A multi-scale remote sensing small and micro terrestrial water body refinement extraction method

Abstract

This invention discloses a method for refined extraction of small land surface water bodies based on multi-scale remote sensing, comprising: constructing a high-medium-low resolution image pyramid using multi-source satellite remote sensing data to achieve adaptive band combination optimization based on the spectral characteristics of small water bodies, and performing multi-scale noise suppression and radiometric normalization processing; pre-setting a geometric shape quantification index for small water bodies to construct a small water body screening mechanism constrained by geometric features, thereby achieving coarse localization of candidate regions for small water bodies; employing a scale weight adaptive allocation algorithm to dynamically adjust the contribution weights of data at different scales according to the geometric features of candidate regions, establishing a joint discrimination model of spectral-spatial-geometric features for small water bodies, thereby achieving accurate extraction of small water bodies; and constructing a boundary optimization method based on a functional energy model, and combining it with small-area noise removal, connected region merging, and consistency verification of results constrained by temporal data to achieve boundary optimization of small water bodies.

Description

Technical Field

[0001] This invention belongs to the technical field of intelligent analysis of remote sensing images, specifically involving a method for refining and extracting small-scale land surface water bodies based on multi-scale remote sensing. Background Technology

[0002] Small-scale surface water bodies typically refer to water bodies with an area between 0.01 and 1 hectare, including small ponds, farmland irrigation ditches, small reservoirs, and urban landscape water bodies. These water bodies are an important component of surface water resources, playing a crucial role in maintaining regional ecological balance, regulating local climate, and supporting agricultural irrigation. With the increasing demand for ecological environment governance and refined water resource management, the need for high-precision, large-scale, and dynamic monitoring of small-scale water bodies is becoming increasingly urgent. Traditional ground survey methods suffer from high costs and low efficiency, making it difficult to meet the requirements of large-scale, high-frequency monitoring. Remote sensing technology, due to its wide coverage, lower cost, and high timeliness, has become the main technical means for water body monitoring.

[0003] Currently, water body extraction methods based on remote sensing imagery mainly include spectral index methods, supervised classification methods, and object-oriented classification methods. While spectral index methods (such as NDWI and MNDWI) are computationally simple and efficient, they are easily affected by mixed pixels and surrounding land features, and have limited ability to identify small, irregularly shaped water bodies. Supervised classification methods rely on a large number of labeled samples and have relatively high classification accuracy, but their ability to distinguish between land features with similar spectral characteristics (such as shadows and moist soil) remains insufficient. Object-oriented classification methods can improve classification results to some extent through image object segmentation, but their complex segmentation parameter settings and low automation limit their application in large-scale monitoring.

[0004] In recent years, deep learning technology has made significant progress in semantic segmentation of remote sensing images, with convolutional neural network models such as U-Net and DeepLab demonstrating good performance in water body extraction tasks. However, existing methods still have the following problems: First, single-scale processing struggles to simultaneously preserve details and suppress noise in small water bodies; second, there is a lack of specialized design for the geometric features of small water bodies; third, boundary extraction accuracy is not high enough to meet the needs of refined applications; and fourth, insufficient temporal consistency constraints affect the reliability of long-term monitoring. Therefore, there is an urgent need to develop a refined extraction method for small water bodies that can effectively process multi-scale information, fully utilize geometric feature constraints, and achieve high-precision boundary extraction. Summary of the Invention

[0005] To address the technical problems of low accuracy in identifying small water bodies and inaccurate boundary extraction in existing technologies, this invention provides a refined extraction method for small land surface water bodies based on multi-scale remote sensing. The three-stage refined extraction strategy for small water bodies constructed by this method—coarse positioning, fine boundary, and post-optimization—can effectively identify small water bodies with an area of ​​0.01-1 hectare, and the boundary positioning accuracy reaches the sub-pixel level, providing important support for precise water resource supervision.

[0006] To achieve the above objectives, the present invention provides the following solution:

[0007] A method for refined extraction of small-scale land surface water bodies based on multi-scale remote sensing, the method comprising:

[0008] Using multi-source satellite remote sensing data, a high-medium-low resolution image pyramid is constructed to achieve adaptive band combination optimization based on the spectral characteristics of small water bodies, and multi-scale noise suppression and radiometric normalization processing are performed.

[0009] Based on preprocessed multi-source remote sensing image data, a geometric shape quantification index for small water bodies is preset. Based on the geometric shape feature quantification index for small water bodies, a small water body screening mechanism constrained by geometric features is constructed to achieve coarse localization of candidate areas for small water bodies.

[0010] Based on preprocessed multi-source remote sensing image data, a scale weight adaptive allocation algorithm based on the similarity of water body geometric features is adopted. The contribution weight of data at different scales is dynamically adjusted according to the geometric features of candidate regions. A joint discrimination model of spectral-spatial-geometric features of small water bodies is established to achieve accurate extraction of small water bodies.

[0011] A boundary optimization method based on a functional energy model is constructed, and the results of small-area noise removal, connected region merging, and time-series data constraint consistency verification are combined to achieve boundary optimization of small water bodies.

[0012] Preferably, the method for constructing a high-medium-low resolution image pyramid using multi-source satellite remote sensing data, achieving adaptive band combination optimization based on the spectral characteristics of small water bodies, and performing multi-scale noise suppression and radiometric normalization processing includes:

[0013] The image pixel values ​​are unified to a dimensionless reflectance space using a radiometric normalization method. The processing method is as follows:

[0014] ;

[0015] in, For the first Normalized reflectance value for the band; These are the original image pixel values; and These are the pixel values ​​for dark and bright targets, respectively;

[0016] A multi-scale pyramid structure is adopted to unify the imagery into three levels: high-resolution layer ≤2m, medium-resolution layer 5~30m, and low-resolution layer ≥30m. Spatial resampling uses bicubic interpolation, with the following formula:

[0017] ;

[0018] in, Indicates the location in the image coordinates after resampling. Pixel values; Indicates that the original image is located in The pixel digital value; of which and This represents the relative coordinate offset, with a value range of [value range missing]. This corresponds to 16 neighboring pixels. The weighting function is a bicubic interpolation function, the value of which is determined by the pixel offset distance, which can smooth the calculation results and preserve local details; coordinates The grid coordinates are the resampled target image, with the top left corner of the image as the origin. x Indicates column direction, y Indicates line direction; offset The relative positions of neighboring pixels involved in interpolation in the original image are defined, where The offset is in the horizontal direction. The offset is in the vertical direction;

[0019] Wavelet decomposition and reconstruction methods are applied to images of different scales, with the following formula:

[0020] ;

[0021] in, The image is after filtering. For scale ,direction wavelet basis functions, These are the corresponding wavelet coefficients;

[0022] Cloud and cloud shadow detection combining spectral and temporal features: The Fmask method based on spectral thresholds is used to automatically identify cloud regions and cloud shadow regions, obtaining a cloud mask matrix. Combined with time-series images Based on the spectral consistency constraint, data interpolation is performed on pixels in cloud-occluded areas, and the interpolation formula is as follows:

[0023] ;

[0024] in, This represents the image value of the cloud-occluded area at time t after interpolation; and These represent the denoised image values ​​at adjacent time points; As a weighting factor, its value is dynamically determined based on the spectral similarity of pixels in the time series and the time interval, and it can adaptively adjust the contribution of the previous and next images to the interpolation results.

[0025] Preferably, the method for coarsely locating candidate regions of small water bodies by constructing a small water body screening mechanism based on the geometric shape quantification index of small water bodies includes:

[0026] ;

[0027] in, For joint discriminant function, To form a comprehensive density index, The boundary complexity index, It is the shape regularity index. For the weight parameters, satisfying ;when threshold Time, region It has been identified as a candidate area for small water bodies.

[0028] Preferably, a scale-weighted adaptive allocation algorithm based on water body geometric similarity is used to dynamically adjust the contribution weights of data at different scales according to the geometric features of candidate regions, and a joint discrimination model of spectral-spatial-geometric features for small water bodies is established. This method for accurately extracting small water bodies includes:

[0029] Based on the preprocessed multi-source remote sensing image data, denoted as high-resolution image Medium resolution images With low-resolution images Different scale levels are formed through the pyramid decomposition method:

[0030] ;

[0031] Where DownSample(·) represents the downsampling operator, For scale levels;

[0032] Standardization is performed using the min-max normalization method:

[0033] ;

[0034] An improved small water body index is constructed based on an adaptive band combination optimization method using entropy weighting. This index is achieved through a weighted combination of the Normalized Differential Water Index (NDWI) and the Improved Normalized Differential Water Index (MNNDWI), as shown below:

[0035] ;

[0036] in, Representing scale Next pixel An improved micro-water body index is used to measure the intensity of water body features in a pixel. , and These represent the green band, near-infrared band, and short-wave infrared band at scale s, respectively, with parameters... and The band combination weights are used to adjust the contribution of each band to water body identification; in the weight determination process, the entropy weight method is introduced. and Based on the relative importance of NDWI and MNNDWI, adaptive optimization of band combinations is achieved:

[0037] ;

[0038] in, The band combination coefficients of the optimized NDWI are used to enhance the significance of the spectral characteristics of water bodies. Their values ​​are calculated by the entropy weight method and reflect the relative contribution of NDWI to distinguishing water bodies from non-water bodies. The band combination coefficients of the optimized MNNDWI are used to supplement the identification ability of small water body edges and complex backgrounds. The values ​​are calculated by the entropy weight method and reflect the relative contribution of MNNDWI to the water body extraction accuracy.

[0039] After obtaining water body indices at various scales, we first construct a geometric feature quantification index by combining the geometric characteristics of the candidate water body regions; simultaneously, we introduce a water body probability model. The probability of each pixel being a body of water is quantified; a density index and boundary complexity are introduced to define a geometric consistency index at scale s. Based on the geometric consistency index, an adaptive scale weight allocation function is defined, ultimately yielding a multi-scale adaptive water index. :

[0040] ;

[0041] in, To adapt water quality indices at multiple scales, For adaptive scaling weight allocation function, For scale levels.

[0042] Preferably, boundary optimization methods based on functional energy models include:

[0043] ;

[0044] in, For the active contour curve C ( s The functional energy of ) These are boundary smoothing control parameters used to suppress boundary noise and ensure overall contour smoothness. This is a curvature adjustment parameter used to maintain boundary continuity and prevent excessive bending; λ External energy weights control the guiding effect of image information on contour evolution; P ( C ( s The gradient potential function is constructed based on the grayscale or spectral feature gradient of water body pixels. It attracts the contour to converge towards the boundary of the real water body. Let be the first derivative vector, representing the boundary curve under the parameter . The tangent vector at a given point is used to describe the local change in the direction of the curve. The second derivative vector represents the boundary curve under the parameter. The rate of change of curvature at a given point is used to control the degree of curvature and continuity of the curve.

[0045] Preferred methods for small-area noise removal and connected region merging include:

[0046] Based on boundary refinement, a connected component labeling algorithm is used to analyze small water body regions. Let the set of connected components of small water bodies in the extracted results be denoted as . , Its area is Perform a threshold operation on each connected region:

[0047] ;

[0048] in, This represents the set of valid connected regions of small water bodies that are retained, i.e., all connected regions that satisfy the area threshold. The threshold is the minimum effective water area; areas smaller than this threshold will be considered noise and removed. Meanwhile, areas that are spatially adjacent and have boundaries narrower than the threshold will also be removed. For small water bodies, perform a region merging operation:

[0049] .

[0050] Preferably, the methods for verifying the consistency of time-series data constraints include:

[0051] Suppose a certain area is t The extraction result of time is ,exist t The result at time +1 is A temporal similarity constraint function is constructed by integrating spectral similarity, geometric similarity, and spatial neighborhood consistency.

[0052] ;

[0053] in, A consistency index representing boundary complexity and shape regularity. Indicators representing spatial continuity of the surrounding area , , The adaptive weighting coefficients are determined based on the water body type, area, shape, and background features.

[0054] when When the threshold θ is less than the threshold value, it indicates that there is temporal inconsistency in the region, which requires dynamic optimization and correction.

[0055] Preferably, when When the threshold θ is less than the threshold value, it indicates that there is temporal inconsistency in this region. Methods for dynamic optimization and correction include:

[0056] Using historical results { R 1, R 2, …, R t-1} and the current result R t The weighted multiple decisions have been updated:

[0057] ;

[0058] Where weighted-mode(·) represents the weighted majority voting function, and the weights are... w t The allocation is dynamically determined based on the reliability of historical time series, cloud shadow occlusion, and detection confidence.

[0059] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0060] (1) By using multi-scale information fusion and geometric feature constraints, the accuracy of identifying small water bodies is significantly improved, with a 15-25% improvement in accuracy compared to traditional methods.

[0061] (2) The active contour model is used for boundary refinement, which realizes the precise boundary extraction at the sub-pixel level and controls the boundary positioning error within 1-2 pixels.

[0062] (3) The adaptive weight allocation algorithm can dynamically adjust the processing strategy according to the characteristics of different regions and has good adaptability to complex terrain and diverse small water body types.

[0063] (4) It can effectively identify ultra-small water bodies with an area of ​​0.01-1 hectare, and the boundary positioning accuracy reaches the sub-pixel level. It is suitable for high-precision intelligent monitoring of small water bodies in fields such as urban waterlogging monitoring, precision agricultural irrigation, dynamic assessment of ecological environment, and refined management of water resources. Attached Figure Description

[0064] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1 This is a schematic diagram of a method for refining and extracting small-scale land surface water bodies based on multi-scale remote sensing, according to an embodiment of the present invention. Detailed Implementation

[0066] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0067] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0068] Example 1

[0069] like Figure 1 As shown, this invention provides a method for refined extraction of small-scale land surface water bodies based on multi-scale remote sensing, the method comprising:

[0070] Using multi-source satellite remote sensing data, a high-medium-low resolution image pyramid is constructed to achieve adaptive band combination optimization based on the spectral characteristics of small water bodies, and multi-scale noise suppression and radiometric normalization processing are performed.

[0071] Based on preprocessed multi-source remote sensing image data, a geometric shape quantification index for small water bodies, including density index, boundary complexity, and shape regularity, is preset. Based on the geometric shape quantification index of small water bodies, a small water body screening mechanism constrained by geometric features is constructed to achieve coarse localization of candidate areas for small water bodies.

[0072] Based on preprocessed multi-source remote sensing image data, a scale weight adaptive allocation algorithm based on the similarity of water body geometric features is adopted. The contribution weight of data at different scales is dynamically adjusted according to the geometric features of candidate regions. A joint discrimination model of spectral-spatial-geometric features of small water bodies is established to achieve accurate extraction of small water bodies.

[0073] A boundary optimization method based on a functional energy model is constructed, and the results of small-area noise removal, connected region merging, and time-series data constraint consistency verification are combined to achieve boundary optimization of small water bodies.

[0074] In this embodiment, multi-source remote sensing data acquisition:

[0075] 1. The data required for this invention mainly includes the following categories:

[0076] (1) High spatial resolution data

[0077] Acquire sub-meter to meter-level high spatial resolution satellite images from Gaofen-2 (GF-2), Gaofen-6 (GF-6), WorldView series, and GeoEye series covering the study area, with panchromatic band spatial resolution better than 1 meter.

[0078] (2) Hyperspectral data

[0079] Acquire hyperspectral satellite images of the study area from ZY1-02D, HJ-2A / 2B, Gaofen-5 (GF-5), and EO-1 Hyperion.

[0080] (3) High temporal resolution data

[0081] Acquire multi-temporal resolution satellite images from Sentinel-2A / 2B, Landsat 8 / 9, and domestic Gaofen-1 and Gaofen-6 satellites within the research period (e.g., 3 months).

[0082] In this embodiment, multi-source remote sensing data preprocessing:

[0083] Before performing refined extraction of small water bodies, this invention first preprocesses multi-source, multi-scale remote sensing data to ensure consistency in spectral, spatial, and radiometric characteristics across images of different resolutions, thus providing reliable input for subsequent geometric feature constraints and boundary refinement. The specific steps are as follows:

[0084] (1) Image radiometric normalization processing

[0085] Due to differences in imaging time, imaging angle, and atmospheric conditions among different satellite sensors, there are significant radiometric deviations between the original images. To achieve comparability of multi-source images, a radiometric normalization method is used to unify the image pixel values ​​into a dimensionless reflectance space. The processing method is as follows:

[0086] ;

[0087] in, For the first Normalized reflectance value for the band; These are the original image pixel values; and These are the pixel values ​​for dark and bright targets, respectively. This normalization process effectively eliminates systematic errors between different data sources.

[0088] (2) Spatial resolution uniformity and pyramid construction

[0089] For high, medium, and low resolution remote sensing data from different sources, this invention proposes a multi-scale image pyramid structure to unify the original remote sensing images into three levels: a high-resolution layer (≤2m), a medium-resolution layer (5~30m), and a low-resolution layer (≥30m), so as to achieve collaborative extraction of information on small water bodies at multiple scales. To achieve spatial resolution consistency, this invention resamples images of different resolutions using a bicubic interpolation method. The resampling formula is as follows:

[0090] ;

[0091] in, Indicates the location in the image coordinates after resampling. Pixel values; Indicates that the original image is located in The pixel digital values, of which and This represents the relative coordinate offset, with a value range of [value range missing]. This corresponds to 16 neighboring pixels. The weighting function is a bicubic interpolation function, the value of which is determined by the pixel offset distance, which can smooth the calculation results and preserve local details; coordinates These are the grid coordinates after resampling the target image, typically with the top-left corner of the image as the origin. x Indicates column direction, y Indicates line direction; offset The relative positions of neighboring pixels involved in interpolation in the original image are defined, where The offset is in the horizontal direction. This is a vertical offset.

[0092] This method can preserve spatial detail information in multi-scale pyramid levels and avoid excessive amplification of high-frequency noise during high-resolution image resampling, providing a high-quality image foundation for the subsequent fine extraction of small water bodies.

[0093] (3) Multi-scale noise suppression and cloud removal

[0094] To reduce noise and cloud interference during the extraction of small water bodies, this invention employs wavelet transform filtering to suppress high-frequency noise in multi-scale image processing. It also introduces a cloud removal and interpolation mechanism combining spectral and temporal features, thereby achieving effective restoration of missing information and stable detection of water body targets. In the noise suppression stage, this invention uses wavelet decomposition and reconstruction methods for images at different scales, with the following formula:

[0095] ;

[0096] in, The image is after filtering. For scale ,direction wavelet basis functions, These are the corresponding wavelet coefficients. By setting an adaptive threshold in the high-frequency subband to suppress high-frequency noise and retaining the main spectral features of the water body in the low-frequency subband, the details of small water bodies are preserved while effectively reducing background interference.

[0097] (4) In this invention, to further ensure the continuity and accuracy of monitoring small water bodies in multiple time phases, a cloud and cloud shadow detection and data interpolation method combining spectral features and temporal features is proposed. Specifically, the following steps are included: First, using the spectral features of multi-source remote sensing images, an improved Fmask method based on spectral thresholds is adopted to achieve automatic identification of cloud regions and cloud shadow regions, obtaining the cloud mask matrix C, whose expression is:

[0098] ;

[0099] in, x , y For the row and column coordinates of the image, This indicates that the pixel at that location is covered by a cloud or cloud shadow. This indicates that the pixel at that location is a valid observation. Compared with existing technologies, this invention not only performs cloud detection based on the spectral threshold of a single image, but also introduces a dynamic threshold adjustment mechanism for small water bodies on top of the Fmask, to enhance the ability to identify small shadows and semi-transparent clouds, achieving accurate masking coverage of small water bodies. Subsequently, for pixel areas obscured by clouds, the time-series image is combined... Based on the spectral consistency constraint, temporal interpolation of pixel values ​​is performed. The interpolation formula is:

[0100] ;

[0101] in, This represents the image value of the cloud-occluded area at time t after interpolation; and These represent the denoised image values ​​at adjacent time points; The weighting factor is dynamically determined based on the spectral similarity of pixels over time and the time interval, enabling adaptive adjustment of the contribution of previous and subsequent images to the interpolation results. This method effectively recovers water body information lost due to cloud interference, ensuring the continuity and integrity of small water bodies in multi-temporal monitoring.

[0102] By using multi-scale wavelet noise suppression and cloud removal and interpolation processing that combines spectral and temporal features, this invention significantly reduces noise interference and cloud occlusion while ensuring the preservation of boundary details of small water bodies and the temporal stability of the extraction results, providing high-quality input data for subsequent geometric feature constraints and boundary refinement.

[0103] The innovation of this invention lies in the weighting factor Coupled with local spectral statistical properties and contrast indices of images, dynamic adaptive optimization is achieved, eliminating reliance on manual parameter settings. Compared to traditional fixed-parameter MNDWI enhancement methods, this significantly improves the recognition rate and boundary accuracy of small water bodies, offering a significant advantage in detecting small water bodies against complex backgrounds.

[0104] In this embodiment, geometric feature-driven coarse localization of candidate regions for small water bodies is performed:

[0105] To effectively distinguish between small water bodies and pseudo-water bodies (such as shadows, moist soil, and road puddles), a method for locating candidate regions of small water bodies based on geometric feature constraints is proposed. By calculating geometric indices such as the density, boundary complexity, and shape regularity of the target region, rapid screening and optimization of candidate regions of small water bodies are achieved. The specific steps are as follows:

[0106] (1) Extraction of initial water body objects

[0107] To further highlight the spectral differences between water bodies and background features, this invention introduces an adaptive water index enhancement algorithm based on preprocessed multi-source remote sensing data. Using the Normalized Water Index (NDWI) as a foundation and combining it with a weight optimization strategy, it achieves accurate extraction of preliminary water body objects. Specifically, the improved adaptive water index NDWI is defined. The expression is:

[0108] ;

[0109] Where G represents the reflectance in the green band, and NIR represents the reflectance in the near-infrared band. α , β , It is an adaptive weighting factor that is dynamically adjusted based on the spectral distribution of the image region.

[0110] In this invention, α , β , The initialization is based on global optimization using image statistical characteristics. To fully consider the local spectral differences between water bodies and non-water background features in the image, this invention innovatively proposes a method for calculating the global mean and standard deviation based on weighted spatial neighborhoods, rather than traditional simple global statistics. Specifically:

[0111] ;

[0112] ;

[0113] Where SWIR represents the reflectivity of the short-wave infrared band, and N is the total number of image pixels. The adaptive weight for each pixel is defined as a local spectral similarity weight function of neighboring pixels. Specifically, it is calculated by coupling the spectral gradient with spatial location to enhance the response of the water area and suppress background interference. This neighborhood-weighted statistical method can fully reflect the local spectral characteristics, which is significantly different from the approach in the prior art that only relies on the simple global mean and standard deviation.

[0114] Based on the above global statistics, the initial weights α, β, and γ are set as follows:

[0115] ;

[0116] in, To prevent small constants from being divided by zero, α, β, and γ are dynamically adjusted, combined with NDWI. The index can adaptively enhance the spectral contrast between water bodies and background features in different image regions, making the initial extraction of water objects more accurate and the boundaries clearer.

[0117] The image is further divided into several local windows (e.g., 32×32 or 64×64 pixels), and for each window, the local water body index contrast is calculated. ,in and These are the average reflectances of pixels representing water and non-water bodies, respectively. Then, the weights are optimized based on contrast.

[0118] ;

[0119] in, For the green band within the local window and Joint standard deviation of reflectivity across bands It is a regulating factor used to enhance the stability of the spectral response.

[0120] The weights are then iteratively updated for each local window to maximize the spectral difference between the water body and the background. The iterative formula is:

[0121] ;

[0122] in, For contrast gradient, The learning rate is used to iterate until... Convergence or reaching the maximum number of iterations.

[0123] This method achieves adaptive weight adjustment, highlights the spectral characteristics of small water bodies, and suppresses pseudo-water body information such as vegetation, building shadows, and soil. Using the Otsu method, it establishes a water body / non-water body segmentation threshold, determines the initial water body region M, and further segments the water body region into different connected water body regions based on pixel connectivity principles. .

[0124] (2) Extraction of high-confidence candidate regions for small water bodies based on geometric features

[0125] For each connected water area Multidimensional geometric feature indices are introduced, including comprehensive compactness index, shape dispersion index, boundary fractal dimension index, radial variance index, etc., to more comprehensively characterize the morphological features of small water bodies, thereby improving the accuracy of small water body extraction.

[0126] Comprehensive tightness index for

[0127] ;

[0128] This index reflects the compactness of the region's shape. When the region is an ideal circle, The narrower or more irregular the shape, the better. The smaller the value.

[0129] Shape Dispersion Index This is used to measure the degree of deviation of the region boundary from the ideal ellipse fit. Let the region be... The length of the major axis is The length of the minor axis is Then the area of ​​its fitted ellipse is Defined as:

[0130] ;

[0131] When the region contour is close to the fitted ellipse A smaller value indicates a larger value, while a larger value indicates a greater number of complex disturbances at the boundary.

[0132] Boundary fractal dimension index This is used to characterize boundary complexity. Fractal analysis of the region boundary is performed using box counting, with a scale of [missing information]. The minimum number of boxes required to cover the boundary is , is defined as:

[0133] ;

[0134] Theoretically, the boundary dimension of a regular geometric shape is close to 1, while the boundary dimension of a region is complex and highly tortuous. Approaching 2.

[0135] Introducing the radial variance index This is used to reflect the symmetry and regularity of a water body region relative to its centroid. Specifically, let the centroid coordinates of the water body region to be analyzed be... The set of boundary points of the region is ,in This represents the total number of sampling points on the boundary of the water body region, i.e., the number of discrete points used to characterize the boundary. For each boundary point... Calculate its radial distance to the centroid. The formula is:

[0136] ;

[0137] Based on this, the radial variance index The definition is as follows.

[0138] ;

[0139] in, This represents the mean radial distance of all boundary points, i.e.

[0140] This index can quantitatively reflect the geometric regularity of a water body: when the shape of the water body approaches a circle, the radial distance from each boundary point to the centroid changes little, therefore... The value is relatively small; when the water body area has an irregular shape or obvious protrusions, the radial distance distribution of each boundary point varies significantly, leading to... The value increases significantly. This index can be used to quantitatively evaluate the regularity of the shape of small water bodies during the screening of candidate regions and the constraint of geometric features, thereby further optimizing the accuracy of water body boundary extraction.

[0141] By analyzing the above multidimensional geometric feature indicators The present invention uses a combined discrimination method, setting multiple threshold constraint rules in the initial screening stage: Only when the candidate region simultaneously satisfies... , , , hour, , , , The threshold values ​​are determined using a probability histogram.

[0142] Through the above constraint mechanism, the small water bodies that are ultimately identified as high-confidence candidate areas are effectively removed, thereby effectively eliminating areas with unreasonable shapes or interference caused by pseudo-water bodies such as shadows and stagnant water.

[0143] (2) Location of candidate areas for small water bodies under the joint constraints of multiple indicators

[0144] After identifying high-confidence candidate regions for small water bodies, this invention designs a multi-index joint constraint mechanism, including a comprehensive density index. Boundary complexity index and shape regularity index It is used to quantify the spatial morphological characteristics of small water bodies, thereby enabling accurate identification of candidate areas for small water bodies.

[0145] 1. Comprehensive density index

[0146] The Comprehensive Density Index measures the compactness of a region's internal morphology, effectively distinguishing between bodies of water and pseudo-water features such as narrow shadows or roads. Its definition is:

[0147] ;

[0148] in, Indicates the region area, Indicates the region The boundary length. For circular or approximately regular bodies of water, The value is close to 1; for elongated or irregularly shaped regions, The value decreased significantly.

[0149] 2. Boundary Complexity Index

[0150] The boundary complexity index is used to characterize the tortuosity of water body boundaries and can effectively identify regions with high geometric irregularities. It is defined as follows:

[0151] ;

[0152] The denominator is equal to the area. The same circumference of a circle. If the shape of a body of water is nearly circular, then... If the water body has complex boundaries or is elongated in shape, then The value increased significantly.

[0153] 3. Shape regularity index

[0154] The shape regularity index is used to describe the regularity of the morphology of water bodies, and is particularly suitable for distinguishing between regular small water bodies and naturally formed irregular shapes. It is defined as follows:

[0155] ;

[0156] in, Indicates the region spindle length, This indicates the length of the secondary axis. When the water body is nearly circular or square... The value is close to 1; when the region is a long and narrow strip, The value is close to 0.

[0157] Based on the above three indices, a joint discriminant function is constructed:

[0158] ;

[0159] in, For the weight parameters, satisfying .when Time, region It has been identified as a candidate area for small water bodies.

[0160] This multi-index joint constraint model (joint discriminant function) enables precise segmentation of candidate regions for small water bodies, significantly improving the accuracy and reliability of small water body extraction.

[0161] In this embodiment, based on lightly processed multi-channel wave image data, a scale-weighted adaptive fusion algorithm based on water body geometric similarity is proposed to address the problem of small water body extraction. The specific steps are as follows:

[0162] 1. Targeting a specific region in the image (Obtained through geometric constraint screening), calculate its geometric similarity index on images at different resolutions. Set the image scale to [value missing]. ,in Geometric similarity can be defined as a measure of the similarity in shape between a candidate region and the actual water body boundary. For example, normalized Hausdorff distance or shape features can be used.

[0163] ;

[0164] in, For the candidate region boundary, For scale Boundary estimation of groundwater bodies This represents the Hausdorff distance. The higher the geometric similarity, the closer the value is to 1.

[0165] 2. Based on this similarity index, an adaptive weighting formula is defined for data at different scales:

[0166] ;

[0167] Through this weight The influence of images at different scales on the extraction of small water bodies is dynamically adjusted to maintain high-resolution accuracy while also considering the smoothness and edge suppression effect of low-resolution images. Next, a three-stage self-evolutionary refinement extraction strategy is adopted for candidate regions, implementing boundary extraction and refinement in stages: 1. Coarse-grained stage: Based on weighted fused images at various scales, preliminary water body discrimination is performed on candidate regions, generating coarse-grained boundaries. Stable positioning mainly depends on spectral thresholds and geometric constraints. The formula is expressed as:

[0168] ;

[0169] in, For pixels In scale Water spectral determination function under the following conditions 1. **Coarse localization threshold:** This is the initial threshold. 2. **Refining stage:** Building upon the coarse localization, the boundary is refined using feature constraints and geometric constraints of the candidate region. Through optimization of local gradient, edge energy, and geometric consistency, a refined boundary is generated. :

[0170] ;

[0171] in, For the spectral energy term, For geometric shape error terms, For the energy term constrained by spatial continuity, , , These are the weighting coefficients.

[0172] 3. Subsequent Stages: Based on the refined results, and combining time-series data consistency constraints and small circle noise removal, the boundaries are refined at the sub-pixel level to finally obtain the boundary. :

[0173] ;

[0174] in, For combined spectral-spatial-geometric energy, For timing consistency constraints, For small circle noise terms, and The adjustment coefficient is used. In this invention, the establishment process of the spectral-spatial-geometric feature joint decision model is as follows: Spectral features: Extracting spectral values ​​such as multi-channel band reflectance and single water body indices (ENDW1, MNDWI, etc.) to distinguish water body pixels from non-water body pixels. Spatial features: Including neighborhood relationships, connectivity, and shape similarity, used to improve boundary continuity and consistency between regions. Geometric features: Using quantitative indicators such as shape moments, compactness, length, and brightness to constrain candidate regions and prevent misidentification of non-water bodies. The joint decision model is expressed in the form of a geometrically constrained loss function as follows:

[0175] ;

[0176] in, , , These are the weighting coefficients.

[0177] Pixel classification and boundary delineation are performed by minimizing threshold energy. The advantages of the model are that it not only uses a single feature for judgment, but also uses multiple features for joint decision-making, which significantly improves the extraction accuracy and boundary location accuracy of small water bodies. At the same time, it overcomes the problem of inaccurate identification of large and small water bodies by single-scale and single-feature extraction methods in existing technologies, and achieves sub-pixel level boundary refinement.

[0178] In this embodiment, the adaptive multi-scale fusion algorithm accurately extracts small water bodies:

[0179] To address the mismatch in identification accuracy of small water bodies caused by differences in spatial resolution among multi-scale remote sensing data, this study employs multi-scale image modeling, adaptive optimization, and a scale weighting mechanism to enhance the fine delineation of small water body boundaries. The specific implementation process includes:

[0180] (1) Multiscale image construction and normalization processing

[0181] First, multi-scale construction and normalization are performed on the preprocessed multi-source remote sensing image data. Let the high-resolution image be... Medium resolution image is Low-resolution images are ,in Represents the spatial pixel coordinates of the image; Spatial resolution is typically smaller than , Spatial resolution at Within the range, Spatial resolution greater than .

[0182] To achieve multi-scale analysis, a pyramid decomposition method is used to downsample the images at different resolutions, constructing image representations at different scale levels. Specifically, for arbitrary scales... The multi-scale representation of an image is denoted as By using the downsampling operator DownSample get:

[0183] ;

[0184] Among them, DownSample This indicates a spatial downsampling operation used to generate lower-resolution image layers. Indicates the image scale levels, corresponding to high resolution respectively. medium resolution With low resolution Due to radiometric differences in multi-source images, a minimum-maximum normalization method is used to standardize the images at each scale to eliminate spectral biases between different images. The normalized image is denoted as... The calculation formula is as follows:

[0185] ;

[0186] in, and Representing images The minimum and maximum values ​​across all pixels. Through this normalization process, grayscale values ​​from images of different scales and sources are mapped to the range of [0,1], eliminating the influence of radiation differences on subsequent identification of small water bodies.

[0187] (2) Enhancement of spectral features of small water bodies based on adaptive band combination optimization

[0188] To address the sensitivity of small water bodies to spectral characteristics, this invention proposes an adaptive band combination optimization method based on entropy weighting to construct an improved small water body index. This index is achieved through a weighted combination of the Normalized Differential Water Index (NDWI) and the Modified Normalized Differential Water Index (MNNDWI). Specifically, it is represented as follows:

[0189] ;

[0190] The parameters are defined as follows: Representing scale Next pixel An improved micro-water body index is used to measure the intensity of water body features in a pixel. Representing scale Next pixel The green band reflectance value; Representing scale Next pixel The near-infrared reflectance value is used to calculate the normalized difference water index. ; Representing scale Next pixel The shortwave infrared reflectance value is used to calculate the improved normalized differential water index (MNNDWI). , The band combination weighting coefficients are adaptively determined using the entropy weighting method, and are used to adjust the contribution of different bands in the identification of small water bodies. It represents the image scale level, indicating different levels of the high, medium, and low resolution image pyramid, and is used for multi-scale feature extraction.

[0191] In the weight determination process, this invention introduces the entropy weight method to fully utilize the dispersion and contribution capacity of information in each band. Weight and By considering the relative importance of NDWI and MNNDWI, adaptive optimization of band combinations can be achieved:

[0192] ;

[0193] in, The band combination coefficients of the optimized NDWI are used to enhance the significance of the spectral characteristics of water bodies. Their values ​​are calculated by the entropy weight method and reflect the relative contribution of NDWI to distinguishing water bodies from non-water bodies. The band combination coefficients of the optimized MNNDWI are used to supplement the identification ability of small water body edges and complex backgrounds. The values ​​are calculated by the entropy weight method and reflect the relative contribution of MNNDWI to the water body extraction accuracy.

[0194] The final improved micro water body index was constructed. It can maximize the spectral distinction between water bodies and non-water bodies, improve the accuracy of identifying small water bodies, and is applicable to remote sensing image processing at different scales and under complex backgrounds.

[0195] (3) Construction of multi-scale adaptive water index based on geometric constraints

[0196] Obtaining water body indices at various scales , , Subsequently, this invention first combines the geometric features of candidate water body regions to construct geometric feature quantification indicators (including density index, boundary complexity, etc.), providing a constraint basis for subsequent multi-scale fusion. Simultaneously, a water body probability model is introduced. This is used to quantify the probability that each pixel is a body of water, thereby enhancing the ability to distinguish the edges of small water bodies and complex shapes. Its complete expression is:

[0197] ;

[0198] in, For scale The water index value below, To adjust the coefficient for the steepness of the curve, The threshold for water body identification is set. This probabilistic model quantifies the probability of each pixel being identified as a water body into a probability value between 0 and 1, effectively improving the recognition accuracy for complex boundaries and small water bodies.

[0199] Introducing a density index in, The area of ​​the water body. The length of the water body boundary. The closer to 1, the more regular the shape and the lower the boundary complexity. This is used to reflect the tortuosity and morphological complexity of water body boundaries. Based on the above geometric characteristics, a geometric consistency index is defined at scale s. :

[0200] ;

[0201] Where s ∈ {H, M, L} represents the high, medium, and low resolution image scales; Cs, Bs, and Ps represent the density index, boundary complexity, and boundary length of the water body region at scale s, respectively; the function f(Cs, Bs, Ps) can be specifically expanded as follows:

[0202] ;

[0203] in, α , β , This is an empirical adjustment coefficient used to balance the contributions of shape regularity, boundary complexity, and area influence to the geometric consistency index. Based on the geometric consistency index, an adaptive scale weighting function is defined:

[0204] ;

[0205] in, This represents the scale index corresponding to s. ∈ {H, M, L}; - Q Representing scale The geometric consistency index is used; λ is a semi-constant parameter used to adjust the sensitivity of the weight distribution. The resulting multi-scale adaptive water index is then obtained. The expression is:

[0206] ;

[0207] This comprehensive result automatically enhances the contribution of high-resolution imagery to water body boundary regions, ensuring boundary positioning accuracy. By combining geometric feature constraints and a water body probability model, it achieves spectral feature enhancement and information fusion of water bodies across multiple scales and sources. The Otsu method is then used to determine the water body and non-water body segmentation thresholds (segmentation threshold = the optimal threshold automatically determined using the Otsu method on a multi-scale adaptive water index map). (used for segmentation of water and non-water pixels), and under the constraint of the candidate region range of small water bodies, realizes the automatic extraction of small water bodies and generates a vector object set N.

[0208] In this embodiment, the boundary optimization of small water bodies is performed using both morphological and temporal consistency methods:

[0209] To address the issues of inaccurate boundary treatment, incomplete morphology, and interference from mixed pixels in small water bodies, a boundary optimization method based on a functional energy model is constructed. This method, combined with morphological processing, connected component analysis, and temporal consistency verification, achieves high-precision optimization of small water body boundaries. The implementation process includes the following steps:

[0210] (1) Initial boundary generation and active contour model construction

[0211] For a set of N small water body vector objects, an active contour model is used to refine the boundaries of each small water body object to achieve sub-pixel-level boundary localization. The specific steps are as follows:

[0212] First, for small water body vector objects, an initial boundary curve C(s)=(x(s),y(s)) is generated, where s∈[0,1] represents the parameterized position of the curve; x(s) represents the horizontal coordinate function of the curve in the two-dimensional image coordinate system, and its value range is the continuous real number interval of the image column coordinates, which can achieve sub-pixel level position description between pixel grids; y(s) represents the vertical coordinate function of the curve in the two-dimensional image coordinate system, and its value range is the continuous real number interval of the image row coordinates, which can also achieve sub-pixel level precise positioning; the initial boundary can be fitted by the water body contour in the coarse positioning stage or the region boundary obtained by filtering based on geometric features, ensuring that the initial contour covers the main water body area.

[0213] Secondly, the functional energy of the activity profile curve C(s) is defined as follows:

[0214] ;

[0215] in: These are boundary smoothing control parameters used to suppress boundary noise and ensure overall contour smoothness. This is a curvature adjustment parameter used to maintain boundary continuity and prevent excessive bending; λ External energy weights control the guiding effect of image information on contour evolution; P ( C ( s The image gradient potential function is constructed based on the grayscale or spectral feature gradient of water body pixels, which can attract the contour to converge towards the real water body boundary; based on this, the present invention... The definition is as follows:

[0216] First derivative vector:

[0217] ;

[0218] Indicates the boundary curve in the parameters The tangent vector at a given point is used to describe the local directional change of the curve.

[0219] Second derivative vector:

[0220] ;

[0221] Indicates the boundary curve in the parameters The rate of change of curvature at a given point is used to control the degree of curvature and continuity of the curve.

[0222] In this invention, the refined extraction of the boundary of small water bodies is achieved by iteratively minimizing the functional energy. This is achieved through a process called energy functional analysis. Specifically, the activity profile curve evolves gradually under the drive of energy functional analysis, causing the initial boundary to gradually approach the boundary of the real water body. The basic principle is as follows: First, the functional energy...

[0223] ;

[0224] By performing variational differentiation, the gradient direction of energy descent is obtained. This is then applied to the curve... Regarding time parameters By deriving the evolution equation, we can obtain:

[0225] ;

[0226] Expanding it into a specific form:

[0227] ;

[0228] in, This is a first-order smoothing constraint term used to suppress high-frequency noise at the boundary. This is a second-order curvature adjustment term, used to maintain curve continuity and avoid excessive bending; As an external potential energy term, it guides the curve to gradually converge toward the boundary where the image gradient is strongest.

[0229] In practical calculations, this invention employs a discrete iteration strategy to define the boundary curves. In the The coordinates of each iteration are represented as follows: Then the first The iterative update formula is:

[0230] ;

[0231] ;

[0232] in, This is the iteration step size; and These are the components of the gradient descent direction in the horizontal and vertical directions, respectively, determined by the variational results of the energy functional mentioned above.

[0233] (2) Small-area noise removal and connected region merging

[0234] Based on boundary refinement, a connected component labeling algorithm is used to analyze small water body regions. Let the set of connected components of small water bodies in the extracted results be denoted as . , Its area is Apply a threshold operation to each connected region:

[0235] ;

[0236] in, The minimum effective water area threshold (e.g., 3 pixel units) is used; areas smaller than the threshold will be considered noise and removed. This represents the set of valid connected regions of small water bodies that are retained, i.e., all connected regions that satisfy the area threshold:

[0237] ;

[0238] For connected regions that do not meet the area threshold This is considered noise and removed. Furthermore, for adjacent or geometrically close connected regions, a distance threshold can be used... Merging operations are performed to avoid boundary fragmentation and improve the continuity and integrity of small water body extraction:

[0239] ;

[0240] in, Indicates the region and The shortest boundary distance, This represents the newly connected region after merging. Additionally, for spatially adjacent regions with boundaries narrower than a threshold... For small water bodies, perform a region merging operation:

[0241] .

[0242] (3) Optimization of temporal consistency of small water bodies

[0243] In long-term remote sensing monitoring, to ensure the stability, continuity, and boundary consistency of the extraction results for small water bodies, this invention proposes a dynamic optimization mechanism based on temporal consistency constraints. Let the extraction result for a certain region at time t be... The extraction result at time t + 1 is To evaluate the consistency of water extraction results at different time points, a temporal similarity constraint function is introduced, which integrates spectral similarity, geometric similarity, and spatial neighborhood continuity.

[0244] ;

[0245] in:

[0246] 1. Spectral similarity index

[0247] ;

[0248] It represents the proportion of spatial overlap of water bodies at adjacent times, and is used to measure the spectral consistency of a region.

[0249] 2. Geometric consistency index Defined as:

[0250] ;

[0251] in, Indicates the complexity of water body boundaries (such as the ratio of perimeter to area). This indicates shape regularity (such as shape compactness or roundness). This index measures the degree to which the boundary complexity and shape of a water body remain consistent at different times. The value ranges from [0,1], and the larger the value, the more consistent the geometry.

[0252] 3. Spatial neighborhood continuity index Defined as:

[0253] ;

[0254] in, express The set of neighboring pixels of the region, 1(·) is an indicator function that counts the consistency of adjacent pixels in the water body region in space, reflecting the continuity of the water body boundary and spatial extension.

[0255] 4. Adaptive weighting coefficients , , The determination is based on the water body type, area, morphology, and background features to balance the importance of spectral, geometric, and spatial neighborhood under different temporal conditions.

[0256] when When the threshold θ is less than a certain value, it indicates that there is significant temporal inconsistency in the region, requiring dynamic optimization and correction. This invention utilizes historical results { R 1, R 2, …, Rt -1} and the current result Rt The weighted multiple-decision mechanism has been updated:

[0257] ;

[0258] Where weighted-mode(·) represents the weighted majority voting function, and the weights are... wt It can be dynamically allocated based on the reliability of historical time series, cloud shadow occlusion, and detection confidence.

[0259] This optimization mechanism can effectively correct false water body extraction caused by noise, cloud shadows, seasonal interference, or sudden events, while ensuring the boundary continuity and area stability of small water bodies in long-term series monitoring, thus achieving high precision and high reliability in monitoring dynamic changes of water bodies.

[0260] This method achieves dynamic adaptive optimization of water body extraction results, significantly improving the reliability and accuracy of long-term monitoring of small water bodies. Through the above optimization process, the final output of small water body extraction results is obtained, where water bodies are represented by 1 and non-water bodies by 0, and stored in raster format.

[0261] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made to the technical solutions of the present invention by those skilled in the art without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A method for refined extraction of small-scale land surface water bodies based on multi-scale remote sensing, characterized in that, The method includes: Using multi-source satellite remote sensing data, a high-medium-low resolution image pyramid is constructed to achieve adaptive band combination optimization based on the spectral characteristics of small water bodies, and multi-scale noise suppression and radiometric normalization processing are performed. Based on preprocessed multi-source remote sensing image data, a geometric shape quantification index for small water bodies is preset. Based on the geometric shape feature quantification index for small water bodies, a small water body screening mechanism constrained by geometric features is constructed to achieve coarse localization of candidate areas for small water bodies. Based on preprocessed multi-source remote sensing image data, a scale weight adaptive allocation algorithm based on the similarity of water body geometric features is adopted. The contribution weight of data at different scales is dynamically adjusted according to the geometric features of candidate regions. A joint discrimination model of spectral-spatial-geometric features of small water bodies is established to achieve accurate extraction of small water bodies. After obtaining water body indices at various scales, we first construct a geometric feature quantification index by combining the geometric characteristics of the candidate water body regions; simultaneously, we introduce a water body probability model. The probability of each pixel being a body of water is quantified; a density index and boundary complexity are introduced to define a geometric consistency index at scale s. Based on the geometric consistency index, an adaptive scale weight allocation function is defined, ultimately yielding a multi-scale adaptive water index. : ； in, Image coordinates, To adapt water quality indices at multiple scales, For adaptive scaling weight allocation function, For scale levels; ； Where s ∈ {H, M, L}, H, M, and L represent the image scales of high resolution, medium resolution, and low resolution, respectively. ∈{H, M, L};Q Representing scale The geometric consistency index is used; λ is a parameter used to adjust the sensitivity of the weight distribution. A boundary optimization method based on a functional energy model is constructed, and the results of small-area noise removal, connected region merging, and time-series data constraint consistency verification are combined to achieve boundary optimization of small water bodies.

2. The method according to claim 1, characterized in that, The method for constructing a high-, medium-, and low-resolution image pyramid using multi-source satellite remote sensing data, achieving adaptive band combination optimization based on the spectral characteristics of small water bodies, and performing multi-scale noise suppression and radiometric normalization processing includes: The image pixel values ​​are unified to a dimensionless reflectance space using a radiometric normalization method. The processing method is as follows: ； in, For the first Normalized reflectance value for the band; These are the original image pixel values; and These are the pixel values ​​for dark and bright targets, respectively; A multi-scale pyramid structure is adopted to unify the imagery into three levels: high-resolution layer ≤2m, medium-resolution layer 5~30m, and low-resolution layer ≥30m. Spatial resampling uses bicubic interpolation, with the following formula: ； in, Indicates the location in the image coordinates after resampling. Pixel values; Indicates that the original image is located in The pixel digital value; of which and This represents the relative coordinate offset, with a value range of [value range missing]. This corresponds to 16 neighboring pixels. The weighting function is a bicubic interpolation function, the value of which is determined by the pixel offset distance, which can smooth the calculation results and preserve local details; coordinates The grid coordinates are the resampled target image, with the top left corner of the image as the origin. x Indicates column direction, y Indicates line direction; offset The relative positions of neighboring pixels involved in interpolation in the original image are defined, where The offset is in the horizontal direction. The offset is in the vertical direction; Wavelet decomposition and reconstruction methods are applied to images of different scales, with the following formula: ； in, The image is after filtering. For scale ,direction wavelet basis functions, These are the corresponding wavelet coefficients; Cloud and cloud shadow detection combining spectral and temporal features: The Fmask method based on spectral thresholds is used to automatically identify cloud regions and cloud shadow regions, obtaining a cloud mask matrix. Combined with time-series images Based on the spectral consistency constraint, data interpolation is performed on pixels in cloud-occluded areas, and the interpolation formula is as follows: ； in, This represents the image value of the cloud-occluded area at time t after interpolation; and These represent the denoised image values ​​at adjacent time points; As a weighting factor, its value is dynamically determined based on the spectral similarity of pixels in the time series and the time interval, and it can adaptively adjust the contribution of the previous and next images to the interpolation results.

3. The method according to claim 1, characterized in that, Based on the geometric shape quantification index of small water bodies, a screening mechanism for small water bodies constrained by geometric features is constructed. Methods for coarsely locating candidate regions of small water bodies include: ； in, For joint discriminant function, To form a comprehensive density index, The boundary complexity index, It is the shape regularity index. For the weight parameters, satisfying ;when threshold Time, region It has been identified as a candidate area for small water bodies.

4. The method according to claim 1, characterized in that, A scale-weighted adaptive allocation algorithm based on water body geometric similarity is adopted. This algorithm dynamically adjusts the contribution weights of data at different scales according to the geometric features of candidate regions, establishing a joint discrimination model of spectral, spatial, and geometric features for small water bodies. The method for accurately extracting small water bodies includes: Based on the preprocessed multi-source remote sensing image data, denoted as high-resolution image Medium resolution images With low-resolution images Different scale levels are formed through the pyramid decomposition method: ； Where DownSample(·) represents the downsampling operator, For scale levels; Standardization is performed using the min-max normalization method: ； An improved small water body index is constructed based on an adaptive band combination optimization method using entropy weighting. This index is achieved through a weighted combination of the Normalized Differential Water Index (NDWI) and the Improved Normalized Differential Water Index (MNNDWI), as shown below: ； in, Representing scale Next pixel An improved micro-water body index is used to measure the intensity of water body features in a pixel. , and These represent the green band, near-infrared band, and short-wave infrared band at scale s, respectively, with parameters... and The band combination weights are used to adjust the contribution of each band to water body identification; in the weight determination process, the entropy weight method is introduced. and Based on the relative importance of NDWI and MNNDWI, adaptive optimization of band combinations is achieved: ； in, The band combination coefficients of the optimized NDWI are used to enhance the significance of the spectral characteristics of water bodies. Their values ​​are calculated by the entropy weight method and reflect the relative contribution of NDWI to distinguishing water bodies from non-water bodies. The value represents the band combination coefficient of the optimized MNNDWI, which is used to supplement the identification ability of small water body edges and complex backgrounds. Its value is calculated by the entropy weight method and reflects the relative contribution of MNNDWI to the water body extraction accuracy.

5. The method according to claim 1, characterized in that, Methods for constructing boundary optimization based on functional energy models include: ； in, For the active contour curve C ( s The functional energy of ) These are boundary smoothing control parameters used to suppress boundary noise and ensure overall contour smoothness. This is a curvature adjustment parameter used to maintain boundary continuity and prevent excessive bending; λ External energy weights control the guiding effect of image information on contour evolution; P ( C ( s The gradient potential function is constructed based on the grayscale or spectral feature gradient of water body pixels. It attracts the contour to converge towards the boundary of the real water body. Let be the first derivative vector, representing the boundary curve under the parameter . The tangent vector at a given point is used to describe the local change in the direction of the curve. The second derivative vector represents the boundary curve under the parameter. The rate of change of curvature at a given point is used to control the degree of curvature and continuity of the curve.

6. The method according to claim 1, characterized in that, Methods for small-area noise removal and connected region merging include: Based on boundary refinement, a connected component labeling algorithm is used to analyze small water body regions. Let the set of connected components of small water bodies in the extracted results be denoted as . , Its area is Perform a threshold operation on each connected region: ； in, This represents the set of valid connected regions of small water bodies that are retained, i.e., all connected regions that satisfy the area threshold. The threshold is the minimum effective water area; areas smaller than this threshold will be considered noise and removed. Meanwhile, areas that are spatially adjacent and have boundaries narrower than the threshold will also be removed. For small water bodies, perform a region merging operation: 。 7. The method according to claim 1, characterized in that, Methods for verifying the consistency of time-series data constraints include: Suppose a certain area is t The extraction result of time is ,exist t The result at time +1 is A temporal similarity constraint function is constructed by integrating spectral similarity, geometric similarity, and spatial neighborhood consistency. ； in, A consistency index representing boundary complexity and shape regularity. Indicators representing spatial continuity of the surrounding area , , The adaptive weighting coefficients are determined based on the water body type, area, shape, and background features. when When the threshold θ is less than the threshold θ, it indicates that there is temporal inconsistency in the region, which requires dynamic optimization and correction.

8. The method according to claim 7, characterized in that, when When the threshold θ is less than the threshold value, it indicates that there is temporal inconsistency in this region. Methods for dynamic optimization and correction include: Using historical results { R 1, R 2, …, R t-1 } and the current result R t The weighted multiple decisions have been updated: ； Where weighted-mode(·) represents the weighted majority voting function, and the weights are... w t The allocation is dynamically determined based on the reliability of historical time series, cloud shadow occlusion, and detection confidence.

Images