GLI-MFUNet-based African surface water remote sensing fine extraction method

Abstract

The invention relates to an African surface water remote sensing fine extraction method based on GLI-MFUNet, and the method comprises the steps: constructing each sample through the satellite sample image of each preset sample region in a target region to be recognized, carrying out the training of a GLI-MFUNet model which is constructed through employing a dual-path encoder as the input, carrying out the processing of a feature fusion module, and employing a multi-scale decoder as the output, and obtaining a GLI-MFUNet model; according to the method, the surface water extraction model corresponding to the target to-be-recognized area is obtained, then detection of surface water distribution in the target to-be-recognized area is achieved, the design scheme utilizes Sentinel-2 image data to achieve rapid acquisition of large-scale surface water distribution, dependence of a traditional method on manpower and material resources is reduced, the monitoring cost is greatly saved, and the method is suitable for large-scale detection of surface water distribution in the target to-be-recognized area. The design not only improves the precision and efficiency of surface water identification, but also can provide reliable data support for water resource management, agricultural irrigation and environmental protection.

Description

Technical Field

[0001] The invention relates to a GLI-MFUNet-based remote sensing fine extraction method for African surface water, belonging to the technical field of hydrological detection. Background Art

[0002] With the increasing shortage of global water resources and the intensification of climate change, accurate monitoring and management of surface water resources has become particularly important. Traditional field water resource monitoring methods consume a lot of time and human resources, and it is difficult to achieve large-scale regular monitoring. With the rapid development of space satellite remote sensing technology, the quality and update speed of remote sensing data have been significantly improved. Remote sensing technology has been widely used in water resource management, agriculture, environment and ecology. The use of satellite remote sensing technology for surface water resource monitoring has the advantages of fast, large-scale and low-cost. Remote sensing data can be used to monitor and analyze the distribution, change trend and water quality of surface water, which is of great significance for formulating water resource management policies, responding to flood disasters and protecting the ecological environment. However, the existing traditional remote sensing image processing methods cannot make full use of a large amount of remote sensing data, thus affecting the accuracy of surface water extraction.

[0003] In recent years, the development of deep learning technology has provided a new method for remote sensing data processing. Deep learning algorithms can automatically extract and learn features from remote sensing images, effectively improving the accuracy and efficiency of surface water identification. The use of deep learning technology and remote sensing images, combined with Africa's unique geographical and environmental characteristics, can more accurately monitor and analyze surface water resources. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a remote sensing fine extraction method for African surface water based on GLI-MFUNet, which introduces deep learning technology and can more accurately monitor and analyze surface water resources.

[0005] In order to solve the above technical problems, the present invention adopts the following technical solutions: the present invention designs a remote sensing fine extraction method for African surface water based on GLI-MFUNet, performs the following steps A to C, obtains the surface water extraction model corresponding to the target area to be identified; then performs the following step i, obtains the surface water distribution of the target area to be identified;

[0006] Step A. For the satellite sample images corresponding to the preset sample areas in the target area to be identified, respectively, distinguishing the water area and the non-water area, the satellite sample images are cropped according to the preset sub-image size to obtain the satellite sub-sample images distinguishing the water area and the non-water area, forming a sample set, and then entering step B;

[0007] Step B. Construct a GLI-MFUNet model with a dual-path encoder as input, processed by a feature fusion module, and a multi-scale decoder as output, and then proceed to step C;

[0008] Step C. Based on the sample set, the satellite sub-sample image is used as input, and the water area and non-water area in the satellite sub-sample image are used as output, and the GLI-MFUNet model is trained to obtain the surface water extraction model corresponding to the target area to be identified;

[0009] Step i. For the satellite image corresponding to the target area to be identified, the satellite image is cropped according to the preset sub-image size to obtain each target satellite sub-image, and the surface water extraction model corresponding to the target area to be identified is applied to process each target satellite sub-image separately to obtain the water area and non-water area in each target satellite sub-image, and then combined to form the surface water distribution in the target area to be identified.

[0010] As a preferred technical solution of the present invention: the step A includes the following steps A1 to A3;

[0011] Step A1. Preset each sample area in the target area to be identified, obtain the red band satellite image, near infrared band satellite image, and short wave infrared band satellite image corresponding to the sample area, and superimpose the satellite images of each band to form a satellite sample image corresponding to the sample area, thereby obtaining the satellite sample images corresponding to each sample area, and then proceed to step A2;

[0012] Step A2. For each sample area preset in the target area to be identified, distinguish the water area and the non-water area in the satellite sample image corresponding to the sample area according to the water area and the non-water area in the sample area, that is, distinguish the water area and the non-water area in the satellite sample image corresponding to each sample area, and then proceed to step A3;

[0013] Step A3. For each sample area preset in the target area to be identified, the satellite sample image corresponding to the sample area is cropped according to the preset sub-image size to obtain satellite sub-sample images that distinguish water areas from non-water areas. The satellite sub-sample images corresponding to each sample area together constitute a sample set.

[0014] As a preferred technical solution of the present invention: in the step A1, each sample area in the target area to be identified is preset, and the L2A product of the Sentinel-2 satellite image corresponding to the sample area is obtained, and based on the resampling of the B11 band satellite image resolution being the same as the B4 band satellite image resolution and the B8 band satellite image resolution, the B11 band satellite image, the B4 band satellite image, and the B8 band satellite image are superimposed to form a satellite sample image corresponding to the sample area, thereby obtaining the satellite sample images corresponding to each sample area.

[0015] As a preferred technical solution of the present invention: it also includes step BC as follows, after executing step B, entering step BC;

[0016] Step BC. Based on the definition that the satellite sub-sample images containing water areas in the sample set are positive samples and the satellite sub-sample images not containing water areas are negative samples, a method of eliminating positive samples or negative samples is executed so that the ratio of the number of positive samples to the number of negative samples falls within a preset upper and lower fluctuation range centered on 1, the sample set is updated, and then step C is entered.

[0017] As a preferred technical solution of the present invention: the structure of the GLI-MFUNet model in step B is as follows:

[0018] The dual-path encoder includes a first-path encoder and a second-path encoder, wherein the first-path encoder includes a patch embedding layer Patch Embeding, a first MVT layer MVT Block1, a second MVT layer MVT Block2, and a third MVT layer MVT Block3 connected in series from the input end to the output end; the second-path encoder includes a first convolutional pooling activation module Conv Block1, a second convolutional pooling activation module Conv Block2, a third convolutional pooling activation module Conv Block3, a fourth convolutional pooling activation module Conv Block4, and a fifth convolutional pooling activation module ConvBlock5 connected in series from the input end to the output end; the input end of the first-path encoder and the input end of the second-path encoder constitute the two input ends of the GLI-MFUNet model;

[0019] The feature fusion module includes a first fusion layer SPCAI1 and a second fusion layer SPCAI2 connected in series from the input end to the output end. The output end of the first MVT layer MVT Block1 in the first encoder and the output end of the fourth convolutional pooling activation module Conv Block4 in the second encoder are simultaneously connected to the input end of the first fusion layer SPCAI1. The output end of the second MVT layer MVT Block2 in the first encoder and the output end of the fifth convolutional pooling activation module Conv Block5 in the second encoder are simultaneously connected to the input end of the second fusion layer SPCAI2.

[0020] The multi-scale decoder includes 15 sampling convolution activation modules, which are divided into the first group, the second group, the third group, the fourth group, and the fifth group in the order of 1 sampling convolution activation module, 2 sampling convolution activation modules, 3 sampling convolution activation modules, 4 sampling convolution activation modules, and 5 sampling convolution activation modules, and each group includes the sampling convolution activation modules connected in series in sequence from the input end to the output end; the third MVT layer MVT in the first encoder The output end of Block3 and the output end of the second fusion layer SPCAI2 in the feature fusion module are simultaneously connected to the input end of the sampling convolution activation module in the first group; the output end of the first fusion layer SPCAI1 in the feature fusion module and the output end of the second fusion layer SPCAI2 are simultaneously connected to the input end of the first sampling convolution activation module in the second group, and the output end of the first fusion layer SPCAI1 in the feature fusion module is simultaneously connected to the input end of the second sampling convolution activation module in the second group and the input end of the first sampling convolution activation module in the third group; the input end of the first sampling convolution activation module in the third group is simultaneously connected to the output end of the third convolution pooling activation module ConvBlock3 in the second encoder, and the output end of the third convolution pooling activation module Conv Block3 is simultaneously connected to the input end of the first sampling convolution activation module in the fourth group, the input end of the second sampling convolution activation module in the third group, and the input end of the third sampling convolution activation module in the third group, and the input end of the first sampling convolution activation module in the fourth group is simultaneously connected to the second convolution pooling activation module Conv The output end of Block2 and the output end of the second convolutional pooling activation module Conv Block2 are simultaneously connected to the input end of the first sampling convolutional activation module in the 5th group, the input end of the second sampling convolutional activation module in the 4th group, the input end of the third sampling convolutional activation module in the 4th group, and the input end of the fourth sampling convolutional activation module in the 4th group. The input end of the first sampling convolutional activation module in the 5th group is simultaneously connected to the output end of the first convolutional pooling activation module Conv Block1. The first convolutional pooling activation module Conv The output end of Block1 is simultaneously connected to the input end of the second sampling convolution activation module in the fifth group, the input end of the third sampling convolution activation module in the fifth group, the input end of the fourth sampling convolution activation module in the fifth group, and the input end of the fifth sampling convolution activation module in the fifth group; the output end of the sampling convolution activation module in the first group is connected to the input end of the second sampling convolution activation module in the second group; the output end of the first sampling convolution activation module in the second group is simultaneously connected to the input end of the second sampling convolution activation module in the third group, and the output end of the second sampling convolution activation module in the second group is simultaneously connected to the input end of the third sampling convolution activation module in the third group;The output end of the first sampling convolution activation module in the third group is simultaneously connected to the input end of the third sampling convolution activation module in the third group and the input end of the second sampling convolution activation module in the fourth group, the output end of the second sampling convolution activation module in the third group is simultaneously connected to the input end of the third sampling convolution activation module in the fourth group, and the output end of the third sampling convolution activation module in the third group is simultaneously connected to the input end of the fourth sampling convolution activation module in the fourth group; the output end of the first sampling convolution activation module in the fourth group is simultaneously connected to the input end of the second sampling convolution activation module in the fifth group, the input end of the third sampling convolution activation module in the fourth group, and the input end of the fourth sampling convolution activation module in the fourth group, the output end of the second sampling convolution activation module in the fourth group is simultaneously connected to the input end of the third sampling convolution activation module in the fifth group and the input end of the fourth sampling convolution activation module in the fourth group, and the output end of the third sampling convolution activation module in the fourth group is simultaneously connected to the input end of the third sampling convolution activation module in the fifth group and the input end of the fourth sampling convolution activation module in the fourth group. The output end of the convolution activation module is simultaneously connected to the input end of the 4th sampling convolution activation module in the 5th group, and the output end of the 4th sampling convolution activation module in the 4th group is simultaneously connected to the input end of the 5th sampling convolution activation module in the 5th group; the output end of the 1st sampling convolution activation module in the 5th group is simultaneously connected to the input end of the 3rd sampling convolution activation module in the 5th group, the input end of the 4th sampling convolution activation module in the 5th group, and the input end of the 5th sampling convolution activation module in the 5th group, the output end of the 2nd sampling convolution activation module in the 5th group is simultaneously connected to the input end of the 4th sampling convolution activation module in the 5th group, and the input end of the 5th sampling convolution activation module in the 5th group, the output end of the 3rd sampling convolution activation module in the 5th group is simultaneously connected to the input end of the 5th sampling convolution activation module in the 5th group, and the output end of the 5th sampling convolution activation module in the 5th group constitutes an output end of the GLI-MFUNet model;

[0021] In step C, based on the sample set, satellite subsample images are simultaneously input into two input ends of the GLI-MFUNet model, and one output end of the GLI-MFUNet model outputs the water area and non-water area in the satellite subsample image. The GLI-MFUNet model is trained to obtain a surface water extraction model corresponding to the target area to be identified.

[0022] As a preferred technical solution of the present invention: the structure of the first MVT layer MVT Block1 is the same as the structure of the second MVT layer MVT Block2, and each MVT layer includes, from the input end to the output end, a depthwise separable convolution module DWConv, a first addition module, a first layer standardization module Layer Norm1, a Manhattan self-attention module MaSA, a second addition module, a second layer standardization module Layer Norm2, a feedforward neural network module FFN, a third addition module, and a patch merging module Patch Merging, wherein the output end of the patch merging module Patch Merging constitutes the output end of the MVT layer, the input end of the depthwise separable convolution module DWConv constitutes the input end of the MVT layer, the input end of the MVT layer is simultaneously connected to the input end of the first addition module, the output end of the first addition module is simultaneously connected to the input end of the second addition module, and the output end of the second addition module is simultaneously connected to the input end of the third addition module.

[0023] As a preferred technical solution of the present invention: the structure of the first fusion layer SPCAI1 is the same as that of the second fusion layer SPCAI2, and each fusion layer includes, from the input end to the output end, a first convolution module Conv1×1 with a convolution kernel size of 1×1, an activation function module GELU, a spatial attention module Spatial Attention, a third addition module, a channel attention module Channel Attention, a fourth addition module, and a second convolution module Conv1×1 with a convolution kernel size of 1×1, which are connected in series in sequence, wherein the input end of the first convolution module Conv1×1 constitutes the input end of the fusion layer, the output end of the activation function module GELU is simultaneously connected to the input end of the third addition module, the output end of the third addition module is simultaneously connected to the input end of the fourth addition module, and the output end of the second convolution module Conv1×1 constitutes the output end of the fusion layer.

[0024] As a preferred technical solution of the present invention: the structures of the sampling convolution activation modules in the multi-scale decoder are the same, and each sampling convolution activation module includes a transposed convolution up-sampling module up_sample, a first convolution activation module, and a second convolution activation module connected in series from the input end to the output end, the structure of the first convolution activation module is the same as that of the second convolution activation module, and each convolution activation module includes a convolution module conv and an activation module Relu connected in series from the input end to the output end, wherein the input end of the convolution module conv constitutes the input end of the convolution activation module, and the output end of the activation module Relu constitutes the output end of the convolution activation module.

[0025] As a preferred technical solution of the present invention: the structure of the first convolution pooling activation module ConvBlock1, the structure of the second convolution pooling activation module Conv Block2, the structure of the third convolution pooling activation module ConvBlock3, the structure of the fourth convolution pooling activation module Conv Block4, and the structure of the fifth convolution pooling activation module ConvBlock5 in the second encoder are the same as each other, and each convolution pooling activation module includes a convolution module, a pooling module, and an activation module connected in series in sequence from the input end to the output end, wherein the input end of the convolution module constitutes the input end of the convolution pooling activation module, and the output end of the activation module constitutes the output end of the convolution pooling activation module.

[0026] As a preferred technical solution of the present invention: in the step C, based on the sample set, the AdamW optimizer is applied, and the result of Focal Loss+Dice Loss is used as the loss function result according to the following formula to train the GLI-MFUNet model;

[0027] Focal Loss = -α t (1-p t ) γ log(p t )

[0028]

[0029] Among them, α t Indicates the preset balance factor, p t represents the detection probability of water body area and non-water body area in the satellite sub-sample image, γ represents the preset adjustment factor, P represents the water body category detection probability value matrix of the water body area and non-water body area distribution corresponding to the length and width of the satellite sub-sample image, G represents the true label value matrix of the water body area and non-water body area distribution corresponding to the length and width of the satellite sub-sample image, ∑P represents the sum of the values ​​of each element in the calculated label value matrix P, and ∑G represents the sum of the values ​​of each element in the true label value matrix G.

[0030] The GLI-MFUNet-based remote sensing fine extraction method for African surface water in the present invention has the following technical effects compared with the prior art by using the above technical solution:

[0031] The present invention designs a remote sensing fine extraction method for African surface water based on GLI-MFUNet. Each sample is constructed by using satellite sample images of each preset sample area in the target to-be-identified area. The GLI-MFUNet model constructed by using a dual-channel encoder as input, processed by a feature fusion module, and outputted by a multi-scale decoder is trained to obtain a surface water extraction model corresponding to the target to-be-identified area, thereby realizing the detection of surface water distribution in the target to-be-identified area. The design scheme utilizes Sentinel-2 image data to realize the rapid acquisition of large-scale surface water distribution, reduces the dependence of traditional methods on manpower and material resources, and greatly saves monitoring costs. The design not only improves the accuracy and efficiency of surface water identification, but also can provide reliable data support for water resources management, agricultural irrigation and environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of the structure of the GLI-MFUNet model in the design of the present invention;

[0033] Figure 2 It is a schematic diagram of the structure of the MVT layer in the GLI-MFUNet model designed by the present invention;

[0034] Figure 3 It is a schematic diagram of the structure of the fusion layer in the GLI-MFUNet model designed by the present invention. DETAILED DESCRIPTION

[0035] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0036] The present invention designs a remote sensing fine extraction method for African surface water based on GLI-MFUNet. In practical application, the specific design executes the following steps A to C to obtain a surface water extraction model corresponding to the target area to be identified.

[0037] Step A. For the satellite sample images corresponding to the preset sample areas in the target area to be identified, which distinguish the water area and the non-water area therein, the satellite sample images are cropped according to the preset sub-image size to obtain the satellite sub-sample images that distinguish the water area and the non-water area therein, to form a sample set, and then enter step B.

[0038] In practical applications, the above step A specifically performs the following steps A1 to A3.

[0039] Step A1. Preset each sample area in the target area to be identified, obtain the L2A product of the Sentinel-2 satellite image corresponding to the sample area, and based on the resampling of the B11 band satellite image resolution being the same as the B4 band satellite image resolution and the B8 band satellite image resolution, superimpose the B11 band satellite image, the B4 band satellite image, and the B8 band satellite image to form the satellite sample image corresponding to the sample area, and then obtain the satellite sample images corresponding to each sample area, where the B4 band is the red band satellite image, the B8 band is the near-infrared band satellite image, and the B11 band is the short-wave infrared band satellite image.

[0040] Step A2. Preset each sample area in the target area to be identified, and distinguish the water area and non-water area in the satellite sample image corresponding to the sample area based on the water area and non-water area in the sample area, that is, distinguish the water area and non-water area in the satellite sample image corresponding to each sample area, and then enter step A3.

[0041] Step A3. For each sample area preset in the target area to be identified, the satellite sample image corresponding to the sample area is cropped according to a preset sub-image size, such as 256×256, to obtain satellite sub-sample images that distinguish water areas from non-water areas, and the satellite sub-sample images corresponding to each sample area together constitute a sample set.

[0042] In practical applications, for the acquisition of satellite sample images corresponding to the preset sample areas in the target area to be identified, the water area and the non-water area are distinguished. Specifically, the satellite sample images are first obtained, and then the PIE software is further used to visually interpret the Sentinel-2 images to distinguish the water area and the non-water area.

[0043] Step B. Use the PyTorch deep learning library to build a GLI-MFUNet model with a dual-path encoder as input, processed by a feature fusion module, and a multi-scale decoder as output, and then proceed to step BC.

[0044] Regarding the GLI-MFUNet model constructed here, Figure 1 As shown, the specific structure design is as follows:

[0045] The dual-path encoder includes a first-path encoder and a second-path encoder, wherein the first-path encoder includes a patch embedding layer Patch Embeding, a first MVT layer MVT Block1, a second MVT layer MVT Block2, and a third MVT layer MVT Block3 connected in series from the input end to the output end; the second-path encoder includes a first convolutional pooling activation module Conv Block1, a second convolutional pooling activation module Conv Block2, a third convolutional pooling activation module Conv Block3, a fourth convolutional pooling activation module Conv Block4, and a fifth convolutional pooling activation module ConvBlock5 connected in series from the input end to the output end; the input end of the first-path encoder and the input end of the second-path encoder constitute the two input ends of the GLI-MFUNet model.

[0046] The structure of the first MVT layer MVT Block1 is the same as the structure of the second MVT layer MVT Block2. Figure 2 As shown, each MVT layer includes, from the input end to the output end, a depthwise separable convolution module DWConv, a first addition module, a first-layer normalization module Layer Norm1, a Manhattan self-attention module MaSA, a second addition module, a second-layer normalization module Layer Norm2, a feedforward neural network module FFN, a third addition module, and a patch merging module PatchMerging, which are connected in series in sequence, wherein the output end of the patch merging module Patch Merging constitutes the output end of the MVT layer, the input end of the depthwise separable convolution module DWConv constitutes the input end of the MVT layer, the input end of the MVT layer is simultaneously connected to the input end of the first addition module, the output end of the first addition module is simultaneously connected to the input end of the second addition module, and the output end of the second addition module is simultaneously connected to the input end of the third addition module.

[0047] In addition, the structure of the first convolutional pooling activation module Conv Block1, the structure of the second convolutional pooling activation module Conv Block2, the structure of the third convolutional pooling activation module Conv Block3, the structure of the fourth convolutional pooling activation module Conv Block4, and the structure of the fifth convolutional pooling activation module Conv Block5 in the second encoder are the same as each other, and each convolutional pooling activation module includes a convolution module, a pooling module, and an activation module connected in series in sequence from the input end to the output end, wherein the input end of the convolution module constitutes the input end of the convolutional pooling activation module, and the output end of the activation module constitutes the output end of the convolutional pooling activation module.

[0048] The feature fusion module includes a first fusion layer SPCAI1 and a second fusion layer SPCAI2 connected in series from the input end to the output end. The output end of the first MVT layer MVT Block1 in the first encoder and the output end of the fourth convolutional pooling activation module Conv Block4 in the second encoder are simultaneously connected to the input end of the first fusion layer SPCAI1, and the output end of the second MVT layer MVT Block2 in the first encoder and the output end of the fifth convolutional pooling activation module Conv Block5 in the second encoder are simultaneously connected to the input end of the second fusion layer SPCAI2.

[0049] The structure of the first fusion layer SPCAI1 is the same as the structure of the second fusion layer SPCAI2. Figure 3 As shown, each fusion layer includes, from the input end to the output end, a first convolution module Conv1×1 with a convolution kernel size of 1×1, an activation function module GELU, a spatial attention module Spatial Attention, a third addition module, a channel attention module Channel Attention, a fourth addition module, and a second convolution module Conv1×1 with a convolution kernel size of 1×1, which are connected in series in sequence. The input end of the first convolution module Conv1×1 constitutes the input end of the fusion layer, the output end of the activation function module GELU is also connected to the input end of the third addition module, the output end of the third addition module is also connected to the input end of the fourth addition module, and the output end of the second convolution module Conv1×1 constitutes the output end of the fusion layer.

[0050] The multi-scale decoder includes 15 sampling convolution activation modules, which are divided into the first group, the second group, the third group, the fourth group, and the fifth group in the order of 1 sampling convolution activation module, 2 sampling convolution activation modules, 3 sampling convolution activation modules, 4 sampling convolution activation modules, and 5 sampling convolution activation modules, and each group includes the sampling convolution activation modules connected in series in sequence from the input end to the output end; the third MVT layer MVT in the first encoder The output end of Block3 and the output end of the second fusion layer SPCAI2 in the feature fusion module are simultaneously connected to the input end of the sampling convolution activation module in the first group; the output end of the first fusion layer SPCAI1 in the feature fusion module and the output end of the second fusion layer SPCAI2 are simultaneously connected to the input end of the first sampling convolution activation module in the second group, and the output end of the first fusion layer SPCAI1 in the feature fusion module is simultaneously connected to the input end of the second sampling convolution activation module in the second group and the input end of the first sampling convolution activation module in the third group; the input end of the first sampling convolution activation module in the third group is simultaneously connected to the output end of the third convolution pooling activation module ConvBlock3 in the second encoder, and the output end of the third convolution pooling activation module Conv Block3 is simultaneously connected to the input end of the first sampling convolution activation module in the fourth group, the input end of the second sampling convolution activation module in the third group, and the input end of the third sampling convolution activation module in the third group, and the input end of the first sampling convolution activation module in the fourth group is simultaneously connected to the second convolution pooling activation module Conv The output end of Block2 and the output end of the second convolutional pooling activation module Conv Block2 are simultaneously connected to the input end of the first sampling convolutional activation module in the 5th group, the input end of the second sampling convolutional activation module in the 4th group, the input end of the third sampling convolutional activation module in the 4th group, and the input end of the fourth sampling convolutional activation module in the 4th group. The input end of the first sampling convolutional activation module in the 5th group is simultaneously connected to the output end of the first convolutional pooling activation module Conv Block1. The first convolutional pooling activation module Conv The output end of Block1 is simultaneously connected to the input end of the second sampling convolution activation module in the fifth group, the input end of the third sampling convolution activation module in the fifth group, the input end of the fourth sampling convolution activation module in the fifth group, and the input end of the fifth sampling convolution activation module in the fifth group; the output end of the sampling convolution activation module in the first group is connected to the input end of the second sampling convolution activation module in the second group; the output end of the first sampling convolution activation module in the second group is simultaneously connected to the input end of the second sampling convolution activation module in the third group, and the output end of the second sampling convolution activation module in the second group is simultaneously connected to the input end of the third sampling convolution activation module in the third group;The output end of the first sampling convolution activation module in the third group is simultaneously connected to the input end of the third sampling convolution activation module in the third group and the input end of the second sampling convolution activation module in the fourth group, the output end of the second sampling convolution activation module in the third group is simultaneously connected to the input end of the third sampling convolution activation module in the fourth group, and the output end of the third sampling convolution activation module in the third group is simultaneously connected to the input end of the fourth sampling convolution activation module in the fourth group; the output end of the first sampling convolution activation module in the fourth group is simultaneously connected to the input end of the second sampling convolution activation module in the fifth group, the input end of the third sampling convolution activation module in the fourth group, and the input end of the fourth sampling convolution activation module in the fourth group, the output end of the second sampling convolution activation module in the fourth group is simultaneously connected to the input end of the third sampling convolution activation module in the fifth group and the input end of the fourth sampling convolution activation module in the fourth group, and the output end of the third sampling convolution activation module in the fourth group is simultaneously connected to the input end of the third sampling convolution activation module in the fifth group and the input end of the fourth sampling convolution activation module in the fourth group. The output end of the convolution activation module is simultaneously connected to the input end of the 4th sampling convolution activation module in the 5th group, and the output end of the 4th sampling convolution activation module in the 4th group is simultaneously connected to the input end of the 5th sampling convolution activation module in the 5th group; the output end of the 1st sampling convolution activation module in the 5th group is simultaneously connected to the input end of the 3rd sampling convolution activation module in the 5th group, the input end of the 4th sampling convolution activation module in the 5th group, and the input end of the 5th sampling convolution activation module in the 5th group; the output end of the 2nd sampling convolution activation module in the 5th group is simultaneously connected to the input end of the 4th sampling convolution activation module in the 5th group and the input end of the 5th sampling convolution activation module in the 5th group; the output end of the 3rd sampling convolution activation module in the 5th group is simultaneously connected to the input end of the 5th sampling convolution activation module in the 5th group, and the output end of the 5th sampling convolution activation module in the 5th group constitutes an output end of the GLI-MFUNet model. ;

[0051] The structures of the sampling convolution activation modules in the multi-scale decoder are the same. Each sampling convolution activation module includes a transposed convolution up-sampling module up_sample, a first convolution activation module, and a second convolution activation module connected in series from the input end to the output end. The structure of the first convolution activation module is the same as that of the second convolution activation module. Each convolution activation module includes a convolution module conv and an activation module Relu connected in series from the input end to the output end, wherein the input end of the convolution module conv constitutes the input end of the convolution activation module, and the output end of the activation module Relu constitutes the output end of the convolution activation module.

[0052] In step C, based on the sample set, satellite subsample images are simultaneously input into two input ends of the GLI-MFUNet model, and one output end of the GLI-MFUNet model outputs the water area and non-water area in the satellite subsample image. The GLI-MFUNet model is trained to obtain a surface water extraction model corresponding to the target area to be identified.

[0053] Step BC. Based on the definition that the satellite sub-sample images containing water areas in the sample set are positive samples and the satellite sub-sample images not containing water areas are negative samples, a method of eliminating positive samples or negative samples is performed so that the ratio of the number of positive samples to the number of negative samples is equal to 1, the sample set is updated, and then step C is entered.

[0054] Step C. Based on the sample set, the AdamW optimizer is applied, and the result of Focal Loss+DiceLoss is used as the loss function result according to the following formula. The water area and non-water area in the satellite sub-sample image are used as the output, and the GLI-MFUNet model is trained to obtain the surface water extraction model corresponding to the target area to be identified.

[0055] Focal Loss = -α t (1-p t ) γ log(p t )

[0056]

[0057] Among them, regarding the application of AdamW optimizer, such as designing the initial learning rate of the model to be set to 1×10 -4 , the momentum is set to 0.9, the weight decay coefficient is set to 0.01, and the total number of training epochs is 100; in the above loss function, α t Indicates the preset balance factor, p t represents the detection probability of water body area and non-water body area in the satellite sub-sample image, γ represents the preset adjustment factor, P represents the water body category detection probability value matrix of the water body area and non-water body area distribution corresponding to the length and width of the satellite sub-sample image, G represents the true label value matrix of the water body area and non-water body area distribution corresponding to the length and width of the satellite sub-sample image, ∑P represents the sum of the values ​​of each element in the calculated label value matrix P, and ∑G represents the sum of the values ​​of each element in the true label value matrix G.

[0058] In practical applications, after obtaining the surface water extraction model corresponding to the target area to be identified, the following step i can be performed to obtain the surface water distribution of the target area to be identified.

[0059] Step i. For the satellite image corresponding to the target area to be identified, the satellite image is cropped according to the preset sub-image size to obtain each target satellite sub-image, and the surface water extraction model corresponding to the target area to be identified is applied to process each target satellite sub-image separately to obtain the water area and non-water area in each target satellite sub-image, and then combined to form the surface water distribution in the target area to be identified.

[0060] The above technical solution is designed to construct each sample with the satellite sample images of each preset sample area in the target area to be identified, and train the GLI-MFUNet model constructed with a dual-channel encoder as input, processed by a feature fusion module, and a multi-scale decoder as output to obtain a surface water extraction model corresponding to the target area to be identified, thereby realizing the detection of surface water distribution in the target area to be identified. The design scheme uses Sentinel-2 image data to realize the rapid acquisition of large-scale surface water distribution, reduces the dependence of traditional methods on manpower and material resources, and greatly saves monitoring costs. The design not only improves the accuracy and efficiency of surface water identification, but also can provide reliable data support for water resources management, agricultural irrigation and environmental protection.

[0061] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in this field without departing from the purpose of the present invention.

Claims

1. A remote sensing fine extraction method for African surface water based on GLI-MFUNet, characterized by: Execute the following steps A to C to obtain a surface water extraction model corresponding to the target area to be identified; then execute the following step i to obtain the surface water distribution of the target area to be identified; Step A. For the satellite sample images corresponding to the preset sample areas in the target area to be identified, respectively, distinguishing the water area and the non-water area, the satellite sample images are cropped according to the preset sub-image size to obtain the satellite sub-sample images distinguishing the water area and the non-water area, forming a sample set, and then entering step B; Step B. Construct a GLI-MFUNet model with a dual-path encoder as input, processed by a feature fusion module, and a multi-scale decoder as output, and then proceed to step C; Step C. Based on the sample set, the satellite sub-sample image is used as input, and the water body area and non-water body area in the satellite sub-sample image is used as output, and the GLI-MFUNet model is trained to obtain the surface water extraction model corresponding to the target area to be identified; Step i. For the satellite image corresponding to the target area to be identified, the satellite image is cropped according to the preset sub-image size to obtain each target satellite sub-image, and the surface water extraction model corresponding to the target area to be identified is applied to process each target satellite sub-image respectively to obtain the water body area and non-water body area in each target satellite sub-image, and then combined to constitute the surface water distribution in the target area to be identified.

2. The method for fine extraction of African surface water remote sensing based on GLI-MFUNet according to claim 1, characterized in that: The step A includes the following steps A1 to A3; Step A1. Preset each sample area in the target area to be identified, obtain the red band satellite image, near infrared band satellite image, and short wave infrared band satellite image corresponding to the sample area, and superimpose the satellite images of each band to form a satellite sample image corresponding to the sample area, thereby obtaining the satellite sample images corresponding to each sample area, and then proceed to step A2; Step A2. For each sample area preset in the target area to be identified, distinguish the water area and the non-water area in the satellite sample image corresponding to the sample area according to the water area and the non-water area in the sample area, that is, distinguish the water area and the non-water area in the satellite sample image corresponding to each sample area, and then proceed to step A3; Step A3. For each sample area preset in the target area to be identified, the satellite sample image corresponding to the sample area is cropped according to the preset sub-image size to obtain satellite sub-sample images that distinguish water areas from non-water areas. The satellite sub-sample images corresponding to each sample area together constitute a sample set.

3. The method for remote sensing fine extraction of African surface water based on GLI-MFUNet according to claim 2, characterized in that: In the step A1, each sample area in the target area to be identified is preset, and the L2A product of the Sentinel-2 satellite image corresponding to the sample area is obtained. Based on the resampling of the B11 band satellite image resolution being the same as the B4 band satellite image resolution and the B8 band satellite image resolution, the B11 band satellite image, the B4 band satellite image, and the B8 band satellite image are superimposed to form a satellite sample image corresponding to the sample area, thereby obtaining the satellite sample images corresponding to each sample area.

4. The method for remote sensing fine extraction of African surface water based on GLI-MFUNet according to claim 1, characterized in that: It also includes step BC as follows: after executing step B, enter step BC; Step BC. Based on the definition that the satellite sub-sample images containing water areas in the sample set are positive samples and the satellite sub-sample images not containing water areas are negative samples, a method of eliminating positive samples or negative samples is executed so that the ratio of the number of positive samples to the number of negative samples falls within a preset upper and lower fluctuation range centered on 1, the sample set is updated, and then step C is entered.

5. The method for remote sensing fine extraction of African surface water based on GLI-MFUNet according to claim 1, characterized in that: The structure of the GLI-MFUNet model in step B is as follows: The dual-path encoder includes a first-path encoder and a second-path encoder, wherein the first-path encoder includes a patch embedding layer Patch Embeding, a first MVT layer MVT Block1, a second MVT layer MVT Block2, and a third MVT layer MVT Block3 connected in series from the input end to the output end; the second-path encoder includes a first convolutional pooling activation module Conv Block1, a second convolutional pooling activation module Conv Block2, a third convolutional pooling activation module Conv Block3, a fourth convolutional pooling activation module Conv Block4, and a fifth convolutional pooling activation module Conv Block5 connected in series from the input end to the output end; the input end of the first-path encoder and the input end of the second-path encoder constitute the two input ends of the GLI-MFUNet model; The feature fusion module includes a first fusion layer SPCAI1 and a second fusion layer SPCAI2 connected in series from the input end to the output end. The output end of the first MVT layer MVT Block1 in the first encoder and the output end of the fourth convolutional pooling activation module Conv Block4 in the second encoder are simultaneously connected to the input end of the first fusion layer SPCAI1. The output end of the second MVT layer MVT Block2 in the first encoder and the output end of the fifth convolutional pooling activation module Conv Block5 in the second encoder are simultaneously connected to the input end of the second fusion layer SPCAI2. The multi-scale decoder includes 15 sampling convolution activation modules, which are divided into the first group, the second group, the third group, the fourth group, and the fifth group in the order of 1 sampling convolution activation module, 2 sampling convolution activation modules, 3 sampling convolution activation modules, 4 sampling convolution activation modules, and 5 sampling convolution activation modules, and each group includes the sampling convolution activation modules connected in series in sequence from the input end to the output end; the third MVT layer MVT in the first encoder The output end of Block3 and the output end of the second fusion layer SPCAI2 in the feature fusion module are simultaneously connected to the input end of the sampling convolution activation module in the first group; the output end of the first fusion layer SPCAI1 in the feature fusion module and the output end of the second fusion layer SPCAI2 are simultaneously connected to the input end of the first sampling convolution activation module in the second group, and the output end of the first fusion layer SPCAI1 in the feature fusion module is simultaneously connected to the input end of the second sampling convolution activation module in the second group and the input end of the first sampling convolution activation module in the third group; the input end of the first sampling convolution activation module in the third group is simultaneously connected to the output end of the third convolution pooling activation module Conv Block3 in the second encoder, and the output end of the third convolution pooling activation module Conv Block3 is simultaneously connected to the input end of the first sampling convolution activation module in the fourth group, the input end of the second sampling convolution activation module in the third group, and the input end of the third sampling convolution activation module in the third group, and the input end of the first sampling convolution activation module in the fourth group is simultaneously connected to the second convolution pooling activation module Conv The output end of Block2 and the output end of the second convolutional pooling activation module Conv Block2 are simultaneously connected to the input end of the first sampling convolutional activation module in the 5th group, the input end of the second sampling convolutional activation module in the 4th group, the input end of the third sampling convolutional activation module in the 4th group, and the input end of the fourth sampling convolutional activation module in the 4th group. The input end of the first sampling convolutional activation module in the 5th group is simultaneously connected to the output end of the first convolutional pooling activation module Conv Block1. The first convolutional pooling activation module Conv The output end of Block1 is simultaneously connected to the input end of the second sampling convolution activation module in the fifth group, the input end of the third sampling convolution activation module in the fifth group, the input end of the fourth sampling convolution activation module in the fifth group, and the input end of the fifth sampling convolution activation module in the fifth group; the output end of the sampling convolution activation module in the first group is connected to the input end of the second sampling convolution activation module in the second group; the output end of the first sampling convolution activation module in the second group is simultaneously connected to the input end of the second sampling convolution activation module in the third group, and the output end of the second sampling convolution activation module in the second group is simultaneously connected to the input end of the third sampling convolution activation module in the third group;The output end of the first sampling convolution activation module in the third group is simultaneously connected to the input end of the third sampling convolution activation module in the third group and the input end of the second sampling convolution activation module in the fourth group, the output end of the second sampling convolution activation module in the third group is simultaneously connected to the input end of the third sampling convolution activation module in the fourth group, and the output end of the third sampling convolution activation module in the third group is simultaneously connected to the input end of the fourth sampling convolution activation module in the fourth group; the output end of the first sampling convolution activation module in the fourth group is simultaneously connected to the input end of the second sampling convolution activation module in the fifth group, the input end of the third sampling convolution activation module in the fourth group, and the input end of the fourth sampling convolution activation module in the fourth group, the output end of the second sampling convolution activation module in the fourth group is simultaneously connected to the input end of the third sampling convolution activation module in the fifth group and the input end of the fourth sampling convolution activation module in the fourth group, and the output end of the third sampling convolution activation module in the fourth group is simultaneously connected to the input end of the third sampling convolution activation module in the fifth group and the input end of the fourth sampling convolution activation module in the fourth group. The output end of the convolution activation module is simultaneously connected to the input end of the 4th sampling convolution activation module in the 5th group, and the output end of the 4th sampling convolution activation module in the 4th group is simultaneously connected to the input end of the 5th sampling convolution activation module in the 5th group; the output end of the 1st sampling convolution activation module in the 5th group is simultaneously connected to the input end of the 3rd sampling convolution activation module in the 5th group, the input end of the 4th sampling convolution activation module in the 5th group, and the input end of the 5th sampling convolution activation module in the 5th group, the output end of the 2nd sampling convolution activation module in the 5th group is simultaneously connected to the input end of the 4th sampling convolution activation module in the 5th group, and the input end of the 5th sampling convolution activation module in the 5th group, the output end of the 3rd sampling convolution activation module in the 5th group is simultaneously connected to the input end of the 5th sampling convolution activation module in the 5th group, and the output end of the 5th sampling convolution activation module in the 5th group constitutes an output end of the GLI-MFUNet model; In step C, based on the sample set, satellite subsample images are simultaneously input into two input ends of the GLI-MFUNet model, and one output end of the GLI-MFUNet model outputs the water area and non-water area in the satellite subsample image. The GLI-MFUNet model is trained to obtain a surface water extraction model corresponding to the target area to be identified.

6. The method for fine extraction of African surface water remote sensing based on GLI-MFUNet according to claim 5, characterized in that: The structure of the first MVT layer MVT Block1 is the same as the structure of the second MVT layer MVT Block2, and each MVT layer includes, from the input end to the output end, a depthwise separable convolution module DWConv, a first addition module, a first layer standardization module Layer Norm1, a Manhattan self-attention module MaSA, a second addition module, a second layer standardization module Layer Norm2, a feedforward neural network module FFN, a third addition module, and a patch merging module Patch Merging, wherein the output end of the patch merging module Patch Merging constitutes the output end of the MVT layer, the input end of the depthwise separable convolution module DWConv constitutes the input end of the MVT layer, the input end of the MVT layer is simultaneously connected to the input end of the first addition module, the output end of the first addition module is simultaneously connected to the input end of the second addition module, and the output end of the second addition module is simultaneously connected to the input end of the third addition module.

7. The method for fine extraction of African surface water remote sensing based on GLI-MFUNet according to claim 5, characterized in that: The structure of the first fusion layer SPCAI1 is the same as that of the second fusion layer SPCAI2. Each fusion layer includes, from the input end to the output end, a first convolution module Conv1×1 with a convolution kernel size of 1×1, an activation function module GELU, a spatial attention module Spatial Attention, a third addition module, a channel attention module ChannelAttention, a fourth addition module, and a second convolution module Conv1×1 with a convolution kernel size of 1×1, which are connected in series in sequence. The input end of the first convolution module Conv1×1 constitutes the input end of the fusion layer, the output end of the activation function module GELU is also connected to the input end of the third addition module, the output end of the third addition module is also connected to the input end of the fourth addition module, and the output end of the second convolution module Conv1×1 constitutes the output end of the fusion layer.

8. The method for fine extraction of African surface water remote sensing based on GLI-MFUNet according to claim 5, characterized in that: The structures of the sampling convolution activation modules in the multi-scale decoder are the same. Each sampling convolution activation module includes a transposed convolution up-sampling module up_sample, a first convolution activation module, and a second convolution activation module connected in series from the input end to the output end. The structure of the first convolution activation module is the same as that of the second convolution activation module. Each convolution activation module includes a convolution module conv and an activation module Relu connected in series from the input end to the output end, wherein the input end of the convolution module conv constitutes the input end of the convolution activation module, and the output end of the activation module Relu constitutes the output end of the convolution activation module.

9. The method for remote sensing fine extraction of African surface water based on GLI-MFUNet according to claim 5, characterized in that: The structure of the first convolutional pooling activation module Conv Block1, the structure of the second convolutional pooling activation module Conv Block2, the structure of the third convolutional pooling activation module Conv Block3, the structure of the fourth convolutional pooling activation module Conv Block4, and the structure of the fifth convolutional pooling activation module Conv Block5 in the second encoder are the same as each other, and each convolutional pooling activation module includes a convolution module, a pooling module, and an activation module connected in series in sequence from the input end to the output end, wherein the input end of the convolution module constitutes the input end of the convolutional pooling activation module, and the output end of the activation module constitutes the output end of the convolutional pooling activation module.

10. The method for fine extraction of African surface water remote sensing based on GLI-MFUNet according to claim 1, characterized in that: In step C, based on the sample set, the AdamW optimizer is applied, and the GLI-MFUNet model is trained according to the following formula, combining the result of Focal Loss+DiceLoss as the loss function result; Focal Loss=-α t (1-p t ) γ log(p t ) Among them, α t Indicates the preset balance factor, p t represents the detection probability of water body area and non-water body area in the satellite sub-sample image, γ represents the preset adjustment factor, P represents the water body category detection probability value matrix of the water body area and non-water body area distribution corresponding to the length and width of the satellite sub-sample image, G represents the true label value matrix of the water body area and non-water body area distribution corresponding to the length and width of the satellite sub-sample image, ∑P represents the sum of the values ​​of each element in the calculated label value matrix P, and ∑G represents the sum of the values ​​of each element in the true label value matrix G.

Images