A SAR water depth inversion method driven by variable window sliding segmentation

Abstract

The present invention discloses a SAR water depth inversion method driven by variable window sliding segmentation, which belongs to the field of synthetic aperture radar technology and is used for water depth inversion, including image segmentation and water depth inversion. Image segmentation includes regular adjustment of the original image, information storage, coastline identification and noise processing, pixel extreme value judgment, determination of pixel change function, and window sliding. After extracting the coastline and determining the starting point, the pixels are expanded to both sides of the starting point on the coastline and the pixels invaded by the coastline are eliminated, thereby improving the utilization of nearshore images. By dynamically adjusting the pixel size, a more accurate surge wavelength is obtained. Compared with the existing technology, the present invention accurately extracts wavelength information of different regions, avoids complex manual judgment, and improves segmentation efficiency and inversion accuracy. For irregular coastlines, the utilization rate of water depth inversion of images in areas near the coastline is increased by changing the starting point along the coastline and expanding outward.

Description

Technical Field

[0001] The invention discloses a SAR water depth inversion method driven by variable window sliding segmentation, and belongs to the technical field of synthetic aperture radar. Background Art

[0002] Water depth inversion is a crucial research topic in marine geology and marine resource development. With the continuous advancement of marine science and technology and the increasing demand for its applications, water depth inversion has become a key technology in ocean mapping, marine resource exploration, and marine environmental monitoring. Synthetic Aperture Radar (SAR), as a remote sensing method, has demonstrated unique advantages and broad application prospects in water depth inversion.

[0003] Traditional methods for measuring water depth primarily include plumb-bar depth and sonar depth. Plumb-bar depth measurement involves sinking a weight to the seafloor to measure depth. While simple, it is inefficient and suitable for local measurements in shallow waters. Sonar depth measurement utilizes the propagation characteristics of sound waves in water and is categorized into single-beam and multi-beam sonar. Single-beam sonar has limited coverage and low efficiency, while multi-beam sonar offers greater range and high-precision measurements, but the equipment is expensive and complex to operate. Furthermore, while sidescan sonar is primarily used for seafloor topography mapping, it can also assist in water depth measurement. With the advancement of remote sensing technology, water depth inversion methods are gaining increasing attention. Optical remote sensing uses multispectral imagery acquired by satellites or aircraft and combines it with empirical models to estimate water depth. While suitable for clear, shallow waters, it is susceptible to the effects of water transparency and suspended matter. Laser depth measurement uses airborne laser sounders to measure water depth using laser pulses. It is suitable for high-precision measurements in shallow waters and along coastlines, but is limited by water depth, has expensive equipment, and is complex to operate. Although these methods have achieved certain results in water depth measurement, their respective limitations are also obvious.

[0004] With the development and application of SAR technology, using SAR data for water depth inversion has become a new and effective method. SAR technology transmits and receives microwave signals, enabling it to obtain surface reflection signals, regardless of weather, time, or lighting conditions, and thereby derive information about sea surface characteristics. Compared to optical remote sensing, SAR technology offers all-weather, all-day, and all-weather observation capabilities, making it particularly suitable for ocean areas with poor atmospheric transparency or severe cloud cover. Therefore, using SAR technology for water depth inversion overcomes the limitations of traditional bathymetric methods due to natural conditions, enabling efficient and accurate detection of ocean depth.

[0005] In the study of water depth inversion, SAR technology primarily obtains water depth information by analyzing reflected signals from the ocean surface. Because water depth is related to factors such as surface waves and tides, the distribution of water depth can be deduced by analyzing wave characteristics and reflection intensity in SAR images. Traditional inversion methods rely on a series of complex physical equations and radar backscatter models, directly inverting the SAR imaging process to invert shallow-water topography. This approach performs well in areas with continuously undulating seafloor topography. However, it places stringent demands on SAR image quality. In practical applications, the complexity of the ocean environment and the influence of SAR image noise limit its application. While theoretically innovative, methods based on the interaction of strong tidal currents and local seafloor topography face challenges in their widespread application due to computational complexity, sensitivity to initial water depth accuracy, and relatively low detection resolution. Therefore, in the field of shallow-water topography inversion, continuous exploration of new technologies and methods is necessary to improve the accuracy and reliability of inversion. Currently, water depth inversion, relying on the refraction of long surface gravity waves propagating toward the coast and the effects of shallow water, is gaining increasing application by establishing a direct relationship between surge and water depth. With the development of spaceborne SAR technology, SAR satellite data is increasingly being used for shallow-water topography exploration. Water depth inversion has achieved excellent results by calculating wave information through fast Fourier transforms and combining them with linear dispersion relations. Data from satellites such as ERS-2, RESAT-1, HJ-1C SAR, and Sentinel-2 have also been used in water depth exploration experiments. These studies have demonstrated the feasibility of detecting water depth based on surge characteristics and linear dispersion relations.

[0006] Using a linear dispersion relationship to obtain water depth improves the accuracy and efficiency of SAR data in water depth inversion. However, when dealing with areas with uneven seafloor topography, this method requires more sophisticated algorithms and parameter settings to improve the accuracy of wavelength and water depth inversion. The key to using a linear dispersion relationship to invert water depth is to accurately obtain wave wavelength information. The size of the image element and the segmentation method play a key role in the wavelength extraction process. In previous studies, the size of the image element has rarely been accurately determined, typically given as 5-10 times the wavelength. However, wavelength changes with water depth, and applying a fixed image element size to the entire remote sensing image is unacceptable. Reliance on experience is often required, reducing the accuracy and efficiency of the method. In addition, human activities and irregular coastlines lead to difficulties in image element segmentation in nearshore areas, making this method difficult to apply to areas with irregular coastline changes.

[0007] To address these issues, the present invention proposes a SAR water depth inversion method based on variable window image element segmentation. This method dynamically adjusts the size of image elements when segmenting remote sensing images, determines pixel changes based on linear functions, the Atanh function, and its symmetric functions, accurately extracting wavelength information from different regions. Summary of the Invention

[0008] The purpose of the present invention is to provide a SAR water depth inversion method based on variable window image element segmentation to solve the problems in the prior art of complex manual judgment, low efficiency of pixel segmentation, low water depth inversion accuracy, and low utilization rate of water depth inversion of remote sensing images near the coastline.

[0009] A SAR water depth inversion method driven by variable window sliding segmentation includes image segmentation and water depth inversion;

[0010] Image segmentation includes regular adjustment of original image, information storage, coastline recognition and noise processing, pixel extreme value judgment, determination of pixel change function, and window sliding.

[0011] The regularization adjustment of the original image includes adjusting the irregular remote sensing image, eliminating the edge null values, and obtaining a regular image to improve the water depth accuracy of the image edge inversion.

[0012] Information storage includes using software to store remote sensing images as intensity information matrices and position information matrices.

[0013] Coastline identification and noise processing include using software or programs to identify the coastline and coastal obstacles in remote sensing images, avoid introducing external interference, and determine the shape of the coastline; the noise part is reduced by averaging the surrounding pixels to reduce inversion errors.

[0014] The pixel extreme value judgment includes that the pixel size gradually increases from the coastline to the open sea, with the minimum pixel being 50*50 pixels and the maximum being 400*400 pixels.

[0015] Determining the pixel change function includes determining the pixel change process from minimum to maximum based on three functions, namely, linear function, inverse hyperbolic tangent Atanh function, and symmetric function of inverse hyperbolic tangent Atanh with respect to the linear function.

[0016] Window sliding involves determining a starting point on the coastline, expanding pixels on both sides of the starting point on the coastline, and removing pixels invaded by the coastline to improve the utilization of nearshore images.

[0017] After determining the starting point on the coastline, pixel segmentation is performed along the x-direction on the coastline with a sliding step of 25 pixels. When the image segmentation reaches the end, the next starting point moves along the y-direction on the coastline, and then the coastline identification and noise processing, pixel extreme value judgment, and pixel change function are repeated.

[0018] The water depth inversion includes the wavelength λ as:

[0019] λ=λ0tanh(kh);

[0020]

[0021] Where λ0 is the intermediate parameter, tanh() is the hyperbolic tangent function, k is the wave number, h is the seabed depth, g is the gravitational acceleration, and T is the wave period.

[0022] The water depth inversion includes ignoring the mean flow, and the sea depth is:

[0023]

[0024] Where Αtanh() is the inverse hyperbolic tangent function.

[0025] The wavelength of the segmented pixels is obtained by using two-dimensional Fourier transform, and the longitude and latitude information of the pixel center is recorded synchronously. The wavelength is used to invert the water depth, and the water depth inversion result is filtered using a Gaussian filter.

[0026] Compared with the existing technology, the present invention has the following beneficial effects: it accurately extracts wavelength information of different areas, avoids complex manual judgment, and improves segmentation efficiency and inversion accuracy; for irregular coastlines, by changing the starting point along the coastline and expanding outward, it increases the utilization rate of image water depth inversion in areas near the coastline. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a Gaofen-3 SAR remote sensing image;

[0028] Figure 2 It is to separate the coastline in the remote sensing image to obtain a curve graph;

[0029] Figure 3 This is the first way to divide the curved coastline;

[0030] Figure 4 This is the second curved coastline segmentation diagram;

[0031] Figure 5 This is a diagram of the segmentation method at the critical position where the coastline protrudes outward;

[0032] Figure 6This is a diagram showing the first curved coastline segmentation method, which results in reduced resolution.

[0033] Figure 7 This is a diagram showing the situation where the second curved coastline segmentation method results in reduced resolution;

[0034] Figure 8 This is a diagram of the division method of the critical position of the coastline sinking inward;

[0035] Figure 9 This is the wavelength inversion result image after 50*50 pixel processing;

[0036] Figure 10 This is the wavelength inversion result image after 100*100 pixel processing;

[0037] Figure 11 This is the wavelength inversion result image after 150*150 pixel processing;

[0038] Figure 12 This is the wavelength inversion result image after 200*200 pixel processing;

[0039] Figure 13 This is the wavelength inversion result image after 300*300 pixel processing;

[0040] Figure 14 This is the wavelength inversion result image after 400*400 pixel processing;

[0041] Figure 15 This is the water depth inversion result map after 50*50 pixel processing;

[0042] Figure 16 This is the water depth inversion result map after 100*100 pixel processing;

[0043] Figure 17 This is the water depth inversion result map after 150*150 pixel processing;

[0044] Figure 18 This is the water depth inversion result map after 200*200 pixel processing;

[0045] Figure 19 This is the water depth inversion result map after 300*300 pixel processing;

[0046] Figure 20 This is the water depth inversion result map after 400*400 pixel processing;

[0047] Figure 21 This is the result of wavelength calculation using a linear function;

[0048] Figure 22 This is the result of wavelength calculation using the Atanh function;

[0049] Figure 23 This is the result of wavelength calculation using the symmetrical Atanh function;

[0050] Figure 24 This is the water depth inversion result diagram after linear function processing;

[0051] Figure 25 This is the water depth inversion result diagram after processing with the Atanh function;

[0052] Figure 26 This is the water depth inversion result diagram after processing with the symmetrical Atanh function;

[0053] Figure 27 is the root mean square error diagram of the inversion results at different water depths after sliding window processing;

[0054] Figure 28 It is a numerical statistical graph of water depth using the Atanh segmentation function;

[0055] Figure 29 It is a map of the east-west gradient of water depth;

[0056] Figure 30 This is a map of the north-south gradient of water depth. DETAILED DESCRIPTION

[0057] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention are described clearly and completely below. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0058] A SAR water depth inversion method driven by variable window sliding segmentation includes image segmentation and water depth inversion;

[0059] Image segmentation includes regular adjustment of original image, information storage, coastline recognition and noise processing, pixel extreme value judgment, determination of pixel change function, and window sliding.

[0060] The regularization adjustment of the original image includes adjusting the irregular remote sensing image, eliminating the edge null values, and obtaining a regular image to improve the water depth accuracy of the image edge inversion.

[0061] Information storage includes using software to store remote sensing images as intensity information matrices and position information matrices.

[0062] Coastline identification and noise processing include using software or programs to identify the coastline and coastal obstacles in remote sensing images, avoid introducing external interference, and determine the shape of the coastline; the noise part is reduced by averaging the surrounding pixels to reduce inversion errors.

[0063] The pixel extreme value judgment includes that the pixel size gradually increases from the coastline to the open sea, with the minimum pixel being 50*50 pixels and the maximum being 400*400 pixels.

[0064] Determining the pixel change function includes determining the pixel change process from minimum to maximum based on three functions, namely, linear function, inverse hyperbolic tangent Atanh function, and symmetric function of inverse hyperbolic tangent Atanh with respect to the linear function.

[0065] Window sliding involves determining a starting point on the coastline, expanding pixels on both sides of the starting point on the coastline, and removing pixels invaded by the coastline to improve the utilization of nearshore images.

[0066] After determining the starting point on the coastline, pixel segmentation is performed along the x-direction on the coastline with a sliding step of 25 pixels. When the image segmentation reaches the end, the next starting point moves along the y-direction on the coastline, and then the coastline identification and noise processing, pixel extreme value judgment, and pixel change function are repeated.

[0067] The water depth inversion includes the wavelength λ as:

[0068] λ=λ0tanh(kh);

[0069]

[0070] Where λ0 is the intermediate parameter, tanh() is the hyperbolic tangent function, k is the wave number, h is the seabed depth, g is the gravitational acceleration, and T is the wave period.

[0071] The water depth inversion includes ignoring the mean flow, and the sea depth is:

[0072]

[0073] Where Αtanh() is the inverse hyperbolic tangent function.

[0074] The wavelength of the segmented pixels is obtained by using two-dimensional Fourier transform, and the longitude and latitude information of the pixel center is recorded synchronously. The wavelength is used to invert the water depth, and the water depth inversion result is filtered using a Gaussian filter.

[0075] The experimental sea area was selected as an area with a tortuous coastline and complex terrain. The experimental data was selected from the fine strip 1 in the strip imaging mode of the Gaofen-3 satellite, with a resolution of 5m and a width of 50km, with dual polarization.

[0076] Gaofen-3 SAR remote sensing images such as Figure 1 As shown in the figure, the coastline processing method is to first separate the coastline in the remote sensing image to obtain a curve, such as Figure 2 shown. Figure 3 It is the first way to divide the curved coastline. Figure 4 This is the second way to divide the curved coastline. Figure 5 This is the segmentation method for the critical position where the coastline protrudes outward. After determining the starting point on the coastline, in order to make full use of the image information, the starting point is extended to the upper right and lower right to form a pixel, and it is judged whether the coastline invades the interior of the pixel. If it does, the pixel is removed. In fact, in order to avoid the coastline invading the pixel, different expansion methods were considered according to the inclination of the coastline. However, this method will lead to segmentation gaps when there are inflection points on the coastline. Figure 6 This is the case where the first curved coastline segmentation method results in a reduction in resolution. Figure 7 This is the case where the second curved coastline segmentation method results in reduced resolution. This problem can be solved by extending the starting point image upward and downward at the inflection point, but this requires identifying the inflection point, which increases complexity. Therefore, the method of extending each starting point image in two directions is adopted. This method is more efficient and convenient, and can also avoid the errors introduced by the complete intrusion of the coastline in a timely manner. Figure 8 It is a way to divide the critical position of the coastline into inward depressions.

[0077] To invert water depth over a large area, a remote sensing image must be segmented into multiple small pixels, and then the pixels must be processed individually to obtain the corresponding water depth. However, the change in water depth is relatively small compared to remote sensing images with wider swaths, which requires manual selection of pixel size during image segmentation, reducing the inversion efficiency. Therefore, pixel size is the premise and basis for water depth inversion and plays a decisive role in its accuracy.

[0078] Given that the wavelength of surface swells and waves in shallow waters is positively correlated with water depth, the pixel size should also vary during segmentation. Previous segmentation methods were often fixed or manually determined, significantly reducing efficiency. Such ambiguous segmentation methods often make it difficult to replicate the results when using swells to infer water depth. Therefore, a variable window sliding segmentation method is proposed for segmenting remote sensing images.

[0079] First, six fixed windows were selected to perform water depth inversion in the experimental sea area. On the one hand, the inaccuracy of the fixed window inversion was observed, and on the other hand, the appropriate range of the window was determined. The wavelength inversion results after 50*50 pixel processing are as follows: Figure 9 As shown, the wavelength inversion results after 100*100 pixel processing are as follows Figure 10 As shown, the wavelength inversion results after 150*150 pixel processing are as follows Figure 11 As shown, the wavelength inversion results after 200*200 pixel processing are as follows Figure 12 As shown, the wavelength inversion results after 300*300 pixel processing are as follows Figure 13As shown, the wavelength inversion results after 400*400 pixel processing are as follows Figure 14 When the window is small, the wavelength calculation resolution effect is better in shallow water areas (near the coastline), but as the distance from the coastline increases, the wavelength resolution effect becomes worse. Figure 9 A very obvious phenomenon can be observed in the green area in the figure. As the fixed window gradually increases, the wavelength of the area far from the coast gradually becomes distinguishable. Although the wavelength of the nearshore area has a certain resolving power, the wavelength is larger than the calculated result of the small window. The wavelength of the nearshore surge is shorter, and its spatial variation is also faster. A window that is too large contains too much image information, and of course it also contains more wavelength information, which is obviously inaccurate for obtaining the wavelength of the surge in the nearshore area. When far away from the coast, the wavelength of the surge is longer. If the window is too small, a window cannot even contain a complete wave cycle. Therefore, a small window must be used near the coast, and a larger window must be used far away from the coast, which also reflects the necessity of a dynamically changing window in the proposed method.

[0080] It can be observed that as the window increases, the left boundary of the calculation area is also moving away from the coastline, and the boundary line of the left boundary is deformed, which is quite different from the original coastline. When the window is too large and expands outward, the center point of the window near the coastline is further away from the coastline, causing the left boundary of the inversion area to shift to the right. The reason for the deformation is that the larger the window is, the greater the distance between the center points of each window is under a fixed sliding step size, the boundary resolution is weaker, and the coastline is deformed. This situation will not occur if a smaller window is used. In addition, the proposed outward expansion method is also used when using fixed window separation. This method can roughly give an irregular coastline even with an inappropriate window. In previous studies, the water depth near the coastline is usually smoothed into a curve.

[0081] The calculated wavelength is used to invert the water depth. The water depth inversion result after 50*50 pixel processing is as follows: Figure 15 As shown, the water depth inversion results after 100*100 pixel processing are as follows Figure 16 As shown, the water depth inversion results after 150*150 pixel processing are as follows Figure 17 As shown, the water depth inversion results after 200*200 pixel processing are as follows Figure 18 As shown, the water depth inversion results after 300*300 pixel processing are as follows Figure 19 As shown, the water depth inversion results after 400*400 pixel processing are as follows Figure 20As shown in the figure. Results from smaller window inversions generally show smaller depth inversion results. This is because the wavelength is smaller in areas far from the coastline, resulting in a smaller fixed wavelength and a smaller overall inversion result. As the window size increases, the depth in areas far from the coast gradually returns to normal, and the depth inversion range increases, closer to the actual situation. However, the problems with wavelength calculation persist in the depth inversion results. When the window size is larger, the spatial resolution of the inversion results also decreases, making it easier to distinguish the shape of the coastline. Therefore, the fixed window segmentation method inevitably brings about multiple problems, both in terms of inversion accuracy and spatial resolution. If human judgment is made, different remote sensing image segmentation methods will consume a lot of manpower and material resources.

[0082] The wavelength calculation under the sliding variable window segmentation method is used, and the linear function wavelength calculation results are as follows Figure 21 As shown, the wavelength calculation results using the Atanh function are as follows Figure 22 As shown, the wavelength calculation results using the symmetrical Atanh function are as follows Figure 23 As shown in the figure, the coastline is close to the coastline identified in the remote sensing imagery, as the left boundary of the inversion region remains unchanged in all three cases. Regarding the calculated wavelength, the sliding variable window method provides more accurate wavelength information for the entire region compared to the fixed window segmentation method. The wavelength is smaller near the coast and gradually increases farther from the coast. The coastline shape remains unchanged in all three cases.

[0083] The water depth distribution was obtained by inverting the calculated wavelength and compared with the water depth results of the fixed window. Figure 24 is the water depth inversion result after linear function processing, Figure 25 is the water depth inversion result after Atanh function processing, Figure 26The inversion results are obtained after processing with a symmetric Atanh function. Compared with small-window segmentation, the inversion results obtained using the three varying functions also show significant resolution in water depths far from shore. Compared with larger windows, the inversion results using the three varying functions exhibit higher resolution at the coastline, not only avoiding boundary shifts but also maintaining good resolution. Overall, the inversion results using the variable window sliding segmentation inherit the advantages of both small and large windows, and the dynamically changing window allows the segmented image to better adapt to the wavelength information in different regions. This results in more detailed spatial distribution of the inverted water depth compared to fixed-window processing. The wavelength inversion results obtained using the sliding window processing show smoother depth variations, while the wavelength inversion results obtained using the fixed window processing show significant variations. Manually changing the window is also possible, but it is highly dependent on operator expertise and is time-consuming, especially for wider swaths and long time series. Therefore, the proposed method effectively addresses these issues.

[0084] The overall distribution of water depth is similar to that of the reanalysis data, but the maximum spatial resolution of the inverted water depth reaches 5.5 m, which is very important for inverting water depth near the coastline. To better demonstrate the reliability of the inversion, the inversion results were positionally aligned with the ETOPO1 data, as the spatial resolutions of the two are different. The water depth inversion results after sliding window and fixed window processing were compared using the linear function, the Atanh function, and the symmetric Atanh function, respectively. Comparison of the two data sets revealed that the coefficient of determination for the three inversion results was 0.98, the root mean square error (RMSE) was less than 6 m, the mean relative error (MRE) was less than 14%, and the mean absolute error (MAE) was less than 5 m. The inversion results of the three window variation curves showed relatively stable fits for water depths less than 50 m. When the water depth exceeded 50 m, the linear function curve showed a smaller inversion result, while the symmetric Atanh function curve showed a larger inversion result. Only the inversion result of the Atanh function curve has a better fitting degree than the first two, and its RMSE and MRE are the smallest among the three, which are 4.8m and 9.8%.

[0085] In order to observe the inversion capability of this method at different water depths, the inversion results are divided into ranges with an interval of 20m and an interval range of 1m to 100m. The root mean square error of the inversion results at different water depths after sliding window processing is shown in the figure below. Figure 27As shown. For relative error, the inversion results under the three window change functions show a large relative error between the water depth of 20m and 60m. Among them, the inversion result of the symmetrical Atanh is the worst, the inversion ability is unstable, and the relative error changes greatly. The inversion results of the linear function and Atanh are similar. For absolute error, as the water depth increases, the absolute error of the linear function inversion result gradually increases. The absolute error of the symmetrical Atanh and Atanh gradually decreases after the water depth is greater than 60m. Overall, the results obtained by the window transformation inversion corresponding to the Atanh function are better, which can also be seen in the RMSE change curve.

[0086] The specific inversion results of the three partitioning functions are shown in Table 1.

[0087] Table 1 Specific inversion results of three partitioning functions

[0088]

[0089]

[0090] In order to further analyze the inversion results, the inversion results of the Atanh function curve window transformation segmentation are taken out separately. The numerical statistics of the water depth under the Atanh segmentation function are shown in the figure below. Figure 28 As shown in the figure, after reducing the spatial resolution, the overall trend of the inversion results and the reanalysis data is more consistent. Statistics show that the maximum water depth in the experimental area is 92 meters, the minimum is 5 meters, and the average water depth is 37 meters. The inversion values mainly range from 10 meters to 50 meters. It is important to note that the number of inversion values is related to the water depth distribution characteristics of the experimental area and the window characteristics. Deeper water depths increase the window size and the data interval.

[0091] Calculate the gradient of water depth change and display the water depth change in the inversion result. Figure 29 As shown, the north-south gradient of water depth varies as follows Figure 30 As shown in Figure 2, the green solid and dashed lines frame the area with a larger gradient near the coastline, and the blue solid and dashed lines frame the area with a larger gradient far from the coastline. Figure 29 The figure shows the gradient change of water depth in the east-west direction. It can be clearly seen that not far from the shore, there is a strip with a more drastic change of water depth in the east-west direction ( Figure 29 The maximum water depth gradient is 9.2m / km. In addition, there are two circular areas with large gradients in the southeast of the experimental sea area ( Figure 29 It can also be found that the north-south gradient in the water depth inversion results has little change, such as Figure 30However, within the belt with sharp changes in the east-west gradient, there are three areas with sharp changes in the north-south direction ( Figure 30 (enclosed by a green dashed line). and Figure 29 Two areas of sharp north-south gradient change appear at the locations roughly aligned with the blue circles in the middle image. In the inversion results, these areas correspond to circular pits of varying depths. This, to some extent, illustrates the importance of improving spatial resolution in remote sensing inversion.

[0092] In fact, a SAR water depth inversion method driven by a variable window sliding segmentation has a wide range of applications in multiple real-world scenarios, including coastal management, maritime navigation, and disaster response. Through high-precision SAR water depth inversion technology, the water depth changes of the coastline can be regularly monitored to assess beach erosion and accumulation. For example, in erosion-prone coastline areas, it can help managers identify areas with severe erosion and formulate protection strategies accordingly. In addition, during maritime navigation, high-precision SAR water depth inversion technology can be used for route planning and obstacle detection. For example, the water depth of the channel can be accurately measured to ensure that ships avoid dangerous areas such as shoals and reefs during navigation.

[0093] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents, and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A SAR water depth inversion method driven by variable window sliding segmentation, characterized in that: Including image segmentation and water depth inversion; Image segmentation includes regularization and adjustment of original images, information storage, coastline recognition and noise processing, pixel extreme value judgment, determination of pixel change function, and window sliding; Pixel extreme value judgment includes that the pixel size gradually increases from the coastline to the offshore direction, with the minimum pixel being 50*50 pixels and the maximum being 400*400 pixels; Determining the pixel change function includes determining the pixel change process from minimum to maximum based on three functions, namely, linear function, inverse hyperbolic tangent Atanh function, and symmetric function of inverse hyperbolic tangent Atanh with respect to the linear function; Window sliding involves determining the starting point on the coastline, expanding pixels to the upper right and lower right of the starting point on the coastline, and removing pixels invaded by the coastline to improve the utilization of nearshore images. After determining the starting point on the coastline, pixel segmentation is performed along the x-direction on the coastline with a sliding step of 25 pixels. When the image segmentation reaches the end, the next starting point moves along the y-direction on the coastline, and then the coastline identification and noise processing, pixel extreme value judgment, and pixel change function are repeated.

2. The SAR water depth inversion method driven by variable window sliding segmentation according to claim 1 is characterized in that: The regularization adjustment of the original image includes adjusting the irregular remote sensing image, eliminating the edge null values, and obtaining a regular image to improve the depth accuracy of the image edge inversion.

3. The SAR water depth inversion method driven by variable window sliding segmentation according to claim 2 is characterized in that: Information storage includes using software to store remote sensing images as intensity information matrices and position information matrices.

4. The SAR water depth inversion method driven by variable window sliding segmentation according to claim 3 is characterized in that: Coastline identification and noise processing include using software or programs to identify the coastline and coastal obstacles in remote sensing images, avoid introducing external interference, and determine the shape of the coastline; the noise part is reduced by averaging the surrounding pixels to reduce inversion errors.

5. The SAR water depth inversion method driven by variable window sliding segmentation according to claim 4 is characterized in that: The water depth inversion includes the wavelength λ as: λ=λ0tanh(kh); Where λ0 is the intermediate parameter, tanh() is the hyperbolic tangent function, k is the wave number, h is the seabed depth, g is the gravitational acceleration, and T is the wave period.

6. The SAR water depth inversion method driven by variable window sliding segmentation according to claim 5 is characterized in that: The water depth inversion includes ignoring the mean flow, and the sea depth is: Where Αtanh() is the inverse hyperbolic tangent function.

7. The SAR water depth inversion method driven by variable window sliding segmentation according to claim 6 is characterized in that: The wavelength of the segmented pixels is obtained by using two-dimensional Fourier transform, and the longitude and latitude information of the pixel center is recorded synchronously. The wavelength is used to invert the water depth, and the water depth inversion result is filtered using a Gaussian filter.

Images