Water body information determination method, device and equipment based on satellite spectrum and medium

Abstract

The invention discloses a satellite spectrum-based water body information determination method, apparatus and device, and a medium, and relates to the technical field of water body identification, the method comprises the following steps: obtaining satellite spectrum images of a target area collected at a plurality of time points; carrying out water body index calculation on the satellite spectral image collected at each time point; performing water body identification on the target area according to the water body index; judging a mountain shadow from the water body area according to the near infrared index and the gradient, and removing the mountain shadow from the water body area to obtain a final water body area; determining the pixel water body frequency of each pixel in the target area according to the final water body area obtained through multiple times of identification, and dividing each pixel into a permanent water body pixel or a seasonal water body pixel according to the pixel water body frequency; and determining the permanent water body area and the seasonal water body area according to the permanent water body pixels and the seasonal water body pixels. According to the method and the device, the water body information identification accuracy is improved, and the water body information identification cost is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of water body identification, and particularly to a method, device, equipment and medium for determining water body information based on satellite spectra. Background Art

[0002] In the application of traditional remote sensing data-based surface water body extraction methods at the basin scale, especially when distinguishing permanent and seasonal water bodies, significant technical challenges are faced. Among them, mountain shadows are often misidentified as seasonal water bodies, seriously affecting the accuracy of the extraction results. In addition, in the extraction of water body areas in large-scale basins, the interference of mountain shadows is more difficult to effectively eliminate. Existing research mainly focuses on the combination of single remote sensing data and measured data, and the analysis of the spatio-temporal variation law of basin water body areas is not yet systematic and comprehensive enough.

[0003] The accurate monitoring of permanent and seasonal water bodies is of great significance for the scientific management of water resources. This not only helps to reduce the negative impacts of water conservancy projects on the functions of basin ecosystems, biodiversity and the sustainable utilization of water resources, but also provides a scientific basis for the formulation of relevant environmental governance decisions. However, at present, the water body area extraction method based on remote sensing images has insufficient automation and low extraction accuracy in the application at the basin scale, especially in effectively eliminating the interference of mountain shadows on seasonal water body areas. Most of the traditional methods for studying the areas of permanent and seasonal water bodies in basins rely on the combination of a small amount of remote sensing data and measured data from basin hydrological monitoring stations. This method not only takes a lot of time and effort, has high resource requirements, but also is difficult to provide a systematic analysis under long time series.

[0004] Especially at the basin scale, the research on the spatio-temporal variation law of the areas of permanent and seasonal water bodies based on multi-source remote sensing data technology is still scarce, and the traditional methods are often limited in the scientificity and rigor of the extraction results due to the insufficient treatment of mountain shadow interference. Summary of the Invention

[0005] The purpose of the present application is to provide a method, device, equipment and medium for determining water body information based on satellite spectra, which improves the accuracy of water body information identification and reduces the cost of water body information identification.

[0006] To achieve the above purpose, the present application provides the following solutions:

[0007] In a first aspect, the present application provides a method for determining water body information based on satellite spectra. The method for determining a water body area based on satellite spectra includes:

[0008] Obtain satellite spectral images of a target area collected at multiple time points;

[0009] Calculate a water body index for the satellite spectral image collected at each time point;

[0010] Identify water bodies in the target area based on the water body index to obtain water body areas and non-water body areas;

[0011] Judge mountain shadows from the water body areas according to the near-infrared index and slope, and remove the mountain shadows from the water body areas to obtain the final water body areas;

[0012] Determine the pixel water frequencies of each pixel in the target area according to the final water body areas corresponding to the satellite spectral images collected at each time point, and divide each pixel into permanent water body pixels or seasonal water body pixels according to the pixel water frequencies;

[0013] Determine the permanent water body area and the seasonal water body area according to the permanent water body pixels and the seasonal water body pixels.

[0014] Optionally, calculate the water body index for the satellite spectral images collected at each time point, specifically including:

[0015] Preprocess the satellite spectral images collected at each time point;

[0016] Calculate the water body index for the preprocessed satellite spectral images.

[0017] Optionally, preprocess the satellite spectral images collected at each time point, specifically including:

[0018] Stitch, mosaic, crop, and de-cloud the satellite spectral images collected at each time point to obtain the preprocessed satellite spectral images; the satellite spectral images collected at each time point include satellite spectral images provided by multiple data sources.

[0019] Optionally, the water body index includes the modified normalized difference water index, the normalized difference vegetation index, and the enhanced vegetation index;

[0020] The calculation formula of the water body index is:

[0021]

[0022] where MNDWI is the modified normalized difference water index, NDVI is the normalized difference vegetation index, EVI is the enhanced vegetation index, ρ green is the green band, ρ SWIR1 is the short-wave infrared band, ρ NIR is the near-infrared band, ρ red is the red band, ρ blue is the blue band.

[0023] Optionally, identify water bodies in the target area based on the water body index to obtain water body areas and non-water body areas, specifically including:

[0024] If a pixel satisfies (MNDWI > NDVI or MNDWI > EVI) and (EVI < 0.1), then the pixel is identified as water; otherwise, the pixel is identified as non-water. The pixels identified as water form a water area, and the pixels identified as non-water form a non-water area.

[0025] Optionally, mountain shadows are determined from the water area according to the near-infrared index and slope, and the mountain shadows are removed from the water area to obtain a final water area, which specifically includes:

[0026] Pixels in the water area with a near-infrared index greater than a first set value and a slope greater than a second set value are determined as mountain shadows, and the mountain shadows are removed from the water area to obtain a final water area.

[0027] Optionally, each pixel is divided into a permanent water pixel or a seasonal water pixel according to the pixel water frequency, which specifically includes:

[0028] Pixels with a pixel water frequency greater than a first set percentage are divided into permanent water pixels, and pixels not greater than the first set percentage and greater than a second set percentage are divided into seasonal water pixels.

[0029] In a second aspect, the present application provides a device for determining water body information based on satellite spectra. The device for determining water body information based on satellite spectra applies the method for determining water body information based on satellite spectra described in any one of the above, and the device for determining water body information based on satellite spectra includes:

[0030] A satellite spectrum image acquisition module, configured to acquire satellite spectrum images of a target area collected at multiple time points;

[0031] A water body index calculation module, configured to calculate a water body index for the satellite spectrum images collected at each time point;

[0032] A water body identification module, configured to identify a water body in the target area according to the water body index to obtain a water area and a non-water area;

[0033] A mountain shadow removal module, configured to determine mountain shadows from the water area according to the near-infrared index and slope, and remove the mountain shadows from the water area to obtain a final water area;

[0034] A permanent and seasonal water body division module, configured to determine the pixel water frequency of each pixel in the target area according to the final water area corresponding to the satellite spectrum images collected at each time point, and divide each pixel into a permanent water pixel or a seasonal water pixel according to the pixel water frequency;

[0035] A permanent and seasonal water body area determination module is used to determine the permanent water body area and the seasonal water body area based on permanent water body pixels and seasonal water body pixels.

[0036] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the steps of the method for determining water body information based on satellite spectra described in any one of the above.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for determining water body information based on satellite spectra described in any one of the above are implemented.

[0038] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application:

[0039] The present application provides a method, device, equipment and medium for determining water body information based on satellite spectra. The mountain shadow is judged from the water body area according to the near-infrared index and the slope, and the mountain shadow is removed from the water body area to obtain the final water body area. The accuracy of water body area recognition is improved by identifying the mountain shadow. By determining the pixel water body frequency of each pixel, the division of permanent water body pixels and seasonal water body pixels is realized. This method does not rely on field measured data, and the water body information can be determined by calculating satellite spectral images, reducing the cost of water body information, and enabling the calculation of water body information for large areas and long time series. Description of the Drawings

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0041] Figure 1 It is a schematic flowchart of a method for determining water body information based on satellite spectra provided by an embodiment of the present application;

[0042] Figure 2 It is a schematic diagram of the water body recognition result in the Yangtze River Basin before removing the mountain shadow provided by an embodiment of the present application;

[0043] Figure 3 It is a schematic diagram of the water body recognition result in the Yangtze River Basin after removing the mountain shadow provided by an embodiment of the present application;

[0044] Figure 4A structural schematic diagram of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0045] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0046] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0047] In a related water body recognition method, by constructing a statistical regression relationship between two remotely sensed images with different spatial resolutions, and substituting the remotely sensed image with a coarse spatial resolution into the calculation by means of the constructed relationship to calculate a new remotely sensed image with a fine spatial resolution to supplement the original fine-resolution image, and according to the different degrees of influence of cloud and fog on the two data, improving the clarity of the data more severely affected by cloud and fog and improving the water body recognition degree. However, this method does not consider the influence of mountain shadows on the clarity of water bodies. Mountain shadows will have a significant impact on the brightness and color characteristics of remotely sensed images. Especially under complex terrain conditions, water bodies in shadow areas may be difficult to identify.

[0048] In another related water body recognition method, it relies on a deep learning model for water body recognition, but lacks targeted processing for removing mountain shadows. The spectral characteristics of mountain shadow areas are similar to those of water bodies, which may lead to misjudgment of shadow areas as water bodies and reduce the accuracy of extraction results. It mainly relies on satellite remote sensing images. Although combined with ground station and laser altimetry satellite data, the processing of complex environments such as mountain shadows is still limited to the image data itself, lacking the fusion of multi-source data to solve the problem of recognition blind spots.

[0049] In an exemplary embodiment, the present application provides a method for determining water body information based on satellite spectra, as Figure 1 shown, the method for determining a water body area based on satellite spectra includes steps 101 to 106.

[0050] Step 101: Obtain satellite spectral images of a target area collected at multiple time points.

[0051] Step 102: Calculate a water body index for the satellite spectral image collected at each time point.

[0052] Step 103: Perform water body recognition on the target area according to the water body index to obtain a water body area and a non-water body area.

[0053] Step 104: Determine the mountain shadow from the water body area according to the near-infrared index and slope, and remove the mountain shadow from the water body area to obtain the final water body area.

[0054] Step 105: Determine the pixel water frequency of each pixel in the target area according to the final water body area corresponding to the satellite spectral image collected at each time point, and divide each pixel into a permanent water body pixel or a seasonal water body pixel according to the pixel water frequency.

[0055] Step 106: Determine the permanent water body area and the seasonal water body area according to the permanent water body pixels and the seasonal water body pixels.

[0056] This application improves the accuracy of water body area recognition by identifying mountain shadows. By determining the pixel water frequency of each pixel, the division of permanent water body pixels and seasonal water body pixels is realized. This method does not rely on field measurement data, and the water body information can be determined by calculating satellite spectral images, reducing the cost of water body information and enabling the calculation of water body information for large areas and long time series.

[0057] In another exemplary embodiment, the multiple time points in the satellite spectral images of the target area collected at multiple time points refer to multiple time points within a set time period. For example, the set time period is 1 year.

[0058] In another exemplary embodiment, step 102 specifically includes: preprocessing the satellite spectral image collected at each time point; calculating the water body index for the preprocessed satellite spectral image.

[0059] Preprocessing the satellite spectral image collected at each time point specifically includes: splicing, mosaicking, cropping, and cloud removal processing the satellite spectral image collected at each time point to obtain the preprocessed satellite spectral image; the satellite spectral image collected at each time point includes satellite spectral images provided by multiple data sources.

[0060] When the set time period includes multiple years, the satellite spectra of the target area after annual cloud removal (removing cloud contamination) are obtained through step 102.

[0061] The satellite spectral images provided by multiple data sources include remote sensing images of the Landsat series, remote sensing images of the Sentinel series, elevation data, and MODIS-derived products. The MODIS-derived products are remote sensing images that provide vegetation index values per pixel. This application combines multi-source remote sensing data and can accurately identify the water body area in the basin through optimized processing and analysis processes, with an overall identification accuracy of over 95%.

[0062] In another exemplary embodiment, the water body form data, i.e., the satellite spectral images, are the Surface Reflectance Tier 1 images of Landsat 5 TM, Landsat 7 ETM+, and Landsat 8 OLI / TIRS provided by Google Earth Engine (GEE). After using codes to perform processing such as stitching, mosaicking, cropping, and cloud removal on the remote sensing images, the satellite spectral images of the entire basin from 1984 to 2021 with cloud pollution removed year by year are obtained.

[0063] The Google Earth Engine platform integrates a vast amount of remote sensing image data and its derived interpretation products, providing efficient and convenient technical support for image screening, preprocessing (such as radiometric calibration, geometric correction, and atmospheric correction), and interpretation work, significantly improving the efficiency of remote sensing research.

[0064] The remote sensing images of the Sentinel series, i.e., Sentinel-2 data, is a wide-swath, medium-resolution multispectral imaging mission. Sentinel-2 data supports Copernicus land monitoring research. Sentinel-2 data includes observations of vegetation, soil, and water coverage, as well as inland waterways and coastal areas. Two coordinated satellites in the same satellite mission jointly form an observation constellation (Constellation A and B) to achieve the Sentinel-2 mission. The Constellation A and B form a revisit cycle of up to 5 days, supporting the monitoring of vegetation changes during the growing season. The S2 Multispectral Instrument (MSI) has 13 spectral bands: visible and near-infrared bands with a resolution of 10 m, red-edge and short-wave infrared bands with a resolution of 20 m, and atmospheric bands with a spatial resolution of 60 m. MSI is the core sensor of the Sentinel-2 satellite, that is to say, Sentinel-2 data is collected by this instrument. The original radiometric data collected by MSI undergoes processing such as radiometric calibration, geometric correction, and atmospheric correction to generate standardized Sentinel-2 data products. The multispectral data, i.e., the entire series of Sentinel-2 remote sensing data, is divided into two data levels: Level-1C (L1C): data that has been geometrically rectified and radiometrically calibrated (apparent reflectance); Level-2A (L2A): further atmospheric correction is performed to generate surface reflectance data.

[0065] L1C-level data is an atmospheric apparent reflectance product after orthorectification and sub-pixel geometric rectification, without atmospheric correction; the L2A dataset contains 12 unsigned 16-bit integer spectral bands, including surface reflectance images with different spatial resolutions (60m, 20m, and 10m), representing surface reflectance (SR) values magnified 10,000 times (without the B10 cirrus band in L1C-level data); aerosol optical thickness (AOT) and water vapour pressure (WV) maps (60m, 20m, and 10m); the scene classification (SCL) map is used internally as the input for atmospheric correction, and quality indicators of cloud and snow probabilities are also used.

[0066] Compared with Landsat series data, Sentinel-2 has higher spatial, temporal, and spectral resolutions, which can support more accurate interpretation of ground objects. The only drawback is the lack of long-term data accumulation, and other satellite data need to be used to supplement the inversion of ground objects before 2017.

[0067] Remote sensing images of the Landsat series are a joint project of the United States Geological Survey (USGS) and the National Aeronautics and Space Administration (NASA), continuously observing the Earth since 1972. The data used in this application is mainly the Collection 1 Tier 1 data of Landsat-5 TM.

[0068] For elevation data, the Shuttle Radar Topography Mission (SRTM) digital elevation data is an international research effort that obtained a near-global digital elevation model. The SRTM V3 product (SRTMPlus) is provided by the Jet Propulsion Laboratory (JPL) of NASA, with a resolution of 1 arc second (about 30m), and the data unit is m.

[0069] For MODIS-derived products, the MYD13Q1 V6.1 product provides vegetation index values per pixel, which includes the Normalized Difference Vegetation Index (NDVI), i.e., MODIS-NDVI. MODIS-NDVI is calculated based on the bidirectional surface reflectance after atmospheric correction. The spatial resolution of this data is 250m, the temporal resolution is 16 days, and the dataset removes the influence and interference of clouds to a certain extent.

[0070] Using Google Earth Engine (GEE) as the computing platform, long-term time-series images covering nearly 30 years (including Landsat series and Sentinel series) are used. Through preprocessing techniques such as cloud cover screening and band synthesis, available remote sensing images covering the basin are extracted. Based on the powerful computing ability of GEE and combined with multi-source remote sensing data, this method realizes the efficient processing and analysis of regional spectral images, laying a foundation for the monitoring and statistics of the spatio-temporal variation characteristics of water bodies in the study area.

[0071] The water indices include the Modified Normalized Difference Water Index (MNDWI), Normalized Vegetation Index, and Enhanced Vegetation Index (EVI).

[0072] This application constructs different input combinations using input variable sets such as the topographic features (Digital Elevation Model, slope, aspect) of the target area, spectral bands, and remote sensing spectral indices (NDVI, NDWI, NDBI, EVI, etc.). Combining long-term time-series hydrological data and MODIS-NDVI data, the water body characteristics of the basin are analyzed. NDVI is the Normalized Vegetation Index, NDWI is the Normalized Difference Water Index, NDBI is the Normalized Difference Built-up Index, and EVI is the Enhanced Vegetation Index.

[0073] The calculation formulas for the water indices are as follows:

[0074]

[0075] Where MNDWI is the Modified Normalized Difference Water Index, NDVI is the Normalized Vegetation Index, EVI is the Enhanced Vegetation Index; ρ green is the green band, that is, band 2 (0.52 - 0.60 μm) corresponding to the Landsat image; ρ SWIR1 is the short-wave infrared band, that is, band 5 (1.55 - 1.75 μm) corresponding to the Landsat image; ρ NIR is the near-infrared band, that is, band 4 (0.77 - 0.90 μm) corresponding to the Landsat image; ρ red is the red band, that is, band 3 (0.63 - 0.69 μm) corresponding to the Landsat image; ρ blue is the blue band, that is, band 1 (0.45 - 0.52 μm) corresponding to the Landsat image.

[0076] This application uses the relative relationships among MNDWI, NDVI, and EVI in the water index method for extraction, which can effectively suppress the influence of vegetation on water body identification.

[0077] In another exemplary embodiment, step 103 specifically includes: if a pixel satisfies (MNDWI > NDVI or MNDWI > EVI) and (EVI < 0.1), then the pixel is identified as water; otherwise, the pixel is identified as non-water. The pixels identified as water form a water area, and the pixels identified as non-water form a non-water area. Thus, the annual water body morphology data of the target basin (target area) from 1984 to 2021 is obtained, with a spatial resolution of 30 m.

[0078] In another exemplary embodiment, step 104 specifically includes: determining the pixels in the water area with a near-infrared index greater than a first set value and a slope greater than a second set value as mountain shadows, and removing the mountain shadows from the water area to obtain the final water area.

[0079] In another exemplary embodiment, step 104 specifically includes: determining the pixels in the water area with NIR > 0.19 and slope > 20° as mountain shadows, and removing the mountain shadows from the water area to obtain the final water area.

[0080] In another exemplary embodiment, for the division of permanent water bodies and seasonal water bodies, the present application determines the annual water body type in the Yangtze River Basin by calculating the water body frequency of each pixel per year. The water body frequency is defined as the ratio of the number of times a pixel is observed as water in a year to the number of good observations (no cloud, cloud shadow, snow interference) in that year.

[0081] Step 105 specifically includes: classifying the pixels with a pixel water body frequency greater than a first set percentage as permanent water body pixels, and classifying the pixels not greater than the first set percentage and greater than a second set percentage as seasonal water body pixels.

[0082] The calculation formula for the pixel water body frequency of each pixel is:

[0083]

[0084] Among them, WaterFrequency represents the pixel water body frequency, and its value ranges from 0% to 100%; N is the number of time points, such as the number of good observations of the pixel in a year; w is used to divide water and non-water, w = 1 for water, and w = 0 for non-water.

[0085] Define the first set percentage as 75% and the second set percentage as 25%. That is, define the range corresponding to the pixels covered by water for at least 75% of the time in a year as permanent water bodies, and the range corresponding to the remaining pixels covered by water as seasonal water bodies. That is, when the pixel water frequency ≥ 0.75, the pixel is a permanent water body; when 0.25 < pixel water frequency < 0.75, the pixel is a seasonal water body. The total annual water area, permanent water area, and seasonal water area of the basin from 1984 to 2021 can be counted.

[0086] In another exemplary embodiment, step 106 specifically includes: counting the permanent water body pixels and seasonal water body pixels in the target area, and determining the permanent water area and seasonal water area according to the pixel size.

[0087] Based on multi-source satellite spectral data, this application constructs a spectral index and explores the discrimination threshold between permanent and seasonal water areas. On this basis, it comprehensively analyzes the spectral reflectance and terrain slope to accurately identify and eliminate the mis-identified water body pixels caused by mountain shadows. Through this method, the data of the total annual water area, permanent water area, and seasonal water area of the basin from 1984 to 2021 are obtained, realizing the accurate estimation of the water area of the basin, and providing important support for counting and monitoring the inter-annual changes and spatio-temporal change laws of the water area of the basin.

[0088] Compared with the traditional field measurement method, the method of this application has the significant advantages of fast calculation speed and wide application range, and can efficiently obtain the estimation results of large-area and long-time series water areas; compared with the existing surface water extraction methods based on remote sensing data, the method of this application significantly enhances the ability to eliminate the interference of mountain shadows when distinguishing permanent and seasonal water bodies. The application of this method provides a powerful technical means for the study of the spatio-temporal change laws of water bodies, and is of great significance for basin water resource management, ecological system protection, and related scientific decision-making.

[0089] In another exemplary embodiment, Landsat 5 / 7 / 8 satellite spectral images of the Yalong River Basin from 1986 to 2022 are obtained, and preprocessing such as image clipping and atmospheric correction is performed on the images. Then, cloud removal processing is carried out, the CFmask algorithm is used to eliminate the influence of clouds in the images on the results, and the images are synthesized on an annual scale to obtain the preprocessed satellite spectral images.

[0090] Based on the above preprocessed satellite spectral images, water body index calculation, water body identification, discrimination between permanent and seasonal water bodies, and calculation of the annual permanent water body and seasonal water area are carried out.

[0091] Based on the Landsat 5 / 7 / 8 satellite spectral satellite images of the Yalong River Basin from 1986 to 2022, the permanent and seasonal water areas of the water bodies in the Yalong River Basin are calculated as shown in Table 1 respectively, and the water body identification results are as Figure 2 and Figure 3 shown. Figure 2 Part (a) in it is a schematic diagram of the water body identification result before removing the mountain shadow, Figure 2 Part (b) in it is Figure 2 a partial enlarged view of part (a) in Figure 3 Part (a) in it is a schematic diagram of the water body identification result after removing the mountain shadow, Figure 3 Part (b) in it is Figure 3 a partial enlarged view of part (a) in Figure 2 and Figure 3

[0092] Table 1 Permanent and seasonal water areas

[0093]

[0094]

[0095] Based on the same inventive concept, the embodiment of the present application also provides a satellite spectrum-based water body information determination device for implementing the above-mentioned satellite spectrum-based water body information determination method. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the satellite spectrum-based water body information determination device provided below can refer to the limitations on the satellite spectrum-based water body information determination method in the above text, and will not be repeated here.

[0096] In another exemplary embodiment, a satellite spectrum-based water body information determination device is provided. The satellite spectrum-based water body information determination device applies the above-mentioned satellite spectrum-based water body information determination method. The satellite spectrum-based water body information determination device includes:

[0097] A satellite spectrum image acquisition module, configured to acquire satellite spectrum images of a target area collected at multiple time points.

[0098] A water body index calculation module, configured to calculate a water body index for the satellite spectrum images collected at each time point.

[0099] A water body identification module, configured to identify a water body in the target area according to the water body index to obtain a water body area and a non-water body area.

[0100] A mountain shadow removal module, which is used to judge the mountain shadow from the water area according to the near-infrared index and slope, and remove the mountain shadow from the water area to obtain the final water area.

[0101] A permanent and seasonal water body division module, which is used to determine the pixel water body frequency of each pixel in the target area according to the final water area corresponding to the satellite spectral image collected at each time point, and divide each pixel into a permanent water body pixel or a seasonal water body pixel according to the pixel water body frequency.

[0102] A permanent and seasonal water body area determination module, which is used to determine the permanent water body area and the seasonal water body area according to the permanent water body pixels and the seasonal water body pixels.

[0103] When distinguishing between permanent water bodies and seasonal water bodies, the present application significantly reduces the influence of mountain shadow interference, thus effectively solving the problem that mountain shadows are misidentified as water bodies in traditional methods, and can quickly and accurately obtain the water body area, especially the permanent and seasonal water body areas of inland rivers and lakes, providing a reliable technical means for water body information extraction, and further providing reliable support for watershed water resource management and environmental governance.

[0104] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 4 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the data for determining the water body information based on the satellite spectrum. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for determining water body information based on satellite spectrum.

[0105] Those skilled in the art can understand, Figure 4The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout. In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0106] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0107] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0108] Those of ordinary skill in the art can understand that all or part of the processes of implementing the above method embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0109] In each of the embodiments provided in this application, the database involved may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., without limitation. The processor involved in each of the embodiments provided in this application may be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a data processing logic unit of a programmable logic device, etc., without limitation.

[0110] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0111] Specific examples are used in this article to elaborate on the principle and implementation manner of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A method for determining water body information based on satellite spectra, characterized in that, The method for determining a water body area based on satellite spectra includes: Obtaining satellite spectral images of a target area collected at multiple time points; Calculating a water body index for the satellite spectral images collected at each time point; Identifying water bodies in the target area according to the water body index to obtain a water body area and a non-water body area; Judging mountain shadows from the water body area according to the near-infrared index and slope, and removing the mountain shadows from the water body area to obtain a final water body area; Determining the pixel water body frequency of each pixel in the target area according to the final water body area corresponding to the satellite spectral images collected at each time point, and classifying each pixel into a permanent water body pixel or a seasonal water body pixel according to the pixel water body frequency; Determining the permanent water body area and the seasonal water body area according to the permanent water body pixels and the seasonal water body pixels.

2. The method for determining water body information based on satellite spectra according to claim 1, characterized in that Calculating a water body index for the satellite spectral images collected at each time point specifically includes: Preprocessing the satellite spectral images collected at each time point; Calculating a water body index for the preprocessed satellite spectral images.

3. The method for determining water body information based on satellite spectra according to claim 2, wherein Preprocessing the satellite spectral images collected at each time point specifically includes: Performing stitching, mosaicking, cropping, and cloud removal processing on the satellite spectral images collected at each time point to obtain preprocessed satellite spectral images; the satellite spectral images collected at each time point include satellite spectral images provided by multiple data sources.

4. The method for determining water body information based on satellite spectra according to claim 1, wherein, The water body index includes a modified normalized difference water index, a normalized difference vegetation index, and an enhanced vegetation index; The calculation formula of the water body index is: Among them, MNDWI is the Modified Normalized Difference Water Index, NDVI is the Normalized Difference Vegetation Index, EVI is the Enhanced Vegetation Index, ρ green is the green band, ρ SWIR1 is the short-wave infrared band, ρ NIR is the near-infrared band, ρ red is the red band, ρ blue is the blue band.

5. The method for determining water body information based on satellite spectra according to claim 4, wherein Identifying water bodies in the target area according to the water body index to obtain a water body area and a non-water body area specifically includes: If a pixel satisfies (MNDWI > NDVI or MNDWI > EVI) and (EVI < 0.1), then the pixel is identified as a water body, otherwise the pixel is identified as a non-water body; the pixels identified as water bodies form a water body area, and the pixels identified as non-water bodies form a non-water body area.

6. The method for determining water body information based on satellite spectra according to claim 1, wherein Judging mountain shadows from the water body area according to the near-infrared index and slope, and removing the mountain shadows from the water body area to obtain a final water body area specifically includes: Determining the pixels in the water body area with a near-infrared index greater than a first set value and a slope greater than a second set value as mountain shadows, and removing the mountain shadows from the water body area to obtain a final water body area.

7. The method for determining water body information based on satellite spectra according to claim 1, wherein Classifying each pixel into a permanent water body pixel or a seasonal water body pixel according to the pixel water body frequency specifically includes: Classifying the pixels with a pixel water body frequency greater than a first set percentage into permanent water body pixels, and classifying the pixels not greater than the first set percentage and greater than a second set percentage into seasonal water body pixels.

8. A device for determining water body information based on satellite spectra, characterized in that, The device for determining water body information based on satellite spectra applies the method for determining water body information based on satellite spectra according to any one of claims 1-7. The device for determining water body information based on satellite spectra includes: A satellite spectral image acquisition module for obtaining satellite spectral images of a target area collected at multiple time points; A water body index calculation module for calculating a water body index for the satellite spectral images collected at each time point; A water body recognition module, configured to recognize water bodies in the target area according to the water body index, so as to obtain water body areas and non-water body areas; A mountain shadow removal module, configured to judge mountain shadows from the water body areas according to the near-infrared index and slope, and remove the mountain shadows from the water body areas to obtain the final water body areas; A permanent and seasonal water body division module, configured to determine the pixel water body frequency of each pixel in the target area according to the final water body areas corresponding to the satellite spectral images collected at each time point, and divide each pixel into a permanent water body pixel or a seasonal water body pixel according to the pixel water body frequency; A permanent and seasonal water body area determination module, configured to determine the permanent water body area and the seasonal water body area according to the permanent water body pixels and the seasonal water body pixels.

9. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the satellite spectral-based water body information determination method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the satellite spectral-based water body information determination method according to any one of claims 1-7.

Images