A hydrological remote sensing data processing method, system, computer and storage medium

Abstract

The application provides a hydrological remote sensing data processing method, system, computer and storage medium, which comprises the following steps: collecting and preprocessing multi-temporal optical and radar images of a target water area; for each pixel, constructing a spectral risk feature matrix based on the multi-temporal and multi-band reflectivity data thereof, and calculating an index representing time sequence stability based on the matrix; performing preliminary segmentation based on the index to obtain a candidate water body region; calculating the spectral risk gradient of each pixel in the region, calculating a local consistency optimization operator for each center pixel by fusing the spectral risk matrix similarity and gradient consistency, optimizing the candidate region according to the operator value, obtaining an optimized water body boundary, and then obtaining the spatial distribution of water quality parameters of the water body based on a preset water quality inversion model. Through time sequence stability analysis and local consistency optimization, the misjudgment of spectral or shadow pixels is effectively overcome, and the water body boundary extraction accuracy and robustness are significantly improved.

Description

Technical Field

[0001] This invention relates to the field of hydrological data processing technology, and in particular to a hydrological remote sensing data processing method, system, computer, and storage medium. Background Technology

[0002] Hydrological remote sensing is a key technology for monitoring the spatial distribution, dynamic changes, and water quality of water bodies, playing an irreplaceable role in water resource management, flood disaster early warning, and water environment assessment. High-precision, automated extraction of water body boundaries is fundamental to all subsequent analyses.

[0003] However, in practical applications, especially in complex environments, existing methods still face significant challenges. Currently, mainstream technical solutions mainly include the following categories: First, threshold segmentation methods based on single-temporal remote sensing image spectral indices (such as NDWI and MNDWI). Although this method is simple and efficient, it heavily relies on image quality and is easily affected by "different objects sharing the same spectrum" phenomena such as mountain shadows, building shadows, and dark vegetation, leading to a large number of false or missed detections, and performing poorly in mountainous and urban areas. Second, methods based on multi-temporal change detection, which identify water bodies by analyzing the spectral or index changes over time. These methods have high requirements for data temporal continuity and struggle to effectively handle the common problems of cloud cover, cloud shadows, and missing data in time-series data, resulting in insufficient stability. Summary of the Invention

[0004] In view of the shortcomings of the prior art, the purpose of this invention is to provide a hydrological remote sensing data processing method, system, computer and storage medium, which aims to solve the technical problem of poor water body boundary extraction in the prior art.

[0005] To achieve the above objectives, in a first aspect, the present invention provides: a method for processing hydrological remote sensing data, comprising the following steps: Collect multi-temporal remote sensing image data of the target water area and perform preprocessing, wherein the multi-temporal remote sensing image data includes optical images and radar images; For each pixel, a spectral risk feature matrix is ​​constructed based on multi-temporal and multi-band reflectance data, and a temporal stability index is calculated based on the spectral risk feature matrix. Based on the aforementioned temporal stability index, preliminary segmentation is performed to obtain candidate water body regions; Calculate the spectral risk gradient of each pixel in the candidate water body region, and calculate the local consistency optimization operator for each central pixel of the candidate water body region based on the spectral risk gradient; The candidate water body region is optimized based on the value of the local consistency operator, and the optimized water body boundary is obtained by removing pixels with consistency below the threshold. The water body pixel region to be inverted is determined based on the optimized water body boundary. Based on the water body pixel region to be inverted and the spectral risk feature matrix, the water quality parameters are obtained through a preset water quality inversion model.

[0006] According to one aspect of the above technical solution, the computational expression of the local consistency optimization operator is:

[0007] ; ; In the formula, For the local consistency optimization operator of pixel p, This indicates that the summation is performed by iterating through each cell in the spatial neighborhood. , Let p and q be the spectral risk feature matrices. Let Frobenius norm be the matrix. , For the spectral risk gradients of pixels p and q, and These are the weight normalization parameters for matrix differences and risk gradient differences, respectively. Let q be the temporal stability index for pixel q. The time series stability threshold, For indicator functions, For the spatial neighborhood of pixel p, For spectral risk gradient, The largest eigenvalue of the spectral risk feature matrix is... Here, S is the spatial gradient operator, and S is the temporal stability index.

[0008] According to one aspect of the above technical solution, the shape and size of the spatial neighborhood are adaptively adjusted based on the local features of the spectral risk gradient around pixel p, and the calculation steps of the spatial neighborhood specifically include: Calculate the local variance of the spectral risk gradient within an initial neighborhood window centered at pixel p; The size of the spatial neighborhood actually used to compute the local consistency optimization operator is adjusted according to the local variance, wherein the expression for calculating the local variance is: ; In the formula, W is the initial neighborhood window centered on pixel p. This represents the total number of pixels within the window. The spectral risk gradient of the k-th pixel within the window. This is the mean of the spectral risk gradients of all pixels within the window.

[0009] According to one aspect of the above technical solution, the spectral risk feature matrix includes matrix elements of reflectance data for each pixel at different times and in different bands, and the calculation expression for the matrix elements is as follows: ; In the formula, The reflectivity of the i-th band The mean over the entire time series, The reflectivity of the j-th band The mean over the entire time series, where T is the total length of the time series.

[0010] According to one aspect of the above technical solution, the calculation expression for the timing stability index is as follows: ; In the formula, The smallest eigenvalue of the spectral risk feature matrix. Let M be the difference matrix between adjacent time points. This is the reference norm value used for normalization.

[0011] According to one aspect of the above technical solution, the step of performing preliminary segmentation based on the time-series stability index to obtain candidate water body regions specifically includes: The temporal stability index of each pixel is compared with the preset temporal stability index threshold, and the pixels that are greater than the preset temporal stability index threshold are marked as water body pixels. Connectivity analysis is performed on the water body pixels, and regions with fewer than a preset number of pixels are removed. The remaining connected regions are then used as candidate water body regions.

[0012] According to one aspect of the above technical solution, the preprocessing steps for multi-temporal remote sensing image data specifically include: Radiometric correction, atmospheric correction, geometric correction, and registration are performed on multi-temporal remote sensing image data.

[0013] Secondly, the present invention provides a hydrological remote sensing data processing system, comprising: The acquisition module is used to acquire multi-temporal remote sensing image data of the target water area and perform preprocessing, wherein the multi-temporal remote sensing image data includes optical images and radar images; The processing module is used to construct a spectral risk feature matrix for each pixel based on multi-temporal and multi-band reflectance data, and to calculate the temporal stability index based on the spectral risk feature matrix. The segmentation module is used to perform preliminary segmentation based on the time-series stability index to obtain candidate water body regions; The calculation module is used to calculate the spectral risk gradient of each pixel in the candidate water body region, so as to calculate the local consistency optimization operator for each central pixel of the candidate water body region based on the spectral risk gradient. The optimization module is used to optimize the candidate water body region based on the value of the local consistency operator, and remove pixels with consistency below the threshold to obtain the optimized water body boundary; The inversion module is used to determine the water body pixel region to be inverted based on the optimized water body boundary, and to obtain water quality parameters based on the water body pixel region to be inverted and the spectral risk feature matrix through a preset water quality inversion model.

[0014] Thirdly, the present invention provides a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the hydrological remote sensing data processing method as described in the above technical solution.

[0015] Fourthly, the present invention provides a storage medium on which a computer program is stored, which, when executed by a processor, implements the hydrological remote sensing data processing method as described in the above technical solution.

[0016] Compared with existing technologies, the beneficial effects of this invention are as follows: By constructing a spectral risk feature matrix and calculating its temporal stability index, water bodies are characterized from the deep features of multi-band coordinated changes and temporal stability, effectively overcoming the misjudgment of "heterogeneous objects with the same spectrum" land features such as shadows by single-phase spectral indices, and enhancing robustness to interference such as cloud noise by utilizing the abrupt change penalty mechanism in temporal analysis; Secondly, for the core problem of shadow interference, a refined processing step combining spectral risk gradient and local consistency optimization operator is adopted. The spectral risk gradient can sensitively capture the variation differences between water bodies and shadow edges in the feature space, and the local consistency optimization operator can accurately identify and remove shadow pixels that are similar to water bodies in spectrum or texture but have inconsistent spatial context by weighted voting through the fusion of spectral risk matrix similarity and gradient consistency between pixels, which greatly improves the accuracy of boundary extraction. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the hydrological remote sensing data processing method in the first embodiment of the present invention; Figure 2 This is a structural block diagram of the hydrological remote sensing data processing system in the second embodiment of the present invention; Figure 3 This is a schematic diagram of the hardware structure of the computer in the third embodiment of the present invention; The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation

[0018] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0019] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0021] Example 1 Please see Figure 1 The figure shows a flowchart of a hydrological remote sensing data processing method according to the first embodiment of the present invention. As shown in the figure, the method includes the following steps: Step S100: Acquire multi-temporal remote sensing image data of the target water area and perform preprocessing. The multi-temporal remote sensing image data includes optical images and radar images. Specifically, the optical images include time-series satellite optical images (such as Landsat-8 / 9 OLI and Sentinel-2 MSI) covering the target water area and spanning multiple hydrological cycles. The data includes multiple bands such as visible light, near-infrared, and shortwave infrared to support spectral feature analysis. Synthetic aperture radar images within the same spatiotemporal range are acquired simultaneously. Radar data is insensitive to cloud cover and illumination, effectively supplementing the missing optical data and providing information on surface scattering and texture.

[0022] Preferably, the above preprocessing steps specifically include: performing radiometric correction, atmospheric correction, geometric correction, and registration on multi-temporal remote sensing image data. Radiometric calibration was performed on optical imagery, converting digitally quantized values ​​into apparent reflectance at the top of the atmosphere. Radar imagery underwent radiometric calibration, thermal noise removal, and topographic correction to obtain the backscattering coefficient. Geometric precision correction and registration were performed on all imagery (optical and radar). High-precision DEMs and ground control points were used to uniformly register imagery from different time phases and sensors to the same geographic coordinate system (e.g., UTM projection), ensuring that the spatial position error of all image pixels was less than half a pixel. Atmospheric correction employed the existing FLAASH physical model to eliminate the effects of atmospheric scattering and absorption, converting apparent reflectance into true surface reflectance.

[0023] Step S200: For each pixel, a spectral risk feature matrix is ​​constructed based on multi-temporal and multi-band reflectance data, and a temporal stability index is calculated based on the spectral risk feature matrix.

[0024] For each pixel, the reflectance data spanning N bands over the entire time series are used to construct the aforementioned spectral risk feature matrix. Each element in the matrix aims to reflect the cumulative degree to which the reflectance of the i-th and j-th bands deviates from their respective temporal means over the entire time dimension. The calculation expression for the matrix elements is as follows: ; In the formula, The reflectivity of the i-th band The mean over the entire time series, The reflectivity of the j-th band The mean over the entire time series, where T is the total length of the time series.

[0025] The calculation expression for the time series stability index is as follows: ; In the formula, The smallest eigenvalue of the spectral risk feature matrix. Let M be the difference matrix between adjacent time points. This is the reference norm value used for normalization.

[0026] Step S300: Perform preliminary segmentation based on the time-series stability index to obtain candidate water body regions.

[0027] Preferably, in this embodiment, the step of performing preliminary segmentation based on the time-series stability index to obtain candidate water body regions specifically includes: The temporal stability index of each pixel is compared with the preset temporal stability index threshold, and the pixels that are greater than the preset temporal stability index threshold are marked as water body pixels. Connectivity analysis is performed on the water body pixels, and regions with fewer than a preset number of pixels are removed. The remaining connected regions are then used as candidate water body regions.

[0028] Step S400: Calculate the spectral risk gradient of each pixel in the candidate water body region, and calculate the local consistency optimization operator for each central pixel of the candidate water body region based on the spectral risk gradient.

[0029] Specifically, in this embodiment, the computational expression of the local consistency optimization operator is:

[0030] ; ; In the formula, For the local consistency optimization operator of pixel p, This indicates that the summation is performed by iterating through each cell in the spatial neighborhood. , Let p and q be the spectral risk feature matrices. Let Frobenius norm be the matrix. , For the spectral risk gradients of pixels p and q, and These are the weight normalization parameters for matrix differences and risk gradient differences, respectively. Let q be the temporal stability index for pixel q. The time series stability threshold, For indicator functions, For the spatial neighborhood of pixel p, For spectral risk gradient, The largest eigenvalue of the spectral risk feature matrix is... Here, S is the spatial gradient operator, and S is the temporal stability index.

[0031] Step S500: Optimize the candidate water body region according to the value of the local consistency operator, and remove pixels with consistency below the threshold to obtain the optimized water body boundary.

[0032] Specifically, this is achieved by plotting histograms of the local consistency optimization operators for pixels within candidate water body regions. Ideally, the pixels of pure water bodies... The value is high, forming the first peak; misjudged pixels (shadows, dark vegetation, etc.) The value is low, forming a second peak. The threshold is set at the valley level between the two peaks. : right The values ​​are smoothed and kernel density is estimated to obtain the probability density function; local maxima and local minima are detected on the probability density function. If there are at least two peaks, the value corresponding to the lowest trough between the highest and second-highest peaks is taken as the threshold.

[0033] Step S600: Determine the water body pixel region to be inverted based on the optimized water body boundary; and obtain water quality parameters based on the water body pixel region to be inverted and the spectral risk feature matrix through a preset water quality inversion model.

[0034] In some application scenarios of this embodiment, the optimized water body boundary is transformed into a ternary mask image with the same spatial resolution and projection as the original remote sensing image, thereby forming a set of water body pixels to be inverted; for each water body pixel in the set, its corresponding spectral risk feature matrix is ​​expanded into a d-dimensional feature vector through matrix upper triangular vectorization and input into the preset water quality inversion model. To make it easier to understand, the water quality inversion model can be selected by adopting a physical mechanism model based on the water body radiative transfer equation to establish an analytical or semi-empirical relationship between spectral risk characteristics and water quality parameters; or by adopting a machine learning model that uses random forest, gradient boosting tree, support vector machine, or neural network as input and water quality parameters as output for supervised training.

[0035] In summary, the hydrological remote sensing data processing method in the above embodiments of the present invention, by constructing a spectral risk feature matrix and calculating its temporal stability index, characterizes water bodies from the deep features of multi-band coordinated changes and temporal stability, effectively overcoming the misjudgment of "heterogeneous objects with the same spectrum" ground features such as shadows by single-phase spectral indices, and enhancing robustness to interference such as cloud noise by utilizing the abrupt change penalty mechanism in temporal analysis. Secondly, addressing the core challenge of shadow interference, a refined processing step combining spectral risk gradient and local consistency optimization operator is adopted. The spectral risk gradient can sensitively capture the variation differences between water bodies and shadow edges in the feature space, while the local consistency optimization operator performs weighted voting by fusing the similarity of the spectral risk matrix between pixels and gradient consistency, which can accurately identify and remove shadow pixels that are similar to water bodies in spectrum or texture but have inconsistent spatial context, greatly improving the accuracy of boundary extraction.

[0036] Example 2 A second embodiment of this application also provides a hydrological remote sensing data processing system for implementing the embodiments and preferred embodiments described herein, which will not be repeated hereafter. As used below, the terms "module," "unit," "subunit," etc., can refer to a combination of software and / or hardware that performs a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0037] like Figure 2 As shown, the system includes: acquisition module 100, processing module 200, segmentation module 300, calculation module 400, optimization module 500 and inversion module 600.

[0038] The acquisition module 100 is used to acquire multi-temporal remote sensing image data of the target water area and perform preprocessing, wherein the multi-temporal remote sensing image data includes optical images and radar images; The processing module 200 is used to construct a spectral risk feature matrix for each pixel based on multi-temporal and multi-band reflectance data, and to calculate the temporal stability index based on the spectral risk feature matrix. The segmentation module 300 is used to perform preliminary segmentation based on the time-series stability index to obtain candidate water body regions; The calculation module 400 is used to calculate the spectral risk gradient of each pixel in the candidate water body region, so as to calculate the local consistency optimization operator for each central pixel of the candidate water body region based on the spectral risk gradient. Optimization module 500 is used to optimize the candidate water body region according to the value of the local consistency operator, and remove pixels with consistency below the threshold to obtain the optimized water body boundary; The inversion module 600 is used to determine the water body pixel region to be inverted based on the optimized water body boundary, and to obtain water quality parameters based on the water body pixel region to be inverted and the spectral risk feature matrix through a preset water quality inversion model.

[0039] It should be noted that the modules can be functional modules or program modules, and can be implemented in software or hardware. For modules implemented in hardware, the modules can reside in the same processor; or the modules can be located in different processors in any combination.

[0040] Example 3 A third embodiment of this application provides a computer that may include a processor 81 and a memory 82 storing computer program commands.

[0041] Specifically, the processor 81 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0042] The memory 82 may include a mass storage device for data or commands. For example, and not limitingly, the memory 82 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 82 may include removable or non-removable (or fixed) media. Where appropriate, the memory 82 may be internal or external to a data processing device. In a particular embodiment, the memory 82 is non-volatile memory. In a particular embodiment, the memory 82 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random-Access Memory (FPMDRAM), Extended Data Out Dynamic Random-Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0043] The memory 82 can be used to store or cache various data files that need to be processed and / or communicated, as well as possible computer program commands executed by the processor 81.

[0044] The processor 81 reads and executes computer program commands stored in the memory 82 to implement any of the hydrological remote sensing data processing methods in the above embodiments.

[0045] In some embodiments, the computer may further include a communication interface 83 and a bus 80. For example, Figure 3 As shown, the processor 81, memory 82, and communication interface 83 are connected through bus 80 and complete communication with each other.

[0046] The communication interface 83 is used to enable communication between the various modules, devices, units, and / or equipment in the embodiments of this application. The communication interface 83 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0047] Bus 80 includes hardware, software, or both, that couples computer components together. Bus 80 includes, but is not limited to, at least one of the following: data bus, address bus, control bus, expansion bus, and local bus. For example, and not as a limitation, bus 80 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 80 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.

[0048] Example 4 The fourth embodiment of this application provides a readable storage medium. This readable storage medium stores computer program commands; when executed by a processor, these computer program commands implement any of the hydrological remote sensing data processing methods described in the above embodiments.

[0049] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0050] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for processing hydrological remote sensing data, characterized in that, Includes the following steps: Collect multi-temporal remote sensing image data of the target water area and perform preprocessing, wherein the multi-temporal remote sensing image data includes optical images and radar images; For each pixel, a spectral risk feature matrix is ​​constructed based on multi-temporal and multi-band reflectance data, and a temporal stability index is calculated based on the spectral risk feature matrix. Based on the aforementioned temporal stability index, preliminary segmentation is performed to obtain candidate water body regions; Calculate the spectral risk gradient of each pixel in the candidate water body region, and calculate the local consistency optimization operator for each central pixel of the candidate water body region based on the spectral risk gradient; The candidate water body region is optimized based on the value of the local consistency operator, and the optimized water body boundary is obtained by removing pixels with consistency below the threshold. The water body pixel region to be inverted is determined based on the optimized water body boundary. Based on the water body pixel region to be inverted and the spectral risk feature matrix, the water quality parameters are obtained through a preset water quality inversion model.

2. The hydrological remote sensing data processing method according to claim 1, characterized in that, The computational expression for the local consistency optimization operator is: ； ； In the formula, For the local consistency optimization operator of pixel p, This indicates that the summation is performed by iterating through each cell in the spatial neighborhood. , Let p and q be the spectral risk feature matrices. Let Frobenius norm be the matrix. , For the spectral risk gradients of pixels p and q, and These are the weight normalization parameters for matrix differences and risk gradient differences, respectively. Let q be the temporal stability index for pixel q. The time series stability threshold, For indicator functions, For the spatial neighborhood of pixel p, For spectral risk gradient, The largest eigenvalue of the spectral risk feature matrix is... Here, S is the spatial gradient operator, and S is the temporal stability index.

3. The hydrological remote sensing data processing method according to claim 2, characterized in that, The shape and size of the spatial neighborhood are adaptively adjusted based on the local features of the spectral risk gradient around pixel p. The calculation steps for the spatial neighborhood specifically include: Calculate the local variance of the spectral risk gradient within an initial neighborhood window centered at pixel p; The size of the spatial neighborhood actually used to compute the local consistency optimization operator is adjusted according to the local variance, wherein the expression for calculating the local variance is: ； In the formula, W is the initial neighborhood window centered on pixel p. This represents the total number of pixels within the window. The spectral risk gradient of the k-th pixel within the window. This is the mean of the spectral risk gradients of all pixels within the window.

4. The hydrological remote sensing data processing method according to claim 1, characterized in that, The spectral risk feature matrix includes matrix elements of reflectance data for each pixel at different times and in different bands. The calculation expression for the matrix elements is as follows: ； In the formula, The reflectivity of the i-th band The mean over the entire time series, The reflectivity of the j-th band The mean over the entire time series, where T is the total length of the time series.

5. The hydrological remote sensing data processing method according to claim 2, characterized in that, The calculation expression for the time series stability index is as follows: ； In the formula, The smallest eigenvalue of the spectral risk feature matrix. Let M be the difference matrix between adjacent time points. This is the reference norm value used for normalization.

6. The hydrological remote sensing data processing method according to claim 1, characterized in that, The specific steps for preliminary segmentation based on the time-series stability index to obtain candidate water body regions include: The temporal stability index of each pixel is compared with the preset temporal stability index threshold, and the pixels that are greater than the preset temporal stability index threshold are marked as water body pixels. Connectivity analysis is performed on the water body pixels, and regions with fewer than a preset number of pixels are removed. The remaining connected regions are then used as candidate water body regions.

7. The hydrological remote sensing data processing method according to claim 1, characterized in that, The specific steps for preprocessing multi-temporal remote sensing image data include: Radiometric correction, atmospheric correction, geometric correction, and registration are performed on multi-temporal remote sensing image data.

8. A hydrological remote sensing data processing system, characterized in that, include: The acquisition module is used to acquire multi-temporal remote sensing image data of the target water area and perform preprocessing, wherein the multi-temporal remote sensing image data includes optical images and radar images; The processing module is used to construct a spectral risk feature matrix for each pixel based on multi-temporal and multi-band reflectance data, and to calculate the temporal stability index based on the spectral risk feature matrix. The segmentation module is used to perform preliminary segmentation based on the time-series stability index to obtain candidate water body regions; The calculation module is used to calculate the spectral risk gradient of each pixel in the candidate water body region, so as to calculate the local consistency optimization operator for each central pixel of the candidate water body region based on the spectral risk gradient. The optimization module is used to optimize the candidate water body region based on the value of the local consistency operator, and remove pixels with consistency below the threshold to obtain the optimized water body boundary; The inversion module is used to determine the water body pixel region to be inverted based on the optimized water body boundary, and to obtain water quality parameters based on the water body pixel region to be inverted and the spectral risk feature matrix through a preset water quality inversion model.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the hydrological remote sensing data processing method as described in any one of claims 1-7.

10. A storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the hydrological remote sensing data processing method as described in any one of claims 1-7 above.

Images