A reservoir water body boundary determination method, apparatus, and processing device

Abstract

The application provides a reservoir water body boundary determination method and device and processing equipment, which are used for finely determining a dynamic range of a reservoir water body based on an improved normalized water index and a combination of a maximum likelihood thresholding method. Compared with a single time phase water body extraction method, the method can capture an outer boundary region with the widest geographical position and the longest time range. Compared with a long time series water body extraction method, the method can exclude the influence of a water body bare area, a drawdown zone and a shore zone, and capture a more accurate inner boundary region. Thus, the method can well meet the high-quality identification requirement for a complex reservoir water body.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of image analysis, in particular to a reservoir water body boundary determination method and device and processing equipment. BACKGROUND

[0002] Through satellite remote sensing technology, the reservoir water body can be accurately identified, which can provide data support for monitoring hydrological conditions. For hydrological management, it is obviously of great practical significance.

[0003] At present, the mainstream water body identification strategy is: 1) based on single time phase to identify water body, mostly using NDWI, MNDWI, AWEI and other water body index to set threshold value manually to extract water body range. 2) Combined with one year or more long time series of multi-spectral or radar images to classify permanent water body and seasonal water body.

[0004] The former single time phase water body identification can meet the time frequency requirements of general reservoir water area monitoring, but it is easy to cause misclassification of water body and other land types, and the recognition accuracy and reliability are low; the latter water body identification has higher accuracy, but it is not representative in single time phase, which is easy to cause missing and multiple division of water body and drawdown zone.

[0005] Therefore, the above two types of water body identification strategies are more suitable for lake and plain river water body identification, which has high recognition accuracy, high calculation efficiency and meets the time resolution requirements, but it is difficult to meet the application requirements of complex reservoir water body identification. SUMMARY

[0006] The present application provides a reservoir water body boundary determination method, device and processing equipment, which is based on improved normalized water body index and Otsu method to determine the dynamic range of reservoir water body in detail. Compared with the single time phase water body extraction method, it can capture the outer boundary area with the widest geographical location and the longest time range. Compared with the long time series water body extraction method, it can exclude the influence of water body bare drawdown zone and bank zone, and capture more accurate inner boundary area, so as to meet the high quality identification requirements of complex reservoir water body.

[0007] In the first aspect, the present application provides a reservoir water body boundary determination method, which comprises:

[0008] Obtaining an initial multi-spectral satellite image in a target area, wherein the initial multi-spectral satellite image has time sequence attribute;

[0009] Performing data enhancement operation on the initial multi-spectral satellite image to obtain a target multi-spectral satellite image;

[0010] On the basis of the improved normalized water index calculated by the target multi-spectral satellite image in time sequence, the index threshold of the improved normalized water index is calculated combined with the Otsu method, the preliminary water body pixels of all time phases are screened out, and the preliminary water body pixel screening result is obtained.

[0011] On the basis of the preliminary water body pixel screening result, the reservoir constant water body and the reservoir time phase water body are calculated respectively, and the reservoir water body boundary range with the reservoir constant water body as the outer boundary and the reservoir time phase water body as the inner boundary is obtained.

[0012] In the second aspect, the application provides a reservoir water body boundary determination device, and the device comprises:

[0013] The acquisition unit is configured to acquire an initial multi-spectral satellite image in a target region, wherein the initial multi-spectral satellite image has a time sequence attribute.

[0014] The operation unit is configured to perform a data enhancement operation on the initial multi-spectral satellite image to obtain a target multi-spectral satellite image.

[0015] The screening unit is configured to calculate an index threshold of an improved normalized water index combined with the Otsu method on the basis of the improved normalized water index calculated by the target multi-spectral satellite image in time sequence, screen out preliminary water body pixels of all time phases, and obtain a preliminary water body pixel screening result.

[0016] The calculation unit is configured to calculate a reservoir constant water body and a reservoir time phase water body respectively on the basis of the preliminary water body pixel screening result, and obtain a reservoir water body boundary range with the reservoir constant water body as the outer boundary and the reservoir time phase water body as the inner boundary.

[0017] In the third aspect, the application provides a processing device comprising a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program in the memory to execute the method provided in the first aspect of the application or any possible implementation manner of the first aspect of the application.

[0018] In the fourth aspect, the application provides a computer readable storage medium, which stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the method provided in the first aspect of the application or any possible implementation manner of the first aspect of the application.

[0019] From the above content, the application has the following beneficial effects:

[0020] In the water body identification target based on satellite remote sensing image of reservoir, the application is based on the improved normalized water index and the Otsu method to determine the dynamic range of reservoir water body. Compared with the single-phase water body extraction method, the method can capture the outer boundary area with the widest geographical location and the longest time range. Compared with the long-time water body extraction method, the method can exclude the influence of water bare out of the drawdown zone and the shore zone, and capture more accurate inner boundary area. Thus, the method can well meet the high-quality identification requirements of complex reservoir water body. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0022] Figure 1 A flowchart of the reservoir water body boundary determination method of the application;

[0023] Figure 2 A structural diagram of the reservoir water body boundary determination device of the application;

[0024] Figure 3 A structural diagram of the processing device of the application. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the application will be described clearly and completely with reference to the drawings of the embodiments of the application. Obviously, the described embodiments are only some embodiments of the application, not all embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0026] The terms "first", "second", and the like in the description and in the claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged, where appropriate, so that the embodiments described herein can be carried out in sequences other than those illustrated or described herein. Furthermore, the terms "comprise" and "have", and any variations thereof, are intended to cover non-exclusive inclusion, for example, processes, methods, systems, products, or devices that include a series of steps or modules are not necessarily limited to those steps or modules that are clearly listed, but can include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. The naming or numbering of the steps appearing in the present application does not mean that the steps in the method flow must be performed in the time / logical order indicated by the naming or numbering, and the named or numbered flow steps can be changed in execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0027] The division of modules appearing in the present application is a logical division, and in actual application, there can be another division manner, for example, a plurality of modules can be combined or integrated in another system, or some features can be ignored or not executed, in addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, the indirect coupling or communication connection between the modules can be electrical or other similar forms, which are not limited in the present application. Moreover, the modules or sub-modules described as separate components can or can not be physically separated, can or can not be physical modules, or can be distributed to a plurality of circuit modules, and part or all of the modules can be selected according to actual needs to achieve the purpose of the present application scheme.

[0028] Before introducing the reservoir water body boundary determination method provided by the present application, the background content involved in the present application is first introduced.

[0029] The reservoir water body boundary determination method, device and computer readable storage medium provided by the present application can be applied to a processing device, which is used to determine the dynamic range of the reservoir water body in detail based on the improved normalized water index and the Otsu method, compared with the single time phase water body extraction method, the most widely located and longest time range outer boundary region can be captured, compared with the long time sequence water body extraction method, the influence of the water body bare leakage out of the drawdown zone and the shore zone can be excluded, and the more accurate inner boundary region can be captured, so that the high quality recognition demand for the complex reservoir water body can be well met.

[0030] The water reservoir water body boundary determination method mentioned in the present application can be executed by a water reservoir water body boundary determination device, or a server, a physical host, a user equipment (UE) or other types of processing devices integrated with the water reservoir water body boundary determination device. The water reservoir water body boundary determination device can be implemented in hardware or software, and the UE can be a terminal device such as a smartphone, a tablet computer, a notebook computer, a desktop computer, or a personal digital assistant (PDA). The processing device can be set up in a device cluster.

[0031] It can be understood that the present application is usually based on existing satellite remote sensing images for data processing (which can also be referred to as image detection and image recognition) in actual application. Therefore, the processing device executing the water reservoir water body boundary determination method or carrying the corresponding application service of the water reservoir water body boundary determination method only needs to meet the data processing capability requirement, and the specific device type and device deployment form are flexible and can be adjusted adaptively according to actual conditions.

[0032] If the specific collection of satellite remote sensing images or further data application based on the determined water reservoir water body is involved, further adaptive adjustment of the device type and device deployment form of the processing device is required.

[0033] As an example, the satellite remote sensing image collection system can also be included in the scope of the processing device of the present application, so that the processing device itself has the function of collecting satellite remote sensing images.

[0034] Next, the water reservoir water body boundary determination method provided by the present application will be introduced.

[0035] First, refer to Figure 1 , Figure 1 Fig. 1 shows a flowchart of the water reservoir water body boundary determination method of the present application. The water reservoir water body boundary determination method provided by the present application can specifically include the following steps S101 to S104:

[0036] Step S101, obtaining an initial multi-spectral satellite image in a target area, wherein the initial multi-spectral satellite image has a time sequence attribute;

[0037] It can be understood that the present application is similar to the prior art, and the boundary of the water reservoir water body (usually known to exist, and in some cases, it can also be attempted to search for the water reservoir water body, i.e. unknown water reservoir water body) contained in the selected target area is identified based on satellite remote sensing images.

[0038] Wherein, the application is based on multispectral satellite images to develop the processing of the scheme, and the multispectral satellite images are a relatively mature concept / thing in satellite remote sensing technology, so this is not specifically expanded. In order to facilitate the description, the multispectral satellite images obtained here are referred to as initial multispectral satellite images, and the subsequent target multispectral satellite images are the same.

[0039] It should be noted that the initial multispectral satellite images obtained here have time sequence properties, or long time series (time series length / time span greater than a corresponding threshold) multispectral satellite images.

[0040] In specific operation, the acquisition of the initial multispectral satellite images here can be manual input, reading from local or other devices, or real-time acquisition, which is adjusted according to actual conditions.

[0041] Further, as an exemplary embodiment here, step S101 obtains initial multispectral satellite images in the target area, which can specifically include:

[0042] For the target area, determine the target satellite remote sensing product with the best evaluation value from the consideration factors including image quality and cloud cover among the candidate different satellite remote sensing products;

[0043] Obtain the initial multispectral satellite images of the target satellite remote sensing product in the target area.

[0044] It can be understood that in actual application, the application can conveniently obtain the initial multispectral satellite images required for the scheme processing from ready-made satellite remote sensing products (or satellite remote sensing products), and in this process, the selection of the specific satellite remote sensing product, that is, the target satellite remote sensing product, can also be involved. Therefore, based on higher-quality initial multispectral satellite images, the identification of the boundary of the reservoir water body in the target area can be more convenient and accurate.

[0045] In the selection link, the evaluation value can be quantified based on a series of pre-set consideration factors, such as weighting method, which can involve specific factors such as image quality and cloud cover. Obviously, higher image quality and less cloud cover mean higher data quality.

[0046] As an example, the target satellite remote sensing product selected or determined by the application can be L1C multispectral images of Sentinel-2 MSI.

[0047] Step S102 performs data enhancement on the initial multispectral satellite images to obtain target multispectral satellite images;

[0048] After obtaining the initial multi-spectral satellite image, instead of directly carrying out the identification processing of the reservoir water body boundary, the application carries out data enhancement operation / processing, so as to continue to improve the image quality through secondary processing of data, and lay a better foundation for subsequent identification processing of the reservoir water body boundary.

[0049] It can be understood that for the data enhancement operation that can be taken in the specific operation, both the existing scheme (the data enhancement operation itself exists a large number of mature and general specific operation means in the prior art) and the further optimization and improvement based on the existing scheme can be adopted, and a novel self-developed scheme can also be adopted, which is all acceptable and can be adjusted according to actual needs.

[0050] Further, as an exemplary embodiment herein, the step S102 carries out data enhancement operation on the initial multi-spectral satellite image to obtain a target multi-spectral satellite image, which can specifically include:

[0051] The initial multi-spectral satellite image is subjected to a preprocessing operation, wherein the preprocessing operation includes radiation calibration, cloud removal, mosaicking and cropping, etc.

[0052] The image obtained by the preprocessing operation is further subjected to cloud layer, cloud shadow, multi-cloud and cirrus cloud pixel removal using a quality control band to obtain the target multi-spectral satellite image.

[0053] The radiation calibration, cloud removal, mosaicking and cropping operations are several types of operations commonly used for data enhancement and data preprocessing of satellite remote sensing images. For example, the data preprocessing herein can be realized by the Sen2cor plug-in in SNAP, and the quality control band can also be understood as a band value setting strategy for effectively classifying / distinguishing cloud attribute pixels such as cloud layer, cloud shadow, multi-cloud and cirrus cloud. In some cases, it can also be an existing application service, such as the quality_scene_classification component of the SNAP product.

[0054] In this embodiment, in the case of obtaining standardized and high-quality image data by the general data enhancement means in the first stage, the data quality is further effectively improved by the quality control band specially designed for cloud attribute pixels in the second stage.

[0055] Step S103, on the basis of the improved normalized water body index calculated by the target multi-spectral satellite image in time sequence, the index threshold of the improved normalized water body index is calculated combined with the Otsu method, and the preliminary water body pixels of all time phases are screened out to obtain a preliminary water body pixel screening result.

[0056] It can be understood that after obtaining the target multispectral satellite image with obviously enhanced quality, specific reservoir water body recognition processing can be carried out.

[0057] Specifically, the present application relates to two stages of reservoir water body recognition processing. The first stage preliminarily identifies water body pixels, and the second stage further processes in detail to accurately capture the boundary of the reservoir water body.

[0058] In the first stage, the present application combines the improved normalized water index (MNDWI) and the OTSU method (also known as the maximum inter-class variance method) to preliminarily divide and screen water body pixels from the pixels of different phases (corresponding to long time series characteristics) involved in the target multispectral satellite image.

[0059] Among them, both belong to the category of prior art / algorithms, and are not the focus of the present application scheme, so they are not specifically expanded here.

[0060] And the index threshold calculated by the OTSU method can be understood as being expanded in a time-phase-by-time-phase manner in the specific calculation process, so as to correspond to the subsequent processing of screening preliminary water body pixels for each phase.

[0061] In specific operation, for the current phase, the corresponding index threshold can be denoted as K. In the current phase, if the improved normalized water index calculated for a pixel is greater than the index threshold, it can be identified / labelled as a water body pixel, that is, the water body pixel belongs to the range of the reservoir water body, otherwise it is identified / labelled as a non-water body pixel.

[0062] Corresponding to the calculation of the improved normalized water index, as a specific embodiment, the present application method can further include:

[0063] According to the following formula, the improved normalized water index is calculated for the target multispectral satellite image in time series:

[0064] ,

[0065] Among them, is the value of the improved normalized water index, is the reflectance value of the green band (560 nm), is the reflectance value of the short-wave infrared band (1610 nm).

[0066] Step S104, on the basis of the preliminary water body pixel screening result, the reservoir constant water body and the reservoir time phase water body are calculated respectively, and the reservoir water body boundary range which takes the reservoir constant water body as the outer boundary and takes the reservoir time phase water body as the inner boundary is obtained.

[0067] On the basis of the improved normalized water index and the Otsu method, it is determined that each pixel belongs to the water body pixel or the non-water body pixel under each time phase, and then the reservoir constant water body and the reservoir time phase water body involved in the scheme are calculated based on the classification result of the two classifications, that is, the preliminary water body pixel screening result.

[0068] The reservoir constant water body can be considered as the relatively fixed reservoir water body of the current reservoir under the actual conditions of the region where the reservoir is located, and the reservoir time phase water body can be considered as the reservoir water body which dynamically changes with the time phase under the actual conditions of the region where the reservoir is located.

[0069] For the former, the application takes it as the outer boundary of the dynamic reservoir water body range, and for the latter, the application takes it as the inner boundary of the dynamic reservoir water body range. From the visualization aspect, the layer of the reservoir time phase water body is superimposed on the layer of the reservoir constant water body, and the dynamic reservoir water body range boundary of the current complex reservoir can be obtained.

[0070] Further, for the calculation and processing of the reservoir constant water body, as an exemplary embodiment, the application calculates the reservoir constant water body on the basis of the preliminary water body pixel screening result, which can specifically include:

[0071] On the basis of the preliminary water body pixel screening result, the total water accumulation probability value of each pixel is obtained by iteratively calculating all the time phases of the preliminary water body pixel respectively through the following formula:

[0072] ,

[0073] Wherein, WF is the numerical value of the total water accumulation probability value, M is the total number of effective observations in the time range involved in the initial multispectral satellite image, and T is a binary variable, T=1 under the water body condition and T=0 under the non-water body condition.

[0074] The set of different pixels with the total water accumulation probability value greater than the total water accumulation probability threshold value is determined as the reservoir constant water body.

[0075] It can be seen that the embodiment herein shows how the application specifically calculates the reservoir constant water body, starting from the quantitative formula level, and gives a specific implementation scheme, which has better practical value, and it can also be seen that the embodiment herein is considered from the overall level, that is, all time phases in the time range (time span) involved in the initial multispectral satellite image / target multispectral satellite image.

[0076] For the total water accumulation probability threshold involved, it can be understood that it can be adjusted adaptively according to actual conditions and actual needs in actual operation, and can also be understood as an empirical coefficient, and different total water accumulation probability thresholds can be configured for different reservoirs.

[0077] Specifically, the total water accumulation probability threshold can be determined according to the proportion of the complex reservoir basin in the rainy season in the whole year. The rainy season is the period of expansion of the water area of the complex reservoir basin, and the dry season is the period of contraction of the water area of the complex reservoir basin.

[0078] As an example, the total water accumulation probability threshold can be 70%.

[0079] On the other hand, for the calculation and processing of the reservoir time phase water body, as an exemplary embodiment, the application calculates the reservoir time phase water body on the basis of the preliminary water body pixel screening result, which can specifically include:

[0080] On the basis of the preliminary water body pixel screening result, in combination with the constraints of the maximum number of connected domain elimination and the maximum number of pixel elimination, for each water body region composed of preliminary water body pixels in each time phase, the connected domains with a size smaller than the connected domain size threshold are removed to obtain the reservoir time phase water body.

[0081] It can be seen that in this embodiment, the unit time phase within the time range (time span) involved in the initial multi-spectral satellite image / target multi-spectral satellite image is specifically considered from a local level, and the corresponding constraints are combined on the basis of the connected domain processing to further simplify all connected domains to obtain the accurate connected domain of the corresponding time phase water body in each time phase.

[0082] The constraints can be configured from the maximum number of connected domain elimination and the maximum number of pixel elimination to exclude the influence of buildings and paddy fields and to obtain more concise and accurate connected domain processing results.

[0083] In addition, it can be understood that the maximum number of connected domain elimination and the maximum number of pixel elimination can also be adjusted according to actual conditions and actual needs in actual application.

[0084] As an example, the maximum number of connected domain elimination can be 8, and the maximum number of pixel elimination can be 50.

[0085] Thus, compared with the single time-phase water body extraction method in the prior art, the outer boundary of the dynamic water body range retains the water body boundary with the widest geographical location and the longest time range in the complex reservoir basin, and can remain relatively fixed to meet the needs of water quality inversion and water bloom extraction remote sensing batch calculation; compared with the long time series water body extraction method in the prior art, the inner boundary of the dynamic water body range excludes the influence of the water body bare exposure out of the drawdown zone and the riparian zone in the complex reservoir basin during the dry season, so as to provide strong data support for hydrological management and the corresponding personnel.

[0086] In terms of application, the application can also continue to be related to the corresponding data application link.

[0087] Specifically, on the basis of the preliminary water body pixel screening result, the reservoir constant water body and the reservoir time-phase water body are calculated respectively to obtain the reservoir water body boundary range with the reservoir constant water body as the outer boundary and the reservoir time-phase water body as the inner boundary, and then the method can further include:

[0088] The reservoir water body boundary range is subjected to at least one of data application processing, such as local storage, off-site storage, result display, output of boundary identification prompt, result forwarding, and further data analysis.

[0089] It can be understood that in actual application, the specific data application processing can be further adjusted according to the pre-configuration and implementation configuration data application strategy / rule, which is not limited in the application.

[0090] Finally, for the above scheme content, as a whole, under the reservoir water body identification target based on satellite remote sensing image, the application determines the dynamic range of the reservoir water body based on the improved normalized water body index and the Otsu method, which can capture the outer boundary region with the widest geographical location and the longest time range compared with the single time-phase water body extraction method, and can exclude the influence of the water body bare exposure out of the drawdown zone and the riparian zone to capture a more accurate inner boundary region compared with the long time series water body extraction method, so as to meet the high-quality identification needs of the complex reservoir water body.

[0091] The above is an introduction to the reservoir water body boundary determination method provided by the application. In order to better implement the reservoir water body boundary determination method provided by the application, the application also provides a reservoir water body boundary determination device from the functional module perspective.

[0092] Referring to Figure 2 , Figure 2 is a structural schematic diagram of the reservoir water body boundary determination device, in the application, the reservoir water body boundary determination device 200 can specifically include the following structures:

[0093] The acquisition unit 201 is configured to acquire initial multi-spectral satellite images in a target area, wherein the initial multi-spectral satellite images have time sequence attributes;

[0094] The operation unit 202 is configured to perform data enhancement operation on the initial multi-spectral satellite images to obtain target multi-spectral satellite images;

[0095] The screening unit 203 is configured to calculate an index threshold of the improved normalized water body index by using the Otsu method on the basis of the improved normalized water body index calculated from the target multi-spectral satellite images in time sequence, and screen out preliminary water body pixels in all time phases to obtain a preliminary water body pixel screening result;

[0096] The calculation unit 204 is configured to calculate reservoir constant water bodies and reservoir time phase water bodies respectively on the basis of the preliminary water body pixel screening result, and obtain a reservoir water body boundary range with the reservoir constant water bodies as outer boundaries and the reservoir time phase water bodies as inner boundaries.

[0097] In an exemplary embodiment, the acquisition unit 201 is specifically configured to:

[0098] For the target area, determine a target satellite remote sensing product with the best evaluation value in terms of image quality and cloud amount from candidate different satellite remote sensing products;

[0099] Acquire initial multi-spectral satellite images of the target satellite remote sensing product in the target area.

[0100] In another exemplary embodiment, the operation unit 202 is specifically configured to:

[0101] Perform preprocessing operation on the initial multi-spectral satellite images, wherein the preprocessing operation includes radiation calibration, cloud removal, mosaicking and cropping;

[0102] Continue to remove pixels of cloud layers, cloud shadows, multiple clouds and cirrus clouds from the images obtained by the preprocessing operation by using a quality control band to obtain the target multi-spectral satellite images.

[0103] In another exemplary embodiment, the calculation unit 204 is further configured to:

[0104] Calculate the improved normalized water body index from the target multi-spectral satellite images in time sequence according to the following formula:

[0105] ,

[0106] wherein, is a numerical value of the improved normalized water body index, is a reflectance value of a green band, is a reflectance value of a short-wave infrared band.

[0107] In yet another exemplary embodiment, the computing unit 204 is specifically configured to:

[0108] On the basis of the preliminary water body pixel screening result, the total water accumulation probability value of each pixel is obtained by performing pixel-by-pixel iterative statistics on all time phases of the preliminary water body pixels according to the following formula:

[0109]

[0110] wherein WF is the numerical value of the total water accumulation probability value, M is the total number of effective observations within the time range involved in the initial multispectral satellite image, and T is a binary variable, T = 1 under the water body condition and T = 0 under the non-water body condition;

[0111] The set of different pixels with the total water accumulation probability value greater than the total water accumulation probability threshold value is determined as the constant water body of the reservoir.

[0112] In yet another exemplary embodiment, the computing unit 204 is specifically configured to:

[0113] On the basis of the preliminary water body pixel screening result, in combination with the constraint of the maximum number of eliminated connected domains and the maximum number of eliminated pixels, the connected domains with a size smaller than the connected domain size threshold value are removed from the water body region composed of the preliminary water body pixels for each time phase, to obtain the reservoir time phase water body.

[0114] In yet another exemplary embodiment, the total water accumulation probability threshold value is specifically 70%, the maximum number of eliminated connected domains is specifically 8, and the maximum number of eliminated pixels is specifically 50.

[0115] The present application also provides a processing device from the hardware structure angle, referring to Figure 3 Figure 3 A structural schematic diagram of the processing device of the present application is shown, specifically, the processing device of the present application can include a processor 301, a memory 302 and an input and output device 303, the processor 301 is used to execute the computer program stored in the memory 302 to realize the functions of the Figure 1 corresponding embodiments of the reservoir water body boundary determination method; or the processor 301 is used to execute the computer program stored in the memory 302 to realize the functions of the Figure 2 corresponding embodiments of each unit, the memory 302 is used to store the computer program required by the processor 301 to execute the above Figure 1 corresponding embodiments of the reservoir water body boundary determination method.

[0116] ​​For example, the computer program can be divided into one or more modules / units, one or more modules / units are stored in the memory 302 and executed by the processor 301 to complete the present application. One or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the computer device.

[0117] The processing device can include, but is not limited to, the processor 301, the memory 302, and the input / output device 303. Those skilled in the art can understand that the schematic is only an example of the processing device, and does not constitute a limitation on the processing device, and can include more or less components than the schematic, or combine certain components, or different components, for example, the processing device can also include a network access device, a bus, etc., and the processor 301, the memory 302, and the input / output device 303 are connected through the bus.

[0118] The processor 301 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The processor is the control center of the processing device, which connects various parts of the entire device through various interfaces and lines.

[0119] The memory 302 can be used to store computer programs and / or modules. The processor 301 realizes various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 302, and calling data stored in the memory 302. The memory 302 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required by a function, etc.; the data storage area can store data created according to the use of the processing device, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0120] The processor 301 is used to execute the computer program stored in the memory 302, and can specifically implement the following functions:

[0121] An initial multi-spectral satellite image in a target region is acquired, wherein the initial multi-spectral satellite image has a time sequence attribute;

[0122] A data enhancement operation is performed on the initial multi-spectral satellite image to obtain a target multi-spectral satellite image;

[0123] On the basis of an improved normalized water body index calculated in a time sequence for the target multi-spectral satellite image, an index threshold of the improved normalized water body index is calculated by using the Otsu method, and preliminary water body pixels of all time phases are screened to obtain a preliminary water body pixel screening result;

[0124] On the basis of the preliminary water body pixel screening result, a reservoir constant water body and a reservoir time phase water body are calculated respectively to obtain a reservoir water body boundary range with the reservoir constant water body as an outer boundary and the reservoir time phase water body as an inner boundary.

[0125] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the reservoir water body boundary determination device, the processing device and the corresponding units thereof described above can be referred to as Figure 1 The description of the reservoir water body boundary determination method in the corresponding embodiment will not be repeated here.

[0126] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by related hardware controlled by the instructions, which can be stored in a computer readable storage medium and loaded and executed by a processor.

[0127] Therefore, the present application provides a computer readable storage medium, which stores a plurality of instructions capable of being loaded by a processor to execute the present application as Figure 1 The specific operation can be referred to as Figure 1 The description of the reservoir water body boundary determination method in the corresponding embodiment will not be repeated here.

[0128] The computer readable storage medium can include a read only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0129] Due to the instructions stored in the computer readable storage medium, the present application as Figure 1 The steps of the reservoir water body boundary determination method in the corresponding embodiment, therefore, the present application as Figure 1The beneficial effects that can be achieved by the reservoir water body boundary determination method in the corresponding embodiments are described in detail in the foregoing description, and will not be described here again.

[0130] The reservoir water body boundary determination method, the device, the processing equipment and the computer readable storage medium provided by the present application are described in detail above, and the principles and implementation modes of the present application are described in this paper. The above example is only used to help understand the core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed; in view of the above, the content of the specification should not be understood as the limitation of the present application.

Claims

1. A method for determining the boundary of a reservoir water body, characterized in that, The method comprises: acquiring initial multi-spectral satellite images in a target region, wherein the initial multi-spectral satellite images have time sequence attributes; performing data enhancement operations on the initial multi-spectral satellite images to obtain target multi-spectral satellite images; on the basis of improved normalized water body indexes calculated from the target multi-spectral satellite images in time sequence, combining the improved normalized water body indexes with index threshold values calculated by the Otsu method to screen out preliminary water body pixels of all time phases to obtain preliminary water body pixel screening results; on the basis of the preliminary water body pixel screening results, calculating reservoir constant water bodies and reservoir time phase water bodies respectively to obtain a reservoir water body boundary range with the reservoir constant water bodies as outer boundaries and the reservoir time phase water bodies as inner boundaries, wherein the reservoir constant water bodies refer to relatively fixed reservoir water bodies of a current reservoir under actual conditions in a region where the reservoir is located, and the reservoir time phase water bodies refer to reservoir water bodies of the current reservoir that dynamically change with time phases under actual conditions in the region where the reservoir is located; on the basis of the preliminary water body pixel screening results, calculating the reservoir constant water bodies, comprising: on the basis of the preliminary water body pixel screening results, performing pixel-by-pixel iterative statistics on the preliminary water body pixels of all time phases respectively by the following formula to obtain total water accumulation probability values of each pixel: ， wherein WF is a numerical value of the total water accumulation probability value, M is a total number of effective observations within a time range related to the initial multi-spectral satellite images, and T is a binary variable, T=1 under water body conditions and T=0 under non-water body conditions; determining a set of different pixels with total water accumulation probability values greater than a total water accumulation probability threshold value as the reservoir constant water bodies; on the basis of the preliminary water body pixel screening results, calculating the reservoir time phase water bodies, comprising: on the basis of the preliminary water body pixel screening results, combining constraints of a maximum number of connected domains to be removed and a maximum number of pixels to be removed, and removing connected domains with sizes less than a connected domain size threshold value from water body regions composed of the preliminary water body pixels for each time phase to obtain the reservoir time phase water bodies; the total water accumulation probability threshold value is specifically 70%, the maximum number of connected domains to be removed is specifically 8, and the maximum number of pixels to be removed is specifically 50; the data enhancement operations on the initial multi-spectral satellite images to obtain target multi-spectral satellite images comprise: performing preprocessing operations on the initial multi-spectral satellite images, wherein the preprocessing operations include radiation calibration, cloud removal, mosaicking, and cropping; continuing to remove pixels of cloud layers, cloud shadows, multiple clouds, and cirrus clouds from the images obtained by the preprocessing operations by using a quality control band to obtain the target multi-spectral satellite images.

2. The method of claim 1, wherein, The acquisition of the initial multi-spectral satellite images in the target region comprises: for the target region, determining a target satellite remote sensing product with best evaluation values of consideration factors including image quality and cloud cover from candidate different satellite remote sensing products; acquiring the initial multi-spectral satellite images of the target satellite remote sensing product in the target region.

3. The method of claim 1, wherein, The method further comprises: The improved normalized water index is calculated for the target multi-spectral satellite image in time sequence according to the following formula: ， wherein, is a value of the improved normalized water index, is a reflectance value of the green waveband, is a reflectance value of the shortwave infrared waveband.

4. A reservoir water body boundary determination apparatus, characterized by, The device comprises: An acquisition unit is configured to acquire an initial multi-spectral satellite image in a target region, wherein the initial multi-spectral satellite image has a time sequence attribute; An operation unit is configured to perform a data enhancement operation on the initial multi-spectral satellite image to obtain a target multi-spectral satellite image; A screening unit is configured to, on the basis of the improved normalized water index calculated for the target multi-spectral satellite image in time sequence, calculate an index threshold of the improved normalized water index by using the Otsu method, and screen out preliminary water body pixels of all time phases to obtain a preliminary water body pixel screening result; A calculation unit is configured to, on the basis of the preliminary water body pixel screening result, calculate a reservoir constant water body and a reservoir time-phase water body respectively to obtain a reservoir water body boundary range with the reservoir constant water body as an outer boundary and the reservoir time-phase water body as an inner boundary, wherein the reservoir constant water body refers to a relatively fixed reservoir water body of a current reservoir under actual conditions of a region where the reservoir is located, and the reservoir time-phase water body refers to a reservoir water body of the current reservoir that dynamically changes with time phases under actual conditions of the region where the reservoir is located; The calculation unit is specifically configured to: On the basis of the preliminary water body pixel screening result, the preliminary water body pixels of all time phases are respectively subjected to an iteration statistics in time sequence by using the following formula to obtain a total water accumulation probability value of each pixel: ， Wherein, WF is a numerical value of the total water accumulation probability value, M is a total number of effective observations in a time range related to the initial multi-spectral satellite image, and T is a binary variable, T=1 under a water body condition and T=0 under a non-water body condition; A set of different pixels with the total water accumulation probability value greater than a total water accumulation probability threshold value is determined as the reservoir constant water body; The calculation unit is specifically configured to: On the basis of the preliminary water body pixel screening result, in combination with a constraint of a maximum number of connected domains to be removed and a maximum number of pixels to be removed, a water body region composed of the preliminary water body pixels for each time phase is removed of connected domains with a size less than a connected domain size threshold value to obtain the reservoir time-phase water body; The total water accumulation probability threshold value is specifically 70%, the maximum number of connected domains to be removed is specifically 8, and the maximum number of pixels to be removed is specifically 50; The operation unit is specifically configured to: perform a preprocessing operation on the initial multi-spectral satellite image, wherein the preprocessing operation includes radiation calibration, cloud removal, mosaicking, and cropping; continue to remove pixels of cloud layers, cloud shadows, multiple clouds, and cirrus clouds from the image obtained by the preprocessing operation by using a quality control band to obtain the target multi-spectral satellite image.

5. A processing device, characterized by The device comprises a processor and a memory, and the memory stores a computer program, and the processor executes the computer program in the memory to perform the method in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a plurality of instructions adapted to be loaded by a processor to execute the method in any one of claims 1 to 3.

Images