is used to increase the layout density of the ocean monitoring points in the sub-area where the overall frequency average value is higher than the first preset value, and reduce the layout density of the ocean monitoring points in the sub-area where the overall frequency average value is not higher than the second preset value.

[0053] Optionally, the obtaining of the regional weight coefficient and the pollution diffusion intensity of each pollution detection area includes:

[0054] Generate a sea surface area outside the pollution detection area, and generate a target pollution area inside the pollution detection area, wherein the sea surface area surrounds the pollution detection area, and the area of ​​the sea surface area is the same as the area of ​​the target pollution area;

[0055] Acquire a first image color parameter in the sea surface area and a second image color parameter in the target pollution area;

[0056] Calculating a color parameter ratio of the first image color parameter to the second image color parameter;

[0057] The regional weight coefficient of the pollution detection area is determined based on the color parameter ratio, wherein the larger the color parameter ratio is, the larger the regional weight coefficient of the pollution detection area is.

[0058] Optionally, the regional center coordinates, regional weight coefficient, pollution diffusion intensity of each of the pollution detection areas, the monitoring point coordinates of each of the ocean monitoring points, and the estimated pollution concentration of each of the ocean monitoring points satisfy the following formula:

[0059]

[0060] Where M represents the total number of pollution detection areas, Q i represents the estimated pollution concentration at the i-th marine monitoring point, k j represents the regional weight coefficient of the jth pollution detection area, (x ci ,y ci ) represents the monitoring point coordinates of the i-th ocean monitoring point, (x wi ,y wi ) represents the center coordinate of the jth pollution detection area, δ j Represents the pollution diffusion intensity of the jth pollution detection area.

[0061] Optionally, the acquiring the first image color parameter in the sea surface area and the second image color parameter in the target pollution area includes:

[0062] Obtain the average pixel value of the red channel, the average pixel value of the green channel and the average pixel value of the blue channel of the sea surface area on the three RGB channels;

[0063] Based on three preset channel weights, weighted summation is performed on the average value of sea surface red channel pixels, the average value of sea surface green channel pixels, and the average value of sea surface blue channel pixels to obtain a first image color parameter in the sea surface area;

[0064] Obtain the average value of polluted red channel pixels, the average value of polluted green channel pixels, and the average value of polluted blue channel pixels in the pollution detection area on the three RGB channels;

[0065] Based on three preset channel weights, a weighted sum is performed on an average value of polluted red channel pixels, an average value of polluted green channel pixels, and an average value of polluted blue channel pixels to obtain a second image color parameter in the target polluted area.

[0066] Optionally, generating a sea surface area outside the pollution detection area and generating a target pollution area inside the pollution detection area includes:

[0067] Obtaining the area boundary of the pollution detection area;

[0068] The region boundary is determined as the inner boundary of the sea surface area, and the enlarged boundary obtained by proportionally enlarging the region boundary is determined as the outer boundary of the sea surface area to obtain the sea surface area; the region boundary is determined as the outer boundary of the target pollution area, and the reduced boundary obtained by proportionally reducing the region boundary is determined as the inner boundary of the target pollution area to obtain the target pollution area.

[0069] Optionally, increasing the layout density of the ocean monitoring points in the sub-region where the overall frequency average value is higher than a first preset value includes:

[0070] In the sub-area where the overall frequency average value is higher than the first preset value, a plurality of candidate monitoring location points are randomly generated,

[0071] Determine a plurality of the ocean monitoring points within the sub-area whose distances to the candidate monitoring location point are less than a preset distance value as neighboring monitoring points of the candidate monitoring location point;

[0072] Establishing a polar coordinate system with the candidate monitoring position point as the origin, and obtaining the polar diameter and polar angle of each of the neighboring monitoring points of the candidate monitoring position point;

[0073] Calculate the polar diameter variance and polar angle variance of each of the neighboring monitoring points of the candidate monitoring location point;

[0074] Determine the layout uniformity parameters of the candidate monitoring location points based on the polar diameter variance and the polar angle variance, and obtain the layout uniformity parameters of each of the candidate monitoring location points, wherein the larger the polar diameter variance is, the smaller the uniformity parameter is, and the larger the polar angle variance is, the smaller the uniformity parameter is;

[0075] New detection location points are added at a preset number of the candidate monitoring location points that are ranked top in order of the uniformity parameters, so as to increase the layout density of the ocean monitoring points.

[0076] Optionally, the identifying of polluted areas based on the satellite remote sensing image to obtain multiple pollution detection areas includes:

[0077] Obtain a pre-trained contamination detection model, wherein the contamination detection model includes an MBConv1 (k3x3) module, an MBConv6 (k3x3) module, a fusion network module, and a detection network module;

[0078] Use the MBConv1(k3x3) module to extract features from the satellite remote sensing image to obtain a first feature map of 112×112×24; perform channel attention feature extraction on the first feature map to obtain a channel attention feature map; perform dot multiplication of the channel attention feature map and the first feature map to obtain a second feature map; perform spatial attention feature extraction on the second feature map to obtain a spatial attention feature map; perform dot multiplication of the spatial attention feature map and the second feature map to obtain a third feature map of 112×112×32, wherein the dimension of the convolution operation of the MBConv1(k3x3) module is 1-dimensional, and a 1-dimensional matrix convolution operation is performed;

[0079] Use the MBConv6 (k3x3) module to extract features from the third feature map to obtain a fourth feature map of 56×56×48, wherein the dimension of the convolution operation performed by the MBConv6 (k3x3) module is 6 dimensions, and a 6-dimensional matrix convolution operation is performed;

[0080] Using a fusion network module, upsampling the fourth feature map by a factor of 2 and fusing it with the third feature map to obtain an upsampled fused feature map; downsampling the upsampled fused feature map by a factor of 2 and fusing it with the fourth feature map to obtain a downsampled fused feature map;

[0081] The detection network module is used to identify the polluted areas of the satellite remote sensing image by using the downsampled fusion feature map to obtain multiple pollution detection areas.

[0082] In a third aspect, the electronic device provided in the present application includes a memory and a processor, the memory stores a computer program, and the processor is used to run the computer program in the memory to implement the steps in the layout adjustment method of the ocean monitoring point provided in the present application.

[0083] In a fourth aspect, the computer-readable storage medium provided in the present application stores a plurality of instructions, which are suitable for loading by a processor to implement the steps in the layout adjustment method of the ocean monitoring points provided in the present application.

[0084] In a fifth aspect, the computer program product provided in the present application includes a computer program or instructions, which, when executed by a processor, implements the steps in the method for adjusting the layout of marine monitoring points provided in the present application.

[0085] In this application, compared with the related art, the monitoring point coordinates of multiple ocean monitoring points in the target sea area are obtained; the satellite remote sensing image of the target sea area is obtained; the pollution area is identified based on the satellite remote sensing image to obtain multiple pollution detection areas; the regional weight coefficient and pollution diffusion intensity of each pollution detection area are obtained; the estimated pollution concentration of each ocean monitoring point is determined based on the regional center coordinates, regional weight coefficient, pollution diffusion intensity and monitoring point coordinates of each pollution detection area; the sampling frequency of each ocean monitoring point is determined based on the estimated pollution concentration of the ocean monitoring point, wherein the higher the estimated pollution concentration, the higher the sampling frequency; the sampling frequency average of the sampling frequency of each ocean monitoring point within a preset time period is obtained; the target sea area is divided into multiple sub-areas, and the overall frequency average of the sampling frequency averages of all ocean monitoring points in the sub-areas is calculated to obtain the overall frequency average corresponding to each sub-area; the layout density of the ocean monitoring points is increased in the sub-area where the overall frequency average is higher than the first preset value, and the layout density of the ocean monitoring points is reduced in the sub-area where the overall frequency average is not higher than the second preset value. This application can dynamically adjust the layout of ocean monitoring points to improve the accuracy of ocean monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0087] Figure 1 It is a scene schematic diagram of the layout adjustment system of the ocean monitoring point provided in the embodiment of the present application;

[0088] Figure 2 It is a flow chart of an embodiment of a method for adjusting the layout of ocean monitoring points provided in an embodiment of the present application;

[0089] Figure 3 It is a structural schematic diagram of a layout adjustment device for ocean monitoring points provided in an embodiment of the present application;

[0090] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0091] It should be noted that the principles of the present application are illustrated by implementing them in an appropriate computing environment. The following description is based on the illustrated specific embodiments of the present application and should not be considered as limiting other specific embodiments of the present application that are not described in detail herein.

[0092] In the following description of the present application, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0093] In the following description of the present application, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0094] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0095] In order to improve the effect of adjusting the layout of ocean monitoring points, the embodiments of the present application provide a method for adjusting the layout of ocean monitoring points, a device for adjusting the layout of ocean monitoring points, an electronic device, a computer-readable storage medium, and a computer program product. The method for adjusting the layout of ocean monitoring points can be executed by the device for adjusting the layout of ocean monitoring points, or by an electronic device in which the device for adjusting the layout of ocean monitoring points is integrated.

[0096] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0097] Please refer to Figure 1 , the present application also provides a layout adjustment system for a marine monitoring point, such as Figure 1 As shown, the layout adjustment system of the ocean monitoring points includes an electronic device 100, and the layout adjustment device of the ocean monitoring points provided by the present application is integrated in the electronic device 100.

[0098] Among them, the electronic device 100 can be any device equipped with a processor and has processing capabilities, such as mobile electronic devices with processors such as smart phones, tablet computers, PDAs, laptops, smart speakers, or fixed electronic devices with processors such as desktop computers, televisions, servers, industrial equipment, etc.

[0099] In addition, if Figure 1As shown, the layout adjustment system of the ocean monitoring points may also include a memory 200 for storing original data, intermediate data and result data.

[0100] In the embodiment of the present application, the memory may be a cloud memory. Cloud storage is a new concept extended and developed from the concept of cloud computing. A distributed cloud storage system (hereinafter referred to as the storage system) refers to a storage system that uses cluster applications, grid technology, and distributed storage file systems to bring together a large number of storage devices of various types (storage devices are also called storage nodes) in the network through application software or application interfaces to work together and provide external data storage and business access functions.

[0101] At present, the storage method of the storage system is: create a logical volume, and when creating a logical volume, allocate physical storage space for each logical volume. The physical storage space may be composed of disks of a storage device or several storage devices. The client stores data on a logical volume, that is, stores the data on the file system. The file system divides the data into many parts, each of which is an object. The object contains not only data but also additional information such as data identification (ID, ID entity). The file system writes each object into the physical storage space of the logical volume, and the file system records the storage location information of each object, so that when the client requests to access the data, the file system can allow the client to access the data according to the storage location information of each object.

[0102] The process of the storage system allocating physical storage space to a logical volume is as follows: based on the estimated capacity of the objects stored in the logical volume (this estimate often has a large margin relative to the actual capacity of the objects to be stored) and the grouping of independent redundant disk arrays (RAID, Redundant Array of Independent Disks), the physical storage space is pre-divided into stripes. A logical volume can be understood as a stripe, thereby allocating physical storage space to the logical volume.

[0103] It should be noted that Figure 1 The scenario diagram of the layout adjustment system of the ocean monitoring points shown is merely an example. The layout adjustment system and scenario of the ocean monitoring points described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided in the embodiment of the present application. A person of ordinary skill in the art can appreciate that with the evolution of the layout adjustment system of the ocean monitoring points and the emergence of new business scenarios, the technical solution provided in the embodiment of the present application is equally applicable to similar technical problems.

[0104] It should be noted that the serial numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

[0105] Please refer to Figure 2 , Figure 2 FIG. 1 is a flow chart of an embodiment of a method for adjusting the layout of ocean monitoring points provided in an embodiment of the present application. Figure 2 As shown, the process of the layout adjustment method of the ocean monitoring points provided by this application is as follows:

[0106] 201. Obtain the monitoring point coordinates of multiple ocean monitoring points in the target sea area.

[0107] Among them, the target sea area can have N ocean monitoring points, which can be obtained according to the current specific settings. (x ci ,y ci ) represents the monitoring point coordinates of the i-th ocean monitoring point.

[0108] 202. Obtain satellite remote sensing images of the target sea area.

[0109] In the embodiment of the present application, the satellite remote sensing image is a high-definition image taken by a satellite.

[0110] 203. Polluted areas are identified based on satellite remote sensing images to obtain multiple pollution detection areas.

[0111] In the embodiment of the present application, pollution areas are identified based on satellite remote sensing images to obtain multiple pollution detection areas, including:

[0112] (1) Obtain a pre-trained contamination detection model, wherein the contamination detection model includes an MBConv1 (k3x3) module, an MBConv6 (k3x3) module, a fusion network module, and a detection network module.

[0113] Specifically, remote sensing image samples are obtained, polluted areas in the remote sensing image samples are marked, and the images of the marked polluted areas are used as labels of the deep learning segmentation network model. The labels and the remote sensing image samples corresponding to the labels constitute the training set images; the training set images are preprocessed to obtain input images that meet the preset standards, and the input images are used to expand the data set; a percentage of images are randomly selected from the expanded data set as the training set, and the remaining percentage of images are used as the verification set; the images and labels of the training set are grouped as a batch for updating the back propagation parameters in a preset group as the network input, and the back propagation algorithm is used for training, and a preset number of epochs are trained in total; the input images of the training set are first encoded by the deep learning segmentation network model The decoder of the deep learning segmentation network model performs feature extraction, and each convolution layer in the encoder generates feature maps of different sizes, and the size of the feature maps decreases layer by layer; the decoder of the deep learning segmentation network model performs upsampling to generate feature maps of increasing size layer by layer, and while upsampling, the feature extraction results and the upsampling results are fused layer by layer; after two more convolution layers, the final heatmap heatmap is reached, and then a 1×1 convolution is used for classification, and the logistic regression function softmax class with a relatively large probability is calculated, which is used as input for cross entropy back propagation training; at the end of each round of epoch training, the image data of the validation set is used for verification, and the loss calculated by the loss function is used as the verification error to characterize the generalization ability of the model and the basis for adjusting hyperparameters.

[0114] (2) Use the MBConv1 (k3x3) module to extract features from the satellite remote sensing image to obtain a first feature map of 112×112×24; perform channel attention feature extraction on the first feature map to obtain a channel attention feature map; multiply the channel attention feature map and the first feature map to obtain a second feature map; perform spatial attention feature extraction on the second feature map to obtain a spatial attention feature map; multiply the spatial attention feature map and the second feature map to obtain a third feature map of 112×112×32, wherein the dimension of the convolution operation of the MBConv1 (k3x3) module is 1-dimensional, and a 1-dimensional matrix convolution operation is performed.

[0115] (3) Use the MBConv6 (k3x3) module to extract features from the third feature map to obtain a fourth feature map of 56×56×48. The dimension of the convolution operation of the MBConv6 (k3x3) module is 6 dimensions, and a 6-dimensional matrix convolution operation is performed.

[0116] (4) Use the fusion network module to upsample the fourth feature map by 2 times and fuse it with the third feature map to obtain an upsampled fused feature map; downsample the upsampled fused feature map by 2 times and fuse it with the fourth feature map to obtain a downsampled fused feature map.

[0117] (5) Use the detection network module to identify polluted areas in satellite remote sensing images based on the downsampled fusion feature map of the detection module to obtain multiple pollution detection areas.

[0118] 204. Obtain the regional weight coefficient and pollution diffusion intensity of each pollution detection area.

[0119] In the embodiment of the present application, the pollution diffusion intensity is determined according to the type of pollution in the pollution detection area, and the type of pollution can be measured in advance.

[0120] In the embodiment of the present application, the regional weight coefficient and pollution diffusion intensity of each pollution detection area are obtained, including:

[0121] (1) Generate a sea surface area outside the pollution detection area, and generate a target pollution area inside the pollution detection area.

[0122] Among them, the sea surface area surrounds the pollution detection area, and the area of ​​the sea surface area is the same as the area of ​​the target pollution area.

[0123] In a specific embodiment, a sea surface area is generated outside the pollution detection area, and a target pollution area is generated inside the pollution detection area, including: obtaining a regional boundary of the pollution detection area, determining the regional boundary as the inner boundary of the sea surface area, and determining the enlarged boundary obtained by proportionally enlarging the regional boundary as the outer boundary of the sea surface area to obtain the sea surface area; determining the regional boundary as the outer boundary of the target pollution area, and determining the reduced boundary obtained by proportionally reducing the regional boundary as the inner boundary of the target pollution area to obtain the target pollution area.

[0124] (2) Obtaining the first image color parameters in the sea area and the second image color parameters in the target pollution area.

[0125] In an embodiment of the present application, obtaining the first image color parameters in the sea surface area and the second image color parameters in the target pollution area includes: obtaining the average value of sea surface red channel pixels, the average value of sea surface green channel pixels and the average value of sea surface blue channel pixels in the sea surface area on the three RGB channels; performing weighted summation on the average value of sea surface red channel pixels, the average value of sea surface green channel pixels and the average value of sea surface blue channel pixels based on three preset channel weights to obtain the first image color parameters in the sea surface area; obtaining the average value of polluted red channel pixels, the average value of polluted green channel pixels and the average value of polluted blue channel pixels in the pollution detection area on the three RGB channels; performing weighted summation on the average value of polluted red channel pixels, the average value of polluted green channel pixels and the average value of polluted blue channel pixels based on three preset channel weights to obtain the second image color parameters in the target pollution area.

[0126] Specifically, the red channel pixel average is R, the green channel pixel average is G, and the blue channel pixel average is B. Based on the three preset channel weights, the sea surface red channel pixel average, the sea surface green channel pixel average, and the sea surface blue channel pixel average are weighted summed to obtain the first image color parameter in the sea surface area.

[0127] Based on the three preset channel weights, the average values ​​of the red channel pixels, the green channel pixels, and the blue channel pixels of the sea surface are weighted and summed to obtain the first image color parameter L. The three preset first weight coefficients are 0.299, 0.587, and 0.114, respectively. The calculation formula of the first image color parameter L is as follows:

[0128] L=0.299*R+0.587*G+0.114*B

[0129] The first image color parameter L is between 0 and 255.

[0130] (3) Calculate the color parameter ratio of the first image color parameter to the second image color parameter.

[0131] (4) Determine the regional weight coefficient of the pollution detection area based on the color parameter ratio, wherein the larger the color parameter ratio, the larger the regional weight coefficient of the pollution detection area.

[0132] Furthermore, the area size of the pollution detection area is obtained, the seawater flow rate in the pollution detection area is obtained, and the regional weight coefficient of the pollution detection area is determined based on the area size, the seawater flow rate, and the color parameter ratio, wherein the larger the color parameter ratio, the larger the regional weight coefficient of the pollution detection area, the larger the area size, the larger the regional weight coefficient of the pollution detection area, and the larger the seawater flow rate, the larger the regional weight coefficient of the pollution detection area.

[0133] Specifically, the area size, seawater flow velocity, and color parameter ratio are normalized to obtain the area size normalization value A, the seawater flow velocity normalization value V, and the color parameter ratio normalization value S. Based on the area size normalization value A, the seawater flow velocity normalization value V, and the color parameter ratio normalization value S, the regional weight coefficient k of the pollution detection area is determined. j , satisfying the following formula:

[0134] k j =A+V+S.

[0135] 205. Determine the estimated pollution concentration of each marine monitoring point based on the regional center coordinates, regional weight coefficient, pollution diffusion intensity and monitoring point coordinates of each pollution detection area.

[0136] In the embodiment of the present application, the regional center coordinates, regional weight coefficient, pollution diffusion intensity of each pollution detection area, the monitoring point coordinates of each ocean monitoring point, and the estimated pollution concentration of each ocean monitoring point satisfy the following formula:

[0137]

[0138] Where M represents the total number of pollution detection areas, Q i represents the estimated pollution concentration at the i-th marine monitoring point, k j represents the regional weight coefficient of the jth pollution detection area, (x ci ,y ci ) represents the monitoring point coordinates of the i-th ocean monitoring point, (x wi ,y wi ) represents the center coordinate of the jth pollution detection area, δ j Represents the pollution diffusion intensity of the jth pollution detection area.

[0139] 206. Determine the sampling frequency of each marine monitoring point based on the estimated pollution concentration at the marine monitoring point.

[0140] The higher the estimated pollution concentration, the higher the sampling frequency. The ocean monitoring point samples according to the sampling frequency. The present application dynamically adjusts the sampling frequency according to different pollution detection areas, so that high pollution areas can be accurately monitored.

[0141] 207. Obtain an average sampling frequency of the sampling frequencies of each ocean monitoring point within a preset time period.

[0142] In the embodiment of the present application, the preset time period can be 1 month, two months, etc., which can be set according to the specific situation.

[0143] When different satellite remote sensing images are acquired within a preset time period, different pollution detection areas are acquired, and the sampling frequency is dynamically adjusted according to the different pollution detection areas, so as to acquire the sampling frequency status within the preset time period.

[0144] 208. Divide the target sea area into multiple sub-areas, calculate the overall frequency average of the sampling frequency averages of all ocean monitoring points in the sub-areas, and obtain the overall frequency average corresponding to each sub-area.

[0145] In a specific embodiment, the multiple sub-regions are arranged in an array, the areas of the multiple sub-regions are equal, and the number of ocean monitoring points in each sub-region is equal.

[0146] 209. In the sub-area where the overall frequency average value is higher than the first preset value, increase the layout density of the ocean monitoring points, and in the sub-area where the overall frequency average value is not higher than the second preset value, reduce the layout density of the ocean monitoring points.

[0147] In an embodiment of the present application, the overall frequency average value of each sub-area is obtained, the average of the overall frequency average values ​​of multiple sub-areas in the target sea area is calculated, the frequency average value of the entire area is obtained, and the frequency average value of the entire area is recorded as a. The variance of the overall frequency average values ​​of multiple sub-areas in the target sea area is calculated to obtain the frequency variance of the entire area, and the frequency variance of the entire area is recorded as b.

[0148] The first preset value and the second preset value are determined based on the weighting coefficient c, the whole-area frequency average a, and the whole-area frequency variance b. The first preset value is (a+cb), and the second preset value is (a-cb).

[0149] Specifically, the value range of the weighting coefficient c is [1,2].

[0150] In a specific embodiment, the total number of regions and the total area of ​​pollution detection areas detected in the target sea area within a preset time period are obtained, the total number of regions and the total area are normalized respectively to obtain the normalized value n1 of the total number of regions and the normalized value n2 of the total area, and the weighting coefficient c is determined based on the normalized value n1 of the total number of regions and the normalized value n2 of the total area.

[0151] In a specific embodiment, the calculation formula of the weighting coefficient c is as follows:

[0152]

[0153] Among them, c is the weighting coefficient, n1 is the normalized value of the total number of regions, and n2 is the normalized value of the total area of ​​the regions.

[0154] In the embodiment of the present application, increasing the layout density of the ocean monitoring points in the sub-area where the overall frequency average value is higher than the first preset value includes:

[0155] (1) A plurality of candidate monitoring location points are randomly generated in a sub-area where the overall frequency average value is higher than a first preset value.

[0156] (2) A plurality of ocean monitoring points within the sub-area whose distances to the candidate monitoring location point are less than a preset distance value are determined as neighboring monitoring points of the candidate monitoring location point.

[0157] (3) A polar coordinate system is established with the candidate monitoring location as the origin to obtain the polar diameter and polar angle of each neighboring monitoring point of the candidate monitoring location.

[0158] (4) Calculate the radial variance and angular variance of each neighboring monitoring point of the candidate monitoring location point.

[0159] (5) Determine the layout uniformity parameters of the candidate monitoring location points based on the polar diameter variance and the polar angle variance, and obtain the layout uniformity parameters of each candidate monitoring location point, wherein the larger the polar diameter variance, the smaller the uniformity parameter, and the larger the polar angle variance, the smaller the uniformity parameter.

[0160] (6) Adding new detection locations at a preset number of candidate monitoring locations that are ranked top in uniformity parameters from small to large to increase the layout density of marine monitoring points.

[0161] In order to facilitate better implementation of the layout adjustment method of the ocean monitoring points provided in the embodiment of the present application, the embodiment of the present application also provides a layout adjustment device for ocean monitoring points based on the layout adjustment method of the ocean monitoring points. The meanings of the terms are the same as those in the layout adjustment method of the ocean monitoring points. For specific implementation details, please refer to the description in the above method embodiment.

[0162] Please refer to Figure 3 , Figure 3 A schematic diagram of the structure of a layout adjustment device for ocean monitoring points provided in an embodiment of the present application, wherein the layout adjustment device for ocean monitoring points may include:

[0163] The first acquisition module 701 is used to acquire the monitoring point coordinates of multiple ocean monitoring points in the target sea area;

[0164] The second acquisition module 702 is used to acquire satellite remote sensing images of the target sea area;

[0165] An identification module 703 is used to identify polluted areas based on satellite remote sensing images to obtain multiple pollution detection areas;

[0166] The third acquisition module 704 is used to obtain the regional weight coefficient and pollution diffusion intensity of each pollution detection area;

[0167] The first determination module 705 is used to determine the estimated pollution concentration of each marine monitoring point based on the regional center coordinates of each pollution detection area, the regional weight coefficient, the pollution diffusion intensity and the monitoring point coordinates of each marine monitoring point;

[0168] A second determination module 706 is used to determine the sampling frequency of each ocean monitoring point based on the estimated pollution concentration of the ocean monitoring point, wherein the higher the estimated pollution concentration, the higher the sampling frequency;

[0169] The third acquisition module 707 is used to obtain the average sampling frequency of the sampling frequencies of each ocean monitoring point within a preset time period;

[0170] The calculation module 708 is used to divide the target sea area into multiple sub-areas, calculate the overall frequency average of the sampling frequency averages of all ocean monitoring points in the sub-areas, and obtain the overall frequency average corresponding to each sub-area;

[0171] The adjustment module 709 is used to increase the layout density of the ocean monitoring points in the sub-area where the overall frequency average value is higher than the first preset value, and reduce the layout density of the ocean monitoring points in the sub-area where the overall frequency average value is not higher than the second preset value.

[0172] Optionally, obtaining the regional weight coefficient and pollution diffusion intensity of each pollution detection area includes:

[0173] Generate a sea surface area outside the pollution detection area, and generate a target pollution area inside the pollution detection area, wherein the sea surface area surrounds the pollution detection area, and the area of ​​the sea surface area is the same as the area of ​​the target pollution area;

[0174] Acquire a first image color parameter in the sea surface area and a second image color parameter in the target pollution area;

[0175] Calculating a color parameter ratio of a first image color parameter to a second image color parameter;

[0176] The regional weight coefficient of the pollution detection area is determined based on the color parameter ratio, wherein the larger the color parameter ratio is, the larger the regional weight coefficient of the pollution detection area is.

[0177] Optionally, the regional center coordinates, regional weight coefficient, pollution diffusion intensity of each pollution detection area and the monitoring point coordinates of each ocean monitoring point and the estimated pollution concentration of each ocean monitoring point satisfy the following formula:

[0178]

[0179] Where M represents the total number of pollution detection areas, Q i represents the estimated pollution concentration at the i-th marine monitoring point, k j represents the regional weight coefficient of the jth pollution detection area, (x ci ,y ci ) represents the monitoring point coordinates of the i-th ocean monitoring point, (x wi ,y wi ) represents the center coordinate of the jth pollution detection area, δ j Represents the pollution diffusion intensity of the jth pollution detection area.

[0180] Optionally, obtaining a first image color parameter in the sea surface area and a second image color parameter in the target pollution area includes:

[0181] Obtain the average pixel values ​​of the red channel, the green channel and the blue channel of the sea surface in the three RGB channels;

[0182] Based on three preset channel weights, weighted summation is performed on the average pixel value of the red channel of the sea surface, the average pixel value of the green channel of the sea surface, and the average pixel value of the blue channel of the sea surface to obtain a first image color parameter in the sea surface area;

[0183] Obtain the average value of polluted red channel pixels, the average value of polluted green channel pixels, and the average value of polluted blue channel pixels in the pollution detection area on the three RGB channels;

[0184] Based on three preset channel weights, a weighted sum is performed on the average values ​​of polluted red channel pixels, the average values ​​of polluted green channel pixels, and the average values ​​of polluted blue channel pixels to obtain a second image color parameter in the target polluted area.

[0185] Optionally, generating a sea surface area outside the pollution detection area and generating a target pollution area inside the pollution detection area includes:

[0186] Get the area boundary of the pollution detection area;

[0187] The regional boundary is determined as the inner boundary of the sea surface area, and the enlarged boundary obtained by proportionally enlarging the regional boundary is determined as the outer boundary of the sea surface area to obtain the sea surface area; the regional boundary is determined as the outer boundary of the target pollution area, and the reduced boundary obtained by proportionally reducing the regional boundary is determined as the inner boundary of the target pollution area to obtain the target pollution area.

[0188] Optionally, increasing the layout density of the ocean monitoring points in the sub-area where the overall frequency average value is higher than the first preset value includes:

[0189] In the sub-area where the overall frequency average value is higher than the first preset value, a plurality of candidate monitoring location points are randomly generated.

[0190] Determine multiple ocean monitoring points within the sub-area whose distances to the candidate monitoring location point are less than a preset distance value as neighboring monitoring points of the candidate monitoring location point;

[0191] A polar coordinate system is established with the candidate monitoring location point as the origin, and the polar diameter and polar angle of each neighboring monitoring point of the candidate monitoring location point are obtained;

[0192] Calculate the polar diameter variance and polar angle variance of each neighboring monitoring point of the candidate monitoring location point;

[0193] Determine the layout uniformity parameters of the candidate monitoring location points based on the polar diameter variance and the polar angle variance, and obtain the layout uniformity parameters of each candidate monitoring location point, wherein the larger the polar diameter variance, the smaller the uniformity parameter, and the larger the polar angle variance, the smaller the uniformity parameter;

[0194] New detection location points are added at a preset number of candidate monitoring location points that are ranked top in uniformity parameters from small to large, so as to increase the layout density of the ocean monitoring points.

[0195] Optionally, pollution areas are identified based on satellite remote sensing images to obtain multiple pollution detection areas, including:

[0196] Obtain a pre-trained pollution detection model, wherein the pollution detection model includes an MBConv1 (k3x3) module, an MBConv6 (k3x3) module, a fusion network module, and a detection network module;

[0197] The MBConv1 (k3x3) module is used to extract features from satellite remote sensing images to obtain a first feature map of 112×112×24; channel attention features are extracted from the first feature map to obtain a channel attention feature map; the channel attention feature map is multiplied by the first feature map to obtain a second feature map; spatial attention features are extracted from the second feature map to obtain a spatial attention feature map; the spatial attention feature map is multiplied by the second feature map to obtain a third feature map of 112×112×32, wherein the dimension of the convolution operation of the MBConv1 (k3x3) module is 1-dimensional, and a 1-dimensional matrix convolution operation is performed;

[0198] The MBConv6 (k3x3) module is used to extract features from the third feature map to obtain a fourth feature map of 56×56×48. The dimension of the MBConv6 (k3x3) module for convolution operation is 6 dimensions, and a 6-dimensional matrix convolution operation is performed;

[0199] The fourth feature map is upsampled by 2 times using the fusion network module and fused with the third feature map to obtain an upsampled fused feature map; the third feature map is downsampled by 2 times and fused with the fourth feature map to obtain a downsampled fused feature map;

[0200] The detection network module is used to identify polluted areas in satellite remote sensing images based on the down-sampled fusion feature map of the detection module to obtain multiple pollution detection areas.

[0201] The specific implementation of each of the above modules can be found in the previous embodiments and will not be described in detail here.

[0202] An embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the processor is used to execute the steps in the layout adjustment method of the ocean monitoring points provided in this embodiment by calling a computer program stored in the memory.

[0203] Please refer to Figure 4 , Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0204] The electronic device may include components such as a processor 101 with one or more processing cores, a memory 102 with one or more computer-readable storage media, a power supply 103, and an input unit 104. Those skilled in the art will appreciate that the electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0205] The processor 101 is the control center of the electronic device, which uses various interfaces and lines to connect various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory 102, and calling data stored in the memory 102. Optionally, the processor 101 may include one or more processing cores; optionally, the processor 101 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 101.

[0206] The memory 102 can be used to store software programs and modules. The processor 101 executes various functional applications and data processing by running the software programs and modules stored in the memory 102. The memory 102 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 102 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 102 may also include a memory controller to provide the processor 101 with access to the memory 102.

[0207] The electronic device also includes a power supply 103 for supplying power to each component. Optionally, the power supply 103 can be logically connected to the processor 101 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 103 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0208] The electronic device may further include an input unit 104, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0209] Although not shown, the electronic device may also include a display unit, an image acquisition component, etc., which will not be described in detail here. Specifically in this embodiment, the processor 101 in the electronic device will load the executable code corresponding to one or more computer programs into the memory 102 according to the following instructions, and the processor 101 will execute the steps in the layout adjustment method of the marine monitoring point provided in the present application, such as:

[0210] Acquire the monitoring point coordinates of multiple marine monitoring points in the target sea area; acquire the satellite remote sensing image of the target sea area; identify the pollution area based on the satellite remote sensing image to obtain multiple pollution detection areas; acquire the regional weight coefficient and pollution diffusion intensity of each pollution detection area; determine the estimated pollution concentration of each marine monitoring point based on the regional center coordinates, regional weight coefficient, pollution diffusion intensity of each pollution detection area and the monitoring point coordinates of each marine monitoring point; determine the sampling frequency of each marine monitoring point based on the estimated pollution concentration of the marine monitoring point, wherein the higher the estimated pollution concentration, the higher the sampling frequency; acquire the sampling frequency average value of the sampling frequency of each marine monitoring point within a preset time period; divide the target sea area into multiple sub-areas, calculate the overall frequency average value of the sampling frequency average values ​​of all marine monitoring points in the sub-areas, and obtain the overall frequency average value corresponding to each sub-area; increase the layout density of marine monitoring points in the sub-area where the overall frequency average value is higher than a first preset value, and reduce the layout density of marine monitoring points in the sub-area where the overall frequency average value is not higher than a second preset value.

[0211] It should be noted that the electronic device provided in the embodiment of the present application and the layout adjustment method of the ocean monitoring points in the above embodiment belong to the same concept, and its specific implementation process is detailed in the above related embodiments and will not be repeated here.

[0212] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program stored therein is executed on a processor of an electronic device provided in an embodiment of the present application, the processor of the electronic device executes the steps in the layout adjustment method of the marine monitoring point provided in the present application. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0213] The present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes various optional implementations of the above-mentioned method for adjusting the layout of marine monitoring points.

[0214] The above is a detailed introduction to a layout adjustment method and device for marine monitoring points provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0215] It should be noted that when the above embodiments of the present application are applied to specific products or technologies, the relevant data of the user is involved, and the user's permission or consent is required, and the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

Claims

1. A method for adjusting the layout of marine monitoring points, characterized in that: include: Obtain the monitoring point coordinates of multiple ocean monitoring points in the target sea area; Acquiring satellite remote sensing images of the target sea area; Identify polluted areas based on the satellite remote sensing images to obtain multiple pollution detection areas; Obtain the regional weight coefficient and pollution diffusion intensity of each pollution detection area; Determine the estimated pollution concentration of each of the ocean monitoring points based on the regional center coordinates, regional weight coefficients, pollution diffusion intensity of each of the pollution detection areas and the monitoring point coordinates of each of the ocean monitoring points; Determining the sampling frequency of each of the ocean monitoring points based on the estimated pollution concentration of the ocean monitoring point, wherein the higher the estimated pollution concentration, the higher the sampling frequency; Obtaining an average sampling frequency of the sampling frequencies of each of the ocean monitoring points within a preset time period; Divide the target sea area into multiple sub-areas, calculate the overall frequency average of the sampling frequency averages of all the ocean monitoring points in the sub-areas, and obtain the overall frequency average corresponding to each of the sub-areas; In the sub-region where the overall frequency average value is higher than the first preset value, the layout density of the ocean monitoring points is increased, and in the sub-region where the overall frequency average value is not higher than the second preset value, the layout density of the ocean monitoring points is reduced.

2. The method for adjusting the layout of ocean monitoring points according to claim 1, characterized in that: The obtaining of the regional weight coefficient and pollution diffusion intensity of each pollution detection area includes: Generate a sea surface area outside the pollution detection area, and generate a target pollution area inside the pollution detection area, wherein the sea surface area surrounds the pollution detection area, and the area of ​​the sea surface area is the same as the area of ​​the target pollution area; Acquire a first image color parameter in the sea surface area and a second image color parameter in the target pollution area; Calculating a color parameter ratio of the first image color parameter to the second image color parameter; The regional weight coefficient of the pollution detection area is determined based on the color parameter ratio, wherein the larger the color parameter ratio is, the larger the regional weight coefficient of the pollution detection area is.

3. The method for adjusting the layout of ocean monitoring points according to claim 2, characterized in that: The regional center coordinates, regional weight coefficients, pollution diffusion intensity of each of the pollution detection areas, the monitoring point coordinates of each of the ocean monitoring points, and the estimated pollution concentration of each of the ocean monitoring points satisfy the following formula: Where M represents the total number of pollution detection areas, Q i represents the estimated pollution concentration at the i-th marine monitoring point, k j represents the regional weight coefficient of the jth pollution detection area, (x ci ,y ci ) represents the monitoring point coordinates of the i-th ocean monitoring point, (x wi ,y wi ) represents the center coordinate of the jth pollution detection area, δ j Represents the pollution diffusion intensity of the jth pollution detection area.

4. The method for adjusting the layout of ocean monitoring points according to claim 3, characterized in that: The acquiring of the first image color parameter in the sea surface area and the second image color parameter in the target pollution area comprises: Obtain the average pixel value of the red channel, the average pixel value of the green channel and the average pixel value of the blue channel of the sea surface area on the three RGB channels; Based on three preset channel weights, weighted summation is performed on the average value of sea surface red channel pixels, the average value of sea surface green channel pixels, and the average value of sea surface blue channel pixels to obtain a first image color parameter in the sea surface area; Obtain the average value of polluted red channel pixels, the average value of polluted green channel pixels, and the average value of polluted blue channel pixels in the pollution detection area on the three RGB channels; Based on three preset channel weights, a weighted sum is performed on an average value of polluted red channel pixels, an average value of polluted green channel pixels, and an average value of polluted blue channel pixels to obtain a second image color parameter in the target polluted area.

5. The method for adjusting the layout of ocean monitoring points according to claim 4, characterized in that: The step of generating a sea surface area outside the pollution detection area and generating a target pollution area inside the pollution detection area includes: Obtaining the area boundary of the pollution detection area; The region boundary is determined as the inner boundary of the sea surface area, and the enlarged boundary obtained by proportionally enlarging the region boundary is determined as the outer boundary of the sea surface area to obtain the sea surface area; the region boundary is determined as the outer boundary of the target pollution area, and the reduced boundary obtained by proportionally reducing the region boundary is determined as the inner boundary of the target pollution area to obtain the target pollution area.

6. The method for adjusting the layout of ocean monitoring points according to claim 4, characterized in that: Increasing the layout density of the ocean monitoring points in the sub-area where the overall frequency average value is higher than the first preset value comprises: In the sub-area where the overall frequency average value is higher than the first preset value, a plurality of candidate monitoring location points are randomly generated, Determine a plurality of the ocean monitoring points within the sub-area whose distances to the candidate monitoring location point are less than a preset distance value as neighboring monitoring points of the candidate monitoring location point; Establishing a polar coordinate system with the candidate monitoring position point as the origin, and obtaining the polar diameter and polar angle of each of the neighboring monitoring points of the candidate monitoring position point; Calculate the polar diameter variance and polar angle variance of each of the neighboring monitoring points of the candidate monitoring location point; Determine the layout uniformity parameters of the candidate monitoring location points based on the polar diameter variance and the polar angle variance, and obtain the layout uniformity parameters of each of the candidate monitoring location points, wherein the larger the polar diameter variance is, the smaller the uniformity parameter is, and the larger the polar angle variance is, the smaller the uniformity parameter is; New detection location points are added at a preset number of the candidate monitoring location points that are ranked top in order of the uniformity parameters, so as to increase the layout density of the ocean monitoring points.

7. The method for adjusting the layout of ocean monitoring points according to claim 6, characterized in that: The polluted area identification based on the satellite remote sensing image is performed to obtain multiple pollution detection areas, including: Obtain a pre-trained pollution detection model, wherein the pollution detection model includes an MBConv1 module, an MBConv6 module, a fusion network module, and a detection network module, wherein the convolution kernel size of the MBConv1 module and the MBConv6 module is 3x3; Use the MBConv1 module to extract features from the satellite remote sensing image to obtain a first feature map of 112×112×24; perform channel attention feature extraction on the first feature map to obtain a channel attention feature map; perform dot multiplication of the channel attention feature map and the first feature map to obtain a second feature map; perform spatial attention feature extraction on the second feature map to obtain a spatial attention feature map; perform dot multiplication of the spatial attention feature map and the second feature map to obtain a third feature map of 112×112×32, wherein the dimension of the convolution operation performed by the MBConv1 module is 1-dimensional, and a 1-dimensional matrix convolution operation is performed; Use the MBConv6 module to perform feature extraction on the third feature map to obtain a fourth feature map of 56×56×48, wherein the dimension of the convolution operation performed by the MBConv6 module is 6 dimensions, and a 6-dimensional matrix convolution operation is performed; Using a fusion network module, upsampling the fourth feature map by a factor of 2 and fusing it with the third feature map to obtain an upsampled fused feature map; downsampling the upsampled fused feature map by a factor of 2 and fusing it with the fourth feature map to obtain a downsampled fused feature map; The detection network module is used to identify the polluted areas of the satellite remote sensing image by using the downsampled fusion feature map to obtain multiple pollution detection areas.

8. A layout adjustment device for marine monitoring points, characterized in that: include: The first acquisition module is used to obtain the monitoring point coordinates of multiple ocean monitoring points in the target sea area; A second acquisition module is used to acquire satellite remote sensing images of the target sea area; An identification module, used to identify polluted areas based on the satellite remote sensing image to obtain multiple pollution detection areas; The third acquisition module is used to obtain the regional weight coefficient and pollution diffusion intensity of each pollution detection area; A first determination module is used to determine the estimated pollution concentration of each of the marine monitoring points based on the regional center coordinates, regional weight coefficients, pollution diffusion intensity and monitoring point coordinates of each of the marine monitoring points; A second determination module is used to determine the sampling frequency of each of the ocean monitoring points based on the estimated pollution concentration of the ocean monitoring point, wherein the higher the estimated pollution concentration, the higher the sampling frequency; A third acquisition module is used to obtain the average sampling frequency of the sampling frequencies of each of the ocean monitoring points within a preset time period; A calculation module, used for dividing the target sea area into a plurality of sub-areas, calculating the overall frequency average of the sampling frequency averages of all the ocean monitoring points in the sub-areas, and obtaining the overall frequency average corresponding to each of the sub-areas; The adjustment module is used to increase the layout density of the ocean monitoring points in the sub-area where the overall frequency average value is higher than the first preset value, and reduce the layout density of the ocean monitoring points in the sub-area where the overall frequency average value is not higher than the second preset value.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the processor is used to run the computer program in the memory to execute the steps in the method for adjusting the layout of marine monitoring points according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the steps in the method for adjusting the layout of marine monitoring points according to any one of claims 1 to 7.

Images