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

Abstract

The invention relates to the technical field of geographic information, in particular to a space-air-ground integrated drainage basin flood disaster monitoring method and device and computer equipment. Sequentially carrying out unmanned aerial vehicle aerial photography and satellite remote sensing flood disaster element simulation on the flood disaster element data corresponding to ground monitoring of the drainage basin to be processed, and constructing flood disaster element data corresponding to satellite remote sensing; the characteristics of high ground monitoring precision and continuous time, the characteristics of no cloud influence, flexibility, rapidness and high resolution of unmanned aerial vehicle aerial photography, and the characteristics of large satellite remote sensing coverage, large information acquisition amount, all weather, all day time and continuous space are fully utilized, so that time-continuous and space-continuous flood disaster element data are obtained; the flood disaster monitoring system and the flood disaster monitoring method are used for monitoring flood disasters, comprehensive, large-range and efficient flood disaster monitoring of the to-be-treated drainage basin is achieved, the flood disaster monitoring requirement is met, and the flood disaster monitoring efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of geographic information technology, and in particular to an air-ground-ground integrated river basin flood disaster monitoring method, device, computer equipment and storage medium. Background Art

[0002] Due to the frequent and severe occurrence of extreme climate, flood disasters have been caused, resulting in serious casualties and property losses. It is urgent to do a good job in flood prevention, disaster reduction and emergency rescue, and flood disaster monitoring is the first task.

[0003] Traditional flood disaster monitoring uses manual surveys and hydrological station monitoring methods, and usually sets up multiple collection points in the basin to monitor flood information. However, the above method can only monitor flood information around the collection points, making it difficult to conduct comprehensive, large-scale and efficient flood disaster monitoring of the entire basin, and cannot meet the current flood disaster monitoring needs. Summary of the invention

[0004] Based on this, the purpose of the present invention is to provide an integrated air-space-ground basin 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 processed basin are photographed by drones and simulated by satellite remote sensing flood disaster elements in turn, and the flood disaster element data corresponding to satellite remote sensing are constructed. The characteristics of high accuracy and temporal continuity of ground monitoring, the characteristics of drone aerial photography that is not affected by clouds, flexibility, speed and high resolution, and the characteristics of large coverage, large amount of information acquisition, all-weather, all-day and spatial continuity of satellite remote sensing are fully utilized to obtain temporally and spatially continuous flood disaster element data for flood disaster monitoring, thereby realizing comprehensive, large-scale and efficient flood disaster monitoring of the processed basin, meeting the needs of flood disaster monitoring and improving the efficiency of flood disaster monitoring.

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

[0006] Obtaining flood disaster element data corresponding to ground monitoring of the watershed to be processed within a preset time period;

[0007] The flood disaster element data corresponding to the ground monitoring is input into a preset first deep learning model to simulate the flood disaster element of drone aerial photography, and the flood disaster element data corresponding to the drone aerial photography is obtained, wherein the flood disaster element data corresponding to the drone aerial photography is time-continuous flood disaster element data; the first deep learning model is a convolutional neural network model constructed by training with the flood disaster element data corresponding to the sample ground monitoring as input and the flood disaster element data corresponding to the sample drone aerial photography as output;

[0008] The flood disaster element data corresponding to the drone aerial photography is input into a preset second deep learning model to simulate the satellite remote sensing flood disaster element, and 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 continuous in both time and space; the second deep learning model is a convolutional neural network model constructed by training with the sample flood disaster element data corresponding to the drone aerial photography as input and the sample flood disaster element data corresponding to the satellite remote sensing as output;

[0009] Flood disaster monitoring is performed according to the flood disaster element data corresponding to the satellite remote sensing to obtain the flood disaster monitoring results of the watershed to be processed.

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

[0011] The first flood disaster element data acquisition module is used to obtain flood disaster element data corresponding to ground monitoring of the basin to be processed within a preset time period;

[0012] A second flood disaster element data acquisition module is used 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 of drone aerial photography, and obtain the flood disaster element data corresponding to the drone aerial photography, wherein the flood disaster element data corresponding to the drone aerial photography is time-continuous flood disaster element data; the first deep learning model uses the sample flood disaster element data corresponding to the ground monitoring as an input item and the sample flood disaster element data corresponding to the drone aerial photography as an output item for training and constructing a convolutional neural network model;

[0013] A third flood disaster element data acquisition module is used to input the flood disaster element data corresponding to the drone aerial photography into a preset second deep learning model to perform satellite remote sensing flood disaster element simulation, and obtain flood disaster element data corresponding to satellite remote sensing, wherein the flood disaster element data corresponding to satellite remote sensing is flood disaster element data that is continuous in both time and space; the second deep learning model is a convolutional neural network model constructed by training with sample flood disaster element data corresponding to the drone aerial photography as input items and sample flood disaster element data corresponding to satellite remote sensing as output items;

[0014] The flood disaster monitoring module is used to perform flood disaster monitoring according to the flood disaster element data corresponding to the satellite remote sensing, and obtain the flood disaster monitoring results of the watershed to be processed.

[0015] In a third aspect, an embodiment of the present application provides a computer device comprising: 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 air-space-ground integrated river basin flood disaster monitoring method as described in the first aspect are implemented.

[0016] In a fourth aspect, an embodiment of the present application provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the integrated air-space-ground-watershed flood disaster monitoring method as described in the first aspect.

[0017] In an embodiment of the present application, a method, device, computer equipment and storage medium for monitoring flood disasters in a river basin that is integrated with air, space and land are provided. Based on the constructed deep learning model, the flood disaster element data corresponding to the ground monitoring of the river basin to be processed are sequentially photographed by drones and simulated by satellite remote sensing flood disaster elements, and the flood disaster element data corresponding to satellite remote sensing are constructed. The characteristics of high accuracy and temporal continuity of ground monitoring, the characteristics of drone aerial photography that is not affected by clouds, flexibility, speed and high resolution, and the characteristics of large coverage, large amount of information acquisition, all-weather, all-day and spatial continuity of satellite remote sensing are fully utilized to obtain temporally and spatially continuous flood disaster element data for flood disaster monitoring, thereby realizing comprehensive, large-scale and efficient flood disaster monitoring of the river basin to be processed, meeting the needs of flood disaster monitoring and improving the efficiency of flood disaster monitoring.

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

[0019] Figure 1 A schematic flow chart of the air-ground-integrated basin flood disaster monitoring method provided in the first embodiment of the present application;

[0020] Figure 2 A schematic diagram of the process of S4 in the air-ground-integrated basin flood disaster monitoring method provided in the first embodiment of the present application;

[0021] Figure 3 A schematic flow chart of a method for monitoring flood disasters in a river basin that integrates air, space and land, provided in accordance with the second embodiment of the present application;

[0022] Figure 4 A schematic diagram of the flow of S6 in the air-ground-integrated basin flood disaster monitoring method provided in the second embodiment of the present application;

[0023] Figure 5 A schematic flow chart of a method for monitoring flood disasters in a river basin that integrates air, space and land, provided in the third embodiment of the present application;

[0024] Figure 6 A schematic diagram of the flow of S9 in the air-ground-integrated basin flood disaster monitoring method provided in the third embodiment of the present application;

[0025] Figure 7 A schematic diagram of the structure of a watershed flood disaster monitoring device integrating air, space and land provided in the fourth embodiment of the present application;

[0026] Figure 8 A schematic diagram of the structure of a computer device provided in the fifth embodiment of the present application. DETAILED DESCRIPTION

[0027] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0028] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0029] It should be understood that, although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" / "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determination".

[0030] See also Figure 1 , Figure 1 A schematic flow chart of a method for monitoring flood disasters in a river basin that integrates air, space and land is provided in the first embodiment of the present application. The method comprises the following steps:

[0031] S1: Obtain flood disaster element data corresponding to ground monitoring of the basin to be processed within a preset time period.

[0032] The executor of the air-space-ground integrated river basin flood disaster monitoring method is the monitoring equipment of the air-space-ground integrated river basin flood disaster monitoring method (hereinafter referred to as the monitoring equipment). In an optional embodiment, the monitoring equipment can be a computer device, a server, or a server cluster composed of multiple computer devices.

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

[0034] S2: Input the flood disaster element data corresponding to the ground monitoring into a preset first deep learning model to simulate the flood disaster elements in drone aerial photography, and obtain the flood disaster element data corresponding to the drone aerial photography.

[0035] The first deep learning model is a convolutional neural network model constructed by training with sample flood disaster element data corresponding to ground monitoring as input and sample flood disaster element data corresponding to drone aerial photography as output.

[0036] In this embodiment, the monitoring equipment inputs the flood disaster element data corresponding to the ground monitoring into a preset first deep learning model to perform UAV aerial photography flood disaster element simulation, and obtains the flood disaster element data corresponding to the UAV aerial photography, wherein the flood disaster element data corresponding to the UAV aerial photography is time-continuous flood disaster element data.

[0037] Based on the flood disaster element data corresponding to ground monitoring, the flood disaster element data corresponding to UAV aerial photography are simulated, and the fusion of ground monitoring information and UAV aerial photography information is realized. The characteristics of high precision and time continuity of ground monitoring and the characteristics of UAV aerial photography that are not affected by clouds, flexible, fast and high-resolution are utilized to improve the accuracy and efficiency of flood disaster monitoring.

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

[0039] The second deep learning model is a convolutional neural network model constructed by training with sample flood disaster element data corresponding to drone aerial photography as input and sample flood disaster element data corresponding to satellite remote sensing as output.

[0040] In this embodiment, the monitoring equipment inputs the flood disaster element data corresponding to the drone aerial photography into a preset second deep learning model to perform satellite remote sensing flood disaster element simulation, and obtains the flood disaster element data corresponding to satellite remote sensing, wherein the flood disaster element data corresponding to the drone aerial photography is time-continuous flood disaster element data.

[0041] Based on the flood disaster element data corresponding to the UAV aerial photography obtained, the flood disaster element data corresponding to the satellite remote sensing is simulated, and the fusion of UAV aerial photography information and satellite remote sensing information is realized. The characteristics of satellite remote sensing, such as large coverage, large amount of information acquisition, all-weather, all-day and time continuity, are utilized to further improve the accuracy and efficiency of flood disaster monitoring.

[0042] S4: Flood disaster monitoring is performed according to the flood disaster element data corresponding to the satellite remote sensing to obtain flood disaster monitoring results of the watershed to be processed.

[0043] In this embodiment, the monitoring device performs flood disaster monitoring according to the flood disaster element data corresponding to the satellite remote sensing, and obtains the flood disaster monitoring result of the watershed to be processed.

[0044] See also Figure 2 , Figure 2 The flowchart of S4 in the air-ground-integrated basin flood disaster monitoring method provided in the first embodiment of the present application includes steps S41 to S44, which are as follows:

[0045] S41: Obtaining flood disaster loss coefficients of several regional types according to the flood disaster element data of several regional types and a preset correspondence table between flood disaster loss coefficients and flood depth data.

[0046] In this embodiment, the monitoring device obtains flood disaster loss coefficients of several regional types according to the flood depth data in the flood disaster element data of several regional types and a preset correspondence table between the flood disaster loss coefficient and the flood depth data.

[0047] Specifically, the monitoring equipment determines the flood depth threshold interval in which the flood depth data is located based on several flood depth threshold intervals and the corresponding flood disaster loss coefficients in the corresponding table of the flood disaster loss coefficient and the flood depth data, obtains the flood disaster loss coefficient corresponding to the flood depth data, and obtains the flood disaster loss coefficients of several regional types.

[0048] S42: Obtain area data and per capita property data of several regional types of the to-be-processed watershed, obtain pre-flood monitoring values ​​of several regional types based on the area data, per capita property data of several regional types and a preset pre-flood monitoring calculation algorithm, and add up the pre-flood monitoring values ​​of several regional types to obtain a total pre-flood monitoring value.

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

[0050]

[0051] In the formula, A i is the flood monitoring value before the ith area type, C is the number of area types, area i is the area data of the ith region type, μ i is the average land property data for the i-th regional type.

[0052] In this embodiment, the monitoring equipment obtains the area data and average property data of several regional types of the river basin to be processed, obtains pre-flood disaster monitoring values ​​of several regional types based on the area data, average property data of several regional types and a preset pre-flood disaster monitoring calculation algorithm, and accumulates the pre-flood disaster monitoring values ​​of several regional types to obtain a total pre-flood disaster monitoring value.

[0053] S43: Obtain flood disaster loss monitoring values ​​for several regional types based on area data, per-unit property data, flood disaster loss coefficients, and a preset flood disaster loss monitoring calculation algorithm for several regional types, and add up the flood disaster loss monitoring values ​​for several regional types to obtain a total flood disaster loss monitoring value.

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

[0055]

[0056] In the formula, B iis the flood disaster loss monitoring value of the i-th regional type, θ i is the flood disaster loss coefficient of the ith regional type.

[0057] In this embodiment, the monitoring equipment obtains flood disaster loss monitoring values ​​of several regional types based on the area data of several regional types, average property data per area, flood disaster loss coefficient and a preset flood disaster loss monitoring calculation algorithm, and accumulates the flood disaster loss monitoring values ​​of several regional types to obtain a total flood disaster loss monitoring value.

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

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

[0060] Based on the constructed deep learning model, the flood disaster element data corresponding to the ground monitoring of the treated basin are photographed by drones and simulated by satellite remote sensing flood disaster elements in turn, and the flood disaster element data corresponding to satellite remote sensing are constructed. The characteristics of high precision and temporal continuity of ground monitoring, the characteristics of drone aerial photography that are not affected by clouds, flexibility, speed and high resolution, and the characteristics of large coverage, large amount of information acquisition, all-weather, all-day and spatial continuity of satellite remote sensing are fully utilized to obtain temporally and spatially continuous flood disaster element data for flood disaster monitoring, thus realizing comprehensive, large-scale and efficient flood disaster monitoring of the treated basin, meeting the needs of flood disaster monitoring and improving the efficiency of flood disaster monitoring.

[0061] See also Figure 3 , Figure 3 The schematic flow chart of the air-ground-integrated basin flood disaster monitoring method provided in the second embodiment of the present application further includes steps S5 to S7. The steps S5 to S7 are before step S2 and are specifically as follows:

[0062] S5: Obtain drone aerial photography data within the flood disaster period of the sample watershed, input the drone aerial photography data into a preset image detection model, perform water body division on the drone aerial photography images at several moments in the drone aerial photography data, and obtain water body division images corresponding to the drone aerial photography images at several moments.

[0063] In this embodiment, the monitoring equipment obtains drone aerial photography data and flood disaster element data corresponding to ground monitoring during the flood disaster time period of the sample basin, wherein the drone aerial photography data includes drone aerial images at several moments. Specifically, the monitoring equipment can use high-speed fiber optic dedicated lines to quickly receive drone aerial photography data and flood disaster element data corresponding to ground monitoring, and store them in a large-scale storage system for subsequent analysis and calculation, wherein the large-scale storage system provides hardware space for intelligent mining and information services of flood disaster information actually observed by satellite remote sensing, drones, and ground hydrological station networks, and supports rapid data reading and management; high-speed data transmission and storage are conducive to improving the timeliness of the integrated air-ground-ground flood disaster monitoring method.

[0064] In an optional embodiment, in order to improve the targetedness, the sample watershed can be set as the watershed to be processed, and the monitoring equipment pre-processes the drone aerial images at several moments in the drone aerial data, performs aerial triangulation encryption, generates topographic maps, orthorectifies and stitches the images, etc., so as to improve the efficiency of quantitative processing of big data on flood disasters in the watershed.

[0065] The monitoring equipment inputs the drone aerial photography data into a preset image detection model, performs water body division on the drone aerial photography images at several moments in the drone aerial photography data, obtains water body division images corresponding to the drone aerial photography images at several moments, and constructs water body samples and non-water body samples required for flood inundation range training, so as to train the first deep learning model to be trained, wherein the water body division image includes water body areas and non-water body areas.

[0066] S6: mining flood disaster elements based on water body division images corresponding to drone aerial images at several moments, and obtaining flood disaster element data corresponding to the drone aerial images within the flood disaster time period of the sample watershed.

[0067] In this embodiment, the monitoring device mines flood disaster elements based on the water body division images corresponding to the drone aerial images at several moments, and obtains flood disaster element data corresponding to the drone aerial images during the flood disaster time period of the sample basin.

[0068] See also Figure 4 , Figure 4 The flowchart of S6 in the air-ground-integrated basin flood disaster monitoring method provided in the second embodiment of the present application includes steps S61 to S62, which are as follows:

[0069] S61: Compare the water body demarcation images corresponding to the drone aerial images at several moments with the water body demarcation images corresponding to the drone aerial images at adjacent moments, and confirm the flood inundation start image and the flood inundation end image in the drone aerial data.

[0070] In this embodiment, the monitoring equipment compares the water body demarcation images corresponding to the drone aerial images at several moments with the water body demarcation images corresponding to the drone aerial images at adjacent moments, and confirms the flood inundation start image and the flood inundation end image in the drone aerial data.

[0071] Specifically, if the areas at the same position of the water body division image and the water body division image at the previous moment are respectively a water body area and a non-water body area, the monitoring device determines that the flooding of the current area has started at this moment, and uses the water body division image at that moment as the flooding start image of the current area.

[0072] If the areas at the same position of the water body division image and the water body division image at the next moment are respectively the water body area and the non-water body area, the monitoring equipment determines that the flooding of the current area has ended at this moment, and uses the water body division image at this moment as the flooding end image of the current area, and confirms the flooding start image and the flooding end image in the drone aerial photography data.

[0073] S62: Flood disaster element mining is performed based on the flood inundation start image and the flood inundation end image in the drone aerial photography data to obtain sample flood disaster element data corresponding to the drone aerial photography within the flood disaster time period of the sample watershed.

[0074] In this embodiment, the monitoring equipment mines flood disaster elements based on the flood inundation start images and flood inundation end images in the drone aerial photography data, and obtains sample flood disaster element data corresponding to the drone aerial photography during the flood disaster time period of the sample watershed.

[0075] Specifically, the monitoring equipment defines the area submerged by the flood as the flood range, and the flood range data is constructed; the time from the start of the flood to the end of the flood is the flood duration, and the flood duration data is constructed; the flood depth is calculated by combining the digital elevation model and the measured water level data, and the flood depth data is constructed, and the sample flood disaster element data corresponding to the drone aerial photography during the flood disaster time period of the sample basin is obtained.

[0076] S7: Obtain sample flood disaster element data corresponding to ground monitoring during the flood disaster time period of the sample watershed; train the first deep learning model to be trained according to the sample flood disaster element data corresponding to ground monitoring during the flood disaster time period of the sample watershed and the sample flood disaster element data corresponding to drone aerial photography to obtain the first deep learning model.

[0077] In this embodiment, the monitoring equipment obtains sample flood disaster element data corresponding to ground monitoring during the flood disaster time period of the sample watershed, and trains the first deep learning model to be trained based on the sample flood disaster element data corresponding to ground monitoring during the flood disaster time period of the sample watershed and the sample flood disaster element data corresponding to drone aerial photography to obtain the first deep learning model, wherein the first deep learning model can generate flood disaster element data corresponding to drone aerial photography of a certain duration through the flood disaster element data corresponding to ground monitoring, so as to provide for the subsequent training of the second deep learning model to be trained.

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

[0079] See also Figure 5 , Figure 5 The schematic flow chart of the air-ground-integrated basin flood disaster monitoring method provided in the third embodiment of the present application further includes steps S8 to S10, wherein steps S8 to S10 are before step S2, and are specifically as follows:

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

[0081] In this embodiment, the monitoring equipment obtains satellite remote sensing data of the sample watershed during the flood disaster period. In an optional embodiment, the monitoring equipment uses parallel computing of a server cluster to automatically perform rapid geometric correction, spectral fusion, surface reflectivity inversion, and mosaic clipping on the satellite remote sensing images at several moments in the collected satellite remote sensing data to improve the efficiency of quantitative processing of big data on watershed flood disasters.

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

[0083] S9: mining flood disaster elements based on water body division images corresponding to satellite remote sensing images at several moments, and obtaining flood disaster element data corresponding to satellite remote sensing within the flood disaster time period of the sample watershed.

[0084] In this embodiment, the monitoring device mines flood disaster elements based on water body division images corresponding to satellite remote sensing images at several moments, and obtains flood disaster element data corresponding to satellite remote sensing within the flood disaster time period of the sample watershed.

[0085] See also Figure 6 , Figure 6 The flowchart of S9 in the air-ground-integrated basin flood disaster monitoring method provided in the third embodiment of the present application includes steps S91 to S92, which are as follows:

[0086] S91: Compare the water body demarcation images corresponding to the satellite remote sensing images at several moments with the water body demarcation images corresponding to the satellite remote sensing images at adjacent moments, and confirm the flood inundation start image and the flood inundation end image in the satellite remote sensing data.

[0087] In this embodiment, the monitoring device compares the water body division images corresponding to the satellite remote sensing images at several moments with the water body division images corresponding to the satellite remote sensing images at adjacent moments, and confirms the flood inundation start image and the flood inundation end image in the satellite remote sensing data. The specific embodiment can refer to step S81, which will not be repeated here.

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

[0089] In this embodiment, the monitoring device mines flood disaster elements according to the flood inundation start image and flood inundation end image in the satellite remote sensing data to obtain the sample flood disaster element data corresponding to the satellite remote sensing in the flood disaster time period of the sample basin. For the specific embodiment, please refer to step S82, which will not be described in detail here.

[0090] S10: Training the second deep learning model to be trained according to the flood disaster element data corresponding to the drone aerial photography during the flood disaster time period of the sample watershed and the flood disaster element data corresponding to the satellite remote sensing to obtain the second deep learning model.

[0091] In this embodiment, the monitoring equipment trains the second deep learning model to be trained based on the sample flood disaster element data corresponding to the drone aerial photography during the flood disaster time period of the sample watershed and the sample flood disaster element data corresponding to satellite remote sensing to obtain the second deep learning model, wherein the second deep learning model can generate flood disaster element data corresponding to satellite remote sensing that is continuous in both time and space through the flood disaster element data corresponding to the drone aerial photography of duration, for subsequent flood disaster monitoring.

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

[0093] Please refer to Figure 7 , Figure 7 This is a schematic diagram of the structure of the air-ground-integrated basin flood disaster monitoring device provided in the fourth embodiment of the present application. The device can realize all or part of the air-ground-integrated basin flood disaster monitoring device through software, hardware, or a combination of both. The device 7 includes:

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

[0095] The second flood disaster element data acquisition module 72 is used to input the flood disaster element data corresponding to the ground monitoring into the preset first deep learning model to simulate the flood disaster element of drone aerial photography, and obtain the flood disaster element data corresponding to the drone aerial photography, wherein the flood disaster element data corresponding to the drone aerial photography is time-continuous flood disaster element data, and the first deep learning model uses the sample flood disaster element data corresponding to the ground monitoring as input items and the sample flood disaster element data corresponding to the drone aerial photography as output items for training and constructing a convolutional neural network model;

[0096] The third flood disaster element data acquisition module 73 is used to input the flood disaster element data corresponding to the drone aerial photography into a preset second deep learning model to perform satellite remote sensing flood disaster element simulation, and obtain the flood disaster element data corresponding to satellite remote sensing, wherein the flood disaster element data corresponding to the drone aerial photography is time-continuous flood disaster element data, and the second deep learning model uses the sample flood disaster element data corresponding to the drone aerial photography as input items and the sample flood disaster element data corresponding to satellite remote sensing as output items for training and constructing a convolutional neural network model;

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

[0098] In an embodiment of the present application, flood disaster element data corresponding to ground monitoring of a to-be-processed basin within a preset time period is obtained through a first flood disaster element data acquisition module; the flood disaster element data corresponding to the ground monitoring is input into a preset first deep learning model through a second flood disaster element data acquisition module to perform drone aerial photography flood disaster element simulation, and obtain flood disaster element data corresponding to drone aerial photography, wherein the flood disaster element data corresponding to drone aerial photography is time-continuous flood disaster element data; the first deep learning model is a convolutional neural network model constructed by training with sample flood disaster element data corresponding to ground monitoring as input items and sample flood disaster element data corresponding to drone aerial photography as output items; Through the third flood disaster element data acquisition module, the flood disaster element data corresponding to the drone aerial photography is input into the preset second deep learning model to perform satellite remote sensing flood disaster element simulation, and the flood disaster element data corresponding to the satellite remote sensing is obtained, wherein the flood disaster element data corresponding to the satellite remote sensing is continuous in both time and space; the second deep learning model uses the sample flood disaster element data corresponding to the drone aerial photography as input items and the sample flood disaster element data corresponding to satellite remote sensing as output items to train and construct a convolutional neural network model; through the flood disaster monitoring module, flood disaster monitoring is performed according to the flood disaster element data corresponding to the satellite remote sensing, and the flood disaster monitoring result of the basin to be processed is obtained. Based on the constructed deep learning model, the flood disaster element data corresponding to the ground monitoring of the treated basin are photographed by drones and simulated by satellite remote sensing flood disaster elements in turn, and the flood disaster element data corresponding to satellite remote sensing are constructed. The characteristics of high precision and temporal continuity of ground monitoring, the characteristics of drone aerial photography that are not affected by clouds, flexibility, speed and high resolution, and the characteristics of large coverage, large amount of information acquisition, all-weather, all-day and spatial continuity of satellite remote sensing are fully utilized to obtain temporally and spatially continuous flood disaster element data for flood disaster monitoring, thus realizing comprehensive, large-scale and efficient flood disaster monitoring of the treated basin, meeting the needs of flood disaster monitoring and improving the efficiency of flood disaster monitoring.

[0099] Please refer to Figure 8 , Figure 8 The structural diagram of the computer device provided for the fifth embodiment of the present application, the computer device 8 includes: a processor 81, a memory 82, and a computer program 83 stored in the memory 82 and executable on the processor 81; the computer device can store multiple instructions, and the instructions are suitable for the processor 81 to load and execute the method steps of the first to third embodiments shown above. The specific execution process can refer to the specific description of the first to third embodiments shown, which will not be repeated here.

[0100] Among them, the processor 81 may include one or more processing cores. The processor 81 uses various interfaces and lines to connect various parts in the server, and executes various functions and processes data of the integrated air-ground-watershed flood disaster monitoring device 7 by running or executing instructions, programs, code sets or instruction sets stored in the memory 82, and calling the data in the memory 82. Optionally, the processor 81 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programble Logic Array, PLA). The processor 81 can integrate one or more combinations of a central processing unit 81 (Central Processing Unit, CPU), an image processor 81 (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the touch display; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 81, and can be implemented by a single chip.

[0101] Among them, the memory 82 may include a random access memory 82 (Random Access Memory, RAM), and may also include a read-only memory 82 (Read-Only Memory). 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 may include a program storage area and a data storage area, wherein the program storage area may 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 may store data involved in the above-mentioned various method embodiments, etc. The memory 82 may also be optionally at least one storage device located away from the aforementioned processor 81.

[0102] An embodiment of the present application also provides a storage medium, which can store multiple instructions. The instructions are suitable for being loaded by a processor and executing the method steps of the first to third embodiments above. The specific execution process can be found in the specific description of the first to third embodiments, which will not be repeated here.

[0103] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0104] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0105] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraint algorithm of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0106] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

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

[0108] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0109] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.

[0110] The present invention is not limited to the above-mentioned embodiments. If various changes or modifications to the present invention do not depart from the spirit and scope of the present invention, and if these changes and modifications fall within the scope of the claims and equivalent technologies of the present invention, the present invention is also intended to include these changes and modifications.

Claims

1. A method for monitoring flood disasters in a river basin integrating air, space and land, characterized in that: The following steps are involved: Obtaining flood disaster element data corresponding to ground monitoring of the watershed to be processed within a preset time period; The flood disaster element data corresponding to the ground monitoring is input into a preset first deep learning model to simulate the flood disaster element of drone aerial photography, and the flood disaster element data corresponding to the drone aerial photography is obtained, wherein the flood disaster element data corresponding to the drone aerial photography is time-continuous flood disaster element data; the first deep learning model is a convolutional neural network model constructed by training with the sample flood disaster element data corresponding to the ground monitoring as input and the sample flood disaster element data corresponding to the drone aerial photography as output; Inputting the flood disaster element data corresponding to the drone aerial photography into a preset second deep learning model to simulate the satellite remote sensing flood disaster elements, and obtaining the flood disaster element data corresponding to the satellite remote sensing, wherein the flood disaster element data corresponding to the satellite remote sensing is continuous in both time and space; the second deep learning model is a convolutional neural network model constructed by training with the sample flood disaster element data corresponding to the drone aerial photography as input and the sample flood disaster element data corresponding to the satellite remote sensing as output; Flood disaster monitoring is performed according to the flood disaster element data corresponding to the satellite remote sensing to obtain the flood disaster monitoring results of the watershed to be processed.

2. The air-ground-integrated basin flood disaster monitoring method according to claim 1 is characterized in that: Also includes the steps: Obtain drone aerial photography data within the flood disaster period of the sample watershed, input the drone aerial photography data into a preset image detection model, perform water body division on the drone aerial images at several moments in the drone aerial photography data, and obtain water body division images corresponding to the drone aerial images at several moments; Mining flood disaster elements based on water body division images corresponding to drone aerial images at several moments to obtain sample flood disaster element data corresponding to drone aerial images within the flood disaster time period of the sample watershed; Obtain sample flood disaster element data corresponding to ground monitoring during the flood disaster time period of the sample watershed; train the first deep learning model to be trained according to the flood disaster element data corresponding to the sample ground monitoring during the flood disaster time period of the sample watershed and the sample flood disaster element data corresponding to drone aerial photography to obtain the first deep learning model.

3. The air-ground-integrated basin flood disaster monitoring method according to claim 2 is characterized in that: The method of mining flood disaster elements according to the water body division images corresponding to the drone aerial images at several moments to obtain sample flood disaster element data corresponding to the drone aerial images within the flood disaster time period of the sample watershed includes the following steps: Comparing the water body demarcation images corresponding to the drone aerial images at several moments with the water body demarcation images corresponding to the drone aerial images at adjacent moments, to confirm the flood inundation start image and the flood inundation end image in the drone aerial data; Flood disaster element mining is performed based on the flood inundation start image and the flood inundation end image in the drone aerial photography data to obtain sample flood disaster element data corresponding to the drone aerial photography within the flood disaster time period of the sample watershed.

4. The air-ground-integrated basin flood disaster monitoring method according to claim 2 is characterized in that: Also includes the steps: Obtain satellite remote sensing data of a sample watershed during a flood disaster period, input the satellite remote sensing data into a preset image detection model, perform water body division on satellite remote sensing images at several moments in the satellite remote sensing data, and obtain water body division images corresponding to the satellite remote sensing images at several moments; Mining flood disaster elements based on water body division images corresponding to satellite remote sensing images at several moments to obtain sample flood disaster element data corresponding to satellite remote sensing within the flood disaster time period of the sample watershed; The second deep learning model to be trained is trained based on the sample flood disaster element data corresponding to the drone aerial photography during the flood disaster time period of the sample watershed and the sample flood disaster element data corresponding to the satellite remote sensing to obtain the second deep learning model.

5. The air-ground-integrated basin flood disaster monitoring method according to claim 3 is characterized in that: The method of mining flood disaster elements according to water body division images corresponding to satellite remote sensing images at a plurality of moments to obtain sample flood disaster element data corresponding to satellite remote sensing within the flood disaster time period of the sample watershed comprises the following steps: Comparing the water body demarcation images corresponding to the satellite remote sensing images at several moments with the water body demarcation images corresponding to the satellite remote sensing images at adjacent moments, respectively, to confirm the flood inundation start image and the flood inundation end image in the satellite remote sensing data; Flood disaster element mining is performed based on the flood inundation start image and the flood inundation end image in the satellite remote sensing data to obtain sample flood disaster element data corresponding to the satellite remote sensing within the flood disaster time period of the sample watershed.

6. The air-ground-integrated basin flood disaster monitoring method according to claim 5 is characterized by: The flood disaster element data includes flood range data, flood depth data and flood duration data of several regional types.

7. The air-ground-integrated basin flood disaster monitoring method according to claim 6 is characterized in that: The flood disaster monitoring is performed according to the flood disaster element data corresponding to the satellite remote sensing to obtain the flood disaster monitoring result of the basin to be processed, including the steps of: According to the flood depth data in the flood disaster element data of the several regional types and the preset correspondence table between the flood disaster loss coefficient and the flood depth data, the flood disaster loss coefficient of the several regional types is obtained; The area data and per capita property data of several regional types of the to-be-processed basin are obtained, and the pre-flood disaster monitoring values ​​of several regional types are obtained according to the area data, per capita property data of several regional types and a preset pre-flood disaster monitoring calculation algorithm. The pre-flood disaster monitoring values ​​of several regional types are accumulated to obtain a total pre-flood disaster monitoring value, wherein the pre-flood disaster monitoring calculation algorithm is: In the formula, A i is the flood monitoring value before the ith area type, C is the number of area types, area i is the area data of the ith region type, μ i is the average land property data of the i-th regional type; According to the area data of several regional types, the average property data per unit area, the flood disaster loss coefficient and the preset flood disaster loss monitoring calculation algorithm, the flood disaster loss monitoring values ​​of several regional types are obtained, and the flood disaster loss monitoring values ​​of several regional types are accumulated to obtain the total flood disaster loss monitoring value, 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 pre-flood monitoring value is divided by the total flood disaster loss monitoring value to obtain the flood disaster loss rate of the basin to be processed as the flood disaster monitoring result.

8. An air-ground-integrated basin flood disaster monitoring device, characterized in that: include: The first flood disaster element data acquisition module is used to obtain flood disaster element data corresponding to ground monitoring of the basin to be processed within a preset time period; A second flood disaster element data acquisition module is used 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 of drone aerial photography, and obtain the flood disaster element data corresponding to the drone aerial photography, wherein the flood disaster element data corresponding to the drone aerial photography is time-continuous flood disaster element data; the first deep learning model uses the sample flood disaster element data corresponding to the ground monitoring as an input item and the sample flood disaster element data corresponding to the drone aerial photography as an output item for training and constructing a convolutional neural network model; A third flood disaster element data acquisition module is used to input the flood disaster element data corresponding to the drone aerial photography into a preset second deep learning model to perform satellite remote sensing flood disaster element simulation, and obtain flood disaster element data corresponding to satellite remote sensing, wherein the flood disaster element data corresponding to satellite remote sensing is flood disaster element data that is continuous in both time and space; the second deep learning model is a convolutional neural network model constructed by training with the sample flood disaster element data corresponding to the drone aerial photography as input and the sample flood disaster element data corresponding to satellite remote sensing as output; The flood disaster monitoring module is used to perform flood disaster monitoring according to the flood disaster element data corresponding to the satellite remote sensing, and obtain the flood disaster monitoring results of the watershed to be processed.

9. A computer device, characterized in that: include: 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 air-space-ground integrated river basin flood disaster monitoring method as described in any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the air-space-ground integrated river basin flood disaster monitoring method as described in any one of claims 1 to 7.

Images