Space-air-ground integrated basin flood disaster monitoring method and device

Abstract

The present application relates to the technical field of geographic information, and particularly relates to a space-air-ground integrated basin flood disaster monitoring method and device and computer equipment, based on a constructed deep learning model, flood disaster element data corresponding to ground monitoring of a to-be-processed basin is sequentially subjected to unmanned aerial vehicle aerial photography and satellite remote sensing flood disaster element simulation, satellite remote sensing corresponding flood disaster element data is constructed, the characteristics of high ground monitoring accuracy and time continuity are fully utilized, the characteristics of unmanned aerial vehicle aerial photography not being affected by clouds, being flexible, fast, and having high resolution, and the characteristics of satellite remote sensing having large coverage, large information acquisition, being all-weather, all-time, and spatially continuous are fully utilized, to obtain time-continuous and spatially-continuous flood disaster element data, for flood disaster monitoring, overall, large-scale, and efficient flood disaster monitoring of the to-be-processed basin is realized, flood disaster monitoring requirements are met, and the efficiency of flood disaster monitoring is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geographic information, in particular to a space-ground-air integrated flood disaster monitoring method and device, computer equipment and storage medium. BACKGROUND

[0002] Due to the frequent occurrence of extreme weather, flood disasters are triggered, causing serious casualties and property losses. It is urgent to do a good job in flood control and disaster reduction and rescue work. Flood disaster monitoring is the first task.

[0003] Traditional flood disaster monitoring adopts manual investigation and hydrological station monitoring method. Multiple collection points are usually set in the basin to monitor flood information. However, the above method can only monitor the flood information around the collection point, and it is difficult to comprehensively, widely and efficiently monitor the flood disaster of the whole basin, which cannot meet the current flood disaster monitoring demand. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a space-ground-air integrated flood disaster monitoring method, device, computer equipment and storage medium. Based on the constructed deep learning model, the flood disaster element data corresponding to the ground monitoring of the to-be-processed basin is sequentially simulated by unmanned aerial vehicle aerial photography and satellite remote sensing flood disaster element simulation, and the satellite remote sensing corresponding flood disaster element data is constructed. Make full use of the characteristics of high ground monitoring accuracy, time continuity, unmanned aerial vehicle aerial photography, which is not affected by cloud layer, flexible, fast, high resolution, and satellite remote sensing, which has the characteristics of large coverage, large amount of information acquisition, all-weather, all-day, spatial continuity, to obtain time-continuous and spatial-continuous flood disaster element data, which is used for flood disaster monitoring, realizing comprehensive, wide and efficient flood disaster monitoring of the to-be-processed basin, meeting the flood disaster monitoring demand and improving the efficiency of flood disaster monitoring.

[0005] In a first aspect, the present application provides a space-ground-air integrated flood disaster monitoring method, comprising the following steps:

[0006] Obtaining the ground monitoring corresponding flood disaster element data of the to-be-processed basin in the preset time period;

[0007] input the flood disaster element data corresponding to the ground monitoring into a preset first deep learning model to simulate the flood disaster element data corresponding to the unmanned aerial vehicle aerial photography, to obtain the flood disaster element data corresponding to the unmanned aerial vehicle aerial photography, wherein the flood disaster element data corresponding to the unmanned aerial vehicle aerial photography is time-continuous flood disaster element data; the first deep learning model is a convolutional neural network model trained and constructed by taking sample flood disaster element data corresponding to the ground monitoring as an input item and taking sample flood disaster element data corresponding to the unmanned aerial vehicle aerial photography as an output item;

[0008] input the flood disaster element data corresponding to the unmanned aerial vehicle aerial photography into a preset second deep learning model to simulate the flood disaster element data corresponding to the satellite remote sensing, to obtain the flood disaster element data corresponding to the satellite remote sensing, wherein the flood disaster element data corresponding to the satellite remote sensing is time- and space-continuous flood disaster element data; the second deep learning model is a convolutional neural network model trained and constructed by taking sample flood disaster element data corresponding to the unmanned aerial vehicle aerial photography as an input item and taking sample flood disaster element data corresponding to the satellite remote sensing as an output item;

[0009] perform flood disaster monitoring according to the flood disaster element data corresponding to the satellite remote sensing, to obtain a flood disaster monitoring result of the to-be-processed river basin.

[0010] In a second aspect, an embodiment of the present application provides a space-air-ground integrated river basin flood disaster monitoring device, comprising:

[0011] a first flood disaster element data obtaining module, configured to obtain flood disaster element data corresponding to ground monitoring of a to-be-processed river basin in a preset time period;

[0012] a second flood disaster element data obtaining module, configured to input the flood disaster element data corresponding to the ground monitoring into a preset first deep learning model to simulate the flood disaster element data corresponding to the unmanned aerial vehicle aerial photography, to obtain the flood disaster element data corresponding to the unmanned aerial vehicle aerial photography, wherein the flood disaster element data corresponding to the unmanned aerial vehicle aerial photography is time-continuous flood disaster element data; the first deep learning model is a convolutional neural network model trained and constructed by taking sample flood disaster element data corresponding to the ground monitoring as an input item and taking sample flood disaster element data corresponding to the unmanned aerial vehicle aerial photography as an output item;

[0013] The third flood disaster element data obtaining module is configured to input the flood disaster element data corresponding to the aerial photography of the unmanned aerial vehicle into a preset second deep learning model to simulate satellite remote sensing flood disaster elements, and obtain satellite remote sensing corresponding flood disaster element data, wherein the satellite remote sensing corresponding flood disaster element data is time- and space-continuous flood disaster element data; and the second deep learning model is a convolutional neural network model trained and constructed by taking the sample flood disaster element data corresponding to the aerial photography of the unmanned aerial vehicle as an input item and taking the sample flood disaster element data corresponding to the satellite remote sensing as an output item.

[0014] The flood disaster monitoring module is configured to perform flood disaster monitoring according to the satellite remote sensing corresponding flood disaster element data, and obtain a flood disaster monitoring result of the to-be-processed river basin.

[0015] In a third aspect, an embodiment of the present application provides a computer device, including a processor, a memory, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the space-ground integration flood disaster monitoring method according to the first aspect are implemented.

[0016] In a fourth aspect, an embodiment of the present application provides a storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of the space-ground integration flood disaster monitoring method according to the first aspect are implemented.

[0017] In the embodiments of the present application, a space-ground integration flood disaster monitoring method, device, computer device, and storage medium are provided, and based on the constructed deep learning model, the ground monitoring corresponding flood disaster element data of the to-be-processed river basin is sequentially subjected to unmanned aerial vehicle aerial photography and satellite remote sensing flood disaster element simulation to construct satellite remote sensing corresponding flood disaster element data. The ground monitoring has the characteristics of high accuracy and time continuity, the unmanned aerial vehicle aerial photography has the characteristics of being not affected by clouds, being flexible, fast, and high resolution, and the satellite remote sensing has the characteristics of large coverage, large amount of acquired information, all-weather, all-day, and space continuity. Therefore, time- and space-continuous flood disaster element data is obtained to perform flood disaster monitoring, the to-be-processed river basin is comprehensively, widely, and efficiently monitored, the flood disaster monitoring demand is met, and the efficiency of flood disaster monitoring is improved.

[0018] For better understanding and implementation, the present application is described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 A flowchart of a space-ground integration flood disaster monitoring method according to the first embodiment of the present application is shown.

[0020] Figure 2 A flowchart of S4 in the space-air-ground integrated basin flood disaster monitoring method provided by the first embodiment of the present application is shown in FIG. 4;

[0021] Figure 3 A flowchart of the space-air-ground integrated basin flood disaster monitoring method provided by the second embodiment of the present application is shown in FIG. 5;

[0022] Figure 4 A flowchart of S6 in the space-air-ground integrated basin flood disaster monitoring method provided by the second embodiment of the present application is shown in FIG. 6;

[0023] Figure 5 A flowchart of the space-air-ground integrated basin flood disaster monitoring method provided by the third embodiment of the present application is shown in FIG. 7;

[0024] Figure 6 A flowchart of S9 in the space-air-ground integrated basin flood disaster monitoring method provided by the third embodiment of the present application is shown in FIG. 8;

[0025] Figure 7 A structural diagram of the space-air-ground integrated basin flood disaster monitoring device provided by the fourth embodiment of the present application is shown in FIG. 9;

[0026] Figure 8 A structural diagram of the computer device provided by the fifth embodiment of the present application is shown in FIG. 10. DETAILED DESCRIPTION

[0027] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The following description is with reference to the drawings, in which like numerals refer to like elements throughout. The embodiments described in the following exemplary embodiments are not meant to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the appended claims.

[0028] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0029] It should be understood that, although the terms first, second, third, etc. can be employed in this application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another type of information. For example, without departing from the scope of the application, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as the first information. Depending on the context, the word "if' as used herein can be interpreted as "when" or "upon" or "in response to determining".

[0030] Please refer to Figure 1 , Figure 1 The flowchart of the space-ground-integrated basin flood disaster monitoring method provided by the first embodiment of the application, the method comprises the following steps:

[0031] S1: obtaining ground monitoring corresponding flood disaster element data of a to-be-processed basin in a preset time period.

[0032] The execution subject of the space-ground-integrated basin flood disaster monitoring method is a monitoring device (hereinafter referred to as a monitoring device) of the space-ground-integrated basin flood disaster monitoring method. In an optional embodiment, the monitoring device can be a computer device, which can be a server, or a server cluster formed by multiple computer devices.

[0033] In this embodiment, the monitoring device performs flood disaster monitoring through a ground hydrological station network to obtain ground monitoring corresponding flood disaster element data of a to-be-processed basin in a preset time period, wherein the flood disaster element data comprises flood submergence range data, flood submergence depth data and flood submergence duration data of several regional types. Specifically, the regional types include crop regions and building regions.

[0034] S2: inputting the ground monitoring corresponding flood disaster element data into a preset first deep learning model to simulate unmanned aerial vehicle (UAV) aerial flood disaster element data.

[0035] The first deep learning model is a convolutional neural network model trained and constructed by taking ground monitoring corresponding sample flood disaster element data as an input item and taking UAV aerial corresponding sample flood disaster element data as an output item.

[0036] In this embodiment, the monitoring device inputs the ground monitoring corresponding flood disaster element data into a preset first deep learning model to simulate unmanned aerial vehicle (UAV) aerial flood disaster element data, wherein the UAV aerial flood disaster element data is time-continuous flood disaster element data.

[0037] The unmanned aerial vehicle corresponding flood disaster element data is input into the preset second deep learning model to simulate satellite remote sensing flood disaster elements, and satellite remote sensing corresponding flood disaster element data is obtained.

[0038] S3: inputting the unmanned aerial vehicle corresponding flood disaster element data into a preset second deep learning model to simulate satellite remote sensing flood disaster elements, and obtaining satellite remote sensing corresponding flood disaster element data.

[0039] The second deep learning model is a convolutional neural network model trained and constructed by taking the unmanned aerial vehicle corresponding sample flood disaster element data as an input item and taking the satellite remote sensing corresponding sample flood disaster element data as an output item.

[0040] In this embodiment, the monitoring device inputs the unmanned aerial vehicle corresponding flood disaster element data into the preset second deep learning model to simulate satellite remote sensing flood disaster elements, and obtains satellite remote sensing corresponding flood disaster element data, wherein the unmanned aerial vehicle corresponding flood disaster element data is time-continuous flood disaster element data.

[0041] Based on the obtained unmanned aerial vehicle corresponding flood disaster element data, satellite remote sensing corresponding flood disaster element data simulation is realized, and unmanned aerial vehicle information and satellite remote sensing information are fused. The satellite remote sensing has the characteristics of large coverage, large amount of information, all-weather, all-day, and time continuity, which further improves the accuracy and efficiency of flood disaster monitoring.

[0042] S4: performing flood disaster monitoring according to the satellite remote sensing corresponding flood disaster element data to obtain the flood disaster monitoring result of the to-be-processed river basin.

[0043] In this embodiment, the monitoring device performs flood disaster monitoring according to the satellite remote sensing corresponding flood disaster element data to obtain the flood disaster monitoring result of the to-be-processed river basin.

[0044] Please refer to Figure 2 , Figure 2 The flowchart of S4 in the space-ground integration river basin flood disaster monitoring method provided by the first embodiment of the present application is shown in FIG. 4, which includes steps S41-S44, and the details are as follows:

[0045] S41: obtaining the flood disaster loss coefficients of the plurality of region types according to the submergence depth data in the flood disaster element data of the plurality of region types and the preset corresponding table of the flood disaster loss coefficients and the submergence depth data.

[0046] In the embodiment, the monitoring device obtains the flood disaster loss coefficients of the plurality of region types according to the submergence depth data in the flood disaster element data of the plurality of region types and a preset corresponding table of the flood disaster loss coefficients and the submergence depth data.

[0047] Specifically, the monitoring device judges the submergence depth threshold interval in which the submergence depth data is located according to a plurality of submergence depth threshold intervals and corresponding flood disaster loss coefficients in the corresponding table of the flood disaster loss coefficients and the submergence depth data, obtains the flood disaster loss coefficient corresponding to the submergence depth data, and obtains the flood disaster loss coefficients of the plurality of region types.

[0048] S42: The monitoring device obtains the area data and the per-unit property data of the plurality of region types of the to-be-processed river basin, obtains the flood pre-disaster monitoring values of the plurality of region types according to the area data, the per-unit property data and a preset flood pre-disaster monitoring calculation algorithm, and accumulates the flood pre-disaster monitoring values of the plurality of region types to obtain a total flood pre-disaster monitoring value.

[0049] The flood pre-disaster monitoring calculation algorithm is as follows:

[0050]

[0051] In the formula, A i is the flood pre-disaster monitoring value of the i-th region type, C is the number of region types, area i is the area data of the i-th region type, μ i is the per-unit property data of the i-th region type.

[0052] In the embodiment, the monitoring device obtains the area data and the per-unit property data of the plurality of region types of the to-be-processed river basin, obtains the flood pre-disaster monitoring values of the plurality of region types according to the area data, the per-unit property data and a preset flood pre-disaster monitoring calculation algorithm, and accumulates the flood pre-disaster monitoring values of the plurality of region types to obtain a total flood pre-disaster monitoring value.

[0053] S43: The monitoring device obtains the flood disaster loss monitoring values of the plurality of region types according to the area data, the per-unit property data, the flood disaster loss coefficients and a preset flood disaster loss monitoring calculation algorithm, and accumulates the flood disaster loss monitoring values of the plurality of region types to obtain a total flood disaster loss monitoring value.

[0054] The flood disaster loss monitoring calculation algorithm is as follows:

[0055]

[0056] In the formula, B iθ is a flood disaster loss monitoring value of an i-th region type i θ is a flood disaster loss coefficient of an i-th region type.

[0057] In the embodiment, the monitoring device obtains flood disaster loss monitoring values of the region types according to the area data of the region types, the per-unit-area property data, the flood disaster loss coefficients, and a preset flood disaster loss monitoring calculation algorithm, accumulates the flood disaster loss monitoring values of the region types, and obtains a total flood disaster loss monitoring value.

[0058] S44: divide the total flood disaster monitoring value by the total flood disaster loss monitoring value to obtain a flood disaster loss rate of the to-be-processed river basin as the flood disaster monitoring result.

[0059] In the embodiment, the monitoring device divides the total flood disaster monitoring value by the total flood disaster loss monitoring value to obtain a flood disaster loss rate of the to-be-processed river basin as the flood disaster monitoring result of the to-be-processed river basin.

[0060] Based on the constructed deep learning model, the flood disaster element data corresponding to the ground monitoring of the to-be-processed river basin are sequentially simulated by unmanned aerial vehicle aerial photography and satellite remote sensing, and satellite remote sensing corresponding flood disaster element data are constructed, so as to fully utilize the characteristics of high ground monitoring accuracy and time continuity, the characteristics of unmanned aerial vehicle aerial photography, such as being not affected by clouds, being flexible, fast, and high resolution, and the characteristics of satellite remote sensing, such as large coverage, large amount of acquired information, all-weather, all-time, and spatial continuity, to obtain time-continuous and spatial-continuous flood disaster element data for flood disaster monitoring, so as to realize comprehensive, large-scale, and efficient flood disaster monitoring of the to-be-processed river basin, meet the flood disaster monitoring demand, and improve the efficiency of flood disaster monitoring.

[0061] Please refer to Figure 3 , Figure 3 The flowchart of the space-ground-air integrated river basin flood disaster monitoring method provided in the second embodiment of the application further includes steps S5-S7, which are before step S2, and specifically as follows.

[0062] S5: obtain unmanned aerial vehicle aerial photography data in a flood disaster time period of a sample river basin, input the unmanned aerial vehicle aerial photography data into a preset image detection model, perform water body division on unmanned aerial vehicle aerial photography images at a plurality of time points in the unmanned aerial vehicle aerial photography data, and obtain water body division images corresponding to the unmanned aerial vehicle aerial photography images at the plurality of time points.

[0063] In the embodiment, the monitoring device obtains the UAV aerial photography data in the flood disaster period of the sample basin and the corresponding flood disaster element data monitored on the ground, wherein the UAV aerial photography data comprises UAV aerial photography images at several time points. Specifically, the monitoring device can quickly receive the UAV aerial photography data and the corresponding flood disaster element data monitored on the ground by using a high-speed optical fiber private line, and store them in a large-scale storage system for subsequent analysis and calculation, wherein the large-scale storage system provides a hardware space for satellite remote sensing, UAV, and ground hydrological station network actual observation flood disaster information intelligent mining and information service, and supports fast data reading and management, data high-speed transmission and storage, which are beneficial to improving the timeliness of the space-ground integrated flood disaster monitoring method.

[0064] In an optional embodiment, in order to improve the pertinence, the sample basin can be set as a basin to be processed, and the monitoring device can pre-process, aerial triangulation encryption process, generate topographic maps, image ortho-correction and splicing, etc. of the UAV aerial photography images at several time points in the UAV aerial photography data, so as to improve the quantitative processing efficiency of the basin flood disaster big data.

[0065] The monitoring device inputs the UAV aerial photography data into a preset image detection model, divides the water body in the UAV aerial photography images at several time points in the UAV aerial photography data, obtains water body division images corresponding to the UAV aerial photography images at several time points, constructs water body samples and non-water body samples required for training the flood inundation range, and trains the first deep learning model to be trained, wherein the water body division images comprise water body regions and non-water body regions.

[0066] S6: flood disaster element mining is performed according to the water body division images corresponding to the UAV aerial photography images at several time points, and the UAV aerial photography corresponding flood disaster element data in the flood disaster period of the sample basin is obtained.

[0067] In the embodiment, the monitoring device performs flood disaster element mining according to the water body division images corresponding to the UAV aerial photography images at several time points, and obtains the UAV aerial photography corresponding flood disaster element data in the flood disaster period of the sample basin.

[0068] Please refer to Figure 4 , Figure 4 The flowchart of S6 in the space-ground integrated basin flood disaster monitoring method provided by the second embodiment of the present application is shown in FIG. 6, which comprises steps S61-S62, and the details are as follows:

[0069] S61: the water body division images corresponding to the UAV aerial photography images at several time points are compared with the water body division images corresponding to the UAV aerial photography images at adjacent time points respectively, and the flood inundation start image and the flood inundation end image in the UAV aerial photography data are confirmed.

[0070] In the embodiment, the monitoring device compares the water body division image corresponding to the UAV aerial image at each time with the water body division image corresponding to the UAV aerial image at the adjacent time, and confirms the flood submergence start image and the flood submergence end image in the UAV aerial data.

[0071] Specifically, if the regions at the same positions of the water body division image and the water body division image at the previous time are the water body region and the non-water body region respectively, the monitoring device determines that the current region is in the flood submergence at the time, and takes the water body division image at the time as the flood submergence start image of the current region.

[0072] If the regions at the same positions of the water body division image and the water body division image at the next time are the water body region and the non-water body region respectively, the monitoring device determines that the current region is in the flood submergence at the time, and takes the water body division image at the time as the flood submergence end image of the current region, and confirms the flood submergence start image and the flood submergence end image in the UAV aerial data.

[0073] S62: flood disaster element mining is performed according to the flood submergence start image and the flood submergence end image in the UAV aerial data, and sample flood disaster element data corresponding to the UAV aerial image in the flood disaster time period of the sample river basin is obtained.

[0074] In the embodiment, the monitoring device performs flood disaster element mining according to the flood submergence start image and the flood submergence end image in the UAV aerial data, and obtains sample flood disaster element data corresponding to the UAV aerial image in the flood disaster time period of the sample river basin.

[0075] Specifically, the monitoring device constructs the submergence range data by taking the range of the flood submergence region as the flood submergence range, constructs the submergence duration data by taking the time length from the flood submergence start to the flood submergence end as the submergence duration, and constructs the submergence depth data by calculating the flood submergence depth in combination with the digital elevation model and the measured water level data, so as to obtain the sample flood disaster element data corresponding to the UAV aerial image in the flood disaster time period of the sample river basin.

[0076] S7: sample flood disaster element data corresponding to the ground monitoring in the flood disaster time period of the sample river basin is obtained; and the first deep learning model to be trained is trained according to the sample flood disaster element data corresponding to the ground monitoring in the flood disaster time period of the sample river basin and the sample flood disaster element data corresponding to the UAV aerial image, so as to obtain the first deep learning model.

[0077] In the embodiment, the monitoring device obtains sample flood disaster element data corresponding to ground monitoring in a flood disaster time period of the sample basin, and trains a first deep learning model to be trained according to the sample flood disaster element data corresponding to ground monitoring in the flood disaster time period of the sample basin and sample flood disaster element data corresponding to aerial photography by a UAV, to obtain the first deep learning model, wherein the first deep learning model can generate flood disaster element data corresponding to aerial photography by a UAV for a duration from flood disaster element data corresponding to ground monitoring, for subsequent training of a second deep learning model to be trained.

[0078] Specifically, the monitoring device divides the sample flood disaster element data corresponding to ground monitoring in the flood disaster time period of the sample basin and the sample flood disaster element data corresponding to aerial photography by a UAV, to construct a training set and a verification set, and the number of the training set and the verification set can be 3:1. When the average relative error percentage between the sample flood disaster element data corresponding to aerial photography by a UAV in the verification set and the sample flood disaster element data corresponding to ground monitoring obtained by processing the sample flood disaster element data corresponding to aerial photography by a UAV in the verification set by the first deep learning model to be trained is lower than 30% and the correlation is higher than 0.6, the first deep learning model is trained.

[0079] Please refer to Figure 5 , Figure 5 The flowchart of the space-air-ground integrated basin flood disaster monitoring method provided by the third embodiment of the present application also includes steps S8-S10, which are before step S2, and specifically as follows.

[0080] S8: Obtain satellite remote sensing data in a flood disaster time period of a sample basin, input the satellite remote sensing data into a preset image detection model, perform water body division on satellite remote sensing images at several time points in the satellite remote sensing data, and obtain water body division images corresponding to the satellite remote sensing images at the several time points.

[0081] In the embodiment, the monitoring device obtains satellite remote sensing data in a flood disaster time period of a sample basin. In an optional embodiment, the monitoring device performs automatic rapid geometric precise correction, spectral fusion, ground reflectivity inversion, and inlaying and cutting on satellite remote sensing images at several time points in the collected satellite remote sensing data through parallel computing of a server cluster, to improve the quantitative processing efficiency of basin flood disaster big data.

[0082] The monitoring device inputs the satellite remote sensing data into a preset image detection model, performs water body division on satellite remote sensing images at several time points in the satellite remote sensing data, and obtains water body division images corresponding to the satellite remote sensing images at the several time points.

[0083] S9: flood disaster element mining is performed on the water body division images corresponding to the satellite remote sensing images of several time points to obtain satellite remote sensing corresponding flood disaster element data in the flood disaster time period of the sample basin.

[0084] In the embodiment, the monitoring device performs flood disaster element mining on the water body division images corresponding to the satellite remote sensing images of several time points to obtain satellite remote sensing corresponding flood disaster element data in the flood disaster time period of the sample basin.

[0085] Please refer to Figure 6 , Figure 6 The flowchart of S9 in the space-ground integration basin flood disaster monitoring method provided by the third embodiment of the present application includes steps S91-S92, and the details are as follows:

[0086] S91: the water body division images corresponding to the satellite remote sensing images of several time points are compared with the water body division images corresponding to the satellite remote sensing images of adjacent time points to confirm the flood inundation start image and the flood inundation end image in the satellite remote sensing data.

[0087] In the embodiment, the monitoring device compares the water body division images corresponding to the satellite remote sensing images of several time points with the water body division images corresponding to the satellite remote sensing images of adjacent time points to confirm the flood inundation start image and the flood inundation end image in the satellite remote sensing data. For specific embodiments, reference can be made to step S81, which will not be repeated here.

[0088] S92: flood disaster element mining is performed according to the flood inundation start image and the flood inundation end image in the satellite remote sensing data to obtain satellite remote sensing corresponding sample flood disaster element data in the flood disaster time period of the sample basin.

[0089] In the embodiment, the monitoring device performs flood disaster element mining according to the flood inundation start image and the flood inundation end image in the satellite remote sensing data to obtain satellite remote sensing corresponding sample flood disaster element data in the flood disaster time period of the sample basin. For specific embodiments, reference can be made to step S82, which will not be repeated here.

[0090] S10: the second deep learning model to be trained is trained according to the flood disaster element data corresponding to the unmanned aerial vehicle aerial photography and the flood disaster element data corresponding to the satellite remote sensing in the flood disaster time period of the sample basin to obtain the second deep learning model.

[0091] In the embodiment, the monitoring device trains the second deep learning model to be trained according to the sample flood disaster element data corresponding to the UAV aerial photography and the sample flood disaster element data corresponding to the satellite remote sensing in the flood disaster time period of the sample basin, and obtains the second deep learning model, wherein the second deep learning model can generate the satellite remote sensing corresponding flood disaster element data which is continuous in time and space from the UAV aerial photography corresponding flood disaster element data of the duration, for subsequent flood disaster monitoring.

[0092] Specifically, the monitoring device divides the sample flood disaster element data corresponding to the UAV aerial photography and the sample flood disaster element data corresponding to the satellite remote sensing in the flood disaster time period of the sample basin, constructs a training set and a verification set, and the number of the training set and the verification set can be 3:1. When the average relative error percentage between the satellite remote sensing corresponding sample flood disaster element data in the verification set and the satellite remote sensing corresponding flood disaster element data obtained by processing the UAV aerial photography corresponding sample flood disaster element data in the verification set by the second deep learning model to be trained is lower than 30%, and the correlation is higher than 0.6, the second deep learning model training is completed.

[0093] Please refer to Figure 7 , Figure 7 The structure schematic diagram of the space-ground integration basin flood disaster monitoring device provided by the fourth embodiment of the present application, the device can realize all or part of the space-ground integration basin flood disaster monitoring device by software, hardware or combination of the two, the device 7 comprises:

[0094] The first flood disaster element data obtaining module 71 is used for obtaining the ground monitoring corresponding flood disaster element data of the basin to be processed in a preset time period;

[0095] The second flood disaster element data obtaining module 72 is used for inputting the ground monitoring corresponding flood disaster element data into a preset first deep learning model to simulate the UAV aerial photography flood disaster element, and obtaining the UAV aerial photography corresponding flood disaster element data, wherein the UAV aerial photography corresponding flood disaster element data is time continuous flood disaster element data, and the first deep learning model is a convolutional neural network model trained and constructed by taking the ground monitoring corresponding sample flood disaster element data as an input item and taking the UAV aerial photography corresponding sample flood disaster element data as an output item.

[0096] The third flood disaster element data obtaining module 73 is configured to input the UAV aerial corresponding flood disaster element data into a preset second deep learning model to perform satellite remote sensing flood disaster element simulation, and obtain satellite remote sensing corresponding flood disaster element data. The UAV aerial corresponding flood disaster element data is time-continuous flood disaster element data. The second deep learning model is a convolutional neural network model trained and constructed by taking UAV aerial corresponding sample flood disaster element data as an input item and satellite remote sensing corresponding sample flood disaster element data as an output item.

[0097] The flood disaster monitoring module 74 is configured to perform flood disaster monitoring according to the satellite remote sensing corresponding flood disaster element data, and obtain a flood disaster monitoring result of the to-be-processed river basin.

[0098] In the embodiment of the present application, the first flood disaster element data obtaining module is used to obtain ground monitoring corresponding flood disaster element data of the to-be-processed river basin in a preset time period; the second flood disaster element data obtaining module is used to input the ground monitoring corresponding flood disaster element data into a preset first deep learning model to perform unmanned aerial vehicle aerial flood disaster element simulation, and obtain unmanned aerial vehicle aerial corresponding flood disaster element data, wherein the unmanned aerial vehicle aerial corresponding flood disaster element data is time-continuous flood disaster element data; the first deep learning model is a convolutional neural network model constructed by taking ground monitoring corresponding sample flood disaster element data as an input item and unmanned aerial vehicle aerial corresponding sample flood disaster element data as an output item for training; the third flood disaster element data obtaining module is used to input the unmanned aerial vehicle aerial corresponding flood disaster element data into a preset second deep learning model to perform satellite remote sensing flood disaster element simulation, and obtain satellite remote sensing corresponding flood disaster element data, wherein the satellite remote sensing corresponding flood disaster element data is time- and space-continuous flood disaster element data; the second deep learning model is a convolutional neural network model constructed by taking unmanned aerial vehicle aerial corresponding sample flood disaster element data as an input item and satellite remote sensing corresponding sample flood disaster element data as an output item for training; the flood disaster monitoring module is used to perform flood disaster monitoring according to the satellite remote sensing corresponding flood disaster element data, and obtain a flood disaster monitoring result of the to-be-processed river basin. Based on the constructed deep learning model, the ground monitoring corresponding flood disaster element data of the to-be-processed river basin is sequentially subjected to unmanned aerial vehicle aerial flood disaster element simulation and satellite remote sensing flood disaster element simulation, and satellite remote sensing corresponding flood disaster element data is constructed. The ground monitoring has the characteristics of high accuracy and time continuity, the unmanned aerial vehicle aerial simulation has the characteristics of being not affected by clouds, being flexible, being fast, and having high resolution, and the satellite remote sensing has the characteristics of large coverage, large amount of acquired information, all-weather, all-day, and space continuity. Therefore, time-continuous and space-continuous flood disaster element data is obtained to perform flood disaster monitoring, the comprehensive, large-scale, and efficient flood disaster monitoring of the to-be-processed river basin is realized, the flood disaster monitoring demand is met, and the efficiency of flood disaster monitoring is improved.

[0099] Reference is made to Figure 8 , Figure 8 The computer device provided in the fifth embodiment of the present application includes a processor 81, a memory 82, and a computer program 83 stored in the memory 82 and capable of running on the processor 81. The computer device can store a plurality of instructions, which are suitable for being loaded by the processor 81 and executed to perform the method steps of the first to third embodiments. For details, refer to the specific description of the first to third embodiments, which will not be repeated here.

[0100] The processor 81 can include one or more processing cores. The processor 81 connects various parts within the server by various interfaces and lines, executes various functions and processes data of the space-earth-ground integrated basin flood disaster monitoring device 7 by running or executing instructions, programs, code sets or instruction sets stored in the memory 82, and calling data in the memory 82. Optionally, the processor 81 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programable logic array (PLA). The processor 81 can be integrated with one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes operating systems, user interfaces, and application programs; the GPU is responsible for rendering and drawing the content displayed on the touch display screen; and the modem is used for processing wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 81, but can be realized by a separate chip.

[0101] The memory 82 can include a random access memory (RAM) and a read-only memory (ROM). Optionally, the memory 82 includes a non-transitory computer-readable storage medium. The memory 82 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 82 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as touch instructions, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 82 can also be at least one storage device located away from the aforementioned processor 81.

[0102] The embodiments of the present application also provide a storage medium, which can store a plurality of instructions. The instructions are suitable for being loaded and executed by a processor to execute the method steps of the first to third embodiments described above. The specific execution process can be referred to the specific description of the first to third embodiments, which will not be described here.

[0103] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be realized in the form of hardware or software. In addition, the specific name of each functional unit and module is only for the convenience of mutual distinction, and does not limit the protection scope of the present application. The specific working process of the unit and module in the above system can be referred to the corresponding process in the foregoing method embodiment, which will not be described here.

[0104] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0105] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the algorithm. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered beyond the scope of the present application.

[0106] In the embodiments provided by the present application, it should be understood that the disclosed apparatus / terminal device and method can be implemented in other ways. For example, the above-mentioned apparatus / terminal device embodiments are only schematic. The division of the modules or units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0107] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0108] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0109] The integrated module / unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, an executable file, or some intermediate form.

[0110] The present application is not limited to the above-described embodiments, and various modifications or alterations can be made to the present application without departing from the spirit and scope of the present application. Therefore, if the modifications and alterations belong to the scope of the claims of the present application and the equivalent technical scope, they are also intended to be included in the present application.

Claims

1. A space-air-ground integrated basin flood disaster monitoring method, characterized in that, The method comprises the following steps: obtaining ground monitoring corresponding flood disaster element data of a to-be-processed watershed in a preset time period; inputting the ground monitoring corresponding flood disaster element data into a preset first deep learning model to simulate unmanned aerial vehicle (UAV) aerial flood disaster elements, and obtaining UAV aerial corresponding flood disaster element data, wherein the UAV aerial corresponding flood disaster element data is time-continuous flood disaster element data; the first deep learning model is a convolutional neural network model trained and constructed by taking ground monitoring corresponding sample flood disaster element data as an input item and taking UAV aerial corresponding sample flood disaster element data as an output item; inputting the UAV aerial corresponding flood disaster element data into a preset second deep learning model to simulate satellite remote sensing flood disaster elements, and obtaining satellite remote sensing corresponding flood disaster element data, wherein the satellite remote sensing corresponding flood disaster element data is time- and space-continuous flood disaster element data; the second deep learning model is a convolutional neural network model trained and constructed by taking UAV aerial corresponding sample flood disaster element data as an input item and taking satellite remote sensing corresponding sample flood disaster element data as an output item; performing flood disaster monitoring according to the satellite remote sensing corresponding flood disaster element data, and obtaining a flood disaster monitoring result of the to-be-processed watershed. 2.The space-ground integration basin flood disaster monitoring method according to claim 1, characterized in that, The method further comprises the following steps: obtaining UAV aerial data of a sample watershed in a flood disaster time period, inputting the UAV aerial data into a preset image detection model, performing water body division on UAV aerial images at a plurality of time points in the UAV aerial data, and obtaining water body division images corresponding to the UAV aerial images at the plurality of time points; performing flood disaster element mining according to the water body division images corresponding to the UAV aerial images at the plurality of time points, and obtaining UAV aerial corresponding sample flood disaster element data of the sample watershed in the flood disaster time period; obtaining ground monitoring corresponding sample flood disaster element data of the sample watershed in the flood disaster time period; training a first deep learning model to be trained according to the sample ground monitoring corresponding flood disaster element data and the UAV aerial corresponding sample flood disaster element data of the sample watershed in the flood disaster time period, and obtaining the first deep learning model. 3.The space-ground integration basin flood disaster monitoring method according to claim 2, characterized in that, The method of performing flood disaster element mining according to the water body division images corresponding to the UAV aerial images at the plurality of time points, and obtaining the UAV aerial corresponding sample flood disaster element data of the sample watershed in the flood disaster time period, comprises the following steps: comparing the water body division images corresponding to the UAV aerial images at the plurality of time points with water body division images corresponding to UAV aerial images at adjacent time points respectively, and confirming a flood inundation start image and a flood inundation end image in the UAV aerial data; performing flood disaster element mining according to the flood inundation start image and the flood inundation end image in the UAV aerial data, and obtaining the UAV aerial corresponding sample flood disaster element data of the sample watershed in the flood disaster time period. 4.The space-ground integration basin flood disaster monitoring method according to claim 2, characterized in that, The method further comprises the following steps: Satellite remote sensing data in a flood disaster time period of a sample basin is obtained, the satellite remote sensing data is input into a preset image detection model, water body division is performed on satellite remote sensing images at several time points in the satellite remote sensing data, and water body division images corresponding to the satellite remote sensing images at the several time points are obtained; Flood disaster element data corresponding to satellite remote sensing of the sample basin in the flood disaster time period is obtained by performing flood disaster element mining according to the water body division images corresponding to the satellite remote sensing images at the several time points; A second deep learning model to be trained is trained according to sample flood disaster element data corresponding to unmanned aerial vehicle aerial photography in the flood disaster time period of the sample basin and sample flood disaster element data corresponding to satellite remote sensing, and the second deep learning model is obtained. 5.The space-ground integration basin flood disaster monitoring method according to claim 3, characterized in that, The flood disaster element data corresponding to satellite remote sensing of the sample basin in the flood disaster time period is obtained by performing flood disaster element mining according to the water body division images corresponding to the satellite remote sensing images at the several time points, and includes the following steps: The water body division images corresponding to the satellite remote sensing images at the several time points are compared with the water body division images corresponding to the satellite remote sensing images at adjacent time points respectively, and flood inundation start images and flood inundation end images in the satellite remote sensing data are confirmed; The flood disaster element data corresponding to satellite remote sensing of the sample basin in the flood disaster time period is obtained by performing flood disaster element mining according to the flood inundation start images and the flood inundation end images in the satellite remote sensing data. 6.The space-ground integration basin flood disaster monitoring method according to claim 5, characterized in that: The flood disaster element data includes inundation range data, inundation depth data and inundation duration data of several region types. 7.The space-ground integration basin flood disaster monitoring method according to claim 6, characterized in that, The flood disaster monitoring result of the basin to be processed is obtained by performing flood disaster monitoring according to the flood disaster element data corresponding to satellite remote sensing, and includes the following steps: Flood disaster loss coefficients of the several region types are obtained according to the inundation depth data in the flood disaster element data of the several region types and a preset corresponding table of flood disaster loss coefficients and inundation depth data; Area data and per-unit property data of the several region types of the basin to be processed are obtained, flood pre-disaster monitoring values of the several region types are obtained according to the area data, the per-unit property data and a preset flood pre-disaster monitoring calculation algorithm, the flood pre-disaster monitoring values of the several region types are added up, and a total flood pre-disaster monitoring value is obtained, wherein the flood pre-disaster monitoring calculation algorithm is: In the formula, A i is the pre-disaster monitoring value of the flood of the ith region type, C is the number of region types, area i is the area data of the ith region type, μ i is the per capita property data of the ith region type; Flood disaster loss monitoring values of the several region types are obtained according to the area data, the per-unit property data, the flood disaster loss coefficients and a preset flood disaster loss monitoring calculation algorithm, the flood disaster loss monitoring values of the several region types are added up, and a total flood disaster loss monitoring value is obtained, wherein the flood disaster loss monitoring calculation algorithm is: In the formula, B i is the flood disaster loss monitoring value of the i-th regional type, θ i is the flood disaster loss coefficient of the i-th regional type; The total flood disaster loss monitoring value is divided by the total flood pre-disaster monitoring value, and a flood disaster loss rate of the basin to be processed is obtained as the flood disaster monitoring result.

8. A space-air-ground integrated basin flood disaster monitoring device, characterized in that, It includes: The first flood disaster element data obtaining module is configured to obtain ground monitoring corresponding flood disaster element data of a to-be-processed watershed in a preset time period. The second flood disaster element data obtaining module is configured to input the ground monitoring corresponding flood disaster element data into a preset first deep learning model to simulate unmanned aerial vehicle (UAV) aerial flood disaster element data, so as to obtain UAV aerial corresponding flood disaster element data, wherein the UAV aerial corresponding flood disaster element data is time-continuous flood disaster element data; the first deep learning model is a convolutional neural network model trained and constructed by taking ground monitoring corresponding sample flood disaster element data as an input item and taking UAV aerial corresponding sample flood disaster element data as an output item. The third flood disaster element data obtaining module is configured to input the UAV aerial corresponding flood disaster element data into a preset second deep learning model to simulate satellite remote sensing flood disaster element data, so as to obtain satellite remote sensing corresponding flood disaster element data, wherein the satellite remote sensing corresponding flood disaster element data is time- and space-continuous flood disaster element data; the second deep learning model is a convolutional neural network model trained and constructed by taking sample UAV aerial corresponding flood disaster element data as an input item and taking sample satellite remote sensing corresponding flood disaster element data as an output item. The flood disaster monitoring module is configured to perform flood disaster monitoring according to the satellite remote sensing corresponding flood disaster element data, so as to obtain a flood disaster monitoring result of the to-be-processed watershed.

9. A computer device, comprising: The processor, the memory, and the computer program stored in the memory and executable on the processor; the computer program is executed by the processor to implement the steps of the space-ground integration flood disaster monitoring method of the watershed according to any one of claims 1 to 7. The storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the space-ground integration flood disaster monitoring method of the watershed according to any one of claims 1 to 7.

10. A storage medium characterized by: ​

Images