Remote sensing image enhancement processing method and device for soil pollution observation

Abstract

The invention provides a remote sensing image enhancement processing method and device for soil pollution observation. The method comprises the following steps: acquiring a remote sensing image for observing soil pollution; performing fast Fourier transform on the remote sensing image to obtain a spectrogram; extracting an edge intensity graph of the remote sensing image to construct a spatial weight matrix; acting the spatial weight matrix on the remote sensing image to obtain a spatial domain edge enhanced image; based on the high-frequency component and the low-frequency component in the spectrogram, enhancing the spectrogram to obtain an enhanced spectrogram; combining the enhanced spectrogram with the original phase spectrum of the original remote sensing image, and performing inverse Fourier transform to obtain a frequency domain enhanced image; fusing the frequency domain enhanced image and the spatial domain edge enhanced image to obtain a fused image; and performing local contrast optimization processing on the fused image based on the brightness gradient map and the edge intensity map of the fused image to obtain a final remote sensing image. According to the method, the identification precision and the visual discernibility of the soil pollution area are effectively enhanced.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to an enhancement processing method and apparatus for remote sensing images used for soil pollution observation. Background Technology

[0002] Traditional remote sensing image enhancement techniques mainly include spatial domain methods and frequency domain methods. Spatial domain methods focus on local adjustments of image gray values, such as histogram equalization and edge enhancement filtering. Although computationally simple, they are sensitive to noise and prone to over-enhancing local areas. Frequency domain methods analyze the image spectral characteristics through Fourier transform and adjust the energy distribution of the image at different frequencies to achieve detail enhancement and contrast improvement, but they have shortcomings in parameter selection and adaptive processing.

[0003] Therefore, existing methods cannot simultaneously achieve both detail preservation and contrast optimization in enhanced remote sensing images, which limits the application of remote sensing images in soil pollution detection. Summary of the Invention

[0004] The purpose of this invention is to provide a method and apparatus for enhancing remote sensing images for soil pollution observation, so as to balance the preservation of details and the optimization of contrast in remote sensing images, thereby improving the application effect of remote sensing images in soil pollution detection.

[0005] In a first aspect, embodiments of the present invention provide a method for enhancing remote sensing images used for soil pollution observation, comprising: acquiring an original remote sensing image for observing soil pollution; performing a fast Fourier transform on the original remote sensing image to obtain a spectrum map corresponding to the original remote sensing image; extracting an edge intensity map of the original remote sensing image using the Scharr operator to construct a spatial weight matrix; applying the spatial weight matrix to the original remote sensing image using the Hadamard product to obtain a spatial domain edge enhancement image; enhancing the spectrum map based on a first high-frequency component and a first low-frequency component to obtain an enhanced spectrum map; combining the enhanced spectrum map with the original phase spectrum of the original remote sensing image and performing an inverse Fourier transform to obtain a frequency domain enhancement image; fusing the frequency domain enhancement image and the spatial domain edge enhancement image to obtain a fused image; and performing local contrast optimization processing on the fused image based on the brightness gradient map and edge intensity map of the fused image to obtain a final enhanced remote sensing image.

[0006] In a preferred embodiment of the present invention, the step of enhancing the spectrum based on the first high-frequency component and the first low-frequency component in the spectrum to obtain an enhanced spectrum includes: separating the first high-frequency component and the first low-frequency component in the spectrum; sharpening and enhancing the first high-frequency component and adjusting the contrast of the first low-frequency component to obtain a second high-frequency component and a second low-frequency component; and fusing and reconstructing the second high-frequency component and the second low-frequency component to obtain the enhanced spectrum.

[0007] In a preferred embodiment of the present invention, before the step of sharpening and enhancing the first high-frequency component, the method includes: centering the spectrum to obtain a centered spectrum; calculating the total energy of the centered spectrum; calculating the total energy of the first high-frequency component; constructing a base gain based on the total energy of the first high-frequency component and the total energy of the centered spectrum; calculating the first amplitude mean of all frequency points in the first high-frequency component to obtain a high-frequency mean; constructing a local intensity term based on the amplitude value of the frequency points and the high-frequency mean; and sharpening and enhancing the first high-frequency component to obtain a second high-frequency component, which includes: constructing a gain coefficient using the base gain and the local intensity term; and sharpening and enhancing the first high-frequency component using the gain coefficient to obtain the second high-frequency component.

[0008] In a preferred embodiment of the present invention, the aforementioned basic gain is expressed by the following formula: ;in, It is the base gain. It is the global high-frequency gain weighting coefficient. It is the total energy of the first high-frequency component. It is the total energy of the above-mentioned centralized spectrum diagram. It is the nonlinear adjustment index of the high-frequency component; the above local intensity term is expressed by the following formula: ;in, It is a local strength term. It is a local high-frequency enhancement weighting coefficient. It is the amplitude value of the frequency point in the first high-frequency component mentioned above. It is the above high-frequency average. It is a very small constant. It is a local enhancement nonlinear adjustment index; the above gain coefficient is expressed by the following formula: ;in, It is the aforementioned gain coefficient. It is the energy variance of the first high-frequency component. It is the noise threshold parameter.

[0009] In a preferred embodiment of the present invention, before the step of contrast adjustment of the first low-frequency component, the method includes: calculating the second amplitude mean and standard deviation of all frequency points in the first low-frequency component to obtain the low-frequency mean and low-frequency standard deviation; constructing a dynamic compression kernel term based on the Tukey double-weight function, according to the low-frequency mean and low-frequency standard deviation; calculating the frequency domain gradient map of the first low-frequency component; constructing a frequency gradient suppression term based on the frequency domain gradient map; multiplying the dynamic compression kernel term and the frequency gradient suppression term to obtain a dynamic compression coefficient; the step of contrast adjustment of the first low-frequency component includes: adjusting the contrast of the first low-frequency component using the dynamic compression coefficient to obtain a second low-frequency component.

[0010] In a preferred embodiment of the present invention, the above-mentioned dynamic compression kernel term is expressed by the following formula. ;in, These are the aforementioned dynamic compression kernel terms. It is the amplitude value at a frequency point in the first low-frequency component. This is the aforementioned low-frequency average. This is the aforementioned low-frequency standard deviation. It is the spectral deviation sensitivity factor; the above frequency gradient suppression term is expressed by the following formula: ;in, This is the frequency gradient suppression term mentioned above. It is a frequency domain gradient adjustment factor. It is the gradient amplitude value of the frequency point in the low-frequency amplitude diagram corresponding to the first low-frequency component mentioned above.

[0011] In a preferred embodiment of the present invention, the step of fusing the frequency domain enhanced image and the spatial domain edge enhanced image to obtain a fused image includes: determining a frequency domain enhancement mask based on the frequency domain enhanced image; determining a spatial domain edge enhancement mask based on the spatial domain edge enhanced image; constructing a joint mask based on the frequency domain enhanced mask and the spatial domain edge enhancement mask using a first preset weight parameter; and fusing the frequency domain enhanced image and the spatial domain edge enhanced image based on the joint mask to obtain the fused image.

[0012] In a preferred embodiment of the present invention, the step of performing local contrast optimization processing on the fused image based on the brightness gradient map and edge intensity map of the fused image to obtain the final enhanced remote sensing image includes: generating an adaptive compression factor map based on the brightness gradient map and edge intensity map of the fused image; and performing local contrast optimization on the fused image using the adaptive compression factor map to obtain the final enhanced remote sensing image.

[0013] In a preferred embodiment of the present invention, the step of generating an adaptive compression factor map based on the brightness gradient map and edge intensity map of the fused image includes: linearly fusing the brightness gradient map and the edge intensity map based on preset weight parameters to obtain a fused feature map; smoothing the fused feature map and dynamically generating the adaptive compression factor map using a preset exponential function.

[0014] Secondly, embodiments of the present invention also provide an enhancement processing apparatus for remote sensing images used in soil pollution observation, comprising: a data acquisition module for acquiring original remote sensing images for soil pollution observation; a processing module for performing a fast Fourier transform on the original remote sensing image to obtain a spectrum map corresponding to the original remote sensing image; extracting an edge intensity map of the original remote sensing image using the Scharr operator to construct a spatial weight matrix; applying the spatial weight matrix to the original remote sensing image using the Hadamard product to obtain a spatial domain edge enhancement image; enhancing the spectrum map based on a first high-frequency component and a first low-frequency component to obtain an enhanced spectrum map; combining the enhanced spectrum map with the original phase spectrum of the original remote sensing image and performing an inverse Fourier transform to obtain a frequency domain enhancement image; fusing the frequency domain enhancement image and the spatial domain edge enhancement image to obtain a fused image; and an output module for performing local contrast optimization processing on the fused image based on the brightness gradient map and edge intensity map of the fused image to obtain a final enhanced remote sensing image.

[0015] The embodiments of the present invention have the following beneficial technical effects: This invention provides a method and apparatus for enhancing remote sensing images used for soil pollution observation, comprising: acquiring an original remote sensing image for observing soil pollution; performing a fast Fourier transform on the original remote sensing image to obtain a spectrum corresponding to the original remote sensing image; extracting an edge intensity map of the original remote sensing image using the Scharr operator to construct a spatial weight matrix; applying the spatial weight matrix to the original remote sensing image using the Hadamard product to obtain a spatial domain edge-enhanced image; enhancing the spectrum based on a first high-frequency component and a first low-frequency component in the spectrum to obtain an enhanced spectrum; combining the enhanced spectrum with the original phase spectrum of the original remote sensing image and performing an inverse Fourier transform to obtain a frequency domain enhanced image; fusing the frequency domain enhanced image and the spatial domain edge-enhanced image to obtain a fused image; and performing local contrast optimization processing on the fused image based on the brightness gradient map and edge intensity map to obtain the final enhanced remote sensing image. This method significantly improves the detail clarity and dynamic range of remote sensing images by fusing spatial domain edge enhancement and frequency domain multi-scale feature optimization, combined with local contrast adjustment, effectively enhancing the identification accuracy and visual discernibility of soil pollution areas. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a schematic flowchart of a remote sensing image enhancement method for soil pollution observation provided in an embodiment of the present invention. Figure 2 A schematic flowchart illustrating another method for enhancing remote sensing images used for soil pollution observation, provided in an embodiment of the present invention. Figure 3 A schematic diagram of an original remote sensing image provided in an embodiment of the present invention; Figure 4 A schematic diagram of an enhanced original remote sensing image provided in an embodiment of the present invention; Figure 5 A schematic diagram of a remote sensing image enhancement processing device for soil pollution observation provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0018] Icons: 31-Data acquisition module; 32-Processing module; 33-Output module; 41-Memory; 42-Processor; 43-Bus; 44-Communication interface. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0020] Traditional remote sensing image enhancement techniques mainly include spatial domain methods and frequency domain methods. Spatial domain methods focus on local adjustments of image grayscale values, such as histogram equalization and edge enhancement filtering. Although computationally simple, they are sensitive to noise and prone to over-enhancing local areas. Frequency domain methods analyze the image's spectral characteristics through Fourier transform and adjust the energy distribution of the image at different frequencies to achieve detail enhancement and contrast improvement, but they have shortcomings in parameter selection and adaptive processing. Therefore, existing methods cannot simultaneously achieve both detail preservation and contrast optimization in enhanced remote sensing images, limiting the application effectiveness of remote sensing images in soil pollution detection.

[0021] Based on this, embodiments of the present invention provide an enhancement method and apparatus for remote sensing images used for soil pollution observation. This method significantly improves the detail clarity and dynamic range of remote sensing images by fusing spatial domain edge enhancement and frequency domain multi-scale feature optimization, combined with local contrast adjustment, effectively enhancing the identification accuracy and visual discernibility of soil pollution areas. For ease of understanding, an enhancement method for remote sensing images used for soil pollution observation is first introduced.

[0022] Example 1 In this embodiment, Figure 1 This is a flowchart illustrating a method for enhancing remote sensing images used for soil pollution observation, provided in an embodiment of the present invention.

[0023] Depend on Figure 1 As seen, the method includes: Step S101: Obtain the original remote sensing image of the soil pollution situation.

[0024] Step S102: Perform a fast Fourier transform on the original remote sensing image to obtain the spectrum corresponding to the original remote sensing image; and extract the edge intensity map of the original remote sensing image using the Scharr operator to construct a spatial weight matrix; and apply the spatial weight matrix to the original remote sensing image using the Hadamard product to obtain a spatial domain edge enhancement image.

[0025] Step S103: Based on the first high-frequency component and the first low-frequency component in the above spectrum diagram, the above spectrum diagram is enhanced to obtain an enhanced spectrum diagram.

[0026] Here, a gain coefficient is applied to the first high-frequency component. Sharpening and enhancement are performed, and a dynamic compression factor is applied to the first low-frequency component. Contrast adjustment is performed to obtain the second high-frequency component and the second low-frequency component, which are then fused and reconstructed to obtain the enhanced spectrogram.

[0027] Step S104: Combine the enhanced spectrogram with the original phase spectrum of the original remote sensing image and perform inverse Fourier transform to obtain the frequency domain enhanced image.

[0028] Step S105: Fuse the above frequency domain enhanced image and the above spatial domain edge enhanced image to obtain a fused image.

[0029] In practice, the enhanced spectrogram is combined with the original phase spectrum to construct an enhanced frequency domain representation. The enhanced frequency domain image is obtained through inverse Fourier transform. A joint mask is constructed, which is obtained by weighted superposition of the enhanced frequency domain mask and the enhanced spatial domain edge mask. The enhanced frequency domain image and the enhanced spatial domain edge image are fused using the constructed joint mask as weights to obtain the fused image.

[0030] Step S106: Based on the brightness gradient map and edge intensity map of the above-mentioned fused image, perform local contrast optimization processing on the above-mentioned combined image to obtain the final enhanced remote sensing image.

[0031] Here, an adaptive compression factor map is constructed, which is jointly generated from the brightness gradient map and edge intensity map of the fused image. Based on the constructed adaptive factor map, the local contrast of the fused image is optimized to obtain the final enhanced remote sensing image.

[0032] Among them, the fused image is also known as the frequency dual-sensory enhanced image.

[0033] This invention provides a method for enhancing remote sensing images used for soil pollution observation, comprising: acquiring an original remote sensing image for observing soil pollution; performing a fast Fourier transform on the original remote sensing image to obtain a spectrum map corresponding to the original remote sensing image; extracting an edge intensity map of the original remote sensing image using the Scharr operator to construct a spatial weight matrix; applying the spatial weight matrix to the original remote sensing image using the Hadamard product to obtain a spatial domain edge-enhanced image; enhancing the spectrum map based on a first high-frequency component and a first low-frequency component to obtain an enhanced spectrum map; combining the enhanced spectrum map with the original phase spectrum of the original remote sensing image and performing an inverse Fourier transform to obtain a frequency domain enhanced image; fusing the frequency domain enhanced image and the spatial domain edge-enhanced image to obtain a fused image; and performing local contrast optimization processing on the fused image based on the brightness gradient map and edge intensity map of the fused image to obtain the final enhanced remote sensing image. This method significantly improves the detail clarity and dynamic range of remote sensing images by fusing spatial domain edge enhancement and frequency domain multi-scale feature optimization, combined with local contrast adjustment, effectively enhancing the identification accuracy and visual discernibility of soil pollution areas.

[0034] Example 2 Based on the above embodiments, Figure 2 This is a schematic flowchart of another remote sensing image enhancement method for soil pollution observation provided in an embodiment of the present invention.

[0035] Depend on Figure 2 As seen, the method includes: Step S201: Obtain the original remote sensing image of the soil pollution situation.

[0036] Step S202: Perform a fast Fourier transform on the original remote sensing image to obtain the spectrum corresponding to the original remote sensing image; and extract the edge intensity map of the original remote sensing image using the Scharr operator to construct a spatial weight matrix; and apply the spatial weight matrix to the original remote sensing image using the Hadamard product to obtain a spatial domain edge-enhanced image.

[0037] Step S203: Separate the first high-frequency component and the first low-frequency component in the above spectrum diagram.

[0038] Step S204: Sharpen and enhance the first high-frequency component and adjust the contrast of the first low-frequency component to obtain the second high-frequency component and the second low-frequency component.

[0039] Step S205: The second high-frequency component and the second low-frequency component are fused and reconstructed to obtain the enhanced spectrum.

[0040] Step S206: Combine the enhanced spectrogram with the original phase spectrum of the original remote sensing image and perform inverse Fourier transform to obtain the frequency domain enhanced image.

[0041] Step S207: Fuse the above frequency domain enhanced image and the above spatial domain edge enhanced image to obtain a fused image.

[0042] Step S208: Based on the brightness gradient map and edge intensity map of the above fused image, perform local contrast optimization processing on the above fused image to obtain the final enhanced remote sensing image.

[0043] Before the step of sharpening and enhancing the first high-frequency component, the method includes: centering the spectrum to obtain a centered spectrum; calculating the total energy of the centered spectrum; calculating the total energy of the first high-frequency component; constructing a base gain based on the total energy of the first high-frequency component and the total energy of the centered spectrum; calculating the first amplitude mean of all frequency points in the first high-frequency component to obtain a high-frequency mean; constructing a local intensity term based on the amplitude value of the frequency points and the high-frequency mean; and sharpening and enhancing the first high-frequency component to obtain a second high-frequency component, which includes: constructing a gain coefficient using the base gain and the local intensity term; and sharpening and enhancing the first high-frequency component using the gain coefficient to obtain the second high-frequency component.

[0044] Furthermore, the aforementioned base gain is expressed by the following formula: ;in, It is the base gain. It is the global high-frequency gain weighting coefficient. It is the total energy of the first high-frequency component. It is the total energy of the above-mentioned centralized spectrum diagram. It is the nonlinear adjustment index of the high-frequency component; The aforementioned local strength term is expressed by the following formula: ;in, It is a local strength term. It is a local high-frequency enhancement weighting coefficient. It is the amplitude value of the frequency point in the first high-frequency component mentioned above. It is the above high-frequency average. It is a very small constant. It is a locally enhanced nonlinear adjustment index; The above gain coefficient is expressed by the following formula: ;in, It is the aforementioned gain coefficient. It is the energy variance of the first high-frequency component. It is the noise threshold parameter.

[0045] Furthermore, before the step of adjusting the contrast of the first low-frequency component, the method includes: calculating the second amplitude mean and standard deviation of all frequency points in the first low-frequency component to obtain the low-frequency mean and low-frequency standard deviation; constructing a dynamic compression kernel term based on the Tukey double-weight function, according to the low-frequency mean and low-frequency standard deviation; calculating the frequency domain gradient map of the first low-frequency component; constructing a frequency gradient suppression term based on the frequency domain gradient map; multiplying the dynamic compression kernel term and the frequency gradient suppression term to obtain a dynamic compression coefficient; the step of adjusting the contrast of the first low-frequency component includes: adjusting the contrast of the first low-frequency component using the dynamic compression coefficient to obtain a second low-frequency component.

[0046] Furthermore, the aforementioned dynamic compression kernel term is expressed by the following formula: ;in, These are the aforementioned dynamic compression kernel terms. It is the amplitude value at a frequency point in the first low-frequency component. This is the aforementioned low-frequency average. This is the aforementioned low-frequency standard deviation. It is the spectral deviation sensitivity factor; the above frequency gradient suppression term is expressed by the following formula: ;in, This is the frequency gradient suppression term mentioned above. It is a frequency domain gradient adjustment factor. It is the gradient amplitude value of the frequency point in the low-frequency amplitude diagram corresponding to the first low-frequency component mentioned above.

[0047] The step of fusing the frequency domain enhanced image and the spatial domain edge enhanced image to obtain a fused image includes: determining a frequency domain enhancement mask based on the frequency domain enhanced image; determining a spatial domain edge enhancement mask based on the spatial domain edge enhanced image; constructing a joint mask based on the frequency domain enhanced mask and the spatial domain edge enhancement mask using a first preset weight parameter; and fusing the frequency domain enhanced image and the spatial domain edge enhanced image based on the joint mask to obtain the fused image.

[0048] Finally, the step of performing local contrast optimization processing on the fused image based on the brightness gradient map and edge intensity map of the fused image to obtain the final enhanced remote sensing image includes: generating an adaptive compression factor map based on the brightness gradient map and edge intensity map of the fused image; and performing local contrast optimization on the fused image using the adaptive compression factor map to obtain the final enhanced remote sensing image.

[0049] Here, the step of generating an adaptive compression factor map based on the brightness gradient map and edge intensity map of the fused image includes: linearly fusing the brightness gradient map and the edge intensity map based on preset weight parameters to obtain a fused feature map; smoothing the fused feature map and dynamically generating the adaptive compression factor map using a preset exponential function.

[0050] This invention provides a method for enhancing remote sensing images used for soil pollution observation, comprising: acquiring an original remote sensing image of soil pollution; performing a fast Fourier transform on the original remote sensing image to obtain a spectrum corresponding to the original remote sensing image; extracting an edge intensity map of the original remote sensing image using the Scharr operator to construct a spatial weight matrix; applying the spatial weight matrix to the original remote sensing image using the Hadamard product to obtain a spatial domain edge-enhanced image; separating a first high-frequency component and a first low-frequency component in the spectrum; and processing the first high-frequency component... The method involves sharpening and enhancing the image, adjusting the contrast of the first low-frequency component to obtain a second high-frequency component and a second low-frequency component. These two components are then fused and reconstructed to obtain an enhanced spectrogram. This enhanced spectrogram is combined with the original phase spectrum of the original remote sensing image and subjected to inverse Fourier transform to obtain a frequency-domain enhanced image. The frequency-domain enhanced image and the spatial-domain edge-enhanced image are then fused to obtain a fused image. Based on the brightness gradient map and edge intensity map of the fused image, local contrast optimization is performed on the fused image to obtain the final enhanced remote sensing image. This method significantly improves the detail clarity, contrast, and edge sharpness of remote sensing images by fusing spatial-domain edge enhancement, frequency-domain high-frequency sharpening, and low-frequency contrast adjustment, combined with local contrast optimization. This effectively enhances the identifiability and observation accuracy of soil pollution characteristics.

[0051] Example 3 To facilitate understanding of this application, the following practical example will be used for illustration. In its implementation, this application includes the following steps: Step S1: Perform a fast Fourier transform on the original remote sensing image to obtain the spectrum corresponding to the original remote sensing image. Perform spectral energy analysis based on the energy distribution characteristics in the spectrum and adaptively separate the first high-frequency component and the first low-frequency component of the spectrum.

[0052] Step S2: Apply a gain coefficient to the first high-frequency component. Sharpening and enhancement are performed, and a dynamic compression factor is applied to the first low-frequency component. Contrast adjustment is performed, and the enhanced second high-frequency component and the second low-frequency component are fused and reconstructed to obtain the enhanced spectrum.

[0053] Step S3: Use the Scharr operator to extract the edge intensity map of the original remote sensing image, construct a spatial weight matrix based on the edge intensity map, and apply the spatial weight matrix to the original remote sensing image through the Hadamard product to obtain a spatial domain edge-enhanced image.

[0054] Step S4: Combine the enhanced spectrogram with the original phase spectrum to construct the enhanced frequency domain representation. Obtain the frequency domain enhanced image through inverse Fourier transform. Construct a joint mask image, which is obtained by weighted superposition of the frequency domain enhanced mask image and the spatial domain edge enhanced mask image. Use the constructed joint mask image as weight to fuse the frequency domain enhanced image and the spatial domain edge enhanced image to obtain the fused image.

[0055] Step S5: Since soil pollution in remote sensing images often manifests as a mixture of weak high-frequency features and low-frequency background, directly enhancing the entire frequency band would lead to noise amplification or loss of detail. Therefore, this invention achieves differentiated processing of high and low frequencies through adaptive spectrum separation. Step S1 specifically includes: inputting the original remote sensing image, using a two-dimensional fast Fourier transform algorithm to transform the original remote sensing image from the spatial domain to the frequency domain to obtain a frequency domain representation, extracting the amplitude spectrum from the frequency domain representation to obtain a spectrum map; utilizing the conjugate symmetry of the spectrum, centering the spectrum map, and shifting the zero-frequency component to the frequency domain through quadrant swapping. The central location of the spectrum ensures that low-frequency components are concentrated at the center, while high-frequency components are distributed in the peripheral regions, resulting in a centered spectrum. Based on this centered spectrum, the energy of each frequency point is calculated, along with the distance from each frequency point to the spectrum center, yielding a radial distance matrix. The energy of each frequency point in the spectrum is grouped according to the radial distance matrix, and the total energy of each corresponding radial distance interval is calculated to obtain the spectral energy distribution function. The energy of each radial distance interval in the spectral energy distribution function is accumulated in ascending order of radial distance, and the accumulated result is normalized to obtain a normalized cumulative energy distribution curve. Based on soil pollution detection requirements, an energy accumulation threshold is set. A binary search method is used to search the normalized cumulative energy distribution curve to find the minimum radial distance at which the normalized cumulative energy first reaches or exceeds the energy accumulation threshold. Using an optimized binary search algorithm, the entire process can be completed in seconds. This minimum radial distance is used as the adaptive boundary frequency radius of the spectral energy distribution. By automatically calculating the boundary frequency radius, it can adapt to original remote sensing images with different resolutions and pollution characteristics, without requiring manual parameter pre-adjustment. This is determined by the normalized cumulative energy distribution curve. The boundary frequency effectively avoids the influence of individual high-frequency noise points on the separation results. A frequency domain mask map is constructed, which includes a low-frequency mask and a high-frequency mask. The low-frequency mask is constructed by setting the mask value of the corresponding point to 1 when the radial distance of the frequency point is less than or equal to the adaptive boundary frequency radius, and otherwise setting it to 0. The high-frequency mask is the complementary region of the low-frequency mask. The mask value of each frequency point in the high-frequency mask is 1 minus the low-frequency mask value at the corresponding position. The centered spectrum map is multiplied point by point with the low-frequency mask and the high-frequency mask respectively to extract the low-frequency and high-frequency components in the spectrum map.

[0056] In some examples, the first high-frequency component contains detailed features such as edges and textures of the original remote sensing image, which are easily affected by noise. By dynamically adjusting the gain coefficient by calculating the proportion of high-frequency energy, noise can be suppressed while enhancing detailed features.

[0057] Therefore, step S2 involves sharpening and enhancing the first high-frequency component, specifically including: inputting the centered spectrum obtained in step S1, calculating the squared modulus of each frequency point in the centered spectrum, summing the squared modulus of all frequency points to obtain the total energy of the centered spectrum; based on the global distribution characteristics of the spectrum energy, constructing a base gain as the core adjustment factor for enhancing the first high-frequency component, and introducing a nonlinear mapping function to achieve adaptive enhancement of high-frequency energy while avoiding excessive noise enhancement caused by direct linear amplification; inputting the high-frequency mask and high-frequency component obtained in step S1, calculating the energy of each frequency point in the first high-frequency component, weighting the energy of each frequency point using the high-frequency mask, summing the weighted energies of all frequency points to obtain the total energy of the first high-frequency component, calculating the ratio of the total energy of the high-frequency component to the total energy of the centered spectrum to obtain the proportion of the first high-frequency energy, and constructing a base gain based on the proportion of the high-frequency energy. The mathematical model of the base gain is as follows: ;in, It is the base gain. It is the global high-frequency gain weighting coefficient. It is the total energy of the first high-frequency component. It is the total energy of the above-mentioned centralized spectrum diagram. It is a nonlinear adjustment index for high-frequency components to control the nonlinear characteristics of the mapping from the proportion of the first high-frequency energy to the gain; a local intensity term is constructed to achieve non-uniform enhancement of the first high-frequency component. By quantifying the deviation of each frequency point in the first high-frequency component from the high-frequency mean, the significant edge and texture features of the original remote sensing image are adaptively enhanced. The amplitude mean of all frequency points in the first high-frequency component is calculated to obtain the high-frequency mean. For each frequency point in the first high-frequency component, the normalized ratio of the amplitude value of the frequency point to the high-frequency mean is calculated. The local intensity term is constructed based on the normalized ratio. The mathematical model of the local intensity term is: ;in, It is a local strength term. It is a local high-frequency enhancement weighting coefficient. It is the amplitude value of the frequency point in the first high-frequency component mentioned above. It is the above high-frequency average. It is a very small constant. The gain coefficient is a local enhancement nonlinear adjustment index that determines the sensitivity and curve shape of high-frequency feature enhancement. It dynamically fuses the base gain and local intensity terms through a noise adaptive weighting mechanism, setting a noise threshold parameter. The noise threshold needs to be dynamically adjusted based on the spectral characteristics of the target pollutant in the soil. The energy variance of the high-frequency components is calculated as a noise assessment index, and an exponential noise suppression factor is constructed. Based on this factor, the base gain and local gain terms are adaptively weighted to obtain the gain coefficient. The mathematical model for the gain coefficient is as follows: ;in, It is the gain coefficient. It is the energy variance of the first high-frequency component. It is the noise threshold parameter; the first high-frequency component is adaptively sharpened according to the gain coefficient to obtain the second high-frequency component.

[0058] Furthermore, the first low-frequency component mainly reflects the overall brightness and contrast of the original remote sensing image, but there are areas with radiometric anomalies or excessive smoothing. By constructing a dynamic compression kernel term using the Tukey dual-weight function, outliers deviating from the low-frequency mean can be adaptively suppressed while preserving smooth transition features. In step S2, the contrast of the first low-frequency component is adjusted, specifically including: Input the low-frequency mask and the first low-frequency component obtained in step S1, calculate the mean and standard deviation of the amplitude at all frequency points in the low-frequency component, obtain the low-frequency mean and standard deviation, introduce the Tukey double-weight function to construct a dynamic compression kernel term, for each frequency point in the low-frequency component, realize the nonlinear adaptive optimization of the low-frequency component according to the degree of deviation of the low-frequency amplitude from the low-frequency mean, the mathematical model of the dynamic compression kernel term is: ;in, It is a dynamically compressed kernel term. It is the amplitude value at a frequency point in the low-frequency component. It is a low-frequency mean. It is the low-frequency standard deviation. This is a spectral deviation sensitivity factor, which dynamically adjusts the compression range and intensity of low-frequency components by setting a threshold. The amplitude of the first low-frequency component is extracted to obtain a low-frequency amplitude map. A differential operator is used to calculate the gradient amplitude value of each frequency point in the low-frequency amplitude map in the frequency domain direction, resulting in a frequency domain gradient map. A frequency gradient suppression term is constructed based on the frequency domain gradient map. The mathematical model of the frequency gradient suppression term is: ;in, It is a frequency gradient suppression term. It is a frequency domain gradient adjustment factor used to control the smoothing intensity of low-frequency components in the frequency domain gradient direction. This represents the gradient amplitude value at a frequency point in the low-frequency amplitude diagram. Multiplying the dynamic compression kernel term and the frequency gradient suppression term by a dot yields the dynamic compression coefficient. The mathematical model for the dynamic compression coefficient is as follows: ;in, It is a dynamic compression factor; the contrast of the low-frequency component is adjusted according to the dynamic compression factor to obtain the enhanced low-frequency component.

[0059] Furthermore, the spatial domain edge enhancement of the original remote sensing image extracts the edge intensity map using the Scharr operator and constructs a spatial weight matrix, which can highlight the edge and structural information in the original remote sensing image. Step S3 specifically includes: The original remote sensing image is input, and the Scharr operator is used to perform edge detection on the original remote sensing image. The horizontal gradient convolution kernel of the Scharr operator is used to perform convolution operation on the original remote sensing image to obtain the horizontal gradient component. The vertical gradient convolution kernel of the Scharr operator is used to perform convolution operation on the original remote sensing image to obtain the vertical gradient component. The square root of the sum of the squares of the horizontal and vertical gradient components is used to obtain the edge intensity of each pixel in the original remote sensing image. The edge intensities of all pixels in the original remote sensing image constitute an edge intensity map. Furthermore, the edge intensity map is normalized to construct a spatial weight matrix. The spatial weight matrix uses an S-shaped curve function to nonlinearly adjust the normalized edge intensity map, so that the weight of the edge region is close to 1 and the weight of the smooth region is close to 0.

[0060] Next, the spatial weight matrix is ​​multiplied point by point with the original remote sensing image to obtain the spatial domain edge enhancement image.

[0061] Furthermore, the frequency domain enhanced image and the spatial domain edge enhanced image improve the quality of the original remote sensing image from different angles, but each has its own emphasis. By constructing a joint mask image, the advantages of the two images can be dynamically mixed. Step S4 specifically includes: The enhanced spectrogram obtained in step S2 is input, and combined with the phase spectrum of the frequency domain representation obtained in step S1 to obtain the enhanced frequency domain representation. An inverse Fourier transform is performed on the enhanced frequency domain representation to obtain the frequency domain enhanced image. A frequency domain enhancement mask is constructed, and the frequency domain enhanced image is decomposed into Gaussian pyramids to generate image layers at different resolutions. Each layer is obtained through Gaussian filtering and downsampling. At each pyramid level, a Laplacian convolution kernel is used to perform convolution operations to obtain the Laplacian response matrix for each level. The response matrix of each layer is normalized, and the global histogram of the normalized response matrix is ​​calculated to determine the 25th percentile. and 75th percentile Calculate the upper threshold and lower threshold , , Regions with response values ​​greater than or equal to the upper threshold are classified as high-response regions, and high-response regions are assigned fixed weights. Regions with response values ​​between the upper and lower thresholds are classified as transition regions, and transition regions are mapped using linear weights. Regions with response values ​​less than or equal to the lower threshold are classified as smooth regions, and smooth regions are assigned a weight of 0. The spatial domain edge enhancement image obtained in step S3 is input, and a spatial domain edge enhancement mask is constructed. Circular LBP operators with radii of 1, 2, and 3 pixels are used to calculate multi-scale LBP maps. The three-scale LBP maps are then fused. For each pixel in the spatial domain edge enhancement image, the difference between the maximum and minimum gray values ​​in its 3×3 neighborhood is calculated. All differences are normalized to obtain a local contrast map. The multi-scale LBP map and the local contrast map are linearly combined with certain weights to obtain a feature map. The Ostu algorithm is used to automatically determine the optimal segmentation threshold. Based on the threshold, the feature map is segmented... Figure 2 Values ​​are assigned to regions with values ​​greater than a threshold, with the mask value set to 1, and the mask value set to 0 for the remaining regions. The constructed frequency domain enhancement mask and spatial domain edge enhancement mask are weighted and superimposed to obtain a joint mask. For each pixel, the frequency domain enhancement image and spatial domain edge enhancement image are dynamically mixed according to the weight values ​​of the joint mask to obtain a fused image.

[0062] Specifically, the fused image generates an adaptive compression factor map by fusing the brightness gradient map and the edge intensity map, which can dynamically adjust the contrast of different regions. Step S5 specifically includes: Input the fused image obtained in step S4, and use the Sobel operator to calculate the horizontal and vertical gradients of each pixel. Calculate the gradient magnitude of each pixel based on the horizontal and vertical gradients, and normalize the gradient magnitude of each pixel. The normalized gradient magnitudes of all pixels constitute the brightness gradient. Use the Scharr operator to perform edge detection on the fused image. Perform convolution operations on the fused image using horizontal and vertical gradient kernels to obtain the horizontal and vertical gradients. Calculate the edge intensity of each pixel based on the horizontal and vertical gradients, and normalize the edge intensity of each pixel. The edge intensity map is constructed by normalizing the edge intensity of all pixels. The brightness gradient map and edge intensity map are then linearly fused using set weights to obtain a fused feature map. This fused feature map is then Gaussian smoothed. Based on the smoothed feature map, an adaptive compression factor map is dynamically generated using an exponential function. For each pixel in the fused image, a fixed-size neighborhood window is set centered on each pixel. The average grayscale value of all pixels within the neighborhood window is calculated. Based on the adaptive compression factor map and the average grayscale value, the contrast of the fused image is dynamically adjusted to obtain the enhanced original remote sensing image.

[0063] For ease of understanding, Figure 3A schematic diagram of an original remote sensing image provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of an enhanced original remote sensing image provided in an embodiment of the present invention.

[0064] After the Figure 3 and Figure 4 As can be seen from the comparison, the enhanced original remote sensing image improves the detail clarity, contrast and edge sharpness of the original remote sensing image.

[0065] Example 3 Based on the above embodiments, Figure 5 This is a schematic diagram of a remote sensing image enhancement processing device for soil pollution observation provided in an embodiment of the present invention.

[0066] Depend on Figure 5 As seen, the device includes: The data acquisition module 31 is used to acquire raw remote sensing images for soil pollution observation.

[0067] Processing module 32 is used to perform a fast Fourier transform on the original remote sensing image to obtain the spectrum map corresponding to the original remote sensing image; and to extract the edge intensity map of the original remote sensing image using the Scharr operator to construct a spatial weight matrix; and to apply the spatial weight matrix to the original remote sensing image using the Hadamard product to obtain a spatial domain edge enhancement image; to enhance the spectrum map based on the first high-frequency component and the first low-frequency component in the spectrum map to obtain an enhanced spectrum map; to combine the enhanced spectrum map with the original phase spectrum of the original remote sensing image and perform an inverse Fourier transform to obtain a frequency domain enhancement image; and to fuse the frequency domain enhancement image and the spatial domain edge enhancement image to obtain a fused image.

[0068] The output module 33 is used to perform local contrast optimization processing on the fused image based on the brightness gradient map and edge intensity map of the fused image to obtain the final enhanced remote sensing image.

[0069] The data acquisition module 31, the processing module 32, and the output module 33 are connected in sequence.

[0070] In one embodiment, the processing module 32 is further configured to separate the first high-frequency component and the first low-frequency component in the spectrum; sharpen and enhance the first high-frequency component and adjust the contrast of the first low-frequency component to obtain a second high-frequency component and a second low-frequency component; and fuse and reconstruct the second high-frequency component and the second low-frequency component to obtain an enhanced spectrum.

[0071] In one embodiment, the processing module 32 is further configured to center the spectrum to obtain a centered spectrum; calculate the total energy of the centered spectrum; calculate the total energy of the first high-frequency component; construct a base gain based on the total energy of the first high-frequency component and the total energy of the centered spectrum; calculate the first amplitude mean of all frequency points in the first high-frequency component to obtain a high-frequency mean; construct a local intensity term based on the amplitude value of the frequency points and the high-frequency mean; and sharpen and enhance the first high-frequency component to obtain a second high-frequency component. The steps include: constructing a gain coefficient using the base gain and the local intensity term; and sharpening and enhancing the first high-frequency component using the gain coefficient to obtain a second high-frequency component.

[0072] In one embodiment, the processing module 32 is further configured to calculate the second amplitude mean and standard deviation of all frequency points in the first low-frequency component to obtain the low-frequency mean and low-frequency standard deviation; construct a dynamic compression kernel term based on the Tukey double weight function and the low-frequency mean and low-frequency standard deviation; calculate the frequency domain gradient map of the first low-frequency component; and adjust the contrast of the first low-frequency component using the dynamic compression coefficient to obtain the second low-frequency component.

[0073] In one embodiment, the processing module 32 is further configured to determine a frequency domain enhancement mask based on the frequency domain enhancement image; and determine a spatial domain edge enhancement mask based on the spatial domain edge enhancement image; construct a joint mask based on the frequency domain enhancement mask and the spatial domain edge enhancement mask based on a first preset weight parameter; and fuse the frequency domain enhancement image and the spatial domain edge enhancement image based on the joint mask to obtain the fused image.

[0074] In one embodiment, the output module 33 is further configured to generate an adaptive compression factor map based on the brightness gradient map and edge intensity map of the fused image; and to perform local contrast optimization on the fused image using the adaptive compression factor map to obtain the final enhanced remote sensing image.

[0075] In one embodiment, the output module 33 is further configured to linearly fuse the brightness gradient map and the edge intensity map based on preset weight parameters to obtain a fused feature map; smooth the fused feature map and dynamically generate the adaptive compression factor map through a preset exponential function.

[0076] The remote sensing image enhancement processing device for soil pollution observation provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the embodiments of the remote sensing image enhancement processing device for soil pollution observation can be referred to the corresponding content in the aforementioned method embodiment.

[0077] Example 4 This embodiment provides an electronic device, including a processor and a memory. The memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the steps of a method for detecting defects in municipal pipelines.

[0078] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of a method for detecting defects in municipal pipelines.

[0079] See Figure 6 The diagram shows the structure of an electronic device, which includes a memory 41 and a processor 42. The memory 41 stores a computer program that can run on the processor 42. When the processor executes the computer program, it implements the steps provided by the aforementioned defect detection method for municipal pipelines.

[0080] like Figure 6 As shown, the device also includes a bus 43 and a communication interface 44, with the processor 42, the communication interface 44 and the memory 41 connected via the bus 43; the processor 42 is used to execute executable modules, such as computer programs, stored in the memory 41.

[0081] The memory 41 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this device network element and at least one other network element is achieved through at least one communication interface 44 (which may be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc.

[0082] Bus 43 can be an ISA bus, PCI bus, or EISA bus, etc. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, Figure 6 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0083] The memory 41 stores the program, and the processor 42 executes the program after receiving the execution instruction. The method performed by the defect detection device for municipal pipelines disclosed in any of the foregoing embodiments of the present invention can be applied to the processor 42, or implemented by the processor 42. The processor 42 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor 42 or by instructions in the form of software. The processor 42 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this invention can be directly manifested as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 41, and processor 42 reads information from memory 41 and, in conjunction with its hardware, completes the steps of the above method.

[0084] Furthermore, this embodiment of the invention also provides a machine-readable storage medium storing machine-executable instructions. When these machine-executable instructions are invoked and executed by the processor 42, they cause the processor 42 to implement the aforementioned defect detection method for municipal pipelines.

[0085] The electronic devices and computer-readable storage media provided in the embodiments of the present invention have the same technical features, so they can also solve the same technical problems and achieve the same technical effects.

[0086] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

Claims

1. A method for enhancing remote sensing images used for soil pollution observation, characterized in that, include: Acquire raw remote sensing images of soil pollution; Perform a fast Fourier transform on the original remote sensing image to obtain the spectrum corresponding to the original remote sensing image; Furthermore, the edge intensity map of the original remote sensing image is extracted using the Scharr operator to construct a spatial weight matrix; and the spatial weight matrix is ​​applied to the original remote sensing image using the Hadamard product to obtain a spatial domain edge-enhanced image. Based on the first high-frequency component and the first low-frequency component in the spectrum, the spectrum is enhanced to obtain an enhanced spectrum. The enhanced spectrogram is combined with the original phase spectrum of the original remote sensing image, and an inverse Fourier transform is performed to obtain a frequency domain enhanced image. The frequency domain enhanced image and the spatial domain edge enhanced image are fused to obtain a fused image; Based on the brightness gradient map and edge intensity map of the fused image, local contrast optimization processing is performed on the fused image to obtain the final enhanced remote sensing image.

2. The method for enhancing remote sensing images for soil pollution observation according to claim 1, characterized in that, The step of enhancing the spectrum based on the first high-frequency component and the first low-frequency component in the spectrum to obtain an enhanced spectrum includes: Separate the first high-frequency component and the first low-frequency component in the spectrum; The first high-frequency component is sharpened and enhanced, and the contrast of the first low-frequency component is adjusted to obtain the second high-frequency component and the second low-frequency component. The second high-frequency component and the second low-frequency component are fused and reconstructed to obtain the enhanced spectrum.

3. The method for enhancing remote sensing images for soil pollution observation according to claim 2, characterized in that, Before the step of sharpening and enhancing the first high-frequency component, the method includes: The spectrum is centered to obtain a centered spectrum. Calculate the total energy of the centered spectrum; Calculate the total energy of the first high-frequency component; The basic gain is constructed based on the total energy of the first high-frequency component and the total energy of the centered spectrum. Calculate the first amplitude mean of all frequency points in the first high-frequency component to obtain the high-frequency mean; Based on the amplitude value at the frequency point and the high-frequency mean, a local intensity term is constructed; The step of sharpening and enhancing the first high-frequency component to obtain the second high-frequency component includes: The gain coefficients are constructed using the base gain and the local intensity terms. The first high-frequency component is sharpened and enhanced using the gain coefficient to obtain the second high-frequency component.

4. The method for enhancing remote sensing images for soil pollution observation according to claim 3, characterized in that, The fundamental gain is expressed by the following formula: ； in, It is the base gain. It is the global high-frequency gain weighting coefficient. It is the total energy of the first high-frequency component. It is the total energy of the centralized spectrum. It is the nonlinear adjustment index of the high-frequency component; The local strength term is expressed by the following formula: ； in, It is a local strength term. It is a local high-frequency enhancement weighting coefficient. It is the amplitude value of the frequency point in the first high-frequency component. It is the high-frequency mean. It is a very small constant. It is a locally enhanced nonlinear adjustment index; The gain coefficient is expressed by the following formula: in, It is the gain coefficient, It is the energy variance of the first high-frequency component. It is the noise threshold parameter.

5. The method for enhancing remote sensing images for soil pollution observation according to claim 2, characterized in that, Before the step of contrast adjustment of the first low-frequency component, the method includes: Calculate the second amplitude mean and standard deviation of all frequency points in the first low-frequency component to obtain the low-frequency mean and low-frequency standard deviation; Based on the Tukey double-weight function, a dynamic compression kernel term is constructed according to the low-frequency mean and the low-frequency standard deviation; Calculate the frequency domain gradient plot of the first low-frequency component; Based on the frequency domain gradient plot, a frequency gradient suppression term is constructed; Multiply the dynamic compression kernel term and the frequency gradient suppression term by the dot product to obtain the dynamic compression coefficient; The step of adjusting the contrast of the first low-frequency component includes: The contrast of the first low-frequency component is adjusted using the dynamic compression coefficient to obtain the second low-frequency component.

6. The method for enhancing remote sensing images for soil pollution observation according to claim 5, characterized in that, The dynamic compression kernel term is expressed by the following formula: in, It is the aforementioned dynamic compression kernel term. It is the amplitude value at a frequency point in the first low-frequency component. It is the low-frequency mean. It is the low-frequency standard deviation, It is a spectral deviation sensitive factor; The frequency gradient suppression term is expressed by the following formula: ； in, It is the frequency gradient suppression term. It is a frequency domain gradient adjustment factor. It is the gradient amplitude value of the frequency point in the low-frequency amplitude diagram corresponding to the first low-frequency component.

7. The method for enhancing remote sensing images for soil pollution observation according to claim 1, characterized in that, The step of fusing the frequency domain enhanced image and the spatial domain edge enhanced image to obtain a fused image includes: Based on the frequency domain enhanced image, a frequency domain enhanced mask is determined; and based on the spatial domain edge enhanced image, a spatial domain edge enhanced mask is determined. Based on the first preset weight parameters, a joint mask map is constructed according to the frequency domain enhancement mask map and the spatial domain edge enhancement mask map; The frequency domain enhanced image and the spatial domain edge enhanced image are fused based on the joint mask image to obtain the fused image.

8. The method for enhancing remote sensing images for soil pollution observation according to claim 1, characterized in that, The steps of performing local contrast optimization processing on the fused image based on the brightness gradient map and edge intensity map of the fused image to obtain the final enhanced remote sensing image include: An adaptive compression factor map is generated based on the brightness gradient map and edge intensity map of the fused image; The fused image is then subjected to local contrast optimization using the adaptive compression factor map to obtain the final enhanced remote sensing image.

9. The method for enhancing remote sensing images for soil pollution observation according to claim 8, characterized in that, The step of generating an adaptive compression factor map based on the brightness gradient map and edge intensity map of the fused image includes: Based on preset weight parameters, the brightness gradient map and the edge intensity map are linearly fused to obtain a fused feature map; The fused feature map is smoothed, and the adaptive compression factor map is dynamically generated using a preset exponential function.

10. An enhancement processing device for remote sensing images used for soil pollution observation, characterized in that, include: The data acquisition module is used to acquire raw remote sensing images for soil pollution observation. The processing module is used to perform a fast Fourier transform on the original remote sensing image to obtain the spectrum map corresponding to the original remote sensing image; and to extract the edge intensity map of the original remote sensing image through the Scharr operator to construct a spatial weight matrix; and to apply the spatial weight matrix to the original remote sensing image through the Hadamard product to obtain a spatial domain edge enhancement image. Based on the first high-frequency component and the first low-frequency component in the spectrum, the spectrum is enhanced to obtain an enhanced spectrum. The enhanced spectrogram is combined with the original phase spectrum of the original remote sensing image, and an inverse Fourier transform is performed to obtain a frequency domain enhanced image. The frequency domain enhanced image and the spatial domain edge enhanced image are fused to obtain a fused image; The output module is used to perform local contrast optimization processing on the fused image based on the brightness gradient map and edge intensity map of the fused image to obtain the final enhanced remote sensing image.

Images