Flood duration extraction method, device and electronic equipment based on multi-period remote sensing

Abstract

The present invention provides a flood duration extraction method, device, and electronic device based on multi-period remote sensing, comprising: obtaining a remote sensing image dataset of a flooded area; wherein the remote sensing image dataset includes remote sensing image data from multiple periods; determining whether the remote sensing image dataset lacks remote sensing image data for a target period; if so, determining water body contour information for each period other than the target period based on the remote sensing image data for each period; and evolving the water body contour information for the target period based on the water body contour information for the previous period and the next period corresponding to the target period; and determining flood inundation duration information corresponding to the flooded area based on each water body contour information. The present invention can quickly obtain the flood inundation range and significantly improve the accuracy of flood inundation duration information.

Description

Technical Field

[0001] The present invention relates to the technical field of flood range extraction, and in particular to a flood duration extraction method, device and electronic equipment based on multi-period remote sensing. Background Art

[0002] Flood disasters refer to river flooding, waterlogging, mountain torrents, landslides, and debris flows caused by rainfall, snowmelt, ice, dam breaches, storm surges, and tropical cyclones, as well as the secondary disasters they trigger. Currently, the duration and extent of floods are typically determined using hydrodynamic models. However, due to model accuracy and other factors, the accuracy of simulated flood duration and extent is poor. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a flood duration extraction method, device and electronic equipment based on multi-period remote sensing, which can quickly obtain the flood inundation range and significantly improve the accuracy of flood inundation duration information.

[0004] In a first aspect, an embodiment of the present invention provides a method for extracting flood duration based on multi-period remote sensing, comprising:

[0005] Acquire a remote sensing image dataset of the flood-affected area; wherein the remote sensing image dataset includes multiple periods of remote sensing image data;

[0006] Determining whether the remote sensing image dataset is missing remote sensing image data for a target period;

[0007] If yes, for each period other than the target period, respectively determine the water body contour information of each period based on the remote sensing image data of each period; and evolve the water body contour information of the target period based on the water body contour information of the previous period corresponding to the target period and the water body contour information of the next period;

[0008] The flood inundation duration information corresponding to the flood occurrence area is determined according to each of the water body contour information.

[0009] In one embodiment, evolving the water body contour information of the target period based on the water body contour information of the previous period and the water body contour information of the next period corresponding to the target period includes:

[0010] Interpolation processing is performed on the water body contour information of a previous period and the water body contour information of a next period corresponding to the target period to evolve the water body contour information of the target period.

[0011] In one embodiment, determining the flood inundation duration information corresponding to the flood occurrence area according to each of the water body contour information includes:

[0012] For each point in the flood-prone area, determining the water information and weight factor corresponding to the point in each period based on each water body contour information, and accumulating the water information and the weight factor to obtain the duration information corresponding to the point;

[0013] Based on the duration information corresponding to each point in the flood occurrence area, the flood inundation duration information corresponding to the flood occurrence area is obtained.

[0014] In one embodiment, determining the weight factor corresponding to each point in each period based on each water body contour information includes:

[0015] If water information is recognized at the point for the first time and continues to be recognized, the weight factor corresponding to the period of water information recognition is determined to be 1;

[0016] Alternatively, if water information is identified at the location for the first time and no water information is identified within a specified number of days, the weight factor corresponding to the period in which water information is identified is determined to be 0;

[0017] Alternatively, if water information is recognized at the point for the first time and within a specified number of days, the weight factor corresponding to the period in which the water information is recognized is determined to be the ratio of 1 to the number of days between the two periods.

[0018] In one embodiment, after determining the flood inundation duration information corresponding to the flood occurrence area according to each water body contour information, the method further includes:

[0019] Determine the water body duration classification color corresponding to each point according to the duration information corresponding to each point in the flood occurrence area;

[0020] Drawing a thematic map of the duration information corresponding to the flood occurrence area based on the water body duration classification color corresponding to each of the points;

[0021] The diachronic information thematic map and geographic projection information corresponding to the flood-occurring area are superimposed to obtain a diachronic-geographic image corresponding to the flood-occurring area.

[0022] In one embodiment, after superimposing the diachronic information thematic map and geographic projection information corresponding to the flood-prone area to obtain a diachronic-geographic image corresponding to the flood-prone area, the method further includes:

[0023] If a query request for the flood-occurring area is received from a designated associated terminal, the diachronic-geographic image corresponding to the flood-occurring area is fed back to the designated associated terminal, so as to display the diachronic-geographic image through the graphical user interface of the designated associated terminal.

[0024] In one embodiment, after determining the flood inundation duration information corresponding to the flood occurrence area according to each water body contour information, the method further includes:

[0025] The remote sensing image dataset and the flood inundation duration information of the flood-occurring area are associated and stored in a designated database.

[0026] In a second aspect, an embodiment of the present invention further provides a flood duration extraction device based on multi-period remote sensing, comprising:

[0027] A data acquisition module is used to acquire a remote sensing image dataset of the flood-affected area; wherein the remote sensing image dataset includes multiple periods of remote sensing image data;

[0028] A judgment module, used to judge whether the remote sensing image data set is missing remote sensing image data of the target period;

[0029] a contour extraction module configured to, when the judgment result of the judgment module is yes, determine, for each period other than the target period, the water body contour information of each period based on the remote sensing image data of each period; and evolve the water body contour information of the target period based on the water body contour information of the previous period corresponding to the target period and the water body contour information of the next period;

[0030] The duration determination module is used to determine the flood inundation duration information corresponding to the flood occurrence area according to each water body contour information.

[0031] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement any one of the methods provided in the first aspect.

[0032] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement any one of the methods provided in the first aspect.

[0033] Embodiments of the present invention provide a method, device, and electronic device for extracting flood duration based on multi-period remote sensing. The method first obtains a remote sensing image dataset of a flood-affected area, comprising multi-period remote sensing image data. If it is determined that the remote sensing image dataset lacks remote sensing image data for a target period, water body contour information for each period outside the target period is determined based on the remote sensing image data for each period. The water body contour information for the target period is then evolved based on the water body contour information for the previous period and the next period corresponding to the target period. The flood duration information corresponding to the flood-affected area is then determined based on each water body contour information. Based on the multi-period remote sensing image data, the method determines water body contour information for each period and uses the water body contour information from adjacent periods to evolve the water body contour information for the missing period. Thus, flood duration information is determined based on each water body contour information. Compared to prior art methods that use hydrodynamic models to simulate flood duration information, the present invention is not affected by model accuracy and can rapidly obtain water body contour information based on multi-period remote sensing image data, significantly improving the accuracy of flood duration information.

[0034] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the present invention. The purposes and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0035] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 A schematic flow chart of a flood duration extraction method based on multi-period remote sensing provided by an embodiment of the present invention;

[0038] Figure 2 A schematic flow chart of another method for extracting flood duration based on multi-period remote sensing provided by an embodiment of the present invention;

[0039] Figure 3 A schematic structural diagram of a flood duration extraction device based on multi-period remote sensing provided by an embodiment of the present invention;

[0040] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0042] Currently, the accuracy of flood duration and extent simulated using hydrodynamic models is poor. Furthermore, with the increasing number of Earth remote sensing satellites in my country, rapidly determining flood inundation extents and efficiently reflecting and displaying flood development processes is becoming increasingly important. This invention provides a method, device, and electronic device for extracting flood duration based on multi-period remote sensing, which can rapidly determine flood inundation extents and significantly improve the accuracy of flood duration information.

[0043] To facilitate understanding of this embodiment, a flood duration extraction method based on multi-period remote sensing disclosed in an embodiment of the present invention is first described in detail. Figure 1 The flowchart of a method for extracting flood duration based on multi-period remote sensing is shown in FIG. 1 , which mainly includes the following steps S102 to S108:

[0044] Step S102 involves obtaining a remote sensing image dataset of the flooded area. The remote sensing image dataset comprises multi-period remote sensing image data, including primarily SAR data and multispectral remote sensing images under clear weather conditions. In one embodiment, remote sensing image data for the flooded area may be obtained at a preset interval, illustratively on a daily basis.

[0045] Step S104 determines whether the remote sensing image dataset is missing remote sensing image data for the target period. In one embodiment, during the process of acquiring remote sensing image data according to a preset period, remote sensing image data acquisition may fail for a certain period. In this case, the period in which data acquisition failed is determined as the target period. For example, assuming that remote sensing image data is acquired on a daily basis, it is possible to determine whether remote sensing image data for a certain day is missing. If missing, the missing date is determined as the target period.

[0046] Step S106, if yes, for each period other than the target period, the water body contour information of each period is determined based on the remote sensing image data of each period; and the water body contour information of the target period is evolved based on the water body contour information of the previous period and the water body contour information of the next period corresponding to the target period. In one embodiment, if the remote sensing image data of the target period is missing, the corresponding water body contour information can be first extracted from the remote sensing image data of the period in which the data is not missing, and then the water body contour information of the target period can be evolved using the water body contour information of the adjacent periods (including the previous period and the next period) of the target period. Exemplarily, continuing to obtain remote sensing image data in units of days as an example, assuming that the remote sensing image data of date A is confirmed, the water body contour information of date A can be evolved using the water body contour information of the day before date A and the water body contour information of the day after date A.

[0047] In another embodiment, if the remote sensing image dataset does not have missing data, the corresponding water body contour information can be directly extracted from the remote sensing image data of each period.

[0048] Step S108: Determine the flooding duration information corresponding to the flooding area based on each water body contour information. In one embodiment, each water body contour information may be processed in an accumulation manner to obtain the flooding duration information corresponding to the flooding area.

[0049] The flood duration extraction method based on multi-period remote sensing provided by the embodiment of the present invention is based on multi-period remote sensing image data, determines the water body contour information of each period respectively, and uses the water body contour information of adjacent periods to evolve the water body contour information of the missing period, thereby determining the flood inundation duration information based on each water body contour information. Compared with the existing technology that uses hydrodynamic models to simulate flood inundation duration information, the embodiment of the present invention is not affected by the model accuracy, and can quickly obtain water body contour information based on multi-period remote sensing image data, and significantly improve the accuracy of flood inundation duration information.

[0050] To facilitate understanding of the aforementioned embodiments, this embodiment provides a specific implementation of a flood duration extraction method based on multi-period remote sensing. The core elements include: multi-source data fusion, water body contour evolution, and rapid display of inundation duration. Specifically, see steps 1 to 3 below:

[0051] Step 1: Multi-source data fusion: For flood-affected areas, obtain daily remote sensing image data. Remote sensing image data mainly consists of SAR (Synthetic Aperture Radar) data, and also includes multispectral remote sensing image data under clear weather conditions to obtain continuous flood monitoring data.

[0052] In one embodiment, conventional preprocessing may be performed on the remote sensing data, wherein the preprocessing performed on SAR data includes noise removal, multi-viewing, orthographic projection, etc., and the preprocessing performed on multispectral remote sensing image data includes atmospheric correction and orthographic projection, etc.

[0053] Step 2, Water Body Profile Evolution: Calculate water body profile information for different loads and time phases, and simulate missing data using a water body profile evolution model. The loads include SAR data or multispectral remote sensing image data.

[0054] For ease of understanding, the embodiments of the present invention are respectively directed to water body extraction with existing remote sensing image data and water body extraction without remote sensing image data, as shown in (1) to (2) below:

[0055] (1) Water Body Extraction from Existing Remote Sensing Image Data: Water body contour information for each period can be determined based on the remote sensing image data for each period. In one specific implementation, water body extraction is performed by combining NDWI (Normalized Difference Water Index), deep learning, time series data, and background water body information. The extracted water body information is then censored to form a vector boundary range, which is also the water body contour information.

[0056] (2) Water body extraction without remote sensing image data: The water body contour information of the target period can be evolved based on the water body contour information of the previous period corresponding to the target period and the water body contour information of the next period. In a specific implementation, the water body contour information of the previous period corresponding to the target period and the water body contour information of the next period can be interpolated to evolve the water body contour information of the target period. In practical applications, multi-source, multi-temporal domain data with dense spatial information is mainly obtained based on remote sensing image data, and the flood boundary in adjacent periods is used as water body contour information. The level set method is used to find the relationship between the two, and the flood inundation duration information within a period of time is obtained by interpolation method, which is mainly described by the evolution equation of the following level set function:

[0057]

[0058] Among them, φ is the level set function, δ ε (φ) is the regularized Dirac function, div is the vector divergence, is the gradient operator, c1 is the water body contour information at the previous moment, c2 is the water body contour information at the next moment, I is the water body contour information at the target moment, and μ, λ1, and λ2 are all constant coefficients.

[0059] Step 3: Rapid display of flood duration: The flood duration information corresponding to the flood occurrence area can be determined based on the contour information of each water body. In a specific implementation, see steps a to b below:

[0060] Step a: for each point in the flood area, determine the water information and weight factor corresponding to the point in each period based on each water body contour information, and accumulate the water information and weight factor to obtain the duration information corresponding to the point.

[0061] Optionally, the weight factor is determined based on the following judgments:

[0062] (1) If water information is recognized at the point for the first time and continues to be recognized, the weight factor corresponding to the period of recognition of water information is determined to be 1. For example, the weight factor is recorded as W k , when the water body appears for the first time and persists continuously, then W k The weight factor is 1 when water bodies appear continuously.

[0063] (2) If water information is recognized at the point for the first time and no water information is recognized within the specified number of days, the weight factor corresponding to the period of water information recognition is determined to be 0. For example, assuming that the specified number of days is 3 days, when a water body appears and is not recognized as a water body within the next 3 days, W k =0.

[0064] (3) Alternatively, if water information is first identified at the location and is identified within a specified number of days, the weight factor corresponding to the period of water information identification is determined to be the ratio of 1 to the number of days between the two periods. For example, when a water body appears and is identified as a water body within the next three days, W k =1 / number of days between intervals.

[0065] Based on the above embodiment, the embodiment of the present invention further provides an implementation method for accumulating the water information and the weight factor to obtain the duration information corresponding to the point. The duration information corresponding to each point can be determined according to the following formula:

[0066]

[0067] Among them, δ (x,y) is the duration information corresponding to the point (x, y), T is the duration, W k is the weight factor, P (x,y) is the water information at the point (x, y).

[0068] Step b: Based on the duration information corresponding to each point in the flood area, obtain the flood inundation duration information corresponding to the flood area. In practical applications, the duration information corresponding to each point in the flood area can constitute the flood inundation duration information in the flood area.

[0069] Furthermore, after determining the duration of flooding in the flooded area, a thematic map of the duration information or a diachronic-geographic image (i.e., a flood duration product) can be generated and published. In one embodiment, cloud computing is used for rapid expression, and dynamic tile generation is used for the requested data to achieve web-based water body animation. Specifically, the generation and publication of the thematic map of the duration information and the diachronic-geographic image can be achieved by following the following steps 1 to 4:

[0070] Step 1: Determine the water body duration classification color corresponding to each point in the flooded area based on the duration information corresponding to each point. In one embodiment, a mapping relationship between duration information and water body classification colors can be pre-configured, so that the water body duration classification color that matches the duration information corresponding to each point is determined based on this mapping relationship.

[0071] Step 2: Draw a thematic map of the flood-affected area based on the water body's time-classified color at each point. In one embodiment, a thematic map of the flood-affected area can be generated by assigning a color value to the corresponding pixel on a blank canvas based on the water body's time-classified color at each point.

[0072] Step 3: Overlay the chronological information thematic map and geographic projection information corresponding to the flood-affected area to obtain a chronological-geographic image of the flood-affected area. In one embodiment, geographic projection information of the flood-affected area can be obtained, and then the chronological information thematic map and geographic projection information can be overlaid to obtain a chronological-geographic image. This allows users to understand the duration of flood inundation corresponding to the flood-affected area by combining geographic information.

[0073] In step 4, if a query request is received from a designated associated terminal regarding the flooded area, the chronological-geographic image corresponding to the flooded area is fed back to the designated associated terminal, so that the chronological-geographic image can be displayed through the designated associated terminal's graphical user interface. In practical applications, the flooded area can be quickly displayed and accessed based on the front-end's request. Optionally, the remote sensing image dataset and flood inundation duration information corresponding to the flooded area can also be fed back to the associated terminal for display. In one embodiment, the remote sensing image dataset and flood inundation duration information of the flooded area can also be associated and stored in a designated database, so that data corresponding to the query request can be searched from the designated database and the retrieved data can be fed back.

[0074] In practical applications, historical information thematic maps are generated based on specific historical values ​​and corresponding dates. The publication of historical information thematic maps primarily utilizes tile generation based on Kubernetes cloud computing. Specifically, in response to front-end map slice requests, image slices compliant with the WMTS specification are dynamically generated, and the historical classification colors of water bodies are dynamically processed. This service is a standard serverless service capable of cloud deployment. Support for serverless services is implemented on the Kubernetes foundation. Kubernetes provides load balancing for remote user requests and manages the starting, stopping, and restarting of serverless service-related pods.

[0075] Based on the above embodiment, the present invention also provides an application example of a flood duration extraction method based on multi-period remote sensing. Figure 2 The flowchart of another flood duration extraction method based on multi-period remote sensing is shown in FIG.

[0076] (1) Obtain multi-temporal water body data (i.e., the aforementioned multi-period remote sensing image data):

[0077] (2) Selecting time parameters, water level parameters, and simulation intervals from multi-temporal water body data;

[0078] (3) Input the specified database;

[0079] (4) Check whether the designated database stores flood inundation duration information; if yes, execute (8); if not, execute (5);

[0080] (5) Water body contour evolution model;

[0081] (6) Calculate flood inundation duration information and execute (7) and (8);

[0082] (7) Storing flood inundation duration information in a designated database;

[0083] (8) Generate thematic maps of historical information;

[0084] (9) Overlay geographic projection information;

[0085] (10) Output flood duration products.

[0086] In summary, the flood duration extraction method based on multi-period remote sensing provided by the embodiment of the present invention can quickly obtain the flood inundation range, quickly and efficiently reflect and display the flood development process.

[0087] Regarding the flood duration extraction method based on multi-period remote sensing provided in the above embodiment, the present invention provides a flood duration extraction device based on multi-period remote sensing, see Figure 3 The schematic diagram of the structure of a flood duration extraction device based on multi-period remote sensing is shown in FIG. The device mainly includes the following parts:

[0088] The data acquisition module 302 is used to acquire a remote sensing image dataset of the flood-affected area; wherein the remote sensing image dataset includes multiple periods of remote sensing image data;

[0089] A judgment module 304 is used to judge whether the remote sensing image data set is missing remote sensing image data of the target period;

[0090] The contour extraction module 306 is configured to, when the judgment result of the judgment module is yes, determine the water body contour information of each period other than the target period based on the remote sensing image data of each period; and evolve the water body contour information of the target period based on the water body contour information of the previous period corresponding to the target period and the water body contour information of the next period;

[0091] The duration determination module 308 is used to determine the flood inundation duration information corresponding to the flood occurrence area according to each water body contour information.

[0092] The flood duration extraction device based on multi-period remote sensing provided by the embodiment of the present invention is based on multi-period remote sensing image data, determines the water body contour information of each period respectively, and uses the water body contour information of adjacent periods to evolve the water body contour information of the missing period, thereby determining the flood inundation duration information based on each water body contour information. Compared with the existing technology that uses hydrodynamic models to simulate flood inundation duration information, the embodiment of the present invention is not affected by the model accuracy, can quickly obtain water body contour information based on multi-period remote sensing image data, and significantly improve the accuracy of flood inundation duration information.

[0093] In one embodiment, the contour extraction module 306 is further configured to:

[0094] The water body contour information of the previous period and the water body contour information of the next period corresponding to the target period are interpolated to evolve the water body contour information of the target period.

[0095] In one embodiment, the duration determination module 308 is further configured to:

[0096] For each point in the flood-prone area, the water information and weight factor corresponding to the point in each period are determined based on the contour information of each water body, and the duration information corresponding to the point is obtained by accumulating the water information and weight factor;

[0097] Based on the duration information corresponding to each point in the flood occurrence area, the flood inundation duration information corresponding to the flood occurrence area is obtained.

[0098] In one embodiment, the duration determination module 308 is further configured to:

[0099] If water information is recognized at the point for the first time and continues to be recognized, the weight factor corresponding to the period of water information recognition is determined to be 1;

[0100] Alternatively, if water information is identified at the location for the first time and no water information is identified within a specified number of days, the weight factor corresponding to the period in which water information is identified is determined to be 0;

[0101] Alternatively, if water information is recognized at the point for the first time and within a specified number of days, the weight factor corresponding to the period in which the water information is recognized is determined to be the ratio of 1 to the number of days between the two periods.

[0102] In one embodiment, the system further includes an image rendering module for:

[0103] According to the duration information corresponding to each point in the flood-prone area, the duration classification color of the water body corresponding to each point is determined;

[0104] Draw the corresponding thematic map of flood occurrence area based on the water body duration classification color corresponding to each point;

[0105] The diachronic information thematic map and geographic projection information corresponding to the flood-prone area are superimposed to obtain a diachronic-geographic image corresponding to the flood-prone area.

[0106] In one embodiment, a query module is further included, which is used to:

[0107] If a query request for a flood-affected area is received from a designated associated terminal, a diachronic-geographic image corresponding to the flood-affected area is fed back to the designated associated terminal, so as to display the diachronic-geographic image through a graphical user interface of the designated associated terminal.

[0108] In one embodiment, the device further includes a storage module for:

[0109] The remote sensing image datasets of the flood-affected areas and the flood inundation duration information are associated and stored in the designated database.

[0110] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those in the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference can be made to the corresponding content in the aforementioned method embodiment.

[0111] An embodiment of the present invention provides an electronic device. Specifically, the electronic device includes a processor and a storage device. The storage device stores a computer program, and when the computer program is executed by the processor, it executes the method described in any one of the above-mentioned embodiments.

[0112] Figure 4 This is a structural diagram of an electronic device provided in an embodiment of the present invention. The electronic device 100 includes: a processor 40, a memory 41, a bus 42 and a communication interface 43. The processor 40, the communication interface 43 and the memory 41 are connected via the bus 42; the processor 40 is used to execute an executable module stored in the memory 41, such as a computer program.

[0113] The memory 41 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage. The system network element communicates with at least one other network element via at least one communication interface 43 (which may be wired or wireless), and may utilize the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0114] The bus 42 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0115] Among them, the memory 41 is used to store programs, and the processor 40 executes the program after receiving the execution instruction. The method executed by the device for flow process definition disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 40 or implemented by the processor 40.

[0116] Processor 40 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method may be completed by hardware integrated logic circuits or software instructions in processor 40. The above processor 40 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or the like. The storage medium is located in the memory 41 , and the processor 40 reads the information in the memory 41 and completes the steps of the above method in combination with its hardware.

[0117] The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method described in the previous method embodiment. The specific implementation can be referred to the previous method embodiment and will not be repeated here.

[0118] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0119] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A flood duration extraction method based on multi-period remote sensing, characterized in that: include: Acquire a remote sensing image dataset of the flood-affected area; wherein the remote sensing image dataset includes multiple periods of remote sensing image data; Determining whether the remote sensing image dataset is missing remote sensing image data for a target period; If so, for each period outside the target period, respectively determine the water body contour information of each period based on the remote sensing image data of each period; and evolve the water body contour information of the target period based on the water body contour information of the previous period corresponding to the target period and the water body contour information of the next period; including: interpolating the water body contour information of the previous period corresponding to the target period and the water body contour information of the next period to evolve the water body contour information of the target period, specifically, using the flood boundary in adjacent periods as the water body contour information, using the level set method to find the relationship between the water body contour information of the previous period corresponding to the target period and the water body contour information of the next period, obtaining the flood inundation duration information within a period of time by the interpolation method, and describing it with the following evolution equation of the level set function: ;in, is the level set function, is the regularized Dirac function, is the vector divergence, is the gradient operator, is the water body contour information at the previous moment, is the water body contour information at the next moment, is the water body contour information at the target moment, 、 、 All are constant coefficients; Determining the flood inundation duration information corresponding to the flood occurrence area based on each of the water body contour information; including: for each point in the flood occurrence area, determining the water information and weight factor corresponding to the point in each period based on each of the water body contour information, and accumulating the water information and the weight factor to obtain the duration information corresponding to the point; obtaining the flood inundation duration information corresponding to the flood occurrence area based on the duration information corresponding to each of the points in the flood occurrence area; specifically, determining the duration information corresponding to each point according to the following formula: ;in, is the duration information corresponding to the point (x, y), T is the duration, is the weight factor, is the water information at the point (x, y).

2. The method for extracting flood duration based on multi-period remote sensing according to claim 1, characterized in that: Determining a weight factor corresponding to each point in each period based on each of the water body contour information includes: If water information is recognized at the point for the first time and continues to be recognized, the weight factor corresponding to the period of water information recognition is determined to be 1; Alternatively, if water information is identified at the location for the first time and no water information is identified within a specified number of days, the weight factor corresponding to the period in which water information is identified is determined to be 0; Alternatively, if water information is recognized at the point for the first time and within a specified number of days, the weight factor corresponding to the period in which the water information is recognized is determined to be the ratio of 1 to the number of days between the two periods.

3. The method for extracting flood duration based on multi-period remote sensing according to claim 1, characterized in that: After determining the flood inundation duration information corresponding to the flood occurrence area according to each of the water body contour information, the method further includes: Determine the water body duration classification color corresponding to each point according to the duration information corresponding to each point in the flood occurrence area; Drawing a thematic map of the duration information corresponding to the flood occurrence area based on the water body duration classification color corresponding to each of the points; The diachronic information thematic map and geographic projection information corresponding to the flood-occurring area are superimposed to obtain a diachronic-geographic image corresponding to the flood-occurring area.

4. The method for extracting flood duration based on multi-period remote sensing according to claim 3, characterized in that: After superimposing the diachronic information thematic map and geographic projection information corresponding to the flood-prone area to obtain a diachronic-geographic image corresponding to the flood-prone area, the method further includes: If a query request for the flood-occurring area is received from a designated associated terminal, the diachronic-geographic image corresponding to the flood-occurring area is fed back to the designated associated terminal, so as to display the diachronic-geographic image through the graphical user interface of the designated associated terminal.

5. The method for extracting flood duration based on multi-period remote sensing according to claim 1, characterized in that: After determining the flood inundation duration information corresponding to the flood occurrence area according to each of the water body contour information, the method further includes: The remote sensing image dataset and the flood inundation duration information of the flood-occurring area are associated and stored in a designated database.

6. A flood duration extraction device based on multi-period remote sensing, characterized in that: include: A data acquisition module is used to acquire a remote sensing image dataset of the flood-affected area; wherein the remote sensing image dataset includes multiple periods of remote sensing image data; A judgment module, used to judge whether the remote sensing image data set is missing remote sensing image data of the target period; A contour extraction module is used to, when the judgment result of the judgment module is yes, determine the water body contour information of each period based on the remote sensing image data of each period for each period outside the target period; and evolve the water body contour information of the target period based on the water body contour information of the previous period corresponding to the target period and the water body contour information of the next period; including: interpolating the water body contour information of the previous period corresponding to the target period and the water body contour information of the next period to evolve the water body contour information of the target period, specifically, using the flood boundary in the adjacent period as the water body contour information, using the level set method to find the relationship between the water body contour information of the previous period corresponding to the target period and the water body contour information of the next period, obtaining the flood inundation duration information within a period by the interpolation method, and describing it with the following level set function evolution equation: ;in, is the level set function, is the regularized Dirac function, is the vector divergence, is the gradient operator, is the water body contour information at the previous moment, is the water body contour information at the next moment, is the water body contour information at the target moment, 、 、 All are constant coefficients; The duration determination module is used to determine the flood inundation duration information corresponding to the flood occurrence area based on each of the water body contour information; including: for each point in the flood occurrence area, determining the water information and weight factor corresponding to the point in each period based on each of the water body contour information, and accumulating the water information and the weight factor to obtain the duration information corresponding to the point; based on the duration information corresponding to each of the points in the flood occurrence area, obtaining the flood inundation duration information corresponding to the flood occurrence area; specifically, determining the duration information corresponding to each point according to the following formula: ;in, is the duration information corresponding to the point (x, y), T is the duration, is the weight factor, is the water information at the point (x, y).

7. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method according to any one of claims 1 to 5.

Images