WO2022198744A1 - 农业险情数据评估方法、装置、计算机设备及存储介质 - Google Patents

农业险情数据评估方法、装置、计算机设备及存储介质 Download PDF

Info

Publication number
WO2022198744A1
WO2022198744A1 PCT/CN2021/090311 CN2021090311W WO2022198744A1 WO 2022198744 A1 WO2022198744 A1 WO 2022198744A1 CN 2021090311 W CN2021090311 W CN 2021090311W WO 2022198744 A1 WO2022198744 A1 WO 2022198744A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
remote sensing
disaster
sensing data
information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2021/090311
Other languages
English (en)
French (fr)
Inventor
高扬磊
汪文娟
任称心
赵倩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2022198744A1 publication Critical patent/WO2022198744A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Forestry; Mining
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Definitions

  • the present application relates to the field of data processing, and in particular, to a method, device, computer equipment and storage medium for evaluating agricultural danger data.
  • An agricultural hazard data assessment method comprising:
  • Receive the sampled disaster damage assessment result sent by the designated terminal obtain sampled spectral data corresponding to the sampled disaster damage assessment result from the aerial photography remote sensing data, and determine according to the sampled spectral data and the sampled disaster damage assessment result Disaster damage level threshold;
  • the spectral data of the satellite remote sensing data is evaluated according to the disaster damage level threshold, so as to generate a disaster damage evaluation result of the designated area.
  • An agricultural danger data evaluation device comprising:
  • the data module is used to obtain meteorological data and satellite remote sensing data of the designated area;
  • a preliminary disaster damage assessment result module configured to generate a preliminary disaster damage assessment result according to the meteorological data and the satellite remote sensing data
  • a sampling module configured to set several sampling points in the designated area according to the preliminary disaster damage assessment result
  • the sampling evaluation result module is used to obtain the field survey data of the sampling point and the aerial photography remote sensing data of the designated area and send them to the designated terminal, so that the designated terminal can perform a Disaster damage analysis to obtain sampling disaster damage assessment results;
  • a disaster damage level threshold module configured to receive the sampled disaster damage assessment result sent by the designated terminal, and obtain sampled spectral data corresponding to the sampled disaster damage assessment result from the aerial photographic remote sensing data, and according to the sampled spectrum Data and sample disaster damage assessment results to determine the disaster damage level threshold;
  • a disaster damage assessment result module configured to evaluate the spectral data of the satellite remote sensing data according to the disaster damage grade threshold, so as to generate a disaster damage assessment result of the designated area.
  • a computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer-readable instructions :
  • Receive the sampled disaster damage assessment result sent by the designated terminal obtain sampled spectral data corresponding to the sampled disaster damage assessment result from the aerial photography remote sensing data, and determine according to the sampled spectral data and the sampled disaster damage assessment result Disaster damage level threshold;
  • One or more readable storage media storing computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the agricultural hazard data assessment method as described above.
  • the above-mentioned agricultural danger data assessment method, device, computer equipment and storage medium can obtain meteorological data and satellite remote sensing data in a designated area; A preliminary understanding of the distribution and the degree of disaster damage can clearly guide the survey site, saving labor costs and time costs. According to the preliminary disaster damage assessment results, several sampling points are set in the designated area, which reduces unnecessary surveys of survey sites. Obtain the field survey data of the sampling point and the aerial photographic remote sensing data of the designated area and send them to the designated terminal, so that the designated terminal can perform disaster damage analysis according to the field investigation data and the aerial photographic remote sensing data to obtain the sampling disaster damage.
  • the unmanned aerial vehicle can be used to survey the harsh terrain, and the high resolution of the unmanned aerial vehicle can obtain a clearer picture of the disaster-damaged land.
  • Receive the sampled disaster damage assessment result sent by the designated terminal obtain sampled spectral data corresponding to the sampled disaster damage assessment result from the aerial photography remote sensing data, and determine according to the sampled spectral data and the sampled disaster damage assessment result
  • Disaster damage level threshold improve the accuracy of the disaster damage level threshold; according to the disaster damage level threshold, the spectral data of the satellite remote sensing data is evaluated to generate the disaster damage assessment result of the designated area, which can be automatically based on the disaster damage level threshold.
  • the grading threshold determines the hazard level of the disaster-damaged plot, reducing labor and time costs.
  • the present application reduces the difficulty of collecting agricultural danger data, reduces the cost of agricultural danger survey and damage assessment, and improves the accuracy of disaster damage assessment.
  • Fig. 1 is a schematic diagram of an application environment of the agricultural danger data evaluation method in an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a method for evaluating agricultural danger data in an embodiment of the present application
  • FIG. 3 is a schematic diagram of the use of satellite remote sensing data of different resolutions and an unmanned aerial vehicle in an embodiment of the present application;
  • FIG. 4 is a schematic diagram of the distribution of the growth status of rice in an embodiment of the present application.
  • FIG. 5 is a schematic diagram of phenological characteristics corresponding to spectral information of rice in different periods in an embodiment of the present application
  • FIG. 6 is a schematic diagram of the specific distribution of sampling routes and sampling points of field investigation in an embodiment of the present application.
  • FIG. 7 is a schematic diagram of the evaluation result of the disaster damage level at the plot level in an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a device for evaluating agricultural danger data in an embodiment of the present application.
  • FIG. 9 is a schematic diagram of a computer device in an embodiment of the present application.
  • the agricultural danger data evaluation method provided in this embodiment can be applied in the application environment as shown in FIG. 1 , in which the client terminal communicates with the server terminal.
  • clients include but are not limited to various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices.
  • the server can be implemented by an independent server or a server cluster composed of multiple servers.
  • a method for evaluating agricultural danger data is provided, and the method is applied to the server in FIG. 1 as an example for description, including the following steps:
  • the designated area may be a large area, such as the North China Plain; or a small area, such as the farmland area of an agricultural county.
  • meteorological data and satellite remote sensing data of a designated area can be automatically acquired according to a preset time.
  • Meteorological data includes, but is not limited to, rainfall, sunshine, temperature and wind direction and speed in a designated area within a preset time.
  • Satellite remote sensing data contains satellite images and spectral remote sensing information within a specified area. Satellite remote sensing data comes from satellites covering a designated area, and satellite remote sensing data with different resolutions are used for different purposes.
  • Figure 3 shows satellite remote sensing data at different resolutions and the use of drones.
  • Data source refers to data sources with different resolutions, and phase refers to the sampling period. As shown in Figure 3, in an example, the data source GF-6 can collect satellite remote sensing data with a resolution of 2 meters. The sampling time includes August 23 and August 27. The satellite remote sensing data is used for rice identification and Flood Assessment.
  • step S10 the obtaining meteorological data and satellite remote sensing data of the designated area includes:
  • the initial satellite remote sensing data can be unprocessed satellite images and unprocessed spectral remote sensing information.
  • the initial satellite remote sensing data can be collected before the disaster, the early stage, the middle stage, and the later stage of the disaster.
  • the initial satellite remote sensing data refers to the unprocessed satellite remote sensing data.
  • S102 Process the initial satellite remote sensing data according to the preprocessing method to generate preprocessing satellite remote sensing data that meets a preset processing standard, where the preset processing standard corresponds to the preprocessing method.
  • a preprocessing method for processing the initial satellite remote sensing data is preset, and after the initial satellite remote sensing data is processed by the preset preprocessing method, preprocessing satellite remote sensing data that meets the preset processing standard is generated.
  • the preset preprocessing methods include, but are not limited to, geometric correction, orthorectification, atmospheric correction, cloud removal and fog removal, and stitching and fusion. Among them, geometric correction, orthorectification, and atmospheric correction can standardize the preprocessing satellite remote sensing data, which is beneficial to extract spectral information.
  • the main reason for removing clouds and fog is that it may exist in the remote sensing data because the crops cannot be clearly seen due to the occlusion of clouds and fog. The purpose of removing clouds and fog is to remove noise.
  • Splicing fusion is based on the fusion of remote sensing data of other periods and the data of this period, and spliced into crops in a designated area.
  • Preprocessed satellite remote sensing data contains preprocessed satellite images and spectral remote sensing information of a specified area.
  • the preset processing standard corresponds to the preprocessing method one-to-one. For example, the standard of the preprocessing method for removing clouds and fogging can be so that crops can be clearly seen.
  • the preset test index may be cloud content
  • the size of cloud content may be preset as a usability test index for testing the preprocessed satellite remote sensing data.
  • Image recognition can be performed on satellite images in a designated area to obtain the number of pixels in the satellite images, and the cloud content can be judged according to the number of pixels. If the cloud content is higher than the preset cloud content threshold, it means that the crops in the satellite image area of this period are too obscured by clouds and fog, and the preprocessed satellite remote sensing data in this period is unavailable. If the cloud content is lower than or equal to the preset cloud content threshold, it means that the crops in the satellite image area of this period are less occluded by clouds and fog, and the pre-processed satellite remote sensing data of this period is available.
  • the preprocessed satellite remote sensing data that has passed the usability test is determined as satellite remote sensing data, and the satellite remote sensing data includes satellite images and other relevant information that have passed the usability test in the designated area.
  • the initial satellite remote sensing data of the specified area at a specified time is obtained, the initial satellite remote sensing data is processed according to the preprocessing method, and the preprocessing satellite remote sensing data satisfying the preset processing standard is generated.
  • the preset processing standard corresponds to the preprocessing method, which improves the accuracy of satellite remote sensing data.
  • the availability of the preprocessed satellite remote sensing data is checked according to a preset test index, and the preprocessed satellite remote sensing data that has passed the availability check is determined as the satellite remote sensing data, thereby improving the availability of the satellite remote sensing data.
  • the preliminary assessment information of the meteorological disaster situation is generated according to the meteorological data and the administrative division information of the designated area.
  • the preliminary assessment information of the meteorological disaster situation includes that the flood level of XX area in XX county is medium.
  • the preliminary assessment information of remote sensing disaster situation includes that the crops in XX area of XX county are in good condition.
  • the crop distribution information includes: XX1 county, rice, 2000 mu; XX2 county, rice, 1800 mu; . . .
  • the preliminary disaster damage assessment results are generated according to the preliminary assessment information of meteorological disasters, the preliminary assessment information of remote sensing disasters and the distribution information of crops.
  • step S20 the generating a preliminary disaster damage assessment result according to the meteorological data and the satellite remote sensing data includes:
  • the preliminary meteorological disaster assessment information includes the preliminary disaster damage degree and preliminary disaster damage scope of each administrative region.
  • the disaster situation data of a number of designated disaster damage factors can be obtained from the meteorological data according to the preset dimensions, the preliminary disaster damage degree and the preliminary disaster damage scope can be preliminarily determined according to the disaster situation data and the administrative division information, and the preliminary meteorological disaster situation assessment information can be generated.
  • the disaster data can be represented as:
  • the administrative division information of the designated area may be obtained through a GPS positioning system or other means.
  • Specified disaster factors include, but are not limited to, rainfall, sunshine, temperature, and wind direction and speed.
  • Preset dimensions include but are not limited to continuous days, cumulative values, cumulative anomalies, extremely high values, extremely low values, and average values.
  • rainfall can be counted through the six dimensions of continuous days, cumulative value, cumulative anomaly, extremely high value, extremely low value and average value.
  • the cumulative anomaly refers to the accumulation of anomalies, and the anomaly is used to represent the difference between the rainfall in a certain period (such as a day) and the average rainfall in a long-term period (such as a year).
  • the preliminary assessment information of meteorological disasters includes preliminary disaster damage degree and preliminary disaster damage scope.
  • designated weather elements are selected from the meteorological data as disaster damage factors for judging the degree of crop damage, and according to preset dimensions, disaster situation data of disaster failure factors are selected from different dimensions.
  • the area where the disaster is distributed is matched in the meteorological data. Since the sensitivity of crops in different regions to disasters is different, it is necessary to consult local agricultural experts to obtain the standard of flood or drought for local crops. According to this standard, the level threshold of the degree of disaster damage is customized, and floods or droughts are divided into six levels, including but not limited to no disaster, mild disaster, mild to moderate disaster, moderate disaster, moderate to severe disaster, and severe disaster. Then, the disaster damage degree of the designated area is evaluated according to the disaster situation data of different dimensions of the disaster damage factor and the grade threshold of the disaster damage degree. Obtain the level of disaster damage in the designated area, and obtain the preliminary assessment information of crops from the meteorological point of view.
  • the preliminary assessment of the degree of disaster damage can also be carried out in combination with the local geographical conditions.
  • the remote sensing disaster preliminary assessment information includes the growing status of crops distribution range.
  • the spectral data of crops in a designated area is obtained from satellite remote sensing data, and preliminary assessment of the growing conditions of crops is performed according to the spectral data to generate preliminary remote sensing disaster assessment information.
  • the spectral data needs to be calculated and processed by the normalized vegetation index.
  • the normalized vegetation index (NDVI) can well reflect the strength of vegetation information and is an important indicator for monitoring vegetation growth.
  • the normalized vegetation index (NDVI) can be calculated from the spectral data of crops, which includes the reflectance of crops in the near-infrared and red light bands.
  • the preliminary assessment information of remote sensing disaster situation includes the distribution range of crop growth condition.
  • the growth status of crops can be divided into five dimensions: good, better, normal, poor, and poor.
  • Figure 4 it is the distribution map of the growth status of rice in Guanghan City, Sichuan province on June 30, in which the growth status is good, good, normal, poor, and poor, accounting for 4.5%, 16.26%, and 4.5%, respectively. 67.76%, 7.12%, 4.36%.
  • the spectral information of crops represents the phenological phenomenon that crops produce different characteristics to the spectrum during different growth stages such as germination, leaf expansion, flowering, leaf discoloration, and defoliation.
  • the spectral information of each crop in different phenological periods has been gradually accumulated, and a spectral information database of crops such as rice, corn, and wheat has been established, which can be used for automatic and rapid identification of crops in disaster-stricken areas.
  • Crop spectral information is the color of crops in satellite remote sensing data at different growth stages.
  • the spectral information of crops in a designated area is obtained from satellite remote sensing data, and the spectral information of crops is obtained from the spectral information database of crops, and the spectral information of crops in the designated area is compared with the spectral information of crops in the spectral information database of crops. Automatically identify and compare to obtain the type of crops, and then generate the distribution range of crops based on the distribution range of growing conditions according to the type of crops.
  • the preliminary disaster damage assessment result is generated according to the preliminary disaster damage degree and preliminary disaster damage scope of the meteorological disaster preliminary assessment information, the growth state distribution range of the remote sensing disaster preliminary assessment information, and the crop type information and distribution range of the crop distribution information.
  • the preliminary disaster damage assessment result includes preliminary disaster damage degree, preliminary disaster damage scope, growth condition distribution scope, crop type information and distribution scope.
  • the disaster situation data of several designated disaster damage factors is obtained from the meteorological data according to the preset dimensions, the disaster situation data is divided according to the administrative division information of the designated area, and the evaluation is performed to generate a preliminary meteorological disaster situation Assessment information, the preliminary meteorological disaster assessment information includes the preliminary disaster damage degree and preliminary disaster damage scope of each administrative region, and the preliminary disaster damage degree and preliminary disaster damage scope can be automatically and quickly obtained from the meteorological point of view, saving time and labor costs.
  • the remote sensing disaster preliminary assessment information includes the distribution range of the growing condition of the crops , which can automatically and quickly obtain the distribution range of growth conditions from the perspective of satellite remote sensing, saving time and labor costs.
  • Obtain spectral information of crops in the designated area from satellite remote sensing data determine the types of crops according to the spectral information, and generate crop distribution information; combine the preliminary meteorological disaster assessment information, the remote sensing disaster preliminary assessment information and the The crop distribution information is used to generate the preliminary disaster damage assessment result, so as to improve the accuracy of the preliminary disaster damage assessment result.
  • step S203 obtaining spectral information of crops in the designated area from satellite remote sensing data, determining the types of crops according to the spectral information, and generating crop distribution information, including:
  • the spectral information of crops represents the phenological phenomenon that crops produce different characteristics to the spectrum during different growth stages such as germination, leaf expansion, flowering, leaf discoloration, and defoliation.
  • the spectral information of each crop in different phenological periods has been gradually accumulated, and a spectral information database of crops such as rice, corn, and wheat has been established, which can be used for automatic and rapid identification of crops in disaster-stricken areas.
  • Spectral information is the color of crops in satellite remote sensing data at different growth stages.
  • the spectral information of crops in a designated area is obtained from satellite remote sensing data, and the spectral information of crops is obtained from a spectral information database of crops.
  • the multi-temporal spectral information of crops in the satellite remote sensing data in the designated area is compared and identified with the spectral information of different crops in different periods contained in the phenological characteristic database to determine the type of crops. Furthermore, according to the types of crops, on the basis of the distribution range of the growing state, the distribution range of the crops is obtained, and the crop distribution information including the type information and the distribution range of the crops is generated.
  • Multi-temporal phase refers to the fusion of satellite remote sensing data at different times. For example, at the first moment, the position A of the designated area has clouds, but the position B has no clouds; at the second moment, the position B of the designated area has clouds, and the position A has no clouds. After multi-temporal fusion, satellite remote sensing data with neither location A nor location B covered by clouds can be obtained.
  • FIG. 5 is the phenological feature map corresponding to the spectral information of rice in different periods.
  • the data source GF-1 can collect the spectral information of rice with a resolution of 2 meters, the sampling time is June 17, and the phenological feature of rice at this time is water, which is in Water storage transplanting period.
  • the spectral information of crops and the spectral information in the satellite remote sensing data are obtained, the spectral information in the satellite remote sensing data is identified according to the spectral information of the crops, and the distribution information of the crops is generated, and the
  • the crop distribution information includes the type information and distribution range of crops.
  • the type information and distribution range of crops can be obtained automatically and quickly, and the survey area can be clearly guided, saving labor costs and time costs.
  • the spectral data of the crops in the designated area is obtained from the satellite remote sensing data, and the preliminary assessment information of the remote sensing disaster situation is generated by preliminarily evaluating the growth status and disaster damage of the crops according to the spectral data.
  • the preliminary assessment information of remote sensing disaster situation includes the distribution range of the growing condition of crops, including:
  • the spectral data of crops in different bands can be obtained from satellite remote sensing data.
  • Spectral data includes near-infrared and red light bands.
  • S2022 Acquire the reflectivity of the near-infrared band and the reflectivity of the red light band of crops in the designated area, and process the reflectivity of the near-infrared band and the reflection of the red light band through a normalized vegetation index calculation formula rate to obtain the normalized vegetation index of the specified area.
  • NDVI normalized vegetation index
  • the normalized vegetation index (NDVI) can well reflect the strength of vegetation information and is an important indicator for monitoring vegetation growth.
  • the normalized vegetation index (NDVI) can be calculated from the spectral data of crops.
  • NDVI (NIR-R)/(NIR+R)
  • the reflectivity of the band and the reflectivity of the red light band can be used to obtain the normalized vegetation index of crops in the specified area.
  • the disaster damage is preliminarily assessed according to the index range of the normalized vegetation index (NDVI). It also conducts qualitative statistics on the growth status of crops in the designated area in five dimensions: good, good, normal, poor, and poor, to determine the growth status of crops, and generate preliminary assessment information of remote sensing disasters including the distribution range of the growth status.
  • steps S2021-S2023 obtain spectral data in the satellite remote sensing data, the spectral data includes a near-infrared band and a red light band; obtain the reflectivity of the near-infrared band of crops in the designated area, and the red light band
  • the reflectivity of the specified area is obtained by processing the reflectivity of the near-infrared band and the reflectivity of the red light band through the calculation formula of the normalized vegetation index to obtain the normalized vegetation index of the designated area;
  • the index range in which the index is located determines the growth status of the crops, and based on the growth status of the crops, the preliminary assessment information of remote sensing disaster situation is generated.
  • the distribution range of the growing situation saves labor costs and time costs.
  • sampling points can be set according to the preliminary disaster damage degree, preliminary disaster damage scope, growth condition distribution scope, crop type information and distribution scope. At least one sampling point is set for each preliminary disaster damage degree, each growing condition, and each crop type. According to the disaster damage level, the crops at the sampling point were photographed and surveyed on the spot, and the field survey data was obtained.
  • the field survey data refers to the data of the surveyor's on-site survey at the sampling point.
  • Field survey data includes photos, shooting time, location (including latitude and longitude), shooting person, and on-site records.
  • Aerial photography remote sensing data can refer to data obtained through drone aerial photography. Plan the route of the UAV on the mobile APP bird's-eye UAV system, and make the UAV take aerial photos of the crops within the initial disaster damage area along the set route, and you can get the aerial photos and other related information. aerial remote sensing data. Multi-resolution and multiple drone aerial photography can be performed as needed.
  • Designated terminals may refer to computer equipment used by agricultural experts. After the designated terminal receives the field survey data and aerial remote sensing data, agricultural experts can view the field survey data and aerial remote sensing data through the designated terminal, and provide sampling disaster damage assessment results.
  • the damage assessment results of sampling include the damage level of crops.
  • Disaster damage levels include but are not limited to six levels: no disaster, mild disaster, mild to moderate disaster, moderate disaster, moderate to severe disaster, and severe disaster.
  • the remote sensing data of UAV aerial photography includes aerial pictures.
  • the aerial photography remote sensing data includes a panoramic image; the acquiring the field survey data of the sampling point, and acquiring the aerial photography remote sensing data of the designated area, includes:
  • the preset route may refer to the route of the UAV planned on the mobile terminal APP bird's-eye UAV system.
  • the drones take drone aerial photography of crops within the initial disaster damage range along the preset route, and collect several aerial photography real pictures. Among them, multi-resolution and multiple drone aerial photography can be performed as needed.
  • S402. Generate the panoramic image according to the several aerial pictures.
  • the DeepSFM algorithm deep structure-from-motion, deep motion recovery structure
  • the parallel operation of GPU can significantly improve the calculation efficiency of motion structure inference, making the picture more efficient. Stitching speed increased by 50%.
  • the drone collects several aerial photographs according to the preset route, and generates the panoramic image according to the several aerial photographs, so that a high-resolution aerial photograph can be obtained, and the panoramic image is automatically generated, which improves the picture quality. processing speed.
  • sampling spectral data of crops with the same disaster damage level are obtained from aerial remote sensing data, and multiple normalized vegetation indices under the disaster damage level are calculated according to the sampling spectral data of crops with the same disaster damage level.
  • the designated area consists of several parcels.
  • the boundaries of each plot in the designated area are automatically recognized.
  • the same plot can have multiple spectral data, that is, there are multiple normalized vegetation indices.
  • the mean value of the normalized vegetation index of each plot in the designated area is evaluated according to the threshold value of the disaster damage level, and the evaluation result of the disaster damage level of each plot in the designated area is obtained. For example, if the mean value of the Normalized Vegetation Index (NDVI) of a plot in a designated area is greater than the threshold of the severe disaster damage level, the disaster damage level of the plot is evaluated as a severe disaster damage.
  • NDVI Normalized Vegetation Index
  • step S60 evaluating the spectral data of the satellite remote sensing data according to the disaster damage level threshold to generate a disaster damage evaluation result of the designated area, including:
  • satellite remote sensing data includes remote sensing data of several satellites in different periods and different resolutions.
  • the resolution of satellite remote sensing data is selected according to actual needs. For example, when using AI to identify parcel boundaries, high-definition data with a resolution of 0.5 meters is required; if data with a resolution of 10 meters is used, the boundaries of parcels cannot meet the accuracy requirements.
  • the resolution of UAV aerial photography is higher than that of satellite remote sensing. In key areas, high-resolution UAV remote sensing data can be selected.
  • S602. Process the satellite remote sensing data through a preset image recognition algorithm to generate the boundary information of the arable land in the designated area.
  • the preset image recognition algorithm includes an AI image recognition algorithm and a deep learning algorithm.
  • AI image recognition algorithm and deep learning algorithm the boundary of each plot in the designated area is automatically identified, and the boundary information of the cultivated land plot is generated.
  • the area of each cultivated land plot can be calculated according to the boundary information.
  • the disaster damage area can be obtained.
  • a visual report of disaster damage can be made according to the assessment results of the disaster damage area and the disaster damage level. In an example, as shown in Figure 7, it is a map of the assessment results of the disaster damage level at the plot level of a village, in which different disaster damage levels use different color standards, and the area of the plot is marked in each plot.
  • the spectral data of each arable land in the designated area is acquired.
  • the normalized vegetation index (NDVI) of each cultivated land plot in the designated area is calculated. Further, all normalized vegetation index (NDVI) values are counted into each plot, and the mean value of normalized vegetation index (NDVI) of each plot in the designated area is obtained. Furthermore, the spectral data of each cultivated land plot in the designated area is evaluated according to the threshold value of the disaster damage level, and the evaluation result of the disaster damage level of each plot in the designated area is obtained. For example, if the mean value of the Normalized Vegetation Index (NDVI) of a plot in a designated area is greater than the threshold of the severe disaster damage level, the disaster damage level of the plot is evaluated as a severe disaster damage.
  • NDVI Normalized Vegetation Index
  • the satellite remote sensing data of the designated area is obtained, the satellite remote sensing data meets the preset resolution requirements, and the satellite remote sensing data is processed by a preset image recognition algorithm to generate the cultivated land in the designated area block boundary information, extract the spectral data of the cultivated land block from the cultivated land block boundary information, evaluate the spectral data of the cultivated land block according to the disaster damage level threshold, and generate the disaster damage assessment result of the cultivated land block,
  • the disaster damage assessment result of the designated area includes the disaster damage assessment results of several cultivated land plots, and the disaster damage level of the disaster damage plot can be automatically determined according to the disaster damage grade division threshold, thereby reducing labor and time costs.
  • steps S10-S60 by acquiring meteorological data and satellite remote sensing data of a designated area; A preliminary understanding of the distribution and the degree of disaster damage can clearly guide the survey site, saving labor costs and time costs. According to the preliminary disaster damage assessment results, several sampling points are set in the designated area, which reduces unnecessary surveys of survey sites. Obtain the field survey data of the sampling point and the aerial photographic remote sensing data of the designated area and send them to the designated terminal, so that the designated terminal can perform disaster damage analysis according to the field investigation data and the aerial photographic remote sensing data to obtain the sampling disaster damage.
  • the unmanned aerial vehicle can be used to survey the harsh terrain, and the high resolution of the unmanned aerial vehicle can obtain a clearer picture of the disaster-damaged land.
  • Receive the sampled disaster damage assessment result sent by the designated terminal obtain sampled spectral data corresponding to the sampled disaster damage assessment result from the aerial photography remote sensing data, and determine according to the sampled spectral data and the sampled disaster damage assessment result
  • Disaster damage level threshold improve the accuracy of the disaster damage level threshold; according to the disaster damage level threshold, the spectral data of the satellite remote sensing data is evaluated to generate the disaster damage assessment result of the designated area, which can be automatically based on the disaster damage level threshold.
  • the grading threshold determines the hazard level of the disaster-damaged plot, reducing labor and time costs.
  • the present application reduces the difficulty of collecting agricultural danger data, reduces the cost of agricultural danger survey and damage assessment, and improves the accuracy of disaster damage assessment.
  • an apparatus for evaluating agricultural danger data which corresponds one-to-one with the method for evaluating agricultural danger data in the above embodiment.
  • the agricultural danger data evaluation device includes a data module 10 , a preliminary evaluation module 20 , a sampling point determination module 30 , a sampling evaluation module 40 , a disaster damage level threshold determination module 50 and a disaster damage evaluation result module 60 .
  • the detailed description of each functional module is as follows:
  • the data module 10 is used to obtain meteorological data and satellite remote sensing data of a designated area;
  • a preliminary assessment module 20 configured to generate a preliminary disaster damage assessment result according to the meteorological data and the satellite remote sensing data
  • a sampling point determination module 30 configured to set several sampling points in the designated area according to the preliminary disaster damage assessment result
  • the sampling evaluation module 40 is used to obtain the field survey data of the sampling point and the aerial photography remote sensing data of the designated area and send them to the designated terminal, so that the designated terminal can perform a Disaster damage analysis to obtain sampling disaster damage assessment results;
  • a disaster damage level threshold determination module 50 configured to receive the sampled disaster damage assessment result sent by the designated terminal, and obtain sampled spectral data corresponding to the sampled disaster damage assessment result from the aerial photography remote sensing data, according to the Sampling spectral data and sampling disaster damage assessment results to determine the disaster damage level threshold;
  • the disaster damage assessment result module 60 is configured to evaluate the spectral data of the satellite remote sensing data according to the disaster damage grade threshold, so as to generate a disaster damage assessment result of the designated area.
  • the aerial photography remote sensing data includes panoramic images; the aerial photography remote sensing data of the described acquisition of the sampling point and the aerial photography remote sensing data of the designated area are sent to the designated terminal, including:
  • Aerial photographing unit used to collect several aerial photographs according to the preset route by the drone
  • a panoramic image unit configured to generate the panoramic image according to the several aerial pictures.
  • generating a preliminary disaster damage assessment result according to the meteorological data and the satellite remote sensing data includes:
  • the meteorological data unit 201 is configured to obtain disaster situation data of several designated disaster damage factors from the meteorological data according to preset dimensions, divide the disaster situation data according to the administrative division information of the designated area, and perform an evaluation to generate a preliminary meteorological disaster situation Assessment information, the preliminary meteorological disaster assessment information includes the preliminary disaster damage degree and preliminary disaster damage scope of each administrative region;
  • the satellite remote sensing data unit 202 is used to obtain the spectral data of crops in the designated area from the satellite remote sensing data, and to evaluate the growth status of the crops according to the spectral data, and to generate preliminary remote sensing disaster assessment information; the remote sensing disaster preliminary assessment
  • the information includes the distribution range of the growing condition of crops;
  • Crop distribution information unit 203 configured to obtain spectral information of crops in the designated area from satellite remote sensing data, determine the type of crops according to the spectral information, and generate crop distribution information;
  • the preliminary disaster damage assessment result unit 204 is configured to generate the preliminary disaster damage assessment result by combining the meteorological disaster preliminary assessment information, the remote sensing disaster preliminary assessment information and the crop distribution information.
  • the spectral information of the crops in the designated area is obtained from the satellite remote sensing data, the type of the crops is determined according to the spectral information, and the crop distribution information is generated, including:
  • a spectral information unit used to obtain the spectral information of crops and the spectral information in the satellite remote sensing data
  • the spectral information identification unit is configured to identify the spectral information in the satellite remote sensing data according to the crop spectral information, and generate the crop distribution information, where the crop distribution information includes the type information and distribution range of the crops.
  • the spectral data of the crops in the designated area is obtained from the satellite remote sensing data, and the remote sensing disaster situation is generated by preliminarily evaluating the growth and damage of the crops according to the spectral data.
  • Preliminary assessment information includes the distribution range of the growing condition of crops, including:
  • a first acquiring spectral data unit configured to acquire spectral data in the satellite remote sensing data, where the spectral data includes a near-infrared band and a red light band;
  • the normalized vegetation index unit is used to obtain the reflectance of the near-infrared band and the reflectance of the red light band of crops in the designated area, and the reflectance of the near-infrared band and the reflectance of the near-infrared band are processed by the normalized vegetation index calculation formula.
  • the remote sensing disaster situation unit is used to determine the growth status of crops according to the index range in which the normalized vegetation index is located, and generate preliminary remote sensing disaster situation assessment information based on the growth status of the crops, and the remote sensing disaster preliminary assessment information includes the crops.
  • the obtaining meteorological data and satellite remote sensing data of the designated area includes:
  • an initial satellite remote sensing data unit used to obtain initial satellite remote sensing data of the specified area at a specified time
  • a unit for preprocessing satellite remote sensing data configured to process the initial satellite remote sensing data according to the preprocessing method, and generate preprocessing satellite remote sensing data that satisfies a preset processing standard, the preset processing standard corresponding to the preprocessing method;
  • an inspection unit configured to inspect the availability of the preprocessed satellite remote sensing data according to a preset inspection index
  • a satellite remote sensing data unit configured to determine the preprocessed satellite remote sensing data that has passed the usability check as the satellite remote sensing data.
  • the spectral data of the satellite remote sensing data is evaluated according to the disaster damage level threshold to generate the disaster damage assessment result of the designated area, including:
  • a resolution unit for acquiring satellite remote sensing data of the designated area, the satellite remote sensing data meeting preset resolution requirements
  • a boundary information unit configured to process the satellite remote sensing data through a preset image recognition algorithm to generate the boundary information of the arable land in the designated area;
  • a second acquiring spectral data unit configured to extract spectral data of the cultivated land block from the border information of the cultivated land block
  • a disaster damage assessment result unit configured to assess the spectral data of the cultivated land plot according to the disaster damage grade threshold, and generate a disaster damage assessment result of the cultivated land plot, and the disaster damage assessment result of the designated area includes a number of the Disaster damage assessment results of cultivated land plots.
  • Each module in the above-mentioned agricultural danger data evaluation device can be realized in whole or in part by software, hardware and combinations thereof.
  • the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
  • a computer device is provided, and the computer device may be a server, and its internal structure diagram may be as shown in FIG. 9 .
  • the computer device includes a processor, memory, a network interface, and a database connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities.
  • the memory of the computer device includes a readable storage medium, an internal memory.
  • the readable storage medium stores an operating system, computer readable instructions and a database.
  • the internal memory provides an environment for the execution of the operating system and computer-readable instructions in the readable storage medium.
  • the database of the computer equipment is used to store the data involved in the agricultural hazard data evaluation method.
  • the network interface of the computer device is used to communicate with an external terminal through a network connection.
  • the computer readable instructions when executed by a processor, implement a method for evaluating agricultural hazard data.
  • the readable storage medium provided by this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.
  • a computer device comprising a memory, a processor, and computer-readable instructions stored on the memory and executable on the processor, and the processor implements the following steps when executing the computer-readable instructions:
  • Receive the sampled disaster damage assessment result sent by the designated terminal obtain sampled spectral data corresponding to the sampled disaster damage assessment result from the aerial photography remote sensing data, and determine according to the sampled spectral data and the sampled disaster damage assessment result Disaster damage level threshold;
  • the spectral data of the satellite remote sensing data is evaluated according to the disaster damage level threshold, so as to generate a disaster damage evaluation result of the designated area.
  • one or more computer-readable storage media storing computer-readable instructions are provided, and the readable storage media provided in this embodiment include non-volatile readable storage media and volatile readable storage media storage medium.
  • Computer-readable instructions are stored on the readable storage medium, and when the computer-readable instructions are executed by one or more processors, implement the following steps:
  • Receive the sampled disaster damage assessment result sent by the designated terminal obtain sampled spectral data corresponding to the sampled disaster damage assessment result from the aerial photography remote sensing data, and determine according to the sampled spectral data and the sampled disaster damage assessment result Disaster damage level threshold;
  • the spectral data of the satellite remote sensing data is evaluated according to the disaster damage level threshold, so as to generate a disaster damage evaluation result of the designated area.
  • Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Educational Administration (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Agronomy & Crop Science (AREA)
  • Animal Husbandry (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Mining & Mineral Resources (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Image Processing (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种农业险情数据评估方法、装置、计算机设备及存储介质，涉及数据处理领域。其中方法包括：获取指定区域的气象数据和卫星遥感数据（10），以生成初步灾损评估结果（20）；根据初步灾损评估结果在指定区域设置若干采样点（30）；获取采样点的实地调查数据和指定区域的航拍遥感数据并发送至指定终端，指定终端根据实地调查数据和航拍遥感数据得到采样灾损评估结果（40）；从航拍遥感数据获取与采样灾损评估结果对应的采样光谱数据，根据采样光谱数据和采样灾损评估结果确定灾损等级阈值（50）；根据灾损等级阈值对卫星遥感数据的光谱数据进行评估，以生成指定区域的灾损评估结果（60）。该方法降低了农业险情数据的收集难度，减少农业险情勘察定损的成本。

Description

农业险情数据评估方法、装置、计算机设备及存储介质
本申请要求于2021年3月23日提交中国专利局、申请号为202110308541.0，发明名称为“农业险情数据评估方法、装置、计算机设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及数据处理领域，尤其涉及一种农业险情数据评估方法、装置、计算机设备及存储介质。
背景技术
目前，在进行农业保险的勘察定损时，需要收集农业险情数据。发明人意识到，这些农业险情数据大多数情况是依靠勘察员在保险标的所在地现场收集完成。而保险标的所在地一般分布在位置偏远的地方，农业险情数据的收集难度大、成本高、周期长，无法及时定损。
申请内容
基于此，有必要针对上述技术问题，提供一种农业险情数据评估方法、装置、计算机设备及存储介质，以解决上述农业险情数据的收集难度大、成本高、周期长，无法及时定损的问题。
一种农业险情数据评估方法，包括：
获取指定区域的气象数据和卫星遥感数据；
根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果；
根据所述初步灾损评估结果在所述指定区域设置若干采样点；
获取所述采样点的实地调查数据和所述指定区域的航拍遥感数据并发送至指定终端，以使所述指定终端根据所述实地调查数据和所述航拍遥感数据进行灾损分析得到采样灾损评估结果；
接收所述指定终端发送的所述采样灾损评估结果，并从所述航拍遥感数据获取与所述采样灾损评估结果对应的采样光谱数据，根据所述采样光谱数据和采样灾损评估结果确定灾损等级阈值；
根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果。
一种农业险情数据评估装置，包括：
数据模块，用于获取指定区域的气象数据和卫星遥感数据；
初步灾损评估结果模块，用于根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果；
采样模块，用于根据所述初步灾损评估结果在所述指定区域设置若干采样点；
采样评估结果模块，用于获取所述采样点的实地调查数据和所述指定区域的航拍遥感数据并发送至指定终端，以使所述指定终端根据所述实地调查数据和所述航拍遥感数据进行灾损分析得到采样灾损评估结果；
灾损等级阈值模块，用于接收所述指定终端发送的所述采样灾损评估结果，并从所述航拍遥感数据获取与所述采样灾损评估结果对应的采样光谱数据，根据所述采样光谱数据和采样灾损评估结果确定灾损等级阈值；
灾损评估结果模块，用于根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果。
一种计算机设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机可读指令，其中，所述处理器执行所述计算机可读指令时实现如如下步骤：
获取指定区域的气象数据和卫星遥感数据；
根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果；
根据所述初步灾损评估结果在所述指定区域设置若干采样点；
获取所述采样点的实地调查数据和所述指定区域的航拍遥感数据并发送至指定终端，以使所述指 定终端根据所述实地调查数据和所述航拍遥感数据进行灾损分析得到采样灾损评估结果；
接收所述指定终端发送的所述采样灾损评估结果，并从所述航拍遥感数据获取与所述采样灾损评估结果对应的采样光谱数据，根据所述采样光谱数据和采样灾损评估结果确定灾损等级阈值；
根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果
一个或多个存储有计算机可读指令的可读存储介质，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行如上述农业险情数据评估方法。
上述农业险情数据评估方法、装置、计算机设备及存储介质，获取指定区域的气象数据和卫星遥感数据；根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果，可迅速对灾损范围的分布和灾损程度有一个初步了解，可明确的指引勘察地，节省了人工成本和时间成本。根据所述初步灾损评估结果在所述指定区域设置若干采样点，减少了不必要的勘察地点的勘察。获取所述采样点的实地调查数据和所述指定区域的航拍遥感数据并发送至指定终端，以使所述指定终端根据所述实地调查数据和所述航拍遥感数据进行灾损分析得到采样灾损评估结果，可利用无人机对恶劣地形进行勘察，且无人机的分辨率高，可以得到更清晰的灾损地块的图片。接收所述指定终端发送的所述采样灾损评估结果，并从所述航拍遥感数据获取与所述采样灾损评估结果对应的采样光谱数据，根据所述采样光谱数据和采样灾损评估结果确定灾损等级阈值，提高灾损等级阈值的准确性；根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果，可自动根据灾损等级划分阈值确定所述灾损地块的灾损等级，减少人工和时间成本。综上，本申请减少了农业险情数据的收集难度，减少了农业险情勘察定损的成本，提高灾损评估精度。
本申请的一个或多个实施例的细节在下面的附图和描述中提出，本申请的其他特征和优点将从说明书、附图以及权利要求变得明显。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对本申请实施例的描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是本申请一实施例中农业险情数据评估方法的一应用环境示意图；
图2是本申请一实施例中农业险情数据评估方法的一流程示意图；
图3是本申请一实施例中不同分辨率的卫星遥感数据以及无人机的用途示意图；
图4是本申请一实施例中水稻的长势状况分布示意图；
图5是本申请一实施例中水稻不同时期光谱信息对应的物候特征示意图；
图6是本申请一实施例中实地调查的采样路线和采样点的具体分布情况示意图；
图7是本申请一实施例中地块级别的灾损等级评估结果示意图；
图8是本申请一实施例中农业险情数据评估装置的一结构示意图；
图9是本申请一实施例中计算机设备的一示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
本实施例提供的农业险情数据评估方法，可应用在如图1的应用环境中，其中，客户端与服务端进行通信。其中，客户端包括但不限于各种个人计算机、笔记本电脑、智能手机、平板电脑和便携式可穿戴设备。服务端可以用独立的服务器或者是多个服务器组成的服务器集群来实现。
在一实施例中，如图2所示，提供一种农业险情数据评估方法，以该方法应用在图1中的服务端为例进行说明，包括如下步骤：
S10、获取指定区域的气象数据和卫星遥感数据。
可理解的，指定区域可以是大区域范围，如华北平原；或者小的区域范围，如一个农业县的农田区域。
具体的，可以根据预设的时间自动获取指定区域的气象数据和卫星遥感数据。气象数据包括但不限于预设时间内指定区域的降雨量、日照、温度和风向风速。卫星遥感数据包含指定区域内的卫星图片和光谱遥感信息。卫星遥感数据来源于覆盖指定区域的卫星，不同分辨率的卫星遥感数据用途不同。图3是不同分辨率的卫星遥感数据以及无人机的用途。数据源指的是不同分辨的数据来源，时相是指采样时期。如图3所示，在一示例中，数据源GF-6可以采集分辨率为2米的卫星遥感数据，采样时间包括8月23日和8月27日，该卫星遥感数据用于水稻识别和水灾评估。
可选的，在步骤S10中，所述获取指定区域的气象数据和卫星遥感数据，包括：
S101、获取所述指定区域的在指定时间的初始卫星遥感数据。
具体的，可以根据预设的时间自动获取指定区域的不同分辨率、不同周期的若干初始卫星遥感数据。初始卫星遥感数据可以是未经预处理的卫星图片和未经预处理的光谱遥感信息。可以采集灾情发生前、灾情前期、灾情中期、灾情后期的初始卫星遥感数据。初始卫星遥感数据指的是未经预处理的卫星遥感数据。
S102、根据所述预处理方法处理所述初始卫星遥感数据，生成满足预设处理标准的预处理卫星遥感数据，所述预设处理标准与所述预处理方法对应。
具体的，预设处理初始卫星遥感数据的预处理方法，初始卫星遥感数据通过预设预处理方法进行处理后，生成满足预设处理标准的预处理卫星遥感数据。预设预处理方法包括但不限于几何校正、正射校正、大气校正、去云去雾、拼接融合。其中，几何校正、正射校正、大气校正可以将预处理卫星遥感数据标准化，这样利于提取光谱信息。去云去雾主要是有可能存在遥感数据里面因为云雾遮挡无法清晰看到农作物，去云去雾是为了去噪。拼接融合是根据其他期的遥感数据和本期数据相融合，拼接成指定区域的农作物。预处理卫星遥感数据包含指定区域的通过预处理的卫星图片和光谱遥感信息。预设处理标准与预处理方法一一对应，比如，去云去雾预处理方法的标准，可以是使农作物可以被清晰的看到。
S103、根据预设检验指标检验所述预处理卫星遥感数据的可用性。
具体的，预设检验指标可以是含云量，可以预设含云量的大小作为检验预处理卫星遥感数据的可用性检验指标。可以对指定区域内的卫星图片，进行图像识别，获得卫星图片像素点的个数，根据像素点的个数，来判断含云量。若含云量高于预设云量阈值，表示该期卫星图片区域的农作物被云雾遮挡过多，则该期预处理卫星遥感数据不可用。若含云量低于或等于预设云量阈值，表示该期卫星图片区域的农作物被云雾遮挡较少，则该期预处理卫星遥感数据可用。
S104、将通过可用性检验的所述预处理卫星遥感数据确定为所述卫星遥感数据。
具体的，将通过可用性检验的预处理卫星遥感数据，确定为卫星遥感数据，卫星遥感数据包含指定区域内通过可用性检验的卫星图片和其他相关信息。
在步骤S101-S104中，获取所述指定区域的在指定时间的初始卫星遥感数据，根据所述预处理方法处理所述初始卫星遥感数据，生成满足预设处理标准的预处理卫星遥感数据，所述预设处理标准与所述预处理方法对应，提高卫星遥感数据的准确性。根据预设检验指标检验所述预处理卫星遥感数据的可用性，将通过可用性检验的所述预处理卫星遥感数据确定为所述卫星遥感数据，提高卫星遥感数据的可用性。
S20、根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果。
具体的，根据气象数据和指定区域的行政区划信息生成气象灾情初步评估信息。在一示例中，气象灾情初步评估信息包括XX县XX区域的水灾等级为中等。根据卫星遥感数据生成遥感灾情初步评估信息。在一示例中，遥感灾情初步评估信息包括XX县XX区域的农作物长势状况较好。根据农作物光谱信息和卫星遥感数据生成农作物分布信息。在一示例中，农作物分布信息包括：XX1县，水稻，2000亩；XX2县，水稻，1800亩；……。最后，根据气象灾情初步评估信息、遥感灾情初步评估信息和农作物分布信息生成初步灾损评估结果。
可选的，在步骤S20中，所述根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果，包括：
S201、根据预设维度从气象数据中获取若干指定灾损因子的灾情数据，按照所述指定区域的行政区划信息对所述灾情数据进行划分，并进行评估，生成气象灾情初步评估信息，所述气象灾情初步评估信息包括每一行政区域的初步灾损程度和初步灾损范围。
具体的，可以根据预设维度从气象数据中获取若干指定灾损因子的灾情数据，根据灾情数据和行政区划信息初步确定初步灾损程度和初步灾损范围，并生成气象灾情初步评估信息。在一示例中，灾情数据可表示为：
表1若干指定灾损因子的灾情数据
灾情数据 降雨量 温度
持续日数 10天 15天
累计值 200mm  
极高值 30mm 28度
可理解的，指定区域的行政区划信息可以通过GPS定位系统或其他途径获取。指定灾损因子包括但不限于降雨量、日照、温度和风向风速。预设维度包括但不限于持续日数、累计值、累计距平、极高值、极低值、平均值。比如，降雨量可以通过持续日数、累计值、累计距平、极高值、极低值和平均值这6个维度进行数据统计。其中，累计距平指的是距平的累加，距平用来表示某个时段(如一天)的降雨量与某个长期时段(如一年)的平均降雨量的差值。气象灾情初步评估信息包括初步灾损程度和初步灾损范围。
具体的，从气象数据中筛选出指定天气要素作为判断农作物灾损程度的灾损因子，并根据预设维度，从不同维度选取灾断因子的灾情数据。在气象数据中匹配出灾损所分布的区域范围，由于不同区域的农作物对灾害的敏感度不同，需要咨询当地农业专家来获取当地农作物水灾或旱灾的标准。并根据该标准自定义灾损程度的等级阈值，将水灾或者旱灾划分为包括但不限于未受灾、轻度受灾、轻中度受灾、中度受灾、中重度受灾、重度受灾6个等级。进而根据灾损因子的不同维度的灾情数据与灾损程度的等级阈值对指定区域灾损程度进行评估。得到指定区域灾损程度的等级，从气象角度得到农作物的初步评估信息。
可选的，由于不同区域对灾害的敏感度不同，初步灾损程度的评估还可以结合当地的地理状况去进行。
S202、从卫星遥感数据中获取所述指定区域内农作物的光谱数据，根据所述光谱数据对农作物的长势状况进行评估，生成遥感灾情初步评估信息；所述遥感灾情初步评估信息包含农作物的长势状况分布范围。
可理解的，从卫星遥感数据中获取指定区域内农作物的光谱数据，根据光谱数据对农作物的长势状况进行初步评估，生成遥感灾情初步评估信息。其中，光谱数据需要经过归一化植被指数计算处理，归一化植被指数(NDVI)能很好地反应植被信息的强弱，是进行植被长势状况监测的重要指标。归一化植被指数(NDVI)可通过农作物的光谱数据计算得到，光谱数据包含农作物在近红外波段和红光波段这两个波段的反射率。归一化植被指数的计算公式为：NDVI＝(NIR-R)/(NIR+R)，其中，NIR为近红外波段，R为红光波段。遥感灾情初步评估信息包含农作物的长势状况分布范围。农作物的长势状况可以分为好、较好、正常、较差、差5个维度。在一示例中，如图4所示，为6月30日四川省广汉市水稻的长势状况分布图，其中，长势状况好、较好、正常、较差、差分别占4.5％、16.26％、67.76％、7.12％、4.36％。
S203、从卫星遥感数据中获取所述指定区域内农作物的光谱信息，根据所述光谱信息确定农作物的种类，生成农作物分布信息。
可理解的，农作物光谱信息表示农作物在发芽、展叶、开花、叶变色、落叶等不同生育期中，对光谱产生不同特征的物候现象。通过验标标注、查勘理赔标注等操作，逐渐沉淀各个农作物不同物候期的光谱信息，建立起了水稻、玉米、小麦等农作物光谱信息库，以用于受灾区域的农作物自动化快速识别。农作物光谱信息是农作物在不同生育期在卫星遥感数据中所表现的颜色。
具体的，从卫星遥感数据中获取指定区域内的农作物的光谱信息，并从农作物光谱信息库中获取农作物光谱信息，将指定区域内的农作物的光谱信息与农作物光谱信息库中的农作物光谱信息进行自动识别比对，得到农作物的种类，进而根据农作物的种类，在长势状况分布范围的基础上，生成农作物的分布范围。
S204、结合所述气象灾情初步评估信息、所述遥感灾情初步评估信息和所述农作物分布信息，生成所述初步灾损评估结果。
具体的，根据气象灾情初步评估信息的初步灾损程度和初步灾损范围、遥感灾情初步评估信息的长势状况分布范围、农作物分布信息的农作物种类信息和分布范围生成初步灾损评估结果。
可理解的，初步灾损评估结果包含初步灾损程度、初步灾损范围、长势状况分布范围、农作物种类信息和分布范围。
在步骤S201-S204中，根据预设维度从气象数据中获取若干指定灾损因子的灾情数据，按照所述指定区域的行政区划信息对所述灾情数据进行划分，并进行评估，生成气象灾情初步评估信息，所述气象灾情初步评估信息包括每一行政区域的初步灾损程度和初步灾损范围，可自动快速从气象角度获取初步灾损程度和初步灾损范围，节省时间和人工成本。从卫星遥感数据中获取所述指定区域内农作物的光谱数据，根据所述光谱数据对农作物的长势状况进行评估，生成遥感灾情初步评估信息；所述遥感灾情初步评估信息包含农作物的长势状况分布范围，可自动快速从卫星遥感角度获取长势状况分布范围，节省时间和人力成本。从卫星遥感数据中获取所述指定区域内农作物的光谱信息，根据所述光谱信息确定农作物的种类，生成农作物分布信息；结合所述气象灾情初步评估信息、所述遥感灾情初步评估信息和所述农作物分布信息，生成所述初步灾损评估结果，提高初步灾损评估结果的准确性。
可选的，在步骤S203中，所述从卫星遥感数据中获取所述指定区域内农作物的光谱信息，根据所述光谱信息确定农作物的种类，生成农作物分布信息，包括：
S2031、获取农作物光谱信息和所述卫星遥感数据中的光谱信息。
可理解的，农作物光谱信息表示农作物在发芽、展叶、开花、叶变色、落叶等不同生育期中，对光谱产生不同特征的物候现象。通过验标标注、查勘理赔标注等操作，逐渐沉淀各个农作物不同物候期的光谱信息，建立起了水稻、玉米、小麦等农作物光谱信息库，以用于受灾区域的农作物自动化快速识别。光谱信息是农作物在不同生育期在卫星遥感数据中所表现的颜色。
具体的，从卫星遥感数据中获取指定区域内的农作物的光谱信息，并从农作物光谱信息库中获取农作物光谱信息。
S2032、根据所述农作物光谱信息对所述卫星遥感数据中的光谱信息进行识别，生成所述农作物分布信息，所述农作物分布信息包括农作物的种类信息和分布范围。
具体的，针对农作物的物候特征，将指定区域内农作物在卫星遥感数据中多时相的光谱信息，与物候特征库中所包含的不同时期不同农作物的光谱信息进行比对识别，确定农作物的种类，进而根据农作物的种类，在长势状况分布范围的基础上，得到农作物的分布范围，生成包含农作物的种类信息和分布范围的农作物分布信息。多时相是指不同时刻的卫星遥感数据融合。例如，在第一时刻，指定区域的位置A有云，位置B无云；第二时刻，指定区域的位置B有云，位置A无云。经过多时相融合，可以获得位置A和位置B均未被云覆盖的卫星遥感数据。
不同时期，农作物的光谱信息存在较大差异。以水稻为例，在6月份的蓄水移栽期，水稻种植范围表现为水体；7月中旬的分叶期前期，水稻冠层不足以覆盖整个地面，遥感影像上呈现弱植被信息；7月下旬的分叶期后期，水稻生长旺盛，表现为深绿色的光谱信息；在8月份的拔节期，水稻呈现出明显的亮绿色光谱信息。可以根据不同时期的光谱变化识别出农作物的种类信息。图5是水稻不同时期光谱信息对应的物候特征图。在一示例中，如图5所示，数据源GF-1可以采集分辨率为2米的水稻光谱信息，采样时间为6月17日，水稻在该光谱信息该时间的物候特征为水体，处于蓄水移栽期。
在步骤S2031-S2032中，获取农作物光谱信息和所述卫星遥感数据中的光谱信息，根据所述农作物光谱信息对所述卫星遥感数据中的光谱信息进行识别，生成所述农作物分布信息，所述农作物分布信息包括农作物的种类信息和分布范围。可自动快速的得到农作物的种类信息和分布范围，明确的指引勘 察地，节省了人工成本和时间成本。
可选的，在步骤S220中，所述从卫星遥感数据中获取所述指定区域内农作物的光谱数据，通过根据所述光谱数据对农作物的长势状况灾损进行初步评估，生成遥感灾情初步评估信息；所述遥感灾情初步评估信息包含农作物的长势状况分布范围，包括：
S2021、获取所述卫星遥感数据中的光谱数据，所述光谱数据包括近红外波段和红光波段。
具体的，可以从卫星遥感数据中获取农作物在不同波段的光谱数据。光谱数据包括近红外波段和红光波段。
S2022、获取所述指定区域内农作物的近红外波段的反射率，以及红光波段的反射率，通过归一化植被指数计算公式处理所述近红外波段的反射率和所述红光波段的反射率，得到所述指定区域的归一化植被指数。
可理解的，归一化植被指数(NDVI)能很好地反应植被信息的强弱，是进行植被长势状况监测的重要指标，归一化植被指数(NDVI)可通过农作物的光谱数据计算得到，归一化植被指数的计算公式为：NDVI＝(NIR-R)/(NIR+R)，其中，NIR为近红外波段，R为红光波段。
具体的，根据从卫星遥感数据中获取指定区域内农作物的近红外波段的反射率和红光波段的反射率，通过计算公式，NDVI＝(NIR-R)/(NIR+R)，处理近红外波段的反射率和红光波段的反射率，可得到指定区域农作物的归一化植被指数。
S2023、根据所述归一化植被指数所处的指数范围确定农作物的长势状况，并基于所述农作物的长势状况生成遥感灾情初步评估信息，所述遥感灾情初步评估信息包含农作物的长势状况分布范围。
具体的，根据归一化植被指数(NDVI)所处的指数范围对灾损进行初步评估。并以好、较好、正常、较差、差5个维度对指定区域内的农作物的长势状况进行定性的统计，确定农作物的长势状况，生成包含长势状况分布范围的遥感灾情初步评估信息。可理解的，归一化植被指数(NDVI)的指数范围可表示为-1<＝NDVI<＝1，负值表示地面覆盖为云、水、雪等，对可见光高反射；0表示有岩石或裸土等，NIR和R近似相等；正值，表示有植被覆盖，且NDVI值随覆盖度增大而增大。
在步骤S2021-S2023中，获取所述卫星遥感数据中的光谱数据，所述光谱数据包括近红外波段和红光波段；获取所述指定区域内农作物的近红外波段的反射率，以及红光波段的反射率，通过归一化植被指数计算公式处理所述近红外波段的反射率和所述红光波段的反射率，得到所述指定区域的归一化植被指数；根据所述归一化植被指数所处的指数范围确定农作物的长势状况，并基于所述农作物的长势状况生成遥感灾情初步评估信息，所述遥感灾情初步评估信息包含农作物的长势状况分布范围，可快速的得到指定区域内农作物的长势状况分布范围，节省了人工成本和时间成本。
S30、根据所述初步灾损评估结果在所述指定区域设置若干采样点。
具体的，获得初步灾损评估结果之后，可以根据初步灾损程度、初步灾损范围、长势状况分布范围、农作物种类信息和分布范围设置若干个采样点。每一初步灾损程度、每一长势状况、每一农作物种类设置有至少一个采样点。灾损等级对采样点的农作物进行实地拍摄调查，得到实地调查数据。
S40、获取所述采样点的实地调查数据和所述指定区域的航拍遥感数据并发送至指定终端，以使所述指定终端根据所述实地调查数据和所述航拍遥感数据进行灾损分析得到采样灾损评估结果。
可理解的，实地调查数据指的是勘查人员到采样点现场勘查的数据。实地调查数据包括照片、拍摄时间、地点(包括经纬度)、拍摄人、现场记录。在一示例中，采样点共224个点，其中，水稻的实地调查数据包括：未受灾81个点，轻度受灾21个点，中度受灾18个点，重度受灾30个点，绝产13个点；其他作物61个点。在一示例中，如图6所示，是勘查人员对水稻未受灾点、轻度受灾点、中度受灾点、重度受灾点、绝产点、其他作物点进行采样实地调查时，实地调查的采样路线和采样点的具体分布情况。
航拍遥感数据可以指通过无人机航拍获得的数据。在移动端APP鸟瞰无人机系统上规划好无人机的航线，使无人机沿设置好的航线对初步灾损范围内的农作物进行无人机航拍，可得到包含航拍图片和其他相关信息的航拍遥感数据。可以根据需要进行多分辨率、多次的无人机航拍。
指定终端可以指农业专家使用的计算机设备。指定终端在接收到实地调查数据和航拍遥感数据之 后，农业专家可以通过指定终端查看实地调查数据和航拍遥感数据，并提供采样灾损评估结果。采样灾损评估结果包括农作物的灾损等级。灾损等级包括但不限于未受灾、轻度受灾、轻中度受灾、中度受灾、中重度受灾、重度受灾6个等级。其中，无人机航拍遥感数据包含航拍图片。
可选的，在步骤S40中，所述航拍遥感数据包括全景图像；所述获取所述采样点的实地调查数据，并获取所述指定区域的航拍遥感数据，包括：
S401、通过无人机按照预设航线采集若干航拍图片。
具体的，预设航线可以指在移动端APP鸟瞰无人机系统上规划好无人机的航线。无人机沿预设好的航线对初步灾损范围内的农作物进行无人机航拍，采集若干航拍实景图片。其中，可以根据需要进行多分辨率、多次的无人机航拍。
S402、根据所述若干航拍图片生成所述全景图像。
具体的，自动从无人机航拍遥感数据中获取所有指定区域的航拍实景图片，包括但不限于通过运动结构推断、特征提取、特征匹配、点云生成、泊松平面重建、多视角立体视觉技术将航拍图片自动拼接成灾损全景图。
可选的，针对航拍图片拼接速度过慢的问题，可引入DeepSFM算法(deep structure-from-motion，深度运动恢复结构)，通过GPU并行运算，显著地提升了运动结构推断的运算效率，使图片拼接速度提升50％。
在步骤S401-S402中，通过无人机按照预设航线采集若干航拍图片，根据所述若干航拍图片生成所述全景图像，可获得高分辨率的航拍图片，且自动生成全景图，提高了图片的处理速度。
S50、接收所述指定终端发送的所述采样灾损评估结果，并从所述航拍遥感数据获取与所述采样灾损评估结果对应的采样光谱数据，根据所述采样光谱数据和采样灾损评估结果确定灾损等级阈值。
可理解的，由于相同灾损等级设置有若干个采样点，则相同灾损等级可得到若干个采样灾损评估结果。从航拍遥感数据中获取同一灾损等级的农作物的采样光谱数据，根据同一灾损等级的农作物的采样光谱数据计算该灾损等级下的多个归一化植被指数。根据灾损等级下的多个归一化植被指数确定该灾损等级的均值和最值，选择该均值和最值设定灾损等级的阈值或区间阈值，即为灾损等级阈值。
S60、根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果。
可理解的，指定区域由若干地块组成。通过AI图像识别及深度学习技术，对指定区域内各个地块的边界进行自动化识。同一地块可有多个光谱数据，即对应有多个归一化植被指数。从卫星遥感数据中获取所有光谱数据，根据所有光谱数据计算出指定区域所有的归一化植被指数。
进一步的，将所有的归一化植被指数值统计到各个地块中，得到各个地块的归一化植被指数均值。进而，根据灾损等级的阈值对指定区域的各个地块的归一化植被指数均值进行评估，得到指定区域内各个地块的灾损等级评估结果。比如，指定区域的某地块归一化植被指数(NDVI)均值大于重度灾损等级的阈值，则评估该地块灾损等级为重度灾损。
可选的，在步骤S60中，所述根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果，包括：
S601、获取所述指定区域的卫星遥感数据，所述卫星遥感数据满足预设分辨率要求。
可理解的，卫星遥感数据包含不同时期不同分辨率的若干卫星的遥感数据。具体的，根据实际需求选择卫星遥感数据的分辨率。例如，通过AI进行地块边界识别时，需要使用0.5米分辨率的高清数据；若使用10米分辨率的数据，地块边界无法满足精度要求。
无人机航拍的分辨率高于卫星遥感的分辨率。在重点区域，可以选用分辨率高的无人机遥感数据。
S602、通过预设图像识别算法处理所述卫星遥感数据，生成所述指定区域的耕地地块边界信息。
具体的，预设图像识别算法包括AI图像识别算法及深度学习算法。比如，通过AI图像识别算法及深度学习算法，对指定区域内各个地块的边界进行自动化识别，生成耕地地块的边界信息。可以根据边界信息计算得出各个耕地地块的面积。结合耕地地块的灾损等级和面积，可以得到灾损面积。可根据灾损面积和灾损等级评估结果制作成灾损可视化报表。在一示例中，如图7所示，是某村地块级别的灾 损等级评估结果图，其中不同的灾损等级用灾不同颜色标准，且在每一地块中标注该地块面积。
S603、从所述耕地地块边界信息中提取耕地地块的光谱数据。
具体的，根据耕地地块边界信息，获取指定区域内各个耕地地块的光谱数据。
S604、根据所述灾损等级阈值对耕地地块的光谱数据进行评估，生成所述耕地地块的灾损评估结果，所述指定区域的灾损评估结果包括若干所述耕地地块的灾损评估结果。
具体的，根据指定区域内各个耕地地块的光谱数据，计算出指定区域内各个耕地地块的归一化植被指数(NDVI)。进一步的，将所有的归一化植被指数(NDVI)值统计到各个地块中，得到该指定区域内各个地块的归一化植被指数(NDVI)均值。进而，根据灾损等级的阈值对指定区域的各个耕地地块的光谱数据进行评估，得到指定区域内各个地块的灾损等级评估结果。比如，指定区域的某地块归一化植被指数(NDVI)均值大于重度灾损等级的阈值，则评估该地块灾损等级为重度灾损。
在步骤S601-S604中，获取所述指定区域的卫星遥感数据，所述卫星遥感数据满足预设分辨率要求，通过预设图像识别算法处理所述卫星遥感数据，生成所述指定区域的耕地地块边界信息，从所述耕地地块边界信息中提取耕地地块的光谱数据，根据所述灾损等级阈值对耕地地块的光谱数据进行评估，生成所述耕地地块的灾损评估结果，所述指定区域的灾损评估结果包括若干所述耕地地块的灾损评估结果，可自动根据灾损等级划分阈值确定所述灾损地块的灾损等级，减少人工和时间成本。
综上，在步骤S10-S60中，本实施例通过获取指定区域的气象数据和卫星遥感数据；根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果，可迅速对灾损范围的分布和灾损程度有一个初步了解，可明确的指引勘察地，节省了人工成本和时间成本。根据所述初步灾损评估结果在所述指定区域设置若干采样点，减少了不必要的勘察地点的勘察。获取所述采样点的实地调查数据和所述指定区域的航拍遥感数据并发送至指定终端，以使所述指定终端根据所述实地调查数据和所述航拍遥感数据进行灾损分析得到采样灾损评估结果，可利用无人机对恶劣地形进行勘察，且无人机的分辨率高，可以得到更清晰的灾损地块的图片。接收所述指定终端发送的所述采样灾损评估结果，并从所述航拍遥感数据获取与所述采样灾损评估结果对应的采样光谱数据，根据所述采样光谱数据和采样灾损评估结果确定灾损等级阈值，提高灾损等级阈值的准确性；根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果，可自动根据灾损等级划分阈值确定所述灾损地块的灾损等级，减少人工和时间成本。综上，本申请减少了农业险情数据的收集难度，减少了农业险情勘察定损的成本，提高灾损评估精度。
应理解，上述实施例中各步骤的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
在一实施例中，提供一种农业险情数据评估装置，该农业险情数据评估装置与上述实施例中农业险情数据评估方法一一对应。如图8所示，该农业险情数据评估装置包括数据模块10、初步评估模块20、确定采样点模块30、采样评估模块40、确定灾损等级阈值模块50和灾损评估结果模块60。各功能模块详细说明如下：
数据模块10，用于获取指定区域的气象数据和卫星遥感数据；
初步评估模块20，用于根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果；
确定采样点模块30，用于根据所述初步灾损评估结果在所述指定区域设置若干采样点；
采样评估模块40，用于获取所述采样点的实地调查数据和所述指定区域的航拍遥感数据并发送至指定终端，以使所述指定终端根据所述实地调查数据和所述航拍遥感数据进行灾损分析得到采样灾损评估结果；
确定灾损等级阈值模块50，用于接收所述指定终端发送的所述采样灾损评估结果，并从所述航拍遥感数据获取与所述采样灾损评估结果对应的采样光谱数据，根据所述采样光谱数据和采样灾损评估结果确定灾损等级阈值；
灾损评估结果模块60，用于根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果。
可选的，在采样评估模块40中，所述航拍遥感数据包括全景图像；所述获取所述采样点的实地 调查数据和所述指定区域的航拍遥感数据并发送至指定终端，包括：
航拍图片单元，用于通过无人机按照预设航线采集若干航拍图片；
全景图像单元，用于根据所述若干航拍图片生成所述全景图像。
可选的，在初步评估模块20中，所述根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果，包括：
气象数据单元201，用于根据预设维度从气象数据中获取若干指定灾损因子的灾情数据，按照所述指定区域的行政区划信息对所述灾情数据进行划分，并进行评估，生成气象灾情初步评估信息，所述气象灾情初步评估信息包括每一行政区域的初步灾损程度和初步灾损范围；
卫星遥感数据单元202，用于从卫星遥感数据中获取所述指定区域内农作物的光谱数据，根据所述光谱数据对农作物的长势状况进行评估，生成遥感灾情初步评估信息；所述遥感灾情初步评估信息包含农作物的长势状况分布范围；
农作物分布信息单元203，用于从卫星遥感数据中获取所述指定区域内农作物的光谱信息，根据所述光谱信息确定农作物的种类，生成农作物分布信息；
初步灾损评估结果单元204，用于结合所述气象灾情初步评估信息、所述遥感灾情初步评估信息和所述农作物分布信息，生成所述初步灾损评估结果。
可选的，在农作物分布信息单元203中，所述从卫星遥感数据中获取所述指定区域内农作物的光谱信息，根据所述光谱信息确定农作物的种类，生成农作物分布信息，包括：
光谱信息单元，用于获取农作物光谱信息和所述卫星遥感数据中的光谱信息；
光谱信息识别单元，用于根据所述农作物光谱信息对所述卫星遥感数据中的光谱信息进行识别，生成所述农作物分布信息，所述农作物分布信息包括农作物的种类信息和分布范围。
可选的，在卫星遥感数据单元202中，所述从卫星遥感数据中获取所述指定区域内农作物的光谱数据，通过根据所述光谱数据对农作物的长势状况灾损进行初步评估，生成遥感灾情初步评估信息；所述遥感灾情初步评估信息包含农作物的长势状况分布范围，包括：
第一获取光谱数据单元，用于获取所述卫星遥感数据中的光谱数据，所述光谱数据包括近红外波段和红光波段；
归一化植被指数单元，用于获取所述指定区域内农作物的近红外波段的反射率，以及红光波段的反射率，通过归一化植被指数计算公式处理所述近红外波段的反射率和所述红光波段的反射率，得到所述指定区域的归一化植被指数；
遥感灾情单元，用于根据所述归一化植被指数所处的指数范围确定农作物的长势状况，并基于所述农作物的长势状况生成遥感灾情初步评估信息，所述遥感灾情初步评估信息包含农作物的长势状况分布范围。
可选的，在数据模块10中，所述获取指定区域的气象数据和卫星遥感数据，包括：
初始卫星遥感数据单元，用于获取所述指定区域的在指定时间的初始卫星遥感数据；
预处理卫星遥感数据单元，用于根据所述预处理方法处理所述初始卫星遥感数据，生成满足预设处理标准的预处理卫星遥感数据，所述预设处理标准与所述预处理方法对应；
检验单元，用于根据预设检验指标检验所述预处理卫星遥感数据的可用性；
卫星遥感数据单元，用于将通过可用性检验的所述预处理卫星遥感数据确定为所述卫星遥感数据。
可选的，在灾损评估结果模块60中，所述根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果，包括：
分辨率单元，用于获取所述指定区域的卫星遥感数据，所述卫星遥感数据满足预设分辨率要求；
边界信息单元，用于通过预设图像识别算法处理所述卫星遥感数据，生成所述指定区域的耕地地块边界信息；
第二获取光谱数据单元，用于从所述耕地地块边界信息中提取耕地地块的光谱数据；
灾损评估结果单元，用于根据所述灾损等级阈值对耕地地块的光谱数据进行评估，生成所述耕地地块的灾损评估结果，所述指定区域的灾损评估结果包括若干所述耕地地块的灾损评估结果。
关于农业险情数据评估装置的具体限定可以参见上文中对于农业险情数据评估方法的限定，在此不再赘述。上述农业险情数据评估装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在一个实施例中，提供了一种计算机设备，该计算机设备可以是服务器，其内部结构图可以如图9所示。该计算机设备包括通过系统总线连接的处理器、存储器、网络接口和数据库。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括可读存储介质、内存储器。该可读存储介质存储有操作系统、计算机可读指令和数据库。该内存储器为可读存储介质中的操作系统和计算机可读指令的运行提供环境。该计算机设备的数据库用于存储农业险情数据评估方法所涉及的数据。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机可读指令被处理器执行时以实现一种农业险情数据评估方法。本实施例所提供的可读存储介质包括非易失性可读存储介质和易失性可读存储介质。
在一个实施例中，提供了一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机可读指令，处理器执行计算机可读指令时实现以下步骤：
获取指定区域的气象数据和卫星遥感数据；
根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果；
根据所述初步灾损评估结果在所述指定区域设置若干采样点；
获取所述采样点的实地调查数据和所述指定区域的航拍遥感数据并发送至指定终端，以使所述指定终端根据所述实地调查数据和所述航拍遥感数据进行灾损分析得到采样灾损评估结果；
接收所述指定终端发送的所述采样灾损评估结果，并从所述航拍遥感数据获取与所述采样灾损评估结果对应的采样光谱数据，根据所述采样光谱数据和采样灾损评估结果确定灾损等级阈值；
根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果。
在一个实施例中，提供了一个或多个存储有计算机可读指令的计算机可读存储介质，本实施例所提供的可读存储介质包括非易失性可读存储介质和易失性可读存储介质。可读存储介质上存储有计算机可读指令，计算机可读指令被一个或多个处理器执行时实现以下步骤：
获取指定区域的气象数据和卫星遥感数据；
根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果；
根据所述初步灾损评估结果在所述指定区域设置若干采样点；
获取所述采样点的实地调查数据和所述指定区域的航拍遥感数据并发送至指定终端，以使所述指定终端根据所述实地调查数据和所述航拍遥感数据进行灾损分析得到采样灾损评估结果；
接收所述指定终端发送的所述采样灾损评估结果，并从所述航拍遥感数据获取与所述采样灾损评估结果对应的采样光谱数据，根据所述采样光谱数据和采样灾损评估结果确定灾损等级阈值；
根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机可读指令来指令相关的硬件来完成，所述的计算机可读指令可存储于一非易失性可读取存储介质或易失性可读存储介质中，该计算机可读指令在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将所述装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。
以上所述实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。

Claims (20)

  1. 一种农业险情数据评估方法，其中，包括：
    获取指定区域的气象数据和卫星遥感数据；
    根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果；
    根据所述初步灾损评估结果在所述指定区域设置若干采样点；
    获取所述采样点的实地调查数据和所述指定区域的航拍遥感数据并发送至指定终端，以使所述指定终端根据所述实地调查数据和所述航拍遥感数据进行灾损分析得到采样灾损评估结果；
    接收所述指定终端发送的所述采样灾损评估结果，并从所述航拍遥感数据获取与所述采样灾损评估结果对应的采样光谱数据，根据所述采样光谱数据和采样灾损评估结果确定灾损等级阈值；
    根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果。
  2. 如权利要求1所述的农业险情数据评估方法，其中，所述航拍遥感数据包括全景图像；所述获取所述采样点的实地调查数据和所述指定区域的航拍遥感数据并发送至指定终端，包括：
    通过无人机按照预设航线采集若干航拍图片；
    根据所述若干航拍图片生成所述全景图像。
  3. 如权利要求1所述的农业险情数据评估方法，其中，所述根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果，包括：
    根据预设维度从气象数据中获取若干指定灾损因子的灾情数据，按照所述指定区域的行政区划信息对所述灾情数据进行划分，并进行评估，生成气象灾情初步评估信息，所述气象灾情初步评估信息包括每一行政区域的初步灾损程度和初步灾损范围；
    从卫星遥感数据中获取所述指定区域内农作物的光谱数据，根据所述光谱数据对农作物的长势状况进行评估，生成遥感灾情初步评估信息；所述遥感灾情初步评估信息包含农作物的长势状况分布范围；
    从卫星遥感数据中获取所述指定区域内农作物的光谱信息，根据所述光谱信息确定农作物的种类，生成农作物分布信息；
    结合所述气象灾情初步评估信息、所述遥感灾情初步评估信息和所述农作物分布信息，生成所述初步灾损评估结果。
  4. 如权利要求3所述的农业险情数据评估方法，其中，所述从卫星遥感数据中获取所述指定区域内农作物的光谱信息，根据所述光谱信息确定农作物的种类，生成农作物分布信息，包括：
    获取农作物光谱信息和所述卫星遥感数据中的光谱信息；
    根据所述农作物光谱信息对所述卫星遥感数据中的光谱信息进行识别，生成所述农作物分布信息，所述农作物分布信息包括农作物的种类信息和分布范围。
  5. 如权利要求3所述的农业险情数据评估方法，其中，所述从卫星遥感数据中获取所述指定区域内农作物的光谱数据，根据所述光谱数据对农作物的长势状况进行评估，生成遥感灾情初步评估信息，包括：
    获取所述卫星遥感数据中的光谱数据，所述光谱数据包括近红外波段和红光波段；
    获取所述指定区域内农作物的近红外波段的反射率，以及红光波段的反射率，通过归一化植被指数计算公式处理所述近红外波段的反射率和所述红光波段的反射率，得到所述指定区域的归一化植被指数；
    根据所述归一化植被指数所处的指数范围确定农作物的长势状况，并基于所述农作物的长势状况生成遥感灾情初步评估信息，所述遥感灾情初步评估信息包含农作物的长势状况分布范围。
  6. 如权利要求1所述的农业险情数据评估方法，其中，所述获取指定区域的气象数据和卫星遥感数据，包括：
    获取所述指定区域的在指定时间的初始卫星遥感数据；
    根据所述预处理方法处理所述初始卫星遥感数据，生成满足预设处理标准的预处理卫星遥感数据，所述预设处理标准与所述预处理方法对应；
    根据预设检验指标检验所述预处理卫星遥感数据的可用性；
    将通过可用性检验的所述预处理卫星遥感数据确定为所述卫星遥感数据。
  7. 如权利要求1所述的农业险情数据评估方法，其中，所述根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果，包括：
    获取所述指定区域的卫星遥感数据，所述卫星遥感数据满足预设分辨率要求；
    通过预设图像识别算法处理所述卫星遥感数据，生成所述指定区域的耕地地块边界信息；
    从所述耕地地块边界信息中提取耕地地块的光谱数据；
    根据所述灾损等级阈值对耕地地块的光谱数据进行评估，生成所述耕地地块的灾损评估结果，所述指定区域的灾损评估结果包括若干所述耕地地块的灾损评估结果。
  8. 一种农业险情数据评估装置，其中，包括：
    数据模块，用于获取指定区域的气象数据和卫星遥感数据；
    初步灾损评估结果模块，用于根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果；
    采样模块，用于根据所述初步灾损评估结果在所述指定区域设置若干采样点；
    采样评估结果模块，用于获取所述采样点的实地调查数据和所述指定区域的航拍遥感数据并发送至指定终端，以使所述指定终端根据所述实地调查数据和所述航拍遥感数据进行灾损分析得到采样灾损评估结果；
    灾损等级阈值模块，用于接收所述指定终端发送的所述采样灾损评估结果，并从所述航拍遥感数据获取与所述采样灾损评估结果对应的采样光谱数据，根据所述采样光谱数据和采样灾损评估结果确定灾损等级阈值；
    灾损评估结果模块，用于根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果。
  9. 如权利要求8所述的农业险情数据评估装置，其中，所述采样评估结果模块，包括：
    航拍图片单元，用于通过无人机按照预设航线采集若干航拍图片；
    全景图像单元，用于根据所述若干航拍图片生成所述全景图像。
  10. 一种计算机设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机可读指令，其中，所述处理器执行所述计算机可读指令时实现如如下步骤：
    获取指定区域的气象数据和卫星遥感数据；
    根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果；
    根据所述初步灾损评估结果在所述指定区域设置若干采样点；
    获取所述采样点的实地调查数据和所述指定区域的航拍遥感数据并发送至指定终端，以使所述指定终端根据所述实地调查数据和所述航拍遥感数据进行灾损分析得到采样灾损评估结果；
    接收所述指定终端发送的所述采样灾损评估结果，并从所述航拍遥感数据获取与所述采样灾损评估结果对应的采样光谱数据，根据所述采样光谱数据和采样灾损评估结果确定灾损等级阈值；
    根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果。
  11. 如权利要求10所述的计算机设备，其中，所述航拍遥感数据包括全景图像；所述获取所述采样点的实地调查数据和所述指定区域的航拍遥感数据并发送至指定终端，包括：
    通过无人机按照预设航线采集若干航拍图片；
    根据所述若干航拍图片生成所述全景图像。
  12. 如权利要求10所述的计算机设备，其中，所述根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果，包括：
    根据预设维度从气象数据中获取若干指定灾损因子的灾情数据，按照所述指定区域的行政区划信息对所述灾情数据进行划分，并进行评估，生成气象灾情初步评估信息，所述气象灾情初步评估信息包括每一行政区域的初步灾损程度和初步灾损范围；
    从卫星遥感数据中获取所述指定区域内农作物的光谱数据，根据所述光谱数据对农作物的长势状况进行评估，生成遥感灾情初步评估信息；所述遥感灾情初步评估信息包含农作物的长势状况分布范围；
    从卫星遥感数据中获取所述指定区域内农作物的光谱信息，根据所述光谱信息确定农作物的种类，生成农作物分布信息；
    结合所述气象灾情初步评估信息、所述遥感灾情初步评估信息和所述农作物分布信息，生成所述初步灾损评估结果。
  13. 如权利要求12所述的计算机设备，其中，所述从卫星遥感数据中获取所述指定区域内农作物的光谱信息，根据所述光谱信息确定农作物的种类，生成农作物分布信息，包括：
    获取农作物光谱信息和所述卫星遥感数据中的光谱信息；
    根据所述农作物光谱信息对所述卫星遥感数据中的光谱信息进行识别，生成所述农作物分布信息，所述农作物分布信息包括农作物的种类信息和分布范围。
  14. 如权利要求12所述的计算机设备，其中，所述从卫星遥感数据中获取所述指定区域内农作物的光谱数据，根据所述光谱数据对农作物的长势状况进行评估，生成遥感灾情初步评估信息，包括：
    获取所述卫星遥感数据中的光谱数据，所述光谱数据包括近红外波段和红光波段；
    获取所述指定区域内农作物的近红外波段的反射率，以及红光波段的反射率，通过归一化植被指数计算公式处理所述近红外波段的反射率和所述红光波段的反射率，得到所述指定区域的归一化植被指数；
    根据所述归一化植被指数所处的指数范围确定农作物的长势状况，并基于所述农作物的长势状况生成遥感灾情初步评估信息，所述遥感灾情初步评估信息包含农作物的长势状况分布范围。
  15. 一个或多个存储有计算机可读指令的可读存储介质，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行如下步骤：
    获取指定区域的气象数据和卫星遥感数据；
    根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果；
    根据所述初步灾损评估结果在所述指定区域设置若干采样点；
    获取所述采样点的实地调查数据和所述指定区域的航拍遥感数据并发送至指定终端，以使所述指定终端根据所述实地调查数据和所述航拍遥感数据进行灾损分析得到采样灾损评估结果；
    接收所述指定终端发送的所述采样灾损评估结果，并从所述航拍遥感数据获取与所述采样灾损评估结果对应的采样光谱数据，根据所述采样光谱数据和采样灾损评估结果确定灾损等级阈值；
    根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果。
  16. 如权利要求15所述的可读存储介质，其中，所述根据所述气象数据和所述卫星遥感数据生成初步灾损评估结果，包括：
    根据预设维度从气象数据中获取若干指定灾损因子的灾情数据，按照所述指定区域的行政区划信息对所述灾情数据进行划分，并进行评估，生成气象灾情初步评估信息，所述气象灾情初步评估信息包括每一行政区域的初步灾损程度和初步灾损范围；
    从卫星遥感数据中获取所述指定区域内农作物的光谱数据，根据所述光谱数据对农作物的长势状况进行评估，生成遥感灾情初步评估信息；所述遥感灾情初步评估信息包含农作物的长势状况分布范围；
    从卫星遥感数据中获取所述指定区域内农作物的光谱信息，根据所述光谱信息确定农作物的种类，生成农作物分布信息；
    结合所述气象灾情初步评估信息、所述遥感灾情初步评估信息和所述农作物分布信息，生成所述初步灾损评估结果。
  17. 如权利要求16所述的可读存储介质，其中，所述从卫星遥感数据中获取所述指定区域内农作物的光谱信息，根据所述光谱信息确定农作物的种类，生成农作物分布信息，包括：
    获取农作物光谱信息和所述卫星遥感数据中的光谱信息；
    根据所述农作物光谱信息对所述卫星遥感数据中的光谱信息进行识别，生成所述农作物分布信息，所述农作物分布信息包括农作物的种类信息和分布范围。
  18. 如权利要求16所述的可读存储介质，其中，所述从卫星遥感数据中获取所述指定区域内农作物的光谱数据，根据所述光谱数据对农作物的长势状况进行评估，生成遥感灾情初步评估信息；所述遥感灾情初步评估信息包含农作物的长势状况分布范围，包括：
    获取所述卫星遥感数据中的光谱数据，所述光谱数据包括近红外波段和红光波段；
    获取所述指定区域内农作物的近红外波段的反射率，以及红光波段的反射率，通过归一化植被指数计算公式处理所述近红外波段的反射率和所述红光波段的反射率，得到所述指定区域的归一化植被指数；
    根据所述归一化植被指数所处的指数范围确定农作物的长势状况，并基于所述农作物的长势状况生成遥感灾情初步评估信息，所述遥感灾情初步评估信息包含农作物的长势状况分布范围。
  19. 如权利要求15所述的可读存储介质，其中，所述获取指定区域的气象数据和卫星遥感数据，包括：
    获取所述指定区域的在指定时间的初始卫星遥感数据；
    根据所述预处理方法处理所述初始卫星遥感数据，生成满足预设处理标准的预处理卫星遥感数据，所述预设处理标准与所述预处理方法对应；
    根据预设检验指标检验所述预处理卫星遥感数据的可用性；
    将通过可用性检验的所述预处理卫星遥感数据确定为所述卫星遥感数据。
  20. 如权利要求15所述的可读存储介质，其中，所述根据所述灾损等级阈值对所述卫星遥感数据的光谱数据进行评估，以生成所述指定区域的灾损评估结果，包括：
    获取所述指定区域的卫星遥感数据，所述卫星遥感数据满足预设分辨率要求；
    通过预设图像识别算法处理所述卫星遥感数据，生成所述指定区域的耕地地块边界信息；
    从所述耕地地块边界信息中提取耕地地块的光谱数据；
    根据所述灾损等级阈值对耕地地块的光谱数据进行评估，生成所述耕地地块的灾损评估结果，所述指定区域的灾损评估结果包括若干所述耕地地块的灾损评估结果。
PCT/CN2021/090311 2021-03-23 2021-04-27 农业险情数据评估方法、装置、计算机设备及存储介质 Ceased WO2022198744A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110308541.0A CN113033994B (zh) 2021-03-23 2021-03-23 农业险情数据评估方法、装置、计算机设备及存储介质
CN202110308541.0 2021-03-23

Publications (1)

Publication Number Publication Date
WO2022198744A1 true WO2022198744A1 (zh) 2022-09-29

Family

ID=76472872

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/090311 Ceased WO2022198744A1 (zh) 2021-03-23 2021-04-27 农业险情数据评估方法、装置、计算机设备及存储介质

Country Status (2)

Country Link
CN (1) CN113033994B (zh)
WO (1) WO2022198744A1 (zh)

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115346141A (zh) * 2022-10-19 2022-11-15 山东大学 天-空-地-隧-孔一体化不良地质识别方法及系统
CN115690580A (zh) * 2022-10-27 2023-02-03 吉林大学 一种玉米倒伏遥感监测方法、系统、电子设备及介质
CN115797764A (zh) * 2022-11-18 2023-03-14 江苏星月测绘科技股份有限公司 一种应用于耕地非农化监测的遥感大数据解译方法及系统
CN115855151A (zh) * 2022-11-29 2023-03-28 中国科学院空天信息创新研究院 农作物干旱监测方法、装置、存储介质和设备
CN115937721A (zh) * 2023-03-08 2023-04-07 联通（山东）产业互联网有限公司 一种浒苔监测方法
CN115994701A (zh) * 2022-11-10 2023-04-21 海南空天信息研究院 农田生态环境指数确定方法、装置和设备
CN116310842A (zh) * 2023-05-15 2023-06-23 菏泽市国土综合整治服务中心 基于遥感图像的土壤盐碱区域识别划分方法
CN116453003A (zh) * 2023-06-14 2023-07-18 之江实验室 一种基于无人机监测智能识别水稻生长势的方法和系统
CN117115672A (zh) * 2023-07-22 2023-11-24 农业农村部大数据发展中心 一种基于卫星遥感的涝灾玉米提取方法
CN117197467A (zh) * 2023-09-19 2023-12-08 郑州吉奥地理信息技术有限公司 多源遥感影像地类语义分割应用和测评方法
CN117237820A (zh) * 2023-09-26 2023-12-15 中化现代农业有限公司 害虫危害程度的确定方法、装置、电子设备和存储介质
CN117315492A (zh) * 2023-11-29 2023-12-29 中国平安财产保险股份有限公司 基于无人机技术的种植险预警方法、系统、设备及介质
CN118153784A (zh) * 2024-05-09 2024-06-07 深圳点筹农业供应链有限公司 基于多源数据的农产品信息自动更新方法及系统
CN118230184A (zh) * 2024-04-02 2024-06-21 国网重庆市电力公司电力科学研究院 基于卫星遥感的配网线路树障自动识别系统及方法
CN118898750A (zh) * 2024-09-06 2024-11-05 中国科学院空天信息创新研究院 基于景观复杂性遥感感知模型的农作物分类方法及装置
CN119131511A (zh) * 2024-11-08 2024-12-13 天芯(珠海)芯片科技有限公司 一种林业灾害立体监测预警方法、系统、终端及介质
CN119444112A (zh) * 2024-10-16 2025-02-14 广东国地规划科技股份有限公司 一种基于无人机的生态修复工程监管方法、装置及介质
CN120031676A (zh) * 2025-02-19 2025-05-23 济宁市林业保护和发展服务中心((济宁市野生动植物保护中心、济宁市林业科学研究院)) 一种林业有害生物预警模型构建系统及方法
CN120126026A (zh) * 2025-05-09 2025-06-10 安徽天佳信息服务有限公司 一种耕地资源质量等级评估管理方法及系统

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113362192A (zh) * 2021-07-07 2021-09-07 中国工商银行股份有限公司 农业保险核保方法、系统、设备和存储介质
CN113744074A (zh) * 2021-09-06 2021-12-03 北京超图软件股份有限公司 确定农业作物的减灾保产措施的方法和装置
CN115810154A (zh) * 2022-11-17 2023-03-17 中国农业银行股份有限公司 图像处理方法、装置及服务器

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140245210A1 (en) * 2013-02-28 2014-08-28 Donan Engineering Co., Inc. Systems and Methods for Collecting and Representing Attributes Related to Damage in a Geographic Area
CN104881727A (zh) * 2015-01-13 2015-09-02 北京师范大学 一种基于遥感抽样的农作物灾情损失评估方法
CN106126920A (zh) * 2016-06-23 2016-11-16 北京农业信息技术研究中心 农作物雹灾受灾面积遥感评估方法
CN107169018A (zh) * 2017-04-06 2017-09-15 河南云保遥感科技有限公司 一种农业保险查勘、定损系统及其实现方法
US10134092B1 (en) * 2014-10-09 2018-11-20 State Farm Mutual Automobile Insurance Company Method and system for assessing damage to insured properties in a neighborhood
CN110533544A (zh) * 2019-08-28 2019-12-03 中国科学院遥感与数字地球研究所 农作物冷冻害定损理赔方法及系统

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108038566A (zh) * 2017-11-30 2018-05-15 河南云保遥感科技有限公司 一种基于气象与遥感数据融合的灾害监测定损方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140245210A1 (en) * 2013-02-28 2014-08-28 Donan Engineering Co., Inc. Systems and Methods for Collecting and Representing Attributes Related to Damage in a Geographic Area
US10134092B1 (en) * 2014-10-09 2018-11-20 State Farm Mutual Automobile Insurance Company Method and system for assessing damage to insured properties in a neighborhood
CN104881727A (zh) * 2015-01-13 2015-09-02 北京师范大学 一种基于遥感抽样的农作物灾情损失评估方法
CN106126920A (zh) * 2016-06-23 2016-11-16 北京农业信息技术研究中心 农作物雹灾受灾面积遥感评估方法
CN107169018A (zh) * 2017-04-06 2017-09-15 河南云保遥感科技有限公司 一种农业保险查勘、定损系统及其实现方法
CN110533544A (zh) * 2019-08-28 2019-12-03 中国科学院遥感与数字地球研究所 农作物冷冻害定损理赔方法及系统

Cited By (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115346141A (zh) * 2022-10-19 2022-11-15 山东大学 天-空-地-隧-孔一体化不良地质识别方法及系统
CN115690580A (zh) * 2022-10-27 2023-02-03 吉林大学 一种玉米倒伏遥感监测方法、系统、电子设备及介质
CN115994701A (zh) * 2022-11-10 2023-04-21 海南空天信息研究院 农田生态环境指数确定方法、装置和设备
CN115797764A (zh) * 2022-11-18 2023-03-14 江苏星月测绘科技股份有限公司 一种应用于耕地非农化监测的遥感大数据解译方法及系统
CN115855151A (zh) * 2022-11-29 2023-03-28 中国科学院空天信息创新研究院 农作物干旱监测方法、装置、存储介质和设备
CN115937721A (zh) * 2023-03-08 2023-04-07 联通（山东）产业互联网有限公司 一种浒苔监测方法
CN116310842A (zh) * 2023-05-15 2023-06-23 菏泽市国土综合整治服务中心 基于遥感图像的土壤盐碱区域识别划分方法
CN116453003A (zh) * 2023-06-14 2023-07-18 之江实验室 一种基于无人机监测智能识别水稻生长势的方法和系统
CN116453003B (zh) * 2023-06-14 2023-09-01 之江实验室 一种基于无人机监测智能识别水稻生长势的方法和系统
CN117115672A (zh) * 2023-07-22 2023-11-24 农业农村部大数据发展中心 一种基于卫星遥感的涝灾玉米提取方法
CN117197467A (zh) * 2023-09-19 2023-12-08 郑州吉奥地理信息技术有限公司 多源遥感影像地类语义分割应用和测评方法
CN117237820A (zh) * 2023-09-26 2023-12-15 中化现代农业有限公司 害虫危害程度的确定方法、装置、电子设备和存储介质
CN117315492A (zh) * 2023-11-29 2023-12-29 中国平安财产保险股份有限公司 基于无人机技术的种植险预警方法、系统、设备及介质
CN117315492B (zh) * 2023-11-29 2024-04-02 中国平安财产保险股份有限公司 基于无人机技术的种植险预警方法、系统、设备及介质
CN118230184A (zh) * 2024-04-02 2024-06-21 国网重庆市电力公司电力科学研究院 基于卫星遥感的配网线路树障自动识别系统及方法
CN118230184B (zh) * 2024-04-02 2025-09-23 国网重庆市电力公司电力科学研究院 基于卫星遥感的配网线路树障自动识别系统及方法
CN118153784A (zh) * 2024-05-09 2024-06-07 深圳点筹农业供应链有限公司 基于多源数据的农产品信息自动更新方法及系统
CN118898750A (zh) * 2024-09-06 2024-11-05 中国科学院空天信息创新研究院 基于景观复杂性遥感感知模型的农作物分类方法及装置
CN119444112A (zh) * 2024-10-16 2025-02-14 广东国地规划科技股份有限公司 一种基于无人机的生态修复工程监管方法、装置及介质
CN119131511A (zh) * 2024-11-08 2024-12-13 天芯(珠海)芯片科技有限公司 一种林业灾害立体监测预警方法、系统、终端及介质
CN120031676A (zh) * 2025-02-19 2025-05-23 济宁市林业保护和发展服务中心((济宁市野生动植物保护中心、济宁市林业科学研究院)) 一种林业有害生物预警模型构建系统及方法
CN120031676B (zh) * 2025-02-19 2025-09-19 济宁市林业保护和发展服务中心((济宁市野生动植物保护中心、济宁市林业科学研究院)) 一种林业有害生物预警模型构建系统及方法
CN120126026A (zh) * 2025-05-09 2025-06-10 安徽天佳信息服务有限公司 一种耕地资源质量等级评估管理方法及系统

Also Published As

Publication number Publication date
CN113033994B (zh) 2023-06-02
CN113033994A (zh) 2021-06-25

Similar Documents

Publication Publication Date Title
WO2022198744A1 (zh) 农业险情数据评估方法、装置、计算机设备及存储介质
US12287412B2 (en) Accounting for atmospheric and terrestrial obstacles in geographic positioning
US11403846B2 (en) Crop boundary detection in images
CN102215666B (zh) 植被生长状况分析方法、记录有程序的记录介质和植被生长状况分析器
Torres-Sánchez et al. Assessing UAV-collected image overlap influence on computation time and digital surface model accuracy in olive orchards
KR102738483B1 (ko) 작물 유형 및/또는 파종 날짜 추정
Assmann et al. Vegetation monitoring using multispectral sensors—best practices and lessons learned from high latitudes
Wu et al. Validation of synthetic daily Landsat NDVI time series data generated by the improved spatial and temporal data fusion approach
Xue et al. Flood monitoring by integrating normalized difference flood index and probability distribution of water bodies
Gómez‐Sapiens et al. Improving the efficiency and accuracy of evaluating aridland riparian habitat restoration using unmanned aerial vehicles
US20240062461A1 (en) Method and system for producing a digital terrain model
BR112021014654A2 (pt) Previsões meteorológicas com redução em escala
CN108596029A (zh) 农作物分类方法、装置、计算机设备和存储介质
US20180357720A1 (en) Detection of Real Estate Development Construction Activity
Stylianidis et al. FORSAT: A 3D forest monitoring system for cover mapping and volumetric 3D change detection
FR3124626A1 (fr) Procédé de caractérisation d’une zone d’un territoire destinée à l’installation de panneaux photovoltaïques
Mahmud et al. Drought dynamics of Northwestern Teesta Floodplain of Bangladesh: a remote sensing approach to ascertain the cause and effect
Bruch et al. Vegetation density mapping of urban solid waste landfill coverage using vegetation indexes obtained with UAV
CN115410095A (zh) 灾害信息获取方法、装置、电子设备和计算机可读介质
CN119785231A (zh) 天然草地饲草料需求量遥感预测方法及遥感预测装置
Zhang et al. Fractional Snow Cover Mapping with High Spatiotemporal Resolution based on Landsat, Sentinel-2 And Modis Observation
Al Rawashdeh Evaluation of the differencing pixel-by-pixel change detection method in mapping irrigated areas in dry zones
WO2023209413A1 (en) System and method for monitoring a right of way
Cho et al. Characterizing the spatial distribution of field-scale snowpack using unpiloted aerial system (UAS) lidar and structure-from-motion (SfM) photogrammetry
de Souza et al. O Spatiotemporal variability of reference evapotranspiration estimated using satellite images in the Tibagi River Basin, Paraná State, Brazil

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21932362

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21932362

Country of ref document: EP

Kind code of ref document: A1