Mangrove forest extraction method and device based on multi-source data collaboration

Abstract

The invention discloses a mangrove forest extraction method and device based on multi-source data collaboration, and belongs to the technical field of remote sensing monitoring. Comprising the steps that a Sentinel-2 multispectral image, a GF-2 multispectral image and DEM data are acquired and preprocessed; performing preliminary extraction on the mangrove forest based on the spectral index of the Sentinel-2 multispectral image to obtain a preliminarily extracted mangrove forest region; based on the GF-2 multispectral image, correcting the boundary of the primarily extracted mangrove forest region by adopting a machine learning method to obtain a corrected mangrove forest region; and constructing a terrain correction index based on the DEM data and the GF-2 multispectral image, and removing the potential ponding area from the corrected mangrove forest area to obtain a final mangrove forest distribution area. According to the method, a progressive frame of spectrum-space-terrain is adopted, the problem that the extraction precision of the sparse mangrove forest in the area with small topographic relief is low due to the serious spectrum confusion phenomenon existing between the mangrove forest and the adjacent static ponding area is solved, and the extraction precision of the sparse mangrove forest is improved.

Description

Technical Field

[0001] This invention relates to the field of remote sensing monitoring technology, specifically to a method and apparatus for extracting mangrove forests based on multi-source data collaboration. Background Technology

[0002] Mangroves are precious ecosystems distributed in the intertidal zones of tropical and subtropical coasts, playing vital ecological roles such as wind and wave protection, water purification, carbon sequestration, and biodiversity maintenance. Timely and accurate understanding of their spatial distribution and dynamic changes is fundamental to mangrove protection, restoration, and management. Traditional methods of in-situ monitoring of mangroves provide accurate sample data, laying the foundation for research. However, due to the specific distribution areas of mangroves, in-situ sampling is time-consuming and labor-intensive, and the resulting data exhibits poor spatial continuity.

[0003] Remote sensing technology, capable of long-range detection, is an irreplaceable and crucial tool for mangrove monitoring due to its macroscopic and rapid advantages. With the increasing abundance of remote sensing data sources and continuous advancements in analytical methods, mangrove information extraction technology is evolving from reliance on single data sources and simple algorithms to the integration of multi-source data and complex models. However, in this development process, the severe spectral obfuscation between mangroves located in the flat intertidal zone and adjacent stagnant water areas remains a core challenge and difficulty for high-precision extraction. To overcome this challenge, existing technologies have undergone the following development paths, each of which, while improving accuracy, also reveals its inherent limitations.

[0004] Methods for extracting mangrove forests based on spectral indices offer broad applicability but are limited in accuracy and detail. These methods form the basis of mangrove remote sensing monitoring, primarily relying on spectral information from single-type optical remote sensing images (such as the Landsat series and Sentinel-2). Extraction is achieved by calculating spectral indices (such as Normalized Difference Vegetation Index (NDVI) and Normalized Difference Water Index (NDWI)) and setting empirical thresholds. The advantages of this method are its broad applicability and high computational efficiency, making it suitable for large-scale rapid surveys. However, its inherent limitation lies in the pixel mixing effect caused by image resolution limitations, leading to blurred boundaries and loss of detail in the extracted results. This is particularly pronounced in spectrally confused areas where mangroves and water bodies are interspersed, where misclassification is significant, hindering extraction accuracy. Even utilizing richer spectral information from some images struggles to effectively distinguish fine boundaries at the land-water interface in flat areas.

[0005] With the rapid development of remote sensing technology, the spatial resolution of images has gradually improved. Using high spatial resolution imagery (such as GF-2 and WorldView series) and employing machine learning algorithms to comprehensively mine the spectral and spatial texture features of the images has significantly optimized the geometric contours of mangrove patches, achieving more refined identification than medium-resolution imagery. However, the application of high-resolution imagery often involves the construction of high-dimensional feature sets, which easily introduces feature redundancy. Feature redundancy not only fails to improve model performance but also dilutes the contribution of the truly crucial spectral features for distinguishing mangroves from water bodies, affecting the model's generalization ability. Furthermore, high-resolution imagery is mostly multispectral data with a wide spectral band width and a small number of bands, making it difficult to fully utilize spectral information for accurate mangrove extraction. More importantly, even though the spatial resolution of images has been greatly improved, the problem of spectral confusion caused by mixed pixels between mangroves and stagnant water areas has not been well resolved.

[0006] The limitations of single data sources have made multi-source data fusion a primary method in mangrove research. Current multi-source data fusion strategies commonly combine DEM data with optical imagery. However, existing fusion methods still rely on simply inputting DEM data and spectral features into a classifier, failing to fully utilize the information provided by the DEM data. Summary of the Invention

[0007] To address the aforementioned technical problems, this invention provides a method and apparatus for extracting mangroves based on multi-source data collaboration. This overcomes the problem of low extraction accuracy of sparse mangroves in areas with small topographic relief caused by severe spectral confusion between mangroves and adjacent stagnant water areas, thereby improving the extraction accuracy of sparse mangroves.

[0008] The technical solution provided by this invention is as follows:

[0009] A method for extracting mangrove forests based on multi-source data collaboration, the method comprising:

[0010] S1: Obtain multi-source data for the same time period in the study area;

[0011] The multi-source data includes medium-resolution Sentinel-2 multispectral images, high-resolution GF-2 multispectral images, and DEM data.

[0012] S2: Preprocess the Sentinel-2 multispectral image and the GF-2 multispectral image;

[0013] S3: Based on the spectral indices of the preprocessed Sentinel-2 multispectral image, the mangrove forest area is initially extracted to obtain the initial extracted mangrove forest area;

[0014] S4: Based on the preprocessed GF-2 multispectral image, machine learning methods are used to correct the boundaries of the initially extracted mangrove areas to obtain the corrected mangrove areas;

[0015] S5: Construct a topographic correction index based on DEM data and preprocessed GF-2 multispectral image, and remove potential water accumulation areas from the corrected mangrove area according to the topographic correction index to obtain the final mangrove distribution area;

[0016] The formula for calculating the terrain correction index is as follows:

[0017]

[0018] S represents the terrain correction index, and RE and ESD represent the slope, relative elevation, and standard deviation of elevation obtained from the DEM data, respectively. The normalized water index is calculated based on the preprocessed GF-2 multispectral image, where a, b, c, and d are the weights of slope, relative elevation, elevation standard deviation, and normalized water index, respectively.

[0019] Furthermore, S3 includes:

[0020] S31: Use the boundary vector of the study area to crop the preprocessed Sentinel-2 multispectral image to obtain the medium-resolution image data of the study area;

[0021] S32: Calculate the spectral index of each pixel in the study area based on the medium-resolution image data of the study area;

[0022] The spectral indices include one or more of the following: red-edge normalized vegetation index, red-edge location index, and water stress index, and the calculation formula is as follows:

[0023]

[0024]

[0025]

[0026] RE_NDVI is the red-edge normalized vegetation index, REP is the red-edge position index, MSI is the water stress index, and B4, B5, B7, B8A, and B11 represent the remote sensing reflectance of bands 4, 5, 7, 8A, and 11 of the preprocessed Sentinel-2 multispectral image, respectively.

[0027] S33: Compare each spectral index with the set index thresholds to obtain the initial extracted mangrove area.

[0028] Furthermore, S33 includes:

[0029] S331: For each pixel in the study area, the red-edge normalized vegetation index of the pixel is compared with the set vegetation index threshold. Pixels with a red-edge normalized vegetation index greater than the vegetation index threshold are classified as mangroves to obtain the first initially extracted mangrove range.

[0030] S332: For each pixel in the study area, compare the red edge position index of the pixel with the set position index threshold, and classify the pixels with the red edge position index greater than the position index threshold as mangroves to obtain the second initial extracted mangrove range.

[0031] S333: For each pixel in the study area, the water stress index of the pixel is compared with the set water stress index threshold. Pixels with a water stress index less than the water stress index threshold are classified as mangroves, and the third initial mangrove range is obtained.

[0032] S334: Take the union of the first initially extracted mangrove area, the second initially extracted mangrove area, and the third initially extracted mangrove area to obtain the initially extracted mangrove region.

[0033] Furthermore, S4 includes:

[0034] S41: Based on the boundary of the initially extracted mangrove area, a buffer zone with a set distance is constructed on both the inner and outer sides of the boundary to obtain the boundary area of ​​the initially extracted mangrove area;

[0035] S42: Based on the boundary vector of the initially extracted mangrove boundary region, the preprocessed GF-2 multispectral image is cropped to obtain the boundary region to be corrected.

[0036] S43: The mangrove forests in the boundary area to be corrected are extracted using machine learning methods to obtain the mangrove forest boundary correction result;

[0037] S44: Replace the initially extracted mangrove boundary region within the initially extracted mangrove region with the mangrove boundary correction result to obtain the corrected mangrove region.

[0038] Furthermore, S5 includes:

[0039] S51: Based on DEM data, calculate the slope, relative elevation, and elevation standard deviation of each pixel in the study area using geographic information system software;

[0040] S52: Calculate the normalized water index for each pixel in the study area based on the preprocessed GF-2 multispectral image;

[0041]

[0042] Wherein, NDWI is the normalized water index, and Green and NIR represent the remote sensing reflectance of the green band and near-infrared band of the preprocessed GF-2 multispectral image, respectively.

[0043] S53: The terrain correction index for each pixel within the study area is constructed using the following formula:

[0044]

[0045] S54: Compare the terrain correction index of each pixel in the study area with the determined segmentation threshold, and classify the pixels with terrain correction index greater than the segmentation threshold as potential water accumulation areas.

[0046] S55: Remove the potential waterlogged area from the modified mangrove area to obtain the final mangrove distribution area.

[0047] Furthermore, the weights of the slope, relative elevation, elevation standard deviation, and normalized water index are determined as follows:

[0048] The subjective weights of slope, relative elevation, elevation standard deviation, and normalized water index were determined using the analytic hierarchy process (AHP).

[0049] The objective weights of slope, relative elevation, elevation standard deviation, and normalized water index were determined using the CRITIC method.

[0050] The subjective and objective weights are linearly weighted to obtain the weights of slope, relative elevation, elevation standard deviation, and normalized water index.

[0051] Furthermore, the segmentation threshold is determined in the following manner:

[0052] The dataset of the terrain correction index was subjected to unsupervised clustering fitting using a Gaussian mixture model, resulting in two Gaussian distributions.

[0053] The value of the terrain correction index corresponding to the intersection of the probability density functions of the two Gaussian distributions is used as the segmentation threshold.

[0054] A mangrove forest extraction device based on multi-source data collaboration, the device comprising:

[0055] The data acquisition module is used to acquire multi-source data of the same time period in the study area;

[0056] The multi-source data includes medium-resolution Sentinel-2 multispectral images, high-resolution GF-2 multispectral images, and DEM data.

[0057] The preprocessing module is used to preprocess the Sentinel-2 multispectral images and GF-2 multispectral images;

[0058] The initial extraction module is used to perform preliminary extraction of mangroves based on the spectral indices of the preprocessed Sentinel-2 multispectral image to obtain the initial extracted mangrove area;

[0059] The boundary correction module is used to correct the boundaries of the initially extracted mangrove areas based on the preprocessed GF-2 multispectral image using machine learning methods, so as to obtain the corrected mangrove areas.

[0060] The terrain correction module is used to construct a terrain correction index based on DEM data and preprocessed GF-2 multispectral imagery, and remove potential water accumulation areas from the corrected mangrove area according to the terrain correction index to obtain the final mangrove distribution area.

[0061] The formula for calculating the terrain correction index is as follows:

[0062]

[0063] S represents the terrain correction index, and RE and ESD represent the slope, relative elevation, and standard deviation of elevation obtained from the DEM data, respectively. The normalized water index is calculated based on the preprocessed GF-2 multispectral image, where a, b, c, and d are the weights of slope, relative elevation, elevation standard deviation, and normalized water index, respectively.

[0064] Furthermore, the initial extraction module includes:

[0065] The first cropping unit is used to crop the preprocessed Sentinel-2 multispectral image using the boundary vector of the study area to obtain medium-resolution image data of the study area.

[0066] The spectral index calculation unit is used to calculate the spectral index of each pixel in the study area based on the medium-resolution image data of the study area.

[0067] The spectral indices include one or more of the following: red-edge normalized vegetation index, red-edge location index, and water stress index, and the calculation formula is as follows:

[0068]

[0069]

[0070]

[0071] RE_NDVI is the red-edge normalized vegetation index, REP is the red-edge position index, MSI is the water stress index, and B4, B5, B7, B8A, and B11 represent the remote sensing reflectance of bands 4, 5, 7, 8A, and 11 of the preprocessed Sentinel-2 multispectral image, respectively.

[0072] The spectral index segmentation unit is used to compare each spectral index with the set index thresholds to obtain the initial extracted mangrove area.

[0073] Furthermore, the spectral index segmentation unit includes:

[0074] The first segmentation subunit is used to compare the red-edge normalized vegetation index of each pixel in the study area with the set vegetation index threshold, and classify the pixels with the red-edge normalized vegetation index greater than the vegetation index threshold as mangroves to obtain the first initially extracted mangrove range.

[0075] The second segmentation subunit is used to compare the red edge position index of each pixel in the study area with the set position index threshold, and classify the pixels with the red edge position index greater than the position index threshold as mangroves to obtain the second initial extracted mangrove range.

[0076] The third segmentation subunit is used to compare the water stress index of each pixel in the study area with the set water stress index threshold, and classify the pixels with water stress index less than the water stress index threshold as mangroves to obtain the third initial extraction of mangrove range.

[0077] The initial mangrove area determination subunit is used to combine the first, second, and third initial mangrove areas to obtain the initial mangrove area.

[0078] Furthermore, the boundary correction module includes:

[0079] A buffer unit is used to construct buffer zones at a set distance on both the inner and outer sides of the boundary of the initially extracted mangrove area, based on the boundary of the initially extracted mangrove area, to obtain the boundary area of ​​the initially extracted mangrove area.

[0080] The second cropping unit is used to crop the preprocessed GF-2 multispectral image based on the boundary vector of the initially extracted mangrove boundary region to obtain the boundary region to be corrected.

[0081] The machine learning classification unit is used to extract the mangroves in the boundary area to be corrected using machine learning methods, so as to obtain the mangrove boundary correction result;

[0082] The boundary correction unit is used to replace the initially extracted mangrove boundary region within the initially extracted mangrove region with the mangrove boundary correction result to obtain the corrected mangrove region.

[0083] Furthermore, the terrain correction module includes:

[0084] The topographic factor calculation unit is used to calculate the slope, relative elevation, and elevation standard deviation of each pixel in the study area based on DEM data and using geographic information system software.

[0085] The water index calculation unit is used to calculate the normalized water index of each pixel in the study area based on the preprocessed GF-2 multispectral image.

[0086]

[0087] Wherein, NDWI is the normalized water index, and Green and NIR represent the remote sensing reflectance of the green band and near-infrared band of the preprocessed GF-2 multispectral image, respectively.

[0088] The terrain correction index determination unit is used to construct the terrain correction index for each pixel within the study area using the following formula:

[0089]

[0090] The potential water accumulation area determination unit is used to compare the terrain correction index of each pixel in the study area with a determined segmentation threshold, and classify the pixels with the terrain correction index greater than the segmentation threshold as potential water accumulation areas.

[0091] The mangrove distribution area determination unit is used to remove the potential waterlogged areas from the modified mangrove area to obtain the final mangrove distribution area.

[0092] Furthermore, the weights of the slope, relative elevation, elevation standard deviation, and normalized water index are determined as follows:

[0093] The subjective weights of slope, relative elevation, elevation standard deviation, and normalized water index were determined using the analytic hierarchy process (AHP).

[0094] The objective weights of slope, relative elevation, elevation standard deviation, and normalized water index were determined using the CRITIC method.

[0095] The subjective and objective weights are linearly weighted to obtain the weights of slope, relative elevation, elevation standard deviation, and normalized water index.

[0096] Furthermore, the segmentation threshold is determined in the following manner:

[0097] The dataset of the terrain correction index was subjected to unsupervised clustering fitting using a Gaussian mixture model, resulting in two Gaussian distributions.

[0098] The value of the terrain correction index corresponding to the intersection of the probability density functions of the two Gaussian distributions is used as the segmentation threshold.

[0099] The present invention has the following beneficial effects:

[0100] The present invention aims to solve the problem encountered in existing methods for mangrove extraction, which is that sparse mangroves in flat intertidal areas with little topographic relief are difficult to identify accurately due to the severe spectral confusion between mangroves located in flat intertidal zones and adjacent stagnant water areas.

[0101] This invention employs a progressive framework of "spectral-spatial-topographic," following a research approach of "leveraging strengths and compensating for weaknesses." By integrating the unique advantages of multi-source data, it obtains progressively corrected and highly accurate mangrove extraction results: First, Sentinel-2 multispectral imagery is used for rapid preliminary extraction of potential mangrove distribution areas. Then, sub-meter-level GF-2 imagery is introduced to refine and optimize the geometric boundaries of the preliminary extraction results. Finally, based on digital elevation model (DEM) data, a comprehensive topographic correction index is constructed to correct for spectral confusion between sparse mangrove areas and water bodies and mangroves.

[0102] This invention overcomes the problem of low extraction accuracy of sparse mangroves in areas with relatively small topographic relief due to severe spectral confusion between mangroves and adjacent stagnant water areas. It also mitigates the impact of water bodies on the accurate identification of mangroves in sparse mangrove areas, a problem that even high spatial resolution imagery cannot achieve, thus alleviating the spectral confusion problem caused by water interference and improving the extraction accuracy of sparse mangroves. This provides an effective technical solution for the accurate extraction and dynamic monitoring of coastal mangroves.

[0103] Furthermore, this invention does not simply input multi-source data in parallel, but uses a progressive framework of "spectral-spatial-topographic" to perform step-by-step and directional correction logic, allowing medium-resolution imagery, high-resolution imagery, and DEM data to work together. This ensures that the advantages of each type of data are maximized, leveraging the core strengths of each type in turn, and improving the accuracy of mangrove extraction. Attached Figure Description

[0104] Figure 1 The flowchart shows the mangrove forest extraction method based on multi-source data collaboration of the present invention.

[0105] Figure 2 This is a schematic diagram of the mangrove extraction device based on multi-source data collaboration according to the present invention. Detailed Implementation

[0106] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0107] This invention provides a mangrove extraction method based on multi-source data collaboration. This method aims to solve the problem that sparse mangroves in flat intertidal areas are difficult to accurately identify due to the severe spectral confusion between mangroves located in flat intertidal zones and adjacent stagnant water areas.

[0108] like Figure 1 As shown, the method includes:

[0109] S1: Obtain multi-source data for the same time period in the study area;

[0110] The multi-source data includes medium-resolution Sentinel-2 multispectral imagery, high-resolution GF-2 multispectral imagery, and DEM (Digital Elevation Model) data.

[0111] S2: Preprocess Sentinel-2 and GF-2 multispectral images.

[0112] Preprocessing includes radiometric correction, atmospheric correction, cloud removal, and image mosaicking to obtain remote sensing images at different resolutions at the same time.

[0113] S3: Based on the spectral indices of the preprocessed Sentinel-2 multispectral image, the mangrove forest area is initially extracted to obtain the initial extracted mangrove forest area.

[0114] This step is used for rapid preliminary extraction of mangrove data, and one implementation method includes:

[0115] S31: Use the boundary vector of the study area to crop the preprocessed Sentinel-2 multispectral image to obtain the medium-resolution image data of the study area.

[0116] S32: Calculate the spectral index of each pixel in the study area based on the medium-resolution image data of the study area.

[0117] Based on the unique red-edge band of Sentinel-2 imagery, the spectral indices include one or more of the following: Red Edge Normalized Difference Vegetation Index (RE_NDVI), Red Edge Position Index (REP), and Moisture Stress Index (MSI). The calculation formulas for each spectral index are as follows:

[0118]

[0119]

[0120]

[0121] RE_NDVI is the red-edge normalized vegetation index, REP is the red-edge position index, MSI is the water stress index, and B4, B5, B7, B8A, and B11 represent the remote sensing reflectance of bands 4, 5, 7, 8A, and 11 of the preprocessed Sentinel-2 multispectral image, respectively.

[0122] S33: Compare each spectral index with the set index thresholds to obtain the initial extracted mangrove area.

[0123] After calculating each spectral index, this invention uses a threshold limitation method to quickly extract the mangrove range, resulting in an initial extracted mangrove area, denoted as A1.

[0124] Specifically, including:

[0125] S331: For each pixel in the study area, the red-edge normalized vegetation index of the pixel is compared with the set vegetation index threshold. Pixels with a red-edge normalized vegetation index greater than the vegetation index threshold are classified as mangroves, thus obtaining the first initial extracted mangrove range.

[0126] The higher the red border normalized vegetation index, the more lush the mangroves are. Therefore, areas with a vegetation index value greater than the threshold are classified as mangroves.

[0127] S332: For each pixel in the study area, compare the red edge position index of the pixel with the set position index threshold, and classify the pixels with the red edge position index greater than the position index threshold as mangroves to obtain the second initial extracted mangrove range.

[0128] The red edge location index represents the growth of mangroves. The larger the value, the more vigorous the mangrove growth. Therefore, areas with a location index value greater than the threshold are classified as mangroves.

[0129] S333: For each pixel in the study area, the water stress index of the pixel is compared with the set water stress index threshold. Pixels with a water stress index less than the water stress index threshold are classified as mangroves, and the third initial mangrove range is obtained.

[0130] The water stress index characterizes the water content of mangrove leaves. The healthier the mangrove growth, the higher the water content of its leaves, the stronger the absorption, and the lower the water stress index. Therefore, areas with water stress index values ​​below the threshold are classified as mangroves.

[0131] S334: Take the union of the first, second, and third initial mangrove forest areas to obtain the initial mangrove forest region.

[0132] This invention extracts mangrove data using multiple spectral indices, and the combined results from multiple spectral indices are more accurate.

[0133] S4: Based on the preprocessed GF-2 multispectral image, machine learning methods are used to correct the boundaries of the initially extracted mangrove areas to obtain the corrected mangrove areas.

[0134] This step is used to refine and complete the initially extracted mangrove boundaries using high-resolution GF-2 multispectral imagery. In one example, this step is implemented as follows:

[0135] S41: Based on the boundary of the initially extracted mangrove area, a buffer zone with a set distance is constructed on both the inner and outer sides of the boundary to obtain the boundary area of ​​the initially extracted mangrove area.

[0136] The distance D of the buffer can be determined based on the image resolution or other possible factors; for example, D can be 10 pixels. After constructing buffers with a distance D to both sides of the boundary of the initially extracted mangrove region A1, the resulting initially extracted mangrove boundary region is denoted as B.

[0137] S42: Based on the initial extraction of the boundary vector of the mangrove boundary region B, the preprocessed GF-2 multispectral image is cropped to obtain the boundary region to be corrected.

[0138] S43: Machine learning methods are used to extract mangroves within the boundary area to be corrected, and the mangrove boundary correction results are obtained.

[0139] The machine learning method of this invention can be a supervised classification method, such as a random forest classifier. First, sufficient training samples are selected to train the random forest classifier. Then, the boundary region to be corrected is input into the trained random forest classifier for classification, resulting in the mangrove boundary correction result based on medium-resolution imagery, denoted as A2.

[0140] S44: Replace the initially extracted mangrove boundary region within the initially extracted mangrove region with the mangrove boundary correction result to obtain the corrected mangrove region.

[0141] Specifically, through Boolean operations, A2 is used to replace the corresponding part of A1 in the boundary region B, to fill in the missing patches in A1, and to correct the boundary error of A1, thus obtaining the corrected mangrove region, denoted as A3.

[0142] S5: Based on DEM data and preprocessed GF-2 multispectral images, a topographic correction index is constructed, and potential water accumulation areas are removed from the corrected mangrove areas according to the topographic correction index to obtain the final mangrove distribution area.

[0143] This step is used to collaboratively identify and remove water bodies in sparse mangrove areas using GF-2 imagery and DEM data. The specific steps are as follows:

[0144] S51: Based on DEM data, calculate the slope, relative elevation, and elevation standard deviation of each pixel in the study area using geographic information system software.

[0145] This step is used to construct terrain correction factors such as slope, relative elevation, and elevation standard deviation. These factors can be calculated using the terrain analysis tools built into ArcGIS.

[0146] S52: Calculate the Normalized Difference Water Index (NDWI) for each pixel in the study area based on the preprocessed GF-2 multispectral image.

[0147]

[0148] Wherein, NDWI is the normalized water index, and Green and NIR represent the remote sensing reflectance of the green band and near-infrared band of the preprocessed GF-2 multispectral image, respectively.

[0149] S53: Construct the Potential Waterlogging Index (PWI) for each pixel within the study area using the following formula:

[0150]

[0151] in, S represents the terrain correction index, and RE and ESD represent the slope, relative elevation, and standard deviation of elevation obtained from DEM data, respectively. The normalized water index is calculated based on the preprocessed GF-2 multispectral image, where a, b, c, and d are the weights of slope, relative elevation, elevation standard deviation, and normalized water index, respectively.

[0152] Weights a, b, c, and d are assigned through a comprehensive weighting strategy, specifically determined as follows:

[0153] 1. The Analytic Hierarchy Process (AHP) was used to determine the subjective weights of slope, relative elevation, elevation standard deviation, and normalized water index that reflect expert experience.

[0154] 2. The CRITIC method is used to determine the objective weights of slope, relative elevation, elevation standard deviation, and normalized water index to reflect the inherent laws of the data.

[0155] 3. The subjective and objective weights are linearly weighted to obtain the weights of slope, relative elevation, elevation standard deviation and normalized water index.

[0156] The weights for linearly weighting subjective and objective weights are set according to needs or experience; for example, the weights for subjective and objective weights are each set to 0.5.

[0157] The constructed topographic correction index includes both topographic data (slope, relative elevation, elevation standard deviation) and water index. This topographic correction index comprehensively reflects the potential impact of micro-topography on water accumulation and can represent absolute low-lying areas and water-bearing areas in the study area, i.e. potential water accumulation areas. These water accumulation areas are not areas where mangroves grow and need to be excluded.

[0158] After constructing the terrain correction index, it is necessary to calculate the terrain correction index values ​​of all pixels in the study area to form a dataset.

[0159] S54: Compare the terrain correction index of each pixel in the study area with the determined segmentation threshold, and classify the pixels with terrain correction index greater than the segmentation threshold as potential water accumulation areas.

[0160] The segmentation threshold can be determined using a Gaussian mixture model. First, an unsupervised clustering fit is performed on the terrain correction index dataset using a Gaussian mixture model to obtain two Gaussian distributions. Then, the value of the terrain correction index corresponding to the intersection of the probability density functions of the two Gaussian distributions is used as the segmentation threshold.

[0161] The probability density function of a Gaussian mixture model is a weighted sum of multiple Gaussian distribution components, and its mathematical expression is as follows:

[0162]

[0163] Where x represents a data point, and in this invention, it represents the terrain correction index. K is the number of Gaussian distributions (also known as components). In this invention, K=2, meaning that this invention distinguishes between two types of areas: potentially flooded areas and non-flooded areas. It is the mixture weight of the k-th (k=1,2) Gaussian distribution, satisfying ; It is the k-th Gaussian distribution with a mean of Covariance Matrix .

[0164] The specific operation process is as follows:

[0165] Model initialization: The number of Gaussian distributions is preset to K. In this invention, to distinguish between potentially flooded areas and non-flooded areas, K=2 is set.

[0166] Model training: The Gaussian mixture model is trained using the expectation-maximization algorithm. This process involves iteratively executing the following steps until the parameters of the Gaussian mixture model converge.

[0167] Expectation step: Based on the current parameters, calculate the probability that each PWI value data point belongs to each Gaussian distribution component.

[0168] Maximization step: Based on the probabilities calculated in the previous step, re-estimate the parameters of each Gaussian distribution component, including its mean, variance, and mixing weights.

[0169] Threshold Determination: After training, the Gaussian mixture model fits the overall distribution of PWI values ​​into two Gaussian distributions, representing the "potentially flooded area" and the "non-flooded area," respectively. The segmentation threshold is automatically determined as the PWI value corresponding to the intersection of the probability density functions of these two Gaussian distributions.

[0170] After determining the segmentation threshold, pixels with PWI values ​​greater than the threshold are identified as "potential water accumulation areas" and output as result A4.

[0171] S55: Remove the potential waterlogged area A4 from the corrected mangrove area A3 to achieve further optimization and obtain the final mangrove distribution area, thus achieving accurate extraction of mangroves.

[0172] The present invention aims to solve the problem encountered in existing methods for mangrove extraction, which is that sparse mangroves in flat intertidal areas with little topographic relief are difficult to identify accurately due to the severe spectral confusion between mangroves located in flat intertidal zones and adjacent stagnant water areas.

[0173] This invention employs a progressive framework of "spectral-spatial-topographic," following a research approach of "leveraging strengths and compensating for weaknesses." By integrating the unique advantages of multi-source data, it obtains progressively corrected and highly accurate mangrove extraction results: First, Sentinel-2 multispectral imagery is used for rapid preliminary extraction of potential mangrove distribution areas. Then, sub-meter-level GF-2 imagery is introduced to refine and optimize the geometric boundaries of the preliminary extraction results. Finally, based on digital elevation model (DEM) data, a comprehensive topographic correction index is constructed to correct for spectral confusion between sparse mangrove areas and water bodies and mangroves.

[0174] This invention overcomes the problem of low extraction accuracy of sparse mangroves in areas with relatively small topographic relief due to severe spectral confusion between mangroves and adjacent stagnant water areas. It also mitigates the impact of water bodies on the accurate identification of mangroves in sparse mangrove areas, a problem that even high spatial resolution imagery cannot achieve, thus alleviating the spectral confusion problem caused by water interference and improving the extraction accuracy of sparse mangroves. This provides an effective technical solution for the accurate extraction and dynamic monitoring of coastal mangroves.

[0175] Furthermore, this invention does not simply input multi-source data in parallel, but uses a progressive framework of "spectral-spatial-topographic" to perform step-by-step and directional correction logic, allowing medium-resolution imagery, high-resolution imagery, and DEM data to work together. This ensures that the advantages of each type of data are maximized, leveraging the core strengths of each type in turn, and improving the accuracy of mangrove extraction.

[0176] This invention also provides a mangrove forest extraction device based on multi-source data collaboration, such as... Figure 2 As shown, the device includes:

[0177] Data acquisition module 1 is used to acquire multi-source data of the same time period in the study area.

[0178] The multi-source data includes medium-resolution Sentinel-2 multispectral images, high-resolution GF-2 multispectral images, and DEM data.

[0179] Preprocessing module 2 is used to preprocess Sentinel-2 multispectral images and GF-2 multispectral images.

[0180] The initial extraction module 3 is used to perform preliminary extraction of mangroves based on the spectral indices of the preprocessed Sentinel-2 multispectral image to obtain the initially extracted mangrove area.

[0181] Boundary correction module 4 is used to correct the boundaries of the initially extracted mangrove areas based on the preprocessed GF-2 multispectral image using machine learning methods, so as to obtain the corrected mangrove areas.

[0182] The terrain correction module 5 is used to construct a terrain correction index based on DEM data and preprocessed GF-2 multispectral imagery, and remove potential water accumulation areas from the corrected mangrove areas according to the terrain correction index to obtain the final mangrove distribution area.

[0183] The formula for calculating the terrain correction index is as follows:

[0184]

[0185] S represents the terrain correction index, and RE and ESD represent the slope, relative elevation, and standard deviation of elevation obtained from DEM data, respectively. The normalized water index is calculated based on the preprocessed GF-2 multispectral image, where a, b, c, and d are the weights of slope, relative elevation, elevation standard deviation, and normalized water index, respectively.

[0186] As an example, the initial extraction module includes:

[0187] The first cropping unit is used to crop the preprocessed Sentinel-2 multispectral image using the boundary vector of the study area to obtain medium-resolution image data of the study area.

[0188] The spectral index calculation unit is used to calculate the spectral index of each pixel in the study area based on the medium-resolution image data of the study area.

[0189] Among them, the spectral indices include one or more of the following: red-edge normalized vegetation index, red-edge location index, and water stress index, and the calculation formula is as follows:

[0190]

[0191]

[0192]

[0193] RE_NDVI is the red-edge normalized vegetation index, REP is the red-edge position index, MSI is the water stress index, and B4, B5, B7, B8A, and B11 represent the remote sensing reflectance of bands 4, 5, 7, 8A, and 11 of the preprocessed Sentinel-2 multispectral image, respectively.

[0194] The spectral index segmentation unit is used to compare each spectral index with the set index thresholds to obtain the initial extracted mangrove area.

[0195] Specifically, the spectral index segmentation unit includes:

[0196] The first segmentation subunit is used to compare the red-edge normalized vegetation index of each pixel in the study area with the set vegetation index threshold, and classify the pixels with the red-edge normalized vegetation index greater than the vegetation index threshold as mangroves, thus obtaining the first initially extracted mangrove range.

[0197] The second segmentation subunit is used to compare the red edge position index of each pixel in the study area with the set position index threshold, and classify the pixels with the red edge position index greater than the position index threshold as mangroves, thus obtaining the second initial extracted mangrove range.

[0198] The third segmentation subunit is used to compare the water stress index of each pixel in the study area with the set water stress index threshold, and classify the pixels with water stress index less than the water stress index threshold as mangroves, thus obtaining the third initial extraction of mangrove range.

[0199] The initial mangrove area is determined by defining a sub-unit, which is used to combine the first, second, and third initial mangrove areas to obtain the initial mangrove area.

[0200] As one implementation, the boundary correction module includes:

[0201] The buffer unit is used to construct buffer zones at a set distance on both the inner and outer sides of the initially extracted mangrove area, based on the boundary of the initially extracted mangrove area, to obtain the boundary area of ​​the initially extracted mangrove area.

[0202] The second cropping unit is used to crop the preprocessed GF-2 multispectral image based on the boundary vector of the initially extracted mangrove boundary region to obtain the boundary region to be corrected.

[0203] The machine learning classification unit is used to extract mangroves within the boundary area to be corrected using machine learning methods, and obtain the mangrove boundary correction result.

[0204] The boundary correction unit is used to replace the initially extracted mangrove boundary region within the initially extracted mangrove region with the mangrove boundary correction result, thus obtaining the corrected mangrove region.

[0205] As an improvement to this embodiment of the invention, the terrain correction module includes:

[0206] The topographic factor calculation unit is used to calculate the slope, relative elevation, and elevation standard deviation of each pixel in the study area based on DEM data and using geographic information system software.

[0207] The water index calculation unit is used to calculate the normalized water index of each pixel in the study area based on the preprocessed GF-2 multispectral image.

[0208]

[0209] Wherein, NDWI is the normalized water index, and Green and NIR represent the remote sensing reflectance of the green band and near-infrared band of the preprocessed GF-2 multispectral image, respectively.

[0210] The terrain correction index determination unit is used to construct the terrain correction index for each pixel within the study area using the following formula:

[0211]

[0212] The potential water accumulation area determination unit is used to compare the terrain correction index of each pixel in the study area with a determined segmentation threshold, and classify pixels with terrain correction indices greater than the segmentation threshold as potential water accumulation areas.

[0213] The mangrove distribution area determination unit is used to remove potential waterlogged areas from the modified mangrove area to obtain the final mangrove distribution area.

[0214] The weights of the aforementioned slope, relative elevation, elevation standard deviation, and normalized water index can be determined as follows:

[0215] 1. The subjective weights of slope, relative elevation, elevation standard deviation, and normalized water index were determined using the analytic hierarchy process.

[0216] 2. The objective weights of slope, relative elevation, elevation standard deviation, and normalized water index were determined using the CRITIC method.

[0217] 3. The subjective and objective weights are linearly weighted to obtain the weights of slope, relative elevation, elevation standard deviation and normalized water index.

[0218] In this invention, the segmentation threshold can be determined in the following way:

[0219] An unsupervised clustering fit was performed on the terrain correction index dataset using a Gaussian mixture model, resulting in two Gaussian distributions.

[0220] The value of the terrain correction index corresponding to the intersection of the probability density functions of the two Gaussian distributions is used as the segmentation threshold.

[0221] The apparatus provided in this embodiment of the invention operates on the same principle and produces the same technical effects as the aforementioned method embodiments. For the sake of brevity, any parts not mentioned in the apparatus embodiments can be referred to the corresponding content in the aforementioned method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the apparatus and units described above can all be referred to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0222] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the scope of the technology disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention.

Claims

1. A method for extracting mangrove forests based on multi-source data collaboration, characterized in that, The method includes: S1: Obtain multi-source data for the same time period in the study area; The multi-source data includes medium-resolution Sentinel-2 multispectral images, high-resolution GF-2 multispectral images, and DEM data. S2: Preprocess the Sentinel-2 multispectral image and the GF-2 multispectral image; S3: Based on the spectral indices of the preprocessed Sentinel-2 multispectral image, the mangrove forest area is initially extracted to obtain the initial extracted mangrove forest area; S4: Based on the preprocessed GF-2 multispectral image, machine learning methods are used to correct the boundaries of the initially extracted mangrove areas to obtain the corrected mangrove areas; S5: Construct a topographic correction index based on DEM data and preprocessed GF-2 multispectral image, and remove potential water accumulation areas from the corrected mangrove area according to the topographic correction index to obtain the final mangrove distribution area; The formula for calculating the terrain correction index is as follows: S represents the terrain correction index, and RE and ESD represent the slope, relative elevation, and standard deviation of elevation obtained from the DEM data, respectively. The normalized water index is calculated based on the preprocessed GF-2 multispectral image, where a, b, c, and d are the weights of slope, relative elevation, elevation standard deviation, and normalized water index, respectively.

2. The mangrove forest extraction method based on multi-source data collaboration according to claim 1, characterized in that, S3 includes: S31: Use the boundary vector of the study area to crop the preprocessed Sentinel-2 multispectral image to obtain the medium-resolution image data of the study area; S32: Calculate the spectral index of each pixel in the study area based on the medium-resolution image data of the study area; The spectral indices include one or more of the following: red-edge normalized vegetation index, red-edge location index, and water stress index, and the calculation formula is as follows: RE_NDVI is the red-edge normalized vegetation index, REP is the red-edge position index, MSI is the water stress index, and B4, B5, B7, B8A, and B11 represent the remote sensing reflectance of bands 4, 5, 7, 8A, and 11 of the preprocessed Sentinel-2 multispectral image, respectively. S33: Compare each spectral index with the set index thresholds to obtain the initial extracted mangrove area.

3. The mangrove forest extraction method based on multi-source data collaboration according to claim 2, characterized in that, S33 includes: S331: For each pixel in the study area, the red-edge normalized vegetation index of the pixel is compared with the set vegetation index threshold. Pixels with a red-edge normalized vegetation index greater than the vegetation index threshold are classified as mangroves to obtain the first initially extracted mangrove range. S332: For each pixel in the study area, compare the red edge position index of the pixel with the set position index threshold, and classify the pixels with the red edge position index greater than the position index threshold as mangroves to obtain the second initial extracted mangrove range. S333: For each pixel in the study area, the water stress index of the pixel is compared with the set water stress index threshold. Pixels with a water stress index less than the water stress index threshold are classified as mangroves, and the third initial mangrove range is obtained. S334: Take the union of the first initially extracted mangrove area, the second initially extracted mangrove area, and the third initially extracted mangrove area to obtain the initially extracted mangrove region.

4. The mangrove forest extraction method based on multi-source data collaboration according to claim 1, characterized in that, S4 includes: S41: Based on the boundary of the initially extracted mangrove area, a buffer zone with a set distance is constructed on both the inner and outer sides of the boundary to obtain the boundary area of ​​the initially extracted mangrove area; S42: Based on the boundary vector of the initially extracted mangrove boundary region, the preprocessed GF-2 multispectral image is cropped to obtain the boundary region to be corrected. S43: The mangrove forests in the boundary area to be corrected are extracted using machine learning methods to obtain the mangrove forest boundary correction result; S44: Replace the initially extracted mangrove boundary region within the initially extracted mangrove region with the mangrove boundary correction result to obtain the corrected mangrove region.

5. The mangrove forest extraction method based on multi-source data collaboration according to any one of claims 1-4, characterized in that, S5 includes: S51: Based on DEM data, calculate the slope, relative elevation, and elevation standard deviation of each pixel in the study area using geographic information system software; S52: Calculate the normalized water index for each pixel in the study area based on the preprocessed GF-2 multispectral image; Wherein, NDWI is the normalized water index, and Green and NIR represent the remote sensing reflectance of the green band and near-infrared band of the preprocessed GF-2 multispectral image, respectively. S53: The terrain correction index for each pixel within the study area is constructed using the following formula: S54: Compare the terrain correction index of each pixel in the study area with the determined segmentation threshold, and classify the pixels with terrain correction index greater than the segmentation threshold as potential water accumulation areas. S55: Remove the potential waterlogged area from the modified mangrove area to obtain the final mangrove distribution area.

6. The mangrove forest extraction method based on multi-source data collaboration according to claim 5, characterized in that, The weights of the slope, relative elevation, elevation standard deviation, and normalized water index are determined as follows: The subjective weights of slope, relative elevation, elevation standard deviation, and normalized water index were determined using the analytic hierarchy process (AHP). The objective weights of slope, relative elevation, elevation standard deviation, and normalized water index were determined using the CRITIC method. The subjective and objective weights are linearly weighted to obtain the weights of slope, relative elevation, elevation standard deviation, and normalized water index.

7. The mangrove forest extraction method based on multi-source data collaboration according to claim 5, characterized in that, The segmentation threshold is determined in the following manner: The dataset of the terrain correction index was subjected to unsupervised clustering fitting using a Gaussian mixture model, resulting in two Gaussian distributions. The value of the terrain correction index corresponding to the intersection of the probability density functions of the two Gaussian distributions is used as the segmentation threshold.

8. A mangrove forest extraction device based on multi-source data collaboration, characterized in that, The device includes: The data acquisition module is used to acquire multi-source data of the same time period in the study area; The multi-source data includes medium-resolution Sentinel-2 multispectral images, high-resolution GF-2 multispectral images, and DEM data. The preprocessing module is used to preprocess the Sentinel-2 multispectral images and GF-2 multispectral images; The initial extraction module is used to perform preliminary extraction of mangroves based on the spectral indices of the preprocessed Sentinel-2 multispectral image to obtain the initial extracted mangrove area; The boundary correction module is used to correct the boundaries of the initially extracted mangrove areas based on the preprocessed GF-2 multispectral image using machine learning methods, so as to obtain the corrected mangrove areas. The terrain correction module is used to construct a terrain correction index based on DEM data and preprocessed GF-2 multispectral imagery, and remove potential water accumulation areas from the corrected mangrove area according to the terrain correction index to obtain the final mangrove distribution area. The formula for calculating the terrain correction index is as follows: S represents the terrain correction index, and RE and ESD represent the slope, relative elevation, and standard deviation of elevation obtained from the DEM data, respectively. The normalized water index is calculated based on the preprocessed GF-2 multispectral image, where a, b, c, and d are the weights of slope, relative elevation, elevation standard deviation, and normalized water index, respectively.

Images