Oyster rack extraction method, system and medium based on high-resolution satellite remote sensing images

Abstract

The present invention discloses an oyster rack extraction method, system and medium based on high-resolution satellite remote sensing images, wherein the method comprises: obtaining satellite remote sensing images and performing preprocessing operations to obtain reflectivity data including geometric positioning; performing raster data processing on the reflectivity data, and vectorizing the processed raster data to generate an initial vector result of the oyster rack; processing the initial vector result of the oyster rack based on a vector editing method to obtain a final extraction result of the oyster rack. The present invention is based on the problem of low efficiency in oyster rack extraction from satellite remote sensing images, reduces the workload of manual extraction of oyster racks, reduces recognition errors caused by manual operations, realizes automation of the extraction method, and improves the accuracy and efficiency of oyster rack extraction.

Description

Technical Field

[0001] The present invention relates to the field of remote sensing image processing, and in particular to a method, system and medium for extracting oyster racks based on high-resolution satellite remote sensing images. Background Art

[0002] The rapid development of my country's aquaculture industry has significantly boosted the sustained growth of the fishery economy, particularly in coastal areas, where aquaculture is the primary source of income for fishermen. Oyster farming, in particular, plays a crucial role. The continued expansion of oyster aquaculture, particularly through extensive development, has far exceeded the carrying capacity of the aquatic environment, leading to water quality problems such as increased nitrogen and phosphorus levels and eutrophication, damaging the marine ecosystem. Furthermore, driven by economic interests, illegal aquaculture that does not comply with marine functional planning is widespread. This not only blocks waterways and impacts maritime safety, but also degrades coastal landscapes and hinders the development of large-scale offshore projects. Therefore, scientific management and rational planning of oyster aquaculture are urgently needed. Understanding the spatial distribution of oyster aquaculture areas is a crucial prerequisite for effective management. Traditionally, obtaining the spatial distribution of aquaculture areas requires manual field surveys and local statistical reporting, which consumes manpower, material resources, and time. Furthermore, due to environmental impacts and human interference, data accuracy is low, seriously hindering effective management and macroeconomic regulation by relevant departments.

[0003] With the continuous development and maturity of remote sensing technology, satellite remote sensing data, with its advantages of short cycle times, wide coverage, and rich ground information, provides a real-time, dynamic, and accurate record of surface information, providing favorable conditions for tracking and monitoring. Furthermore, with the improvement of the spatial resolution of remote sensing images, the extraction of tiny ground features has become possible, making it an important data source for oyster aquaculture monitoring. Using remote sensing technology to extract oyster roosts can minimize the influence of human factors and more objectively reflect the true distribution of oyster roosts, thus providing favorable conditions for understanding the status of oyster aquaculture, combating illegal aquaculture activities, and conducting large-scale monitoring.

[0004] At present, the main methods for extracting oyster slabs using satellite remote sensing images are: (1) visual interpretation method, which uses prior knowledge and manual interactive work to visually identify and delineate. This method is time-consuming and labor-intensive, inefficient, highly subjective, and has a low degree of automation; (2) pixel-based method, which realizes oyster slab identification and extraction by analyzing the spectral or texture differences between pixels. This method is mainly achieved by constructing a feature index. This method requires constructing an identification index based on the spectral characteristics of different data, and the extraction accuracy is not high; (3) object-oriented method, which uses a segmentation method to segment the image into different patches. Based on spectral, texture, shape, and contextual features, the category is determined by certain rules. The rule set established by this method has poor universality, the segmentation scale is uncertain, and it takes a long time. Therefore, a convenient, efficient, and versatile technical means is urgently needed to solve the above problems. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a method for extracting oyster roosts based on high-resolution satellite remote sensing imagery. This method significantly reduces manual labor, improves oyster roost extraction efficiency, and ensures the accuracy and efficiency of the extraction results.

[0006] The present invention also proposes an oyster rack extraction system based on high-resolution satellite remote sensing images.

[0007] The present invention also provides a computer-readable storage medium for implementing the above method.

[0008] According to the first aspect of the present invention, the oyster sack extraction method based on high-resolution satellite remote sensing images includes: acquiring satellite remote sensing images and performing preprocessing operations to obtain reflectivity data including geometric positioning; performing raster data processing on the reflectivity data, and vectorizing the processed raster data to generate an initial vector result of the oyster sack; processing the initial vector result of the oyster sack based on a vector editing method to obtain a final extraction result of the oyster sack.

[0009] According to some embodiments of the present invention, the pre-processing operation includes: radiometric calibration, atmospheric correction, image fusion and geometric correction.

[0010] According to some embodiments of the present invention, the raster data processing of the reflectivity data includes: calculating a bright channel image and a dark channel image of the reflectivity data; and subtracting the dark channel image from the bright channel image to obtain a contrast image of the reflectivity data.

[0011] According to some embodiments of the present invention, the raster data processing of the reflectivity data includes: performing threshold segmentation on the contrast image based on the OTSU maximum inter-class variance method, calculating the optimal segmentation threshold between oyster racks and non-oyster rack areas, and performing binarization processing based on the optimal segmentation threshold; setting an area threshold based on the statistical minimum area of ​​the oyster rack, deleting patches with an area smaller than the area threshold to obtain a first image; and processing the first image based on an image processing method.

[0012] According to some embodiments of the present invention, the processing of the first image based on the image processing method includes: performing opening and closing operations on the first image to obtain a second image; filling holes in the second image, wherein the hole filling is based on a morphological algorithm, and after expansion, it is inverted with the original image to obtain a third image; and performing median filtering on the third image.

[0013] According to some embodiments of the present invention, the steps of processing the initial vector results of the oyster rack based on the vector editing method include: performing aggregate surface editing on the initial vector of the oyster rack, merging the surface elements within a specified distance into new surface elements; performing a smooth surface operation, smoothing the sharp corners in the surface contour, and removing burrs; calculating the vector area, and deleting non-oyster rack vectors that are smaller than the minimum threshold according to a set minimum threshold; performing a topology check, setting a topological tolerance, adding topological rules and modifying topological errors.

[0014] According to some embodiments of the present invention, the step of processing the initial vector result of the oyster rack based on the vector editing method includes: modifying the oyster rack extraction result in response to user operation to obtain the final oyster rack extraction result.

[0015] According to the second aspect of the present invention, the oyster rack extraction system based on high-resolution satellite remote sensing images includes: a preprocessing module for acquiring satellite remote sensing images and performing preprocessing operations to obtain reflectivity data including geometric positioning; a raster processing module for performing raster data processing on the reflectivity data and vectorizing the processed raster data to generate an initial vector result of the oyster rack; and a vector editing module for processing the initial vector result of the oyster rack based on a vector editing method to obtain a final extraction result of the oyster rack.

[0016] According to some embodiments of the present invention, the raster processing module includes: a bright channel image module, used to calculate the bright channel image of the reflectance data; a dark channel image module, used to calculate the dark channel image of the reflectance data; and a contrast image module, used to subtract the dark channel image from the bright channel image to obtain a contrast image of the reflectance data.

[0017] According to the computer-readable storage medium of the third aspect embodiment of the present invention, a computer program is stored thereon, and when the computer program is executed by a processor, the method of any one of the embodiments of the first aspect of the present invention is implemented.

[0018] The embodiments of the present invention have the following beneficial effects: the present invention proposes a streamlined method for extracting oyster slats based on high-resolution satellite remote sensing imagery. It proposes using contrast images generated by subtracting bright and dark channel images as the basic data for oyster slat extraction, which can enhance the pixel difference between oyster slats and seawater, highlight the information characteristics of oyster slats, and facilitate oyster slat extraction. The OTSU maximum inter-class variance method is used to automatically calculate the optimal segmentation threshold, ensuring the accuracy of oyster slat identification. Furthermore, the present invention optimizes oyster slat raster images using image processing techniques and quickly and accurately corrects subsequent vectors based on vector editing, further improving the extraction results and making the extracted oyster slat vectors more accurate. Compared to methods such as field surveys, on-site statistics of oyster slat spatial distribution and aquaculture area, and manual delineation of oyster slat vectors for digitization, the technical solution of the present invention can quickly and efficiently extract oyster slat vectors without requiring excessive manual operation. It relies on image processing algorithms for automatic extraction, significantly reducing manual workload and recognition errors caused by manual delineation, improving the accuracy and efficiency of oyster slat extraction, saving costs, time, and effort. It can quickly and easily grasp the spatial distribution of oyster slats and aquaculture area, laying the foundation for subsequent dynamic monitoring.

[0019] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments with reference to the accompanying drawings, in which:

[0021] Figure 1 2. It is a flow chart of oyster rack extraction according to an embodiment of the present invention.

[0022] Figure 2 This is the original satellite remote sensing image of the embodiment of the present invention.

[0023] Figure 3 2 is a schematic diagram of a dark channel according to an embodiment of the present invention.

[0024] Figure 4 This is a contrast image diagram according to an embodiment of the present invention.

[0025] Figure 5 This is an OTSU threshold segmentation effect diagram of an embodiment of the present invention.

[0026] Figure 6 This is a diagram showing the effect of raster data processing according to an embodiment of the present invention.

[0027] Figure 7 This is a vector editing effect diagram of an embodiment of the present invention.

[0028] Figure 8This is an enlarged effect diagram of the oyster rack vector extracted by an embodiment of the present invention.

[0029] Figure 9 This is a diagram showing the superposition of the oyster rack extraction result and the original image according to an embodiment of the present invention.

[0030] Figure 10 It is a schematic block diagram of system modules according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to facilitate those skilled in the art to understand and implement the present invention, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the implementation examples described herein are only used to illustrate and explain the present invention and are not used to limit the present invention.

[0032] In the description of the present invention, "several" means one or more, "more" means two or more, "greater than," "less than," and "exceed" are understood to exclude the number itself, while "above," "below," and "within" are understood to include the number itself. The use of "first" and "second" in the description is solely for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance, implicitly specifying the number of the indicated technical features, or implicitly specifying the order of the indicated technical features.

[0033] It should be understood that the size of the serial numbers of the steps in the embodiment of the present invention does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0034] Please see Figure 1 The embodiment of the present invention provides an oyster rack extraction method based on high-resolution satellite remote sensing images, comprising the following steps:

[0035] Step 1: Acquire high-resolution satellite remote sensing images and perform preprocessing operations on them, including radiometric calibration, atmospheric correction, image fusion, and geometric correction, to convert the raw data into reflectivity data with accurate geometric positioning;

[0036] In this embodiment, the French Pleiades data is used as the remote sensing image for oyster rack extraction. Figure 2The data consists of raw satellite remote sensing imagery, including panchromatic imagery (0.5 meters) and multispectral imagery (2 meters). First, radiometric calibration is performed using the data's inherent absolute radiometric calibration coefficients, converting the raw imagery into calibrated results. The panchromatic imagery uses the absolute radiometric calibration coefficients and solar irradiance to output apparent reflectance, while the multispectral imagery uses the absolute radiometric calibration coefficients to generate radiance. The calibrated multispectral imagery is then atmospherically corrected using the FLAASH model to eliminate radiometric errors caused by atmospheric influences and retrieve the true reflectance of the ground features. The radiometrically calibrated panchromatic imagery and the atmospherically corrected multispectral imagery are then fused using the PANSHARP method. This fusion method uses the least squares method to find matching grayscale values ​​between the fused bands and makes personalized adjustments to the parameters of each band. This fusion improves the spatial resolution of the multispectral imagery, preserves spectral and tonal characteristics, and enhances information interpretation and recognition. Finally, ground control points are collected and the fused imagery is geometrically corrected to eliminate geometric errors and obtain the correct geometric positioning. All of these operations can be performed using ENVI software.

[0037] Step 2, performing raster data processing on the reflectivity data, including calculating the bright channel, dark channel and contrast image, OTSU segmentation, deleting small debris spots, morphological method processing, etc., and vectorizing the processed raster data to generate the initial vector result of the oyster rack;

[0038] In this embodiment, the pre-processed reflectivity data is used to perform raster data processing to generate the initial vector result of the oyster rack. The specific implementation method is as follows:

[0039] Step 2.1, calculating the bright channel image of the reflectance data;

[0040] The mathematical expression of the bright channel is:

[0041]

[0042] Where, J C (y) represents each channel of the image, and Ω(x) represents the window centered at pixel x. With pixel x as the center, the maximum value within each band window Ω is taken, and then the corresponding maximum value is taken as the bright channel value for pixel x. In this example, the bright channel window size is set to 3*3.

[0043] Step 2.2, calculating a dark channel image of the reflectivity data;

[0044] The dark channel is a basic assumption. For most distant images, some pixels always have at least one color channel with a very low value, and the light intensity in this area is a very small number. The mathematical definition of the dark channel is: For any input image J, its dark channel can be expressed as follows:

[0045]

[0046] Where, J C (y) represents each channel of the image, and Ω(x) represents the window centered at pixel x.

[0047] Taking pixel x as the center, take the minimum value in each band window Ω, and then take the corresponding minimum value as the value of the dark channel of pixel x. Figure 3 In this embodiment, the dark channel window size is set to 3*3.

[0048] Step 2.3, calculate the contrast image of the reflectivity data, that is, subtract the dark channel image calculated in step 2.2 from the bright channel image calculated in step 2.1. Figure 4 This is the contrast image effect diagram of this embodiment. The contrast image can enhance the pixel difference between the oyster slab and the seawater, highlighting the information features, which is beneficial for the subsequent extraction of the oyster slab;

[0049] Step 2.4, performing threshold segmentation on the contrast image processed in step 2.3 based on the OTSU maximum inter-class variance method, automatically calculating the optimal segmentation threshold between the oyster rack and non-oyster rack areas, and performing binarization processing based on the threshold;

[0050] OTSU, a highly efficient image binarization algorithm proposed by Japanese researcher Otsu, is considered the optimal threshold selection method for image segmentation. It is computationally simple and unaffected by image brightness and contrast. It separates an image into background and foreground components based on its grayscale characteristics. Because variance is a measure of the uniformity of grayscale distribution, a greater inter-class variance between the background and foreground indicates a greater difference between the two components of the image. Misclassifying parts of the foreground as background or vice versa results in a smaller difference between the two components. Therefore, the segmentation that maximizes the inter-class variance minimizes the probability of misclassification. Given the monotonous ocean background of the oyster rack, the OTSU method is particularly well-suited for threshold segmentation.

[0051] The basic idea of ​​OTSU method is as follows: First, calculate the normalized histogram of the image. Assume that the gray level of the image is L, the number of pixels with gray value i is ni, where i∈[0,L] is a positive integer, then the total number of pixels in the image is The probability of gray value i is Then calculate the cumulative probability and cumulative mean. Assuming that the segmentation threshold we are looking for is T, then those less than T will be classified into one category, and those greater than T will be classified into another category. According to the previous probability and mean calculation formulas, we can get the cumulative probability P(T) and the intra-class mean μ(T). The specific calculation formulas are as follows:

[0052]

[0053]

[0054]

[0055]

[0056] Among them, P0(T) is the cumulative probability of the foreground, μ0(T) is the intra-class mean of the foreground, P1(T) is the cumulative probability of the background, and μ1(T) is the intra-class mean of the background.

[0057] Then, according to the intra-class mean and cumulative probability calculated by the above formula, the inter-class variance σ(T) is calculated. The specific calculation formula is as follows:

[0058] σ(T)=P0(T)×P1(T)×(μ0(T)-μ1(T)) 2

[0059] And it is stipulated that the threshold that maximizes σ(T) is the optimal threshold.

[0060] In this embodiment, the contrast image calculated in step 2.3 is downgraded from 16 bits to 8 bits. The pixel DN value range is [0, 255]. The OTSU method is used to calculate the threshold value of 126 for segmentation between oyster racks and seawater. Pixels with DN values ​​less than 126 are assigned a value of 1, and the remaining pixels are assigned a value of 0. The segmentation result is shown in FIG. Figure 5 As shown;

[0061] Step 2.5: Set an area threshold d based on the minimum area of ​​the oyster racks obtained by statistics, and delete patches with an area smaller than the threshold d to eliminate interfering pixels.

[0062] In this embodiment, the threshold of the oyster rack area is set to 30 square meters, and the debris smaller than the threshold is deleted to reduce the influence of interfering pixels.

[0063] Step 2.6: Use image processing methods, including morphological algorithms such as opening and closing operations, hole filling, and image filtering, to further process the image obtained in step 2.5. This removes noise, eliminates small objects, separates features at subtle locations, and smoothes the boundaries of larger objects, resulting in more accurate oyster scallop extraction results.

[0064] In this embodiment, an opening operation is first performed, that is, corrosion first and then expansion, to remove isolated small dots and burrs; and a closing operation is then performed, that is, expansion first and then corrosion, to fill small holes and bridge small cracks.

[0065] The formulas for corrosion, expansion, opening, and closing operations are as follows:

[0066] corrosion:

[0067] Expansion:

[0068] Open operation:

[0069] Closing operation:

[0070] Where X is the input image and B is the structural element.

[0071] Furthermore, the holes in the image processed in the previous step are filled. Hole filling is based on a morphological algorithm and is achieved by inverting the original image after dilation. The formula is as follows:

[0072]

[0073] Where X is the input image, B is the symmetric structuring element, and A represents the set. First, the coordinates of a hole are extracted, the image is dilated using the structuring element, and then the image is inverted. This process is repeated until all holes are filled.

[0074] Furthermore, in this embodiment, median filtering is used for image filtering. This method has a significant filtering effect, and at the same time, it maintains good image edge details with low computational complexity and good real-time performance. The formula is as follows:

[0075] I(x, y) = median{S I(x，y)}

[0076] Where I(x, y) is the pixel value at the image coordinate (x, y), and S is a 3*3 filter template.

[0077] The above image processing algorithms are all implemented in C++ based on the OpenCV library. Figure 6 This is the effect diagram after raster data processing of this embodiment.

[0078] Step 2.7: Vectorize the image processed in step 2.6 to generate the initial vector result of the oyster rack.

[0079] Step 3: Edit the initial oyster rack vector and obtain the final oyster rack extraction result after several processing. Figure 7 The final vector result of the oyster rack extraction is shown in FIG. 1 . In this embodiment, the vector editing sub-steps are as follows:

[0080] Step 3.1: First, perform an aggregation polygon edit on the initial vector of the oyster rack, merging the polygon features within the specified distance into a new polygon feature;

[0081] In this embodiment, the distance between the boundaries of the surface elements is set to 10 pixels to achieve moderate proportion aggregation.

[0082] Step 3.2: Perform a smoothing operation on the processed vectors to smooth out sharp corners in the surface contour, remove burrs, and retain details;

[0083] In this embodiment, the PEAK (Polynomial Approximation with Exponential Kernel) method is selected to perform smoothing according to a smoothing tolerance, and the smoothing tolerance is set to 8 pixels.

[0084] Step 3.3: Calculate the vector area, set a minimum threshold, and delete non-oyster-row vectors smaller than the threshold. In this embodiment, the minimum threshold is set to 200 pixels to further remove the introduced small patches.

[0085] Step 3.4: Perform a topological check on the above vectors, set the topological tolerance, add topological rules, and correct topological errors to ensure that the vector results have no gaps or overlaps and meet the topological requirements;

[0086] Topology is the arrangement of shared geometry among point, line, and polygon elements. It can restrict the shared geometry of elements and define and enforce data integrity rules. In this embodiment, the topology rules are set to ensure that there are no gaps between adjacent faces and that there is no overlap between face elements. The vector results are topologically checked according to this rule, and related errors are corrected.

[0087] Step 3.5: Manually modify the oyster rack extraction results, delete the error vectors, and add the missing oyster racks to obtain the final extraction results.

[0088] The above vector editing operations are all implemented using Arcgis software. Figure 7 This is the vector editing effect diagram of this embodiment. Figure 8 This is the magnified effect diagram of the extracted oyster steak vector. Figure 9 This is the superposition effect of the oyster rack extraction result and the original image.

[0089] The above content provides a detailed introduction to the oyster shell extraction method based on high-resolution satellite remote sensing imagery provided by the present invention. This article uses specific examples to illustrate the principles and implementation methods of the present invention. The description of the above examples is only intended to facilitate understanding of the method and core concept of the present invention. It should be noted that those skilled in the art may make various improvements and modifications to the present invention without departing from the principles of the present invention, and such improvements and modifications also fall within the scope of protection of the claims of the present invention.

[0090] Corresponding to the above-mentioned embodiments, the present invention also provides system embodiments. As for the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments.

[0091] Reference Figure 10The system of the embodiment of the present invention includes: a preprocessing module, which is used to obtain satellite remote sensing images and perform preprocessing operations to obtain reflectivity data including geometric positioning; a raster processing module, which is used to perform raster data processing on the reflectivity data and vectorize the processed raster data to generate an initial vector result of the oyster rack; and a vector editing module, which is used to process the initial vector result of the oyster rack based on a vector editing method to obtain a final extraction result of the oyster rack.

[0092] Although specific embodiments are described herein, those skilled in the art will recognize that many other modifications or alternative embodiments are also within the scope of the present disclosure. For example, any of the functions and / or processing capabilities described in conjunction with a particular device or component may be performed by any other device or component. In addition, although various exemplary implementations and architectures have been described in accordance with the embodiments of the present disclosure, those skilled in the art will recognize that many other modifications to the exemplary implementations and architectures described herein are also within the scope of the present disclosure.

[0093] Some aspects of the present disclosure have been described above with reference to the block diagrams and flow charts of the systems, methods, systems and / or computer program products according to the exemplary embodiments. It should be understood that the combination of one or more blocks in the block diagram and the flow chart and the blocks in the block diagram and the flow chart can be realized by executing computer executable program instructions respectively. Equally, according to some embodiments, some blocks in the block diagram and the flow chart may not need to be executed in the order shown, or may not need to be executed in full. In addition, additional components and / or operations beyond those components and / or operations shown in the blocks in the block diagram and the flow chart may be present in certain embodiments.

[0094] Therefore, the blocks in the block diagrams and flow charts support combinations of means for performing the specified functions, combinations of elements or steps for performing the specified functions, and program instruction means for performing the specified functions. It should also be understood that each block in the block diagrams and flow charts, and combinations of blocks in the block diagrams and flow charts, can be implemented by a dedicated hardware computer system that performs the specific functions, elements, or steps, or a combination of dedicated hardware and computer instructions.

[0095] The program modules, applications, etc. described herein may include one or more software components, including, for example, software objects, methods, data structures, etc. Each such software component may include computer-executable instructions that, in response to execution, cause at least a portion of the functionality described herein (e.g., one or more operations of the illustrative methods described herein) to be performed.

[0096] Software component can be encoded with any one in various programming languages.A kind of exemplary programming language can be low-level programming language, such as the assembly language associated with specific hardware architecture and / or operating system platform.Comprise that the software component of assembly language instruction may need to be converted to executable machine code by assembler before being executed by hardware architecture and / or platform.Another exemplary programming language can be a more advanced programming language, and it can be transplanted across multiple architectures.Comprise that the software component of more advanced programming language may need to be converted to intermediate representation by interpreter or compiler before execution.Other examples of programming language include but are not limited to macro language, shell or command language, job control language, script language, database query or search language or report writing language.In one or more exemplary embodiments, the software component that comprises the instruction of one in the above-mentioned programming language example can be directly executed by operating system or other software component, without first being converted into another form.

[0097] Software components can be stored as files or other data storage structures. Software components of similar types or related functions can be stored together, such as in a specific directory, folder, or library. Software components can be static (e.g., preset or fixed) or dynamic (e.g., created or modified at execution time).

[0098] The embodiments of the present invention are described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Various changes can be made within the knowledge of ordinary technicians in the relevant technical field without departing from the scope of the present invention.

Claims

1. A method for extracting oyster shells based on high-resolution satellite remote sensing images, characterized in that: include: Acquire satellite remote sensing images and perform preprocessing operations to obtain reflectivity data including geometric positioning; Performing raster data processing on the reflectivity data, and vectorizing the processed raster data to generate an initial vector result of the oyster rack; Processing the initial vector result of the oyster rack based on a vector editing method to obtain a final extraction result of the oyster rack; The preprocessing operation includes: radiation calibration, atmospheric correction, image fusion and geometric correction; wherein the image fusion is used to fuse the panchromatic image after radiation calibration and the multispectral image after atmospheric correction using the PANSHARP method; The grid data processing of the reflectivity data comprises: Calculating a bright channel image and a dark channel image of the reflectivity data; Subtracting the dark channel image from the bright channel image to obtain a contrast image of the reflectivity data; The bright channel mathematical expression used to calculate the bright channel image of the reflectivity data is: In the formula, J C (y) represents each channel of the image, Ω(x) represents a window centered on pixel x; the size of the bright channel window is set to 3*3; The dark channel mathematical expression used to calculate the dark channel image of the reflectivity data is: In the formula, J C (y) represents each channel of the image, Ω(x) represents a window centered on pixel x; the dark channel window size is set to 3*3; The step of processing the initial vector result of the oyster rack based on the vector editing method comprises: Performing aggregate surface editing on the initial vector of the oyster row, merging the surface elements within the specified distance into new surface elements; Perform smoothing operations to smooth sharp corners in the surface contour and remove burrs; Calculate the vector area, and delete non-oyster row vectors smaller than the minimum threshold according to a set minimum threshold; Perform a topology check, set a topology tolerance, add topology rules, and modify topology errors; the topology rules are set to ensure that there are no gaps between adjacent faces and that there is no overlap between face elements; Wherein, performing grid data processing on the reflectivity data comprises: Performing threshold segmentation on the contrast image based on the OTSU maximum inter-class variance method, calculating the optimal segmentation threshold of the oyster rack and non-oyster rack area, and performing binarization processing according to the optimal segmentation threshold; An area threshold is set according to the minimum area value of the oyster racks obtained by statistics, and patches with an area smaller than the area threshold are deleted to obtain a first image; Processing the first image based on an image processing method; The processing of the first image based on the image processing method includes: Performing an opening operation and a closing operation on the first image to obtain a second image; Filling holes in the second image, wherein the hole filling is based on a morphological algorithm, and the third image is obtained by inverting the original image after dilation; Perform median filtering on the third image.

2. The method for extracting oyster shells based on high-resolution satellite remote sensing images according to claim 1, characterized in that: The step of processing the initial vector result of the oyster rack based on the vector editing method includes: modifying the oyster rack extraction result in response to user operation to obtain the final oyster rack extraction result.

3. An oyster rack extraction system based on high-resolution satellite remote sensing images, characterized in that: include: A preprocessing module is used to obtain satellite remote sensing images and perform preprocessing operations to obtain reflectivity data including geometric positioning; A raster processing module, used for performing raster data processing on the reflectivity data, and vectorizing the processed raster data to generate an initial vector result of the oyster rack; A vector editing module, used for processing the initial vector result of the oyster rack based on a vector editing method to obtain a final extraction result of the oyster rack; The preprocessing operation includes: radiation calibration, atmospheric correction, image fusion and geometric correction; the image fusion is used to fuse the panchromatic image after radiation calibration and the multispectral image after atmospheric correction using the PANSHARP method; The grid processing module comprises: A bright channel image module, used for calculating a bright channel image of the reflectivity data; A dark channel image module, used for calculating a dark channel image of the reflectivity data; A contrast image module, used for subtracting the dark channel image from the bright channel image to obtain a contrast image of the reflectivity data; The bright channel mathematical expression used to calculate the bright channel image of the reflectivity data is: In the formula, J C (y) represents each channel of the image, Ω(x) represents a window centered on pixel x; the size of the bright channel window is set to 3*3; The dark channel mathematical expression used to calculate the dark channel image of the reflectivity data is: In the formula, J C (y) represents each channel of the image, Ω(x) represents a window centered on pixel x; the dark channel window size is set to 3*3; The step of processing the initial vector result of the oyster rack based on the vector editing method comprises: Performing aggregate surface editing on the initial vector of the oyster row, merging the surface elements within the specified distance into new surface elements; Perform smoothing operations to smooth sharp corners in the surface contour and remove burrs; Calculate the vector area, and delete non-oyster row vectors smaller than the minimum threshold according to a set minimum threshold; Perform a topology check, set a topology tolerance, add topology rules, and modify topology errors; the topology rules are set to ensure that there are no gaps between adjacent faces and that there is no overlap between face elements; Wherein, performing grid data processing on the reflectivity data comprises: Performing threshold segmentation on the contrast image based on the OTSU maximum inter-class variance method, calculating the optimal segmentation threshold of the oyster rack and non-oyster rack area, and performing binarization processing according to the optimal segmentation threshold; An area threshold is set according to the minimum area value of the oyster racks obtained by statistics, and patches with an area smaller than the area threshold are deleted to obtain a first image; Processing the first image based on an image processing method; The processing of the first image based on the image processing method includes: Performing an opening operation and a closing operation on the first image to obtain a second image; Filling holes in the second image, wherein the hole filling is based on a morphological algorithm, and the third image is obtained by inverting the original image after dilation; Perform median filtering on the third image.

4. A computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method according to any one of claims 1 to 2 when executed by a processor.

Images