Agricultural disaster assessment method, device, equipment, medium and product

Abstract

The invention provides an agricultural disaster assessment method and device, equipment, a medium and a product. The method comprises the steps of obtaining a first remote sensing image of a disaster area; extracting feature data of the first remote sensing image, wherein the feature data comprises a vegetation area and / or a water area of the affected area; and analyzing the feature data to obtain a disaster result corresponding to the affected area. According to the invention, automatic assessment can be carried out on agricultural disasters, and the assessment accuracy of the agricultural disasters is improved.

Description

Technical Field

[0001] The present application belongs to the field of information processing technology, and in particular relates to an agricultural disaster assessment method, device, equipment, medium and product. Background Art

[0002] In agricultural production, natural disasters are one of the main factors that restrict production, and their impact on agricultural production is very critical. For example, in the context of climate change, various extreme weather events are likely to increase significantly, leading to more complex and severe natural disasters. Therefore, a quick and accurate assessment of the disaster situation can enable timely formulation of response measures for agricultural production, thereby reducing the adverse effects of different disasters on agricultural production.

[0003] At present, the traditional method of agricultural disaster assessment is mainly based on manual field surveys and manual image recognition. This method not only has high time and labor costs and unstable results, but is also easily affected by subjective factors, resulting in inaccurate judgments on agricultural disaster assessments. Summary of the invention

[0004] The embodiments of the present application provide an agricultural disaster assessment method, device, equipment, medium and product, which can improve the accuracy of agricultural disaster assessment.

[0005] In a first aspect, an embodiment of the present application provides a method for assessing agricultural disasters, comprising:

[0006] Obtaining first remote sensing images of the disaster-affected areas;

[0007] Extracting feature data of the first remote sensing image, the feature data including vegetation areas and / or water areas in the disaster-affected area;

[0008] The characteristic data are analyzed to obtain the disaster results corresponding to the disaster-stricken areas.

[0009] In a second aspect, an embodiment of the present application provides an agricultural disaster assessment device, comprising:

[0010] An acquisition module, used for acquiring a first remote sensing image of the disaster-stricken area;

[0011] An extraction module, used to extract feature data of the first remote sensing image, the feature data including vegetation areas and / or water areas in the disaster-stricken area;

[0012] The analysis module is used to analyze the characteristic data and obtain the disaster results corresponding to the disaster-stricken area.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, the device comprising:

[0014] a processor and a memory storing computer program instructions;

[0015] When the processor executes the computer program instructions, it is used to execute the agricultural disaster assessment method of the first aspect.

[0016] In a fourth aspect, an embodiment of the present application provides a computer storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the agricultural disaster assessment method of the first aspect described above is implemented.

[0017] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when processed by a processor, implements the agricultural disaster assessment method of the first aspect.

[0018] The agricultural disaster assessment method, device, equipment, medium and product disclosed in the embodiments of the present application can obtain a first remote sensing image of the agricultural disaster area, extract feature data of the first remote sensing image, and analyze the feature data to obtain the disaster results corresponding to the disaster area, thereby realizing automated assessment of agricultural disasters and improving the efficiency and accuracy of agricultural disaster assessments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0020] Figure 1 A flowchart of a method for assessing agricultural disasters provided in accordance with an embodiment of the present application.

[0021] Figure 2 A schematic diagram of an agricultural disaster assessment device provided in accordance with an embodiment of the present application.

[0022] Figure 3 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0024] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0025] In agricultural production, common agricultural disasters include natural disasters, disasters caused by pests, birds and animals, and disasters caused by human factors. Natural disasters include drought, flood, soil erosion, excessive rain and insufficient sunlight, typhoons, etc. caused by bad weather. Pests, birds and animals disasters include various pests, birds, rodents, etc. Human factors such as improper farming that damages the soil structure, or the harm caused by the use of large amounts of chemical pesticides, improper use of drugs, and human trampling. Agricultural meteorological disasters are disasters caused to agriculture by unfavorable meteorological conditions, such as heat damage, freezing damage, frost, tropical crop cold damage and low temperature cold damage caused by temperature factors, and drought, floods, snow damage and hail damage caused by moisture factors. The above different types of disasters will have a huge impact on agricultural production, so a quick and accurate assessment of the disaster situation is the key to formulating agricultural production response measures.

[0026] At present, the traditional method of agricultural disaster assessment is mainly based on manual field surveys and manual image recognition. This method not only has high time and labor costs and unstable results, but is also easily affected by subjective factors, resulting in inaccurate judgments on agricultural disaster assessments.

[0027] In order to solve the above problems, the embodiments of the present application propose an agricultural disaster assessment method, device, equipment, medium and product. By extracting the feature data of the first remote sensing image and analyzing the feature data, the disaster results corresponding to the disaster-stricken area can be obtained, thereby realizing automated assessment of agricultural disasters, improving the efficiency and accuracy of agricultural disaster assessments, and thus facilitating the timely formulation of corresponding agricultural disaster measures and minimizing the adverse effects of agricultural disasters on agriculture.

[0028] like Figure 1 As shown, the embodiment of the present application provides an agricultural disaster assessment method, comprising:

[0029] S110: Acquire a first remote sensing image of the disaster-stricken area.

[0030] Here, the first remote sensing image of the disaster-stricken area is the remote sensing image data of the disaster-stricken area. The remote sensing image data can be collected by satellite or by drone, and then transmitted via the Internet. Therefore, the first remote sensing data of the disaster-stricken area can be easily obtained.

[0031] S120: Extracting feature data of the first remote sensing image, where the feature data includes vegetation areas and / or water areas in the disaster-stricken area.

[0032] Based on the acquired first remote sensing image of the disaster-stricken area, feature data of the first remote sensing image can be extracted. Here, semantic segmentation technology can be used to analyze and infer the pixels of the image in the first remote sensing data to extract feature data of vegetation areas and / or waters in the disaster-stricken area.

[0033] S130: Analyze the characteristic data to obtain the disaster results corresponding to the disaster-stricken area.

[0034] Here, the disaster result can be the disaster type and disaster level of the affected area. The disaster type can be drought and flood disasters caused by bad weather, or freezing disasters and heat disasters caused by temperature, or damage caused by pests, birds and animals, such as various pests, birds and rodents. The disaster level can be a disaster level classification obtained by comprehensively evaluating the affected area and economic losses, and can often be divided into: crop failure, extremely serious disaster, very serious disaster, serious disaster, moderate disaster and mild disaster.

[0035] After obtaining the characteristic data, the characteristic data can be input into a pre-trained neural network model, which is conducive to the neural network model to analyze the characteristic data and obtain the disaster results corresponding to the disaster-stricken area. The neural network model can establish an error signal between the expected output of the training sample and the actual output of the network, and correct the weights and thresholds in the back propagation according to this error signal, and repeatedly input the training sample into the neural network model until the error signal is less than the specified accuracy. Here, the specific neural network model selected is not limited, for example, the Back Propagation neural network model can be selected. Here, the data of the training sample can also be composed of multiple dimensions, such as selecting topography, precipitation, drainage capacity, climate and other quantities related to agricultural disasters.

[0036] In this embodiment, by acquiring a first remote sensing image of the disaster-stricken area and extracting feature data therefrom, and finally analyzing the feature data to obtain the disaster results corresponding to the disaster-stricken area, a reasonable and automated assessment of agricultural disasters can be made based on remote sensing images, thereby overcoming the problems of low accuracy and high cost of traditional manual agricultural disaster assessments.

[0037] In some embodiments, the disaster result includes the disaster type of the disaster-affected area, and the characteristic data is analyzed to obtain the disaster result corresponding to the disaster-affected area, including:

[0038] When it is determined that the drought value of the vegetation area is greater than a preset drought threshold, it is determined that the disaster type corresponding to the disaster-stricken area is drought.

[0039] Here, the disaster result may be a disaster type, and the disaster type is the type of agricultural disaster, such as drought and flood disasters caused by weather, heat and frost disasters caused by temperature, or insect disasters caused by diseases, insects, birds and animals.

[0040] Therefore, when analyzing the characteristic data, here, the characteristic data can be selected to be input into the neural network model for analysis, and the neural network model can be trained based on training samples of dimensions such as topography, precipitation, drainage capacity, and climate. Therefore, after the characteristic data is input into the neural network model for analysis, the neural network model can obtain the possible disaster type of the disaster-stricken area based on the calculation of the above different dimensions, and obtain different characteristic values ​​based on the possible disaster type, which can reflect the degree of disaster in the disaster-stricken area.

[0041] For example, when the neural network model analyzes that a drought may occur in a certain agricultural area A, the drought value of the vegetation area will be calculated. By comparing the drought value with the preset drought threshold, the disaster type or disaster level in the affected area can be determined.

[0042] Exemplarily, when the drought value is greater than a preset drought threshold, it is determined that the disaster type of the disaster-stricken area is drought, that is, the disaster-stricken area is currently in a drought situation. Furthermore, the preset drought threshold can also be divided into a first drought threshold, a second drought threshold, a third drought threshold...an Nth drought threshold, etc. Based on the comparison of different drought values ​​with the divided Nth drought threshold, the disaster degree of the disaster-stricken area can be obtained. For example, when the drought value is greater than the first drought threshold, it indicates that the disaster-stricken area is in a drought and the disaster level is a mild disaster. When the drought value is greater than the second drought threshold, it indicates that the disaster-stricken area is in a drought and the disaster level is a moderate disaster. By analogy, the disaster level of the disaster-stricken area can be obtained.

[0043] When it is determined that the water volume of the water area is greater than a preset water area threshold, the disaster type corresponding to the disaster-stricken area is determined to be waterlogging.

[0044] When the neural network model analyzes that a certain agricultural area A may suffer from waterlogging, the neural network model will calculate the water volume of the water area. By comparing the water volume with the preset water area threshold, the disaster type or disaster level of the affected area can be determined. When the water volume is greater than the preset water area threshold, the disaster type corresponding to the affected area is determined to be waterlogging, that is, the affected area is currently experiencing waterlogging. Furthermore, the preset water area threshold can also be divided into a first preset water area threshold, a second preset water area threshold...Nth preset water area threshold, and the disaster level is obtained based on the comparison results of the water volume with different thresholds.

[0045] In this embodiment, when the disaster results include disaster types, by calculating the drought value of the vegetation area and the water volume of the water area, and determining the disaster type by comparing the drought value with the preset drought threshold, and by comparing the water volume with the preset water area threshold, the disaster type of the disaster area can be obtained quickly and accurately, thereby improving the accuracy and efficiency of disaster assessment.

[0046] In some embodiments, after analyzing the characteristic data to obtain the disaster result corresponding to the disaster-affected area, the method further includes:

[0047] A second remote sensing image of the disaster-stricken area is obtained, wherein the second remote sensing image is collected after disaster relief measures are taken in the disaster-stricken area; the second remote sensing image is input into a pre-trained evaluation model to obtain an evaluation result of the disaster relief measures.

[0048] After obtaining the disaster results corresponding to the disaster-stricken area based on the first remote sensing image, a second remote sensing image of the disaster-stricken area can be obtained. The second image is collected after disaster relief measures are taken in the disaster-stricken area. Here, the second remote sensing image can also be obtained by shooting with a satellite or a drone. The evaluation result can be an evaluation of whether the disaster relief measures are effective or whether the scope of the impact of agricultural disasters has been reduced. Therefore, when constructing an evaluation model, it can be constructed based on a deep learning model for the real scene of the actual disaster-stricken area based on the oblique photography data of the above-mentioned satellite or drone. By inputting the second remote sensing image into the evaluation model, an accurate evaluation result of the disaster relief measures can be obtained.

[0049] It is conceivable that after the disaster result of the disaster-stricken area is determined, corresponding disaster relief measures will be taken. For example, when the disaster result is determined that the disaster type of the disaster area is drought, disaster relief measures such as sprinkling and irrigation may be taken in the agricultural disaster area; when the disaster result is determined that the disaster type of the disaster area is waterlogging, measures such as dredging and timely drainage of waterways in the agricultural disaster area may be taken. Therefore, when the second remote sensing image is input into the evaluation model, an evaluation result of whether the sprinkling and irrigation are appropriate or whether the drainage is timely can be obtained, so as to take further measures to reduce the adverse effects of agricultural disasters.

[0050] In some examples, when evaluating disaster relief measures, while obtaining the second remote sensing image, it is also possible to obtain data such as the public's evaluation of the disaster situation and disaster relief measures based on the Internet, the government's public report on the disaster situation and disaster relief measures, or the media's real report on the disaster situation, and input the above images and data into a pre-trained evaluation model to conduct a comprehensive evaluation of the disaster relief measures. Here, the evaluation model can be trained based on the training samples of the above images and data.

[0051] In this embodiment, by collecting a second remote sensing image after disaster relief measures are taken and inputting the second remote sensing image into a pre-trained evaluation model, it is possible to evaluate the disaster relief measures after an agricultural disaster, thereby obtaining an evaluation result of the disaster relief measures and providing a strong basis for future agricultural disaster prevention and mitigation.

[0052] In some embodiments, step S120 extracting feature data of the first remote sensing image includes:

[0053] The first remote sensing image is divided into regions to obtain at least one detection region; and feature data of each detection region in the first remote sensing image is extracted.

[0054] When extracting the feature data of the first remote sensing image, the first remote sensing image can be divided into regions to obtain at least one detection area. For example, equidistant grid division can be selected to divide the first remote sensing image into different grids, so that each grid is used as a detection area to extract feature data. Here, the feature data of each detection area is summarized and finally analyzed to obtain the disaster results.

[0055] In this embodiment, by dividing the first remote sensing image into regions to obtain at least one detection area and extracting feature data from each detection area separately, the accuracy of feature data when extracting the first remote sensing image can be improved, thereby improving the assessment results of agricultural disaster-stricken areas.

[0056] In some embodiments, after acquiring the first remote sensing image of the disaster-stricken area, the method further includes:

[0057] The first remote sensing image is processed using a region growing algorithm to obtain the target contour of the disaster-stricken area.

[0058] After acquiring the first remote sensing image, the first remote sensing image can be processed by a region growing algorithm to obtain the target contour of the disaster area. Here, the region growing algorithm is an algorithm that can merge pixels with similar properties to form a target contour. For example, the pixels located in the disaster area in the first remote sensing image may have similar grayscale values. In actual operation, a seed point of a target grayscale value is pre-set, and the region growing algorithm can connect points with similar grayscale values ​​based on the seed point to obtain the target contour.

[0059] In this embodiment, by using a region growing algorithm to obtain the target contour of the disaster-stricken area, the specific scope of the disaster-stricken area can be obtained, which can provide beneficial assistance for the implementation of disaster relief measures.

[0060] In some embodiments, before using a region growing algorithm to process the first remote sensing image to obtain a target contour of the disaster-stricken area, the method further includes:

[0061] The first remote sensing image is preprocessed to obtain a preprocessed first remote sensing image.

[0062] Extracting feature data of the first remote sensing image, including:

[0063] Extract feature data of the preprocessed first remote sensing image.

[0064] Before using the region growing algorithm to process the first remote sensing image to obtain the target contour of the disaster-stricken area, the first remote sensing image can also be preprocessed to obtain a preprocessed first remote sensing image. Here, the purpose of preprocessing the first remote sensing image is to enable the first remote sensing image to clearly reflect the specific conditions of the disaster-stricken area, thereby facilitating the subsequent extraction of feature data from the preprocessed first remote sensing image.

[0065] In some examples, preprocessing the first remote sensing image includes performing at least one of the following processing methods on the remote sensing image: orthorectification, image registration, atmospheric correction, image fusion, mosaicking, and cropping.

[0066] Orthorectification is generally performed by selecting some ground control points on the image and using the acquired digital elevation model data within the image range to correct the image for tilt and projection errors.

[0067] Image registration is the process of superimposing two or more images from different sources, taken at different times and angles. The image registration process spatially aligns the matching points between the two or more images from different sources, taken at different times and angles, thereby reducing the error between the image and the real environment.

[0068] Atmospheric correction eliminates the radiation error caused by atmospheric influence, thereby improving the classification accuracy of different objects in the image.

[0069] Image fusion refers to the processing of image data about the same target collected by multiple source channels, extracting the beneficial information in each channel to the maximum extent and improving the spatial resolution and spectral resolution of the original image.

[0070] Mosaicing means that when the study area exceeds the range covered by a single image, two or more images need to be stitched together to form one or a series of larger images covering the entire area.

[0071] Cropping means cutting the image when it is too large.

[0072] In this embodiment, the accuracy of disaster results for agricultural disaster-stricken areas can be improved by preprocessing the first remote sensing image to obtain a preprocessed first remote sensing image and extracting feature data from the preprocessed first remote sensing image.

[0073] In some embodiments, before acquiring the first remote sensing image, the method further includes:

[0074] Acquire an original remote sensing image including an agricultural coverage area; compare the original remote sensing image with an agricultural disaster-stricken image of the agricultural coverage area in a database; and when the original remote sensing image matches the agricultural disaster-stricken image in the database, determine that the agricultural coverage area is a disaster-stricken area and determine that the original remote sensing image is a first remote sensing image.

[0075] Since satellites or drones often take different remote sensing images periodically, when the original remote sensing image of the agricultural coverage area is obtained, the original remote sensing image can be compared with the agricultural disaster image in the database. When the original remote sensing image and the agricultural disaster image match, it means that the agricultural coverage area is in the situation of agricultural disaster. Therefore, the agricultural coverage area is the disaster area, and the original remote sensing image is the first remote sensing image that can be used for agricultural disaster assessment.

[0076] In this embodiment, by comparing the original remote sensing image with the agricultural disaster image, it is possible to determine whether the agricultural coverage area is affected by the disaster, and the agricultural disaster area can be discovered in time, reducing the subjectivity and instability of manual evaluation.

[0077] like Figure 2 As shown, the embodiment of the present application provides an agricultural disaster assessment device, comprising:

[0078] Acquisition module 201, for acquiring a first remote sensing image of the disaster area.

[0079] The extraction module 202 is used to extract feature data of the first remote sensing image, where the feature data includes vegetation areas and / or water areas in the disaster-stricken area.

[0080] The analysis module 203 is used to analyze the characteristic data to obtain the disaster results corresponding to the disaster-stricken area.

[0081] In some embodiments, the disaster result includes the disaster type of the affected area, and the extraction module can be specifically used to:

[0082] When it is determined that the drought value of the vegetation area is greater than a preset drought threshold, it is determined that the disaster type corresponding to the disaster-stricken area is drought.

[0083] When it is determined that the water volume of the water area is greater than a preset water area threshold, the disaster type corresponding to the disaster-stricken area is determined to be waterlogging.

[0084] In some embodiments, the acquisition module 201 may also be used to:

[0085] A second remote sensing image of the disaster-stricken area is acquired, wherein the second remote sensing image is acquired after disaster relief measures are taken in the disaster-stricken area.

[0086] The second remote sensing image is input into a pre-trained evaluation model to obtain the evaluation results of the disaster relief measures.

[0087] In some embodiments, the extraction module may be specifically used to:

[0088] The first remote sensing image is divided into regions to obtain at least one detection region.

[0089] Extract feature data of each detection area in the first remote sensing image.

[0090] In some embodiments, the apparatus further includes a processing module, which may be specifically configured to:

[0091] The first remote sensing image is processed using a region growing algorithm to obtain the target contour of the disaster-stricken area.

[0092] In some embodiments, the extraction module may also be used to:

[0093] Preprocessing the first remote sensing image to obtain a preprocessed first remote sensing image;

[0094] Extract feature data of the preprocessed first remote sensing image.

[0095] The device of the above embodiment is used to implement the corresponding agricultural disaster assessment method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0096] Figure 3A schematic diagram of the hardware structure of an electronic device provided in an application embodiment.

[0097] The electronic device 300 may include a processor 301 and a memory 302 storing computer program instructions.

[0098] Specifically, the processor 301 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0099] The memory 302 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 302 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 302 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 302 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 302 is a non-volatile solid-state memory.

[0100] In certain embodiments, memory 302 includes a read-only memory (ROM). The ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or flash memory, or a combination of two or more of the above, where appropriate.

[0101] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to the first aspect of the present application.

[0102] The processor 301 reads and executes the computer program instructions stored in the memory 302 to implement any one of the agricultural disaster assessment methods in the above embodiments.

[0103] In one example, the electronic device may further include a communication interface 303 and a bus 310. Figure 3The processor 301, the memory 302, and the communication interface 303 are connected via a bus 310 and communicate with each other.

[0104] The communication interface 303 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0105] Bus 310 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 310 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0106] The electronic device of the above embodiment is used to implement the corresponding agricultural disaster assessment method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0107] In addition, in combination with the agricultural disaster assessment method in the above embodiment, the present application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any agricultural disaster assessment method in the above embodiment is implemented.

[0108] In addition, in combination with the agricultural disaster assessment method in the above embodiment, the present application embodiment can provide a computer program product to implement. When the computer program product instructions are executed by a processor of an electronic device, any agricultural disaster assessment method in the above embodiment is implemented.

[0109] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0110] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0111] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or devices based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0112] The above reference is according to the method of the embodiment of the present application, the flow chart of the device (device) and the computer program product and / or the block diagram described various aspects of the present application.It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram.Such a processor can be but is not limited to a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.

[0113] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described devices, modules and units can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application.

Claims

1. A method for assessing agricultural disasters, characterized in that: include: Obtaining first remote sensing images of the disaster-stricken area; Extracting feature data of the first remote sensing image, the feature data including vegetation areas and / or water areas in the disaster-stricken area; The characteristic data are analyzed to obtain disaster results corresponding to the disaster-stricken area.

2. The agricultural disaster assessment method according to claim 1, characterized in that: The disaster result includes the disaster type of the disaster-stricken area. The analysis of the characteristic data to obtain the disaster result corresponding to the disaster-stricken area includes: When it is determined that the drought value of the vegetation area is greater than a preset drought threshold, determining that the disaster type corresponding to the disaster-stricken area is a drought disaster; When it is determined that the water volume of the water area is greater than a preset water area threshold, it is determined that the disaster type corresponding to the disaster-stricken area is a waterlogging disaster.

3. The agricultural disaster assessment method according to claim 1, characterized in that: After analyzing the characteristic data to obtain the disaster result corresponding to the disaster-stricken area, the method further includes: Acquiring a second remote sensing image of the disaster-stricken area, wherein the second remote sensing image is acquired after disaster relief measures are taken in the disaster-stricken area; The second remote sensing image is input into a pre-trained evaluation model to obtain an evaluation result of the disaster relief measures.

4. The agricultural disaster assessment method according to claim 1, characterized in that: The extracting feature data of the first remote sensing image includes: Performing region division on the first remote sensing image to obtain at least one detection region; Extract feature data of each detection area in the first remote sensing image.

5. The agricultural disaster assessment method according to claim 1, characterized in that: After acquiring the first remote sensing image of the disaster-stricken area, the method further includes: The first remote sensing image is processed using a region growing algorithm to obtain a target outline of the disaster-stricken area.

6. The agricultural disaster assessment method according to claim 5, characterized in that: Before processing the first remote sensing image using a region growing algorithm to obtain a target outline of the disaster-stricken area, the method further includes: Preprocessing the first remote sensing image to obtain a preprocessed first remote sensing image; The extracting feature data of the first remote sensing image includes: Extracting feature data of the preprocessed first remote sensing image.

7. An agricultural disaster assessment device, characterized in that: include: An acquisition module, configured to acquire a first remote sensing image of the disaster-stricken area; an extraction module, configured to extract feature data of the first remote sensing image, wherein the feature data includes vegetation areas and / or water areas in the disaster-stricken area; The analysis module is used to analyze the characteristic data to obtain the disaster results corresponding to the disaster-stricken area.

8. An electronic device, characterized in that: The device includes: a processor, and a memory storing computer program instructions; The processor reads and executes the computer program instructions to implement the agricultural disaster assessment method according to any one of claims 1 to 6.

9. A readable storage medium, characterized in that: The readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the agricultural disaster assessment method according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is processed by a processor, the method for assessing agricultural disasters according to any one of claims 1 to 6 is implemented.

Images