Sea ice extraction method based on multi-feature superpixel segmentation

Abstract

The invention provides a sea ice extraction method based on multi-feature superpixel segmentation, and the method comprises the steps: 1, obtaining a dual-polarized SAR image of a target sea area, executing the image preprocessing, and obtaining a preprocessed image; 2, backward heat dissipation coefficient features, standardized features, a morphological feature set, OTSU features and texture features are extracted from the preprocessed image and fused, and a multi-dimensional data feature set is obtained; step 3, segmenting the multi-dimensional data feature set by using an SNIC superpixel segmentation method to obtain a superpixel block set; and step 4, inputting the superpixel block set into a supervised and trained machine learning classifier, and classifying the seawater and the sea ice to extract the sea ice. According to the method, the sea ice classification precision and robustness can be effectively improved, a sea ice distribution feature set with the spatial resolution of 40 meters can be generated, and inter-annual and inter-monthly change monitoring of the north pole channel sea ice can be effectively supported.

Description

TECHNICAL FIELD

[0001] The present application relates to a sea ice extraction method based on multi-feature superpixel segmentation, belonging to the technical field of remote sensing image processing. BACKGROUND

[0002] At present, the extraction of sea ice information in the Arctic shipping route region mainly relies on optical remote sensing images or single-feature SAR data classification methods. These methods have great technical limitations in dealing with the complex and changeable ice conditions in this region. Among them, the traditional method based on optical remote sensing images relies heavily on the reflectivity difference between sea ice and seawater in a specific band (such as near-infrared). Although this method can identify sea ice under certain conditions, its feature set is relatively single, and it is subject to frequent cloud and fog cover and polar night phenomenon in the Arctic region, making it difficult to achieve continuous and effective all-weather monitoring, and unable to meet the high reliability requirements of sea ice information for the safety of Arctic shipping.

[0003] Compared with the traditional method based on optical remote sensing images, the single-feature SAR data classification method has the advantages of all-day and all-weather imaging, but still has some shortcomings. First, the inherent speckle noise of SAR images seriously interferes with the extraction of sea ice texture information, resulting in low classification accuracy based on single backscatter features. Second, the wide scanning characteristics of SAR systems cause the backscatter intensity to change significantly with the incident angle, and the same ground object shows significant differences under different imaging geometries, thereby increasing the difficulty of accurately distinguishing sea ice from open water based on single features. Finally, although the traditional threshold-based image segmentation method has high efficiency in simple scenes, its segmentation effect is easily disturbed by image brightness and noise, and it is highly dependent on the threshold set by humans, with poor generalization ability between different images, making it difficult to adapt to the complex and changeable sea ice environment in the vast Arctic shipping route region.

[0004] The scattering features provided by SAR images can effectively reflect the backscattering of radar beams, and thus exhibit advantages in describing the relationship between the object surface and its surrounding environment. Gray level co-occurrence matrix (GLCM) as an effective texture analysis tool can accurately represent the texture structure of an image, including directionality, interval and amplitude, by describing the spatial joint distribution of pixel gray values, and is therefore widely used in remote sensing image analysis. However, although GLCM can effectively characterize the texture features of sea ice images, the multi-dimensional texture feature set generated by it often has high dimension and information redundancy, and direct application of these features may result in low computational efficiency of the classification model and be easily affected by overfitting.

[0005] In recent years, machine learning algorithms have been widely used in sea ice classification tasks, but the feature combinations used by these algorithms are often not optimized and do not systematically integrate multi-modal features that can fully reflect the physical characteristics and spatial information of sea ice. Therefore, the precision and robustness of existing methods in complex scenarios still cannot meet the high requirements of sea ice classification accuracy for the safety of Arctic shipping routes. In particular, under complex weather and imaging conditions, how to achieve high-precision, high-resolution, and high-robustness automatic classification of sea ice and open water remains a core technical problem that needs to be solved. SUMMARY

[0006] The purpose of the present application is to provide a sea ice extraction method based on multi-feature superpixel segmentation to solve the above-mentioned problems existing in the prior art.

[0007] To solve the above technical problems, the present application provides a sea ice extraction method based on multi-feature superpixel segmentation, comprising: step 1, obtaining a dual-polarized SAR image of a target sea area and performing image preprocessing to obtain a preprocessed image;

[0008] Step 2, extracting the backscattering coefficient feature, the normalized feature, the morphological feature set, the OTSU feature, and the texture feature from the preprocessed image and fusing them to obtain a multi-dimensional data feature set;

[0009] Step 3, using the SNIC superpixel segmentation method to segment the multi-dimensional data feature set to obtain a superpixel block set;

[0010] Step 4, inputting the superpixel block set into a supervised trained machine learning classifier to classify sea water and sea ice to extract sea ice.

[0011] In a specific embodiment, the dual-polarized SAR image is a dual-polarized SAR image based on HH and HV dual-polarization bands obtained by Sentinel-1 in EW imaging mode, and HH and HV are both used as backscattering feature bands.

[0012] In a specific embodiment, the texture feature extraction method is as follows: using principal component analysis (PCA) to reduce the dimensionality of the GLCM texture features of the preprocessed image, and selecting the three texture features with the highest contribution rate, which are contrast, correlation, and variance, respectively.

[0013] In a specific embodiment, the normalized feature is a corrected backscattering coefficient feature, which is obtained by correcting the backscattering coefficient feature of the pre-processed image using incident angle normalization, specifically as follows: a plurality of pixel points are randomly selected in the pre-processed image, and the following steps are performed on each randomly selected pixel point to obtain a corresponding corrected backscattering coefficient value, and the corrected backscattering coefficient values of all randomly selected pixel points form the corrected backscattering coefficient feature of the pre-processed image; step a, extracting the backscattering coefficient value and the incident angle value of the pixel point, constructing a linear fitting function, and the linear fitting function is: ; step b, constructing the inverse function of the linear fitting function using the incident angle average value, and the inverse function of the linear fitting function is: ; step c, constructing the backscattering coefficient equation after incident angle normalization to obtain the corrected backscattering coefficient value of the incident angle θ , and the backscattering coefficient equation after incident angle normalization is: ; wherein a and b are the slope and intercept of the linear fitting function, represents the backscattering coefficient value when the incident angle is θ, is the inverse function of , θ ref is the incident angle average value, θ ref is 33 ° , is the corrected backscattering coefficient value.

[0014] In a specific embodiment, the morphological feature set is obtained by the following method: based on the GEE platform, the erosion feature, dilation feature, opening operation feature, closing operation feature, top-hat transformation feature and bottom-hat transformation feature of the pre-processed image are calculated, the contribution rate of each morphological feature of the pre-processed image is calculated by principal component analysis (PCA), the top 5 morphological features with the highest contribution rate are selected to form the morphological feature set, and the top 5 morphological features with the highest contribution rate are: erosion feature, dilation feature, opening operation feature, closing operation feature and bottom-hat transformation feature.

[0015] In a specific embodiment, the OTSU feature is a binary mask of the pre-processed image based on the OTSU algorithm.

[0016] In a specific embodiment, the machine learning classifier is a random forest classifier.

[0017] In a specific embodiment, the machine learning classifier is supervised trained in advance using labeled sample data before being used for actual classification; the labeled sample data is randomly collected from dual-polarized SAR images that have completed visual interpretation, and the visual interpretation result is used as the true value label.

[0018] In a specific embodiment, the parameter settings of the machine learning classifier during supervised training are dynamically adjusted by a preset parameter combination, the adjustment parameters include a classifier type selection strategy, a model training iteration control method and a precision optimization mechanism, and the best parameter combination that can achieve optimal classification performance is selected.

[0019] Compared with the prior art, the present application has the following beneficial effects.

[0020] The present application extracts the backscattering coefficient feature, the standardized feature, the morphological feature set, the OTSU feature and the texture feature and fuses them to obtain a multi-dimensional data feature set, performs SNIC superpixel segmentation on the multi-dimensional data feature set to obtain a superpixel block set, and inputs the superpixel block set into a machine learning classifier trained under supervision to classify seawater and sea ice. The present application can effectively improve the sea ice classification accuracy and robustness, can generate a sea ice distribution feature set with consistent spatial resolution (40 meters), and effectively supports the monitoring of interannual and intermonthly changes of Arctic sea route sea ice. The core design and innovative functions of the present application include the following aspects.

[0021] 1. Multi-modal feature fusion strategy: The present application breaks through the limitation of relying on single or a small number of features in traditional sea ice classification, and creatively fuses the backscattering coefficient feature, the standardized feature, the morphological feature set, the OTSU feature and the texture feature of the preprocessed image to construct a high-dimensional, complementary multi-dimensional data feature set, which fundamentally improves the separability of sea ice and open water.

[0022] 2. Backscattering coefficient feature correction of dual-polarization SAR image by incident angle normalization: The present application proposes an incident angle normalization algorithm based on cosine correction model to correct the backscattering coefficient feature of satellite wide-swath mode image. In the algorithm, 33° is used as the set incident angle average, which effectively eliminates the gray scale distortion of wide-swath dual-polarization SAR image caused by the change of incident angle, and improves the consistency and robustness of the feature.

[0023] 3. PCA-based texture feature dimension reduction and optimization method: In view of the high dimension and large redundancy of GLCM texture feature, the present application uses principal component analysis (PCA) to reduce the dimension of GLCM texture feature of the preprocessed image, and selects three texture features with the highest contribution rate: contrast, correlation and variance, which retains key information while improving classification efficiency.

[0024] 4. Cooperative processing of superpixel segmentation and feature fusion: The present application uses SNIC superpixel segmentation method to perform superpixel segmentation on the multi-dimensional data feature set, which improves the classification unit from pixel to region, effectively suppresses the salt and pepper noise of SAR image, and ensures the regional consistency and boundary smoothness of the classification result. BRIEF DESCRIPTION OF DRAWINGS

[0025] Figure 1 A flowchart of a sea ice extraction method based on multi-feature superpixel segmentation.

[0026] Figure 2 Figure 1 is a comparison chart of sea ice classification results of an experimental group and a control group in Embodiment 1 of the present application based on summer images, wherein (a) is an original image, (b) is a classification result chart of the control group 1, (c) is a classification result chart of the control group 2, (d) is a classification result chart of the control group 3, and (e) is a classification result chart of the experimental group.

[0027] Figure 3 Figure 2 is a comparison chart of sea ice classification results of an experimental group and a control group in Embodiment 1 of the present application based on winter images, wherein (a) is an original image, (b) is a classification result chart of the control group 1, (c) is a classification result chart of the control group 2, (d) is a classification result chart of the control group 3, and (e) is a classification result chart of the experimental group.

[0028] Figure 4 Figure 3 is a comparison chart of sea ice classification results of an experimental group and sea ice density data in Embodiment 2 of the present application. DETAILED DESCRIPTION

[0029] The present application will be described in detail below with reference to the embodiments and the accompanying drawings. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0030] REFERENCE Figure 1 A sea ice extraction method based on multi-feature superpixel segmentation, comprising: step 1, obtaining a dual-polarization SAR image of a target sea area and performing image preprocessing to obtain a preprocessed image.

[0031] The image preprocessing includes one or more combinations of filtering, cropping, splicing, geometric correction, radiation correction, atmospheric calibration, cloud mask, and land mask. The land mask is used to remove the land area in the image, reduce the influence of irrelevant ground objects, and narrow the research scope; and the cloud mask is used to remove the interference of clouds. The specific image preprocessing needs to be selected according to the actual quality of the remote sensing image.

[0032] Step 2, extracting the backscattering coefficient feature, the standardized feature, the morphological feature set, the OTSU feature, and the texture feature from the preprocessed image and fusing them to obtain a multi-dimensional data feature set, which can fundamentally improve the separability of sea ice and open water.

[0033] Specifically, the dual-polarization SAR image is a dual-polarization SAR image based on HH and HV dual-polarization bands obtained by Sentinel-1 in the EW imaging mode, and HH and HV are both used as backscattering coefficient feature bands, which can reduce the polar night phenomenon and cloud and fog images, thereby optimizing the precision of sea ice extraction.

[0034] Preferably, the texture features include contrast, correlation, and variance. Specifically, the Gray-Level Co-occurrence Matrix (GLCM) effectively characterizes the texture structure of an image by describing the joint spatial distribution of pixel gray levels, including attributes such as directionality, spacing, and amplitude. However, the multidimensional texture feature set it generates suffers from high dimensionality and information redundancy, leading to low computational efficiency and susceptibility to overfitting in the classification model if used directly. Therefore, this invention employs Principal Component Analysis (PCA) to reduce the dimensionality of the GLCM texture features of the preprocessed image, selecting the three texture features with the highest contribution rates for classification. These three features are contrast (CON), correlation (COR), and variance (VAR). This approach preserves the most discriminative texture information while improving the robustness of the feature set and the computational efficiency of the classification model.

[0035] The formula for calculating contrast ratio CON is: .

[0036] The formula for calculating the correlation coefficient (COR) is: .

[0037] The formula for calculating variance VAR is: .

[0038] Where G represents the number of gray levels, p(i,j) represents the probability of a pixel pair with gray levels i and j occurring at a specific distance and direction in the image, x and y represent two classes of adjacent pixels, µ is the mean of p(i,j), and n is the absolute value of the gray level difference, representing the magnitude of the gray level difference between pixel pair i and j. x This represents the expected value of the grayscale value in the horizontal direction, reflecting the average level of the grayscale level in the horizontal direction, µ. y This represents the expected value of the grayscale values ​​along the column direction, reflecting the average level of grayscale levels in the vertical direction. x Indicates the dispersion of gray values ​​along the row direction, measuring the degree of deviation from the mean distribution, ɛ y It indicates the degree of dispersion of gray values ​​in the column direction, and measures the degree of deviation from the mean distribution.

[0039] Specifically, the standardized feature is the corrected backscattering coefficient feature, which is obtained by correcting the backscattering coefficient feature of the preprocessed image using incident angle normalization, as follows: Multiple pixels are randomly selected in the preprocessed image, and the following steps are performed on each randomly selected pixel to obtain the corresponding corrected backscattering coefficient value. The corrected backscattering coefficient values ​​of all randomly selected pixels constitute the corrected backscattering coefficient feature of the preprocessed image; Step a: Extract the backscattering coefficient value and incident angle value of the pixel, and construct a linear fitting function. The linear fitting function is: Step b: Construct the inverse function of the linear fitting function using the average incident angle. The inverse function of the linear fitting function is: Step c: Construct the backscattering coefficient equation after normalizing the incident angle to obtain the corrected backscattering coefficient value at the incident angle θ. The equation for the backscattering coefficient after normalizing the incident angle is: Where a and b are the slope and intercept of the linear fitting function, respectively. This represents the backscattering coefficient value when the incident angle is θ. yes The inverse function of θ ref It is the average incident angle, θ ref The value is 33 ° , This is the corrected backscattering coefficient value.

[0040] The incident angle refers to the angle formed between the radar beam and the vertical line to the ground. For Sentinel-1 EW imaging mode images, the backscattering intensity of sea ice and open water surfaces is closely related to the change in incident angle. As the incident angle increases from near to far, the image brightness gradually decreases. This phenomenon leads to sea ice and open water having the same backscattering coefficient in the same image, which may cause misinterpretation during sample interpretation. The purpose of introducing a corrected backscattering coefficient feature is to eliminate the brightness difference caused by different radar beam incident angles, so that similar ground features have similar brightness values ​​at any location in the image, thereby mitigating the incident angle effect in HH and HV polarized images.

[0041] Sentinel-1 EW images range from approximately 19° in angle of incidence. ° up to 47 ° The incident angles of all images will eventually approach the average incident angle of 33°. ° .

[0042] Specifically, the morphological feature set is obtained through the following method: based on the GEE platform, the erosion features, dilation features, opening operation features, closing operation features, top cap transformation features, and bottom cap transformation features of the preprocessed image are calculated. The contribution rate of each morphological feature of the preprocessed image is calculated using principal component analysis (PCA). The five morphological features with the highest contribution rates are selected to form the morphological feature set. The five morphological features with the highest contribution rates are: erosion features, dilation features, opening operation features, closing operation features, and bottom cap transformation features. The morphological feature set can enhance the contrast of sea ice edges and suppress noise.

[0043] The contribution rates of each feature calculated by Principal Component Analysis (PCA) are as follows: the contribution rate of corrosion feature is 0.306, the contribution rate of expansion feature is 0.154, the contribution rate of opening operation feature is 0.267, the contribution rate of closing operation feature is 0.230, the contribution rate of bottom-hat transformation feature is 0.201, and the contribution rate of top-hat transformation feature is 0.091. The top-hat transformation feature was removed to construct the morphological feature set.

[0044] Specifically, the OTSU feature is a binary mask of the preprocessed image based on the OTSU algorithm. The OTSU algorithm is suitable for image classification where there is a significant grayscale difference between the target and the background. Adaptive thresholding is performed on the preprocessed image based on the OTSU algorithm to generate a binary mask representing the potential sea ice distribution, providing a spatial constraint benchmark for subsequent feature space construction. The specific implementation of the OTSU algorithm is prior art and will not be elaborated upon in this invention.

[0045] Step 3: Use the SNIC superpixel segmentation method to segment the multidimensional data feature set to obtain a set of superpixel blocks;

[0046] The SNIC superpixel segmentation method identifies pixels with similar colors, textures, and other features, clustering pixels with common characteristics to form many superpixel blocks. The advantage of the SNIC algorithm lies in its ability to fully consider the neighborhood information of pixels, preserving the spatial structure information of the image, and exhibiting stronger noise suppression capabilities in sea ice classification. The parameter settings for the SNIC superpixel segmentation method include seed size, compactness, connectivity, and neighborhood size. In the embodiments of this invention, since the classification task is based on multi-dimensional data features with a spatial resolution of 40 meters, the number of seeds is set to 36. The seed size affects the size and number of generated superpixels. The compactness parameter is set to 0.1, controlling the smoothness and shape regularity of the superpixel boundaries. The connectivity parameter is set to 8, indicating that the neighborhood relationship between adjacent pixels and diagonal pixels is considered simultaneously. The neighborhood size is set to 256, determining the sliding window size used in the clustering process.

[0047] Step 4: Input the superpixel block set into a supervised-trained machine learning classifier to classify seawater and sea ice, thereby extracting sea ice. The machine learning classifier can be a support vector machine classifier, a random forest classifier, a gradient tree classifier, etc. In this invention, a random forest classifier is preferred.

[0048] Steps 1 to 4 are the sea ice extraction process in actual application. Before the machine learning classifier is used for actual classification, it is pre-trained using labeled sample data. The labeled sample data is randomly collected from dual-polarization SAR images that have completed visual interpretation of sea ice, and the visual interpretation results are used as ground truth labels.

[0049] In addition, different classification models need to be supervised training according to their respective training requirements. Specifically, the parameter settings of the machine learning classifier during supervised training are dynamically adjusted through preset parameter combinations. The adjusted parameters include classifier type selection strategy, model training iteration control method and accuracy optimization mechanism, and select the best parameter combination that can achieve the best classification performance.

[0050] The present invention will further demonstrate the detailed implementation process and technical effects of the multi-feature superpixel segmentation sea ice extraction method shown in steps 1 to 4 above on a specific dataset through specific embodiments, so as to facilitate understanding of the essence of the present invention.

[0051] Example 1

[0052] To systematically verify that the present invention can effectively improve the accuracy of sea ice classification, an experimental group and three control groups were set up to classify sea ice respectively.

[0053] In this embodiment, Sentinel-1 dual-polarization SAR images of Hokkaido from the past 8 years were collected and preprocessed. The Sentinel-1 imaging mode was selected as EW, and the dual-polarization bands were HH and VV. One winter image and one summer image were selected for sea ice identification and extraction. An experimental area was determined in both the winter and summer images. An experimental group and three control groups were established based on both the winter and summer images.

[0054] Experimental group: The multidimensional data feature set is obtained by fusing backward heat dissipation coefficient features, normalization features, morphological feature set, OTSU features and texture features. The multidimensional data feature set is used to obtain a set of superpixel blocks by the SNIC superpixel segmentation method. The set of superpixel blocks is input into a supervised machine learning classifier to classify seawater and sea ice and extract sea ice.

[0055] Control group 1: The extracted features are backscattered features, which are input into a supervised machine learning classifier to classify seawater and sea ice and extract sea ice.

[0056] Control group 2: The multidimensional data feature set is obtained by fusing the backward heat dissipation coefficient feature and texture feature. The multidimensional data feature set is input into a supervised machine learning classifier to classify seawater and sea ice and extract sea ice.

[0057] Control group 3: The multidimensional data feature set was obtained by fusing backward heat dissipation coefficient features, normalization features, morphological feature set, OTSU features and texture features. The multidimensional data feature set was input into a supervised machine learning classifier to classify seawater and sea ice and extract sea ice.

[0058] from Figure 2 and Figure 3It can be seen that the classification results of the single backscatter feature (control group 1) are poor, with not all sea ice being identified, and only the general outline of the sea ice being visible. This is mainly due to the influence of SAR image noise. Control group 2 incorporates texture features, which enhances the image representation difference between sea ice and open water, resulting in improved sea ice classification accuracy compared to control group 1. However, some sea ice is still not identified, and the classification results for sea ice edges are blurry. The sea ice classification results of control group 3 and the experimental group are better, with all sea ice being identified. However, the sea ice classification results of control group 3 contain misidentifications caused by image noise, while the sea ice classification results of the experimental group do not have misidentifications caused by noise interference, and the sea ice edges are uniform and natural.

[0059] Example 2

[0060] This embodiment demonstrates, by comparing the experimental group and the corresponding sea ice concentration data, that the present invention can effectively improve the accuracy and robustness of sea ice region classification.

[0061] The experimental group in this embodiment is: the winter and summer images selected in Example 1 are used to classify sea ice using the experimental group method of Example 1.

[0062] from Figure 4 As can be seen, even with a spatial resolution of 1km for sea ice concentration data, the sea ice classification results still lose a lot of sea ice information. In contrast, the sea ice classification map of the experimental group, with a spatial resolution of 40m, can still fully show the distribution of sea ice, and has higher sea ice classification accuracy and robustness.

[0063] In summary, this invention extracts and fuses backward heat dissipation coefficient features, normalized features, morphological feature sets, OTSU features, and texture features to obtain a multidimensional data feature set. The multidimensional data feature set is then used to obtain a set of superpixel blocks through the SNIC superpixel segmentation method. The set of superpixel blocks is then input into a supervised machine learning classifier to classify seawater and sea ice, which can effectively improve the accuracy and robustness of sea ice classification.

[0064] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions and substitutions can be made without departing from the inventive concept, and all such modifications and substitutions should be considered within the scope of protection of the present invention.

Claims

1. A sea ice extraction method based on multi-feature superpixel segmentation, characterized in that, include: Step 1: Acquire dual-polarization SAR images of the target sea area and perform image preprocessing to obtain the preprocessed image; Step 2: Extract and fuse backward heat dissipation coefficient features, normalization features, morphological feature set, OTSU features and texture features from the preprocessed image to obtain a multidimensional data feature set; Step 3: Use the SNIC superpixel segmentation method to segment the multidimensional data feature set to obtain a set of superpixel blocks; Step 4: Input the superpixel block set into a supervised machine learning classifier to classify seawater and sea ice in order to extract sea ice.

2. The sea ice extraction method based on multi-feature superpixel segmentation as described in claim 1, characterized in that, The dual-polarization SAR image is a dual-polarization SAR image based on the HH and HV dual-polarization bands obtained by Sentinel-1 in EW imaging mode, with both HH and HV serving as backscattering characteristic bands.

3. The sea ice extraction method based on multi-feature superpixel segmentation as described in claim 2, characterized in that, The method for extracting the texture features is as follows: Principal component analysis (PCA) is used to reduce the dimensionality of the GLCM texture features of the preprocessed image, and the three texture features with the highest contribution rates are selected: contrast, correlation, and variance.

4. The sea ice extraction method based on multi-feature superpixel segmentation as described in claim 3, characterized in that, The standardized feature is the corrected backscattering coefficient feature, which is obtained by correcting the backscattering coefficient feature of the preprocessed image using incident angle normalization, as follows: Multiple pixels are randomly selected in the preprocessed image. The following steps are performed on each randomly selected pixel to obtain the corresponding corrected backscattering coefficient value. The corrected backscattering coefficient values ​​of all randomly selected pixels constitute the corrected backscattering coefficient feature of the preprocessed image. Step a: Extract the backscattering coefficient and incident angle of each pixel, and construct a linear fitting function. The linear fitting function is as follows: ; Step b: Construct the inverse function of the linear fitting function using the average incident angle. The inverse function of the linear fitting function is: ; Step c: Construct the backscattering coefficient equation after normalizing the incident angle to obtain the corrected backscattering coefficient value at the incident angle θ. The equation for the backscattering coefficient after normalizing the incident angle is: ; Where a and b are the slope and intercept of the linear fitting function, respectively. This represents the backscattering coefficient value when the incident angle is θ. yes The inverse function of θ ref It is the average incident angle, θ ref The value is 33 ° , This is the corrected backscattering coefficient value.

5. The sea ice extraction method based on multi-feature superpixel segmentation as described in claim 4, characterized in that, The morphological feature set was obtained by the following method: based on the GEE platform, the erosion features, dilation features, opening operation features, closing operation features, top cap transformation features, and bottom cap transformation features of the preprocessed image were calculated. The contribution rate of each morphological feature of the preprocessed image was calculated by principal component analysis (PCA). The five morphological features with the highest contribution rates were selected to form the morphological feature set. The five morphological features with the highest contribution rates were: erosion features, dilation features, opening operation features, closing operation features, and bottom cap transformation features.

6. The sea ice extraction method based on multi-feature superpixel segmentation as described in claim 5, characterized in that, OTSU features are binary masks of preprocessed images based on the OTSU algorithm.

7. The sea ice extraction method based on multi-feature superpixel segmentation as described in claim 6, characterized in that, The machine learning classifier is a random forest classifier.

8. The sea ice extraction method based on multi-feature superpixel segmentation as described in claim 7, characterized in that... Before being used for actual classification, the machine learning classifier is trained in a supervised manner using labeled sample data. The labeled sample data is randomly collected from dual-polarization SAR images that have completed visual interpretation of sea ice, and the visual interpretation results are used as ground truth labels.

9. The sea ice extraction method based on multi-feature superpixel segmentation as described in claim 8, characterized in that... The parameters of the machine learning classifier during supervised training are dynamically adjusted through preset parameter combinations. The adjusted parameters include classifier type selection strategy, model training iteration control method and accuracy optimization mechanism, to select the best parameter combination that can achieve the best classification performance.

Images