WO2023165007A1 - 农作物长势的监测方法、系统、设备及介质 - Google Patents

农作物长势的监测方法、系统、设备及介质 Download PDF

Info

Publication number
WO2023165007A1
WO2023165007A1 PCT/CN2022/089634 CN2022089634W WO2023165007A1 WO 2023165007 A1 WO2023165007 A1 WO 2023165007A1 CN 2022089634 W CN2022089634 W CN 2022089634W WO 2023165007 A1 WO2023165007 A1 WO 2023165007A1
Authority
WO
WIPO (PCT)
Prior art keywords
growth
crops
early warning
sub
period
Prior art date
Application number
PCT/CN2022/089634
Other languages
English (en)
French (fr)
Inventor
杨鑫
徐伟
姜凯英
Original Assignee
平安科技（深圳）有限公司
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 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2023165007A1 publication Critical patent/WO2023165007A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30181—Earth observation
    • G06T2207/30188—Vegetation; Agriculture

Definitions

  • the present application relates to the technical field of artificial intelligence, in particular to a method, system, equipment and medium for monitoring the growth of crops.
  • the raw data images captured by remote sensing satellites are periodic, and the time period of the image data spans the growth period, sowing period and maturity period of the crops, it is necessary to standardize according to the normalized vegetation data values of the images and the normalized vegetation data values of the crops Corresponding to data such as the density and intensity of crop growth, and assisting users in monitoring and early warning analysis of crop growth through anomaly maps, year-on-year maps, and ring-to-cycle maps.
  • the inventor realizes that there is no interactive strategy for normalized vegetation data monitoring and early warning in the satellite remote sensing agricultural scene on the market.
  • the purpose of the present application is to provide a method, system, equipment and medium for monitoring the growth of crops, so as to overcome one or more problems caused by limitations and defects of related technologies at least to a certain extent.
  • the application provides a method for monitoring the growth of crops, including:
  • the current region includes a plurality of sub-regions
  • the growth state of the crops is judged, and the growth state includes at least the sowing period, the growth period and the maturity period; wherein, each growth state includes at least one reference range, and the reference range is based on the established The scope of the normalized difference vegetation index obtained by pre-calculating the growth state of the above crops;
  • the growth state comparing the normalized difference vegetation index of each sub-region with at least one reference range included in the growth state of the crops, judging and counting the number of corresponding sub-regions within each reference range;
  • a graded early warning is performed, wherein the graded early warning standard is preset.
  • the application also provides a monitoring system for crop growth, including:
  • the data acquisition module is used to obtain the normalized difference vegetation index of at least two sub-regions of crops in the current region; wherein, the current region includes multiple sub-regions;
  • the growth state acquisition module is used to judge the growth state of the crops according to the acquisition time of the normalized difference vegetation index, and the growth state includes at least the sowing period, the growth period and the maturity period; wherein, each growth state contains several reference range, the reference range is the range of the normalized difference vegetation index obtained by pre-calculation based on the growth state of the crops;
  • the sub-region comparison module is used to compare the normalized difference vegetation index of each sub-region with at least one reference range included in the growth state of the crops according to the growth state, and determine and count the corresponding sub-regions within each reference range quantity;
  • the growth monitoring module is used to carry out grading early warning according to the number of sub-regions counted, wherein the grading early warning standard is preset.
  • the present application also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and operable on the processor.
  • a processor executes the computer program, the steps of the method described above.
  • the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are realized.
  • the crop growth monitoring method, system, equipment and medium of the present application obtain multiple normalized vegetation indices in the current regional crop satellite image, and the user analyzes the crop growth monitoring and early warning according to the red, orange and yellow alarm positions and quantities in the region Condition.
  • the remote sensing data can be visualized to realize the visualization of the alarm information and ensure the intuition and image of the remote sensing data.
  • Fig. 1 shows the schematic flow chart of the monitoring method of crop growth in an embodiment of the present application
  • Fig. 2 shows the schematic flow chart obtained for the reference scope in an embodiment of the present application
  • Fig. 3 shows a schematic flow chart of obtaining the maturity reference range in an embodiment of the present application
  • FIG. 4 shows a schematic flow chart of step S40 in an embodiment of the present application
  • Fig. 5 shows the structural block diagram of the monitoring system of crop growth in an embodiment of the present application
  • FIG. 6 is a schematic structural diagram of an electronic device in an embodiment of the present application.
  • Fig. 1 shows a schematic flow chart of the method for monitoring crop growth of the present application.
  • the method for monitoring the growth of crops is applied to one or more electronic devices, and the electronic device is a device that can automatically perform numerical calculation and/or information processing according to preset or stored instructions, and its hardware includes but Not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.
  • ASIC Application Specific Integrated Circuit
  • FPGA Field-Programmable Gate Array
  • DSP Digital Signal Processor
  • the electronic device may be any electronic product capable of man-machine interaction with the user, for example, a personal computer, a tablet computer, a smart phone, a personal digital assistant (Personal Digital Assistant, PDA), a game console, an interactive Internet TV ( Internet Protocol Television, IPTV), smart wearable devices, etc.
  • a personal computer a tablet computer
  • a smart phone a personal digital assistant (Personal Digital Assistant, PDA)
  • PDA Personal Digital Assistant
  • game console an interactive Internet TV ( Internet Protocol Television, IPTV), smart wearable devices, etc.
  • IPTV Internet Protocol Television
  • smart wearable devices etc.
  • the electronic equipment may also include network equipment and/or user equipment.
  • the network device includes, but is not limited to, a single network server, a server group composed of multiple network servers, or a cloud based on cloud computing (Cloud Computing) composed of a large number of hosts or network servers.
  • the network where the electronic device is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (Virtual Private Network, VPN) and the like.
  • VPN Virtual Private Network
  • a method for monitoring crop growth comprising:
  • the normalized difference vegetation index is one of the important parameters that reflect the growth and nutritional information of crops. It is used to detect vegetation growth status, vegetation coverage and eliminate some radiation errors.
  • the normalized difference vegetation index can reflect the background influence of the plant canopy, such as soil, wet ground, snow, dead leaves, roughness, etc., and is related to vegetation coverage.
  • the normalized difference vegetation index of the crops in the current region is based on the satellite images of the growing, sowing and maturing stages of the crops as a reference.
  • the sowing period indicates the period when the seeds of the crops are planted in the soil and has not yet grown and germinated
  • the growth period indicates the period when the crops break out of the ground and start to grow
  • the maturity period indicates the period when the crops can be harvested and fruits can be obtained.
  • the user selects the normalized difference vegetation index (Normalized Difference Vegetation Index, NDVI) image of the satellite image data in the agricultural scene, and selects the corresponding regional interval as the sample data for monitoring and analysis.
  • the current region represents a larger region, for example, divided by city. In order to monitor the growth of crops more comprehensively, the current region can be randomly divided into several different subregions, and each subregion represents a smaller subspace in the current region.
  • the current region is Jinan City, Shandong, and the subregions can be It refers to various districts and counties in Jinan City, such as Lixia District, Shizhong District, Huaiyin District, etc.
  • the crop growth status of the whole city can be further obtained.
  • users can comprehensively understand the growth status of crops according to the anomaly map, year-on-year map and ring-comparison map.
  • the distance map shows the difference between the average growth of crops in each sub-region and the same region, which realizes the overall comparison
  • the year-on-year graph shows the difference between the growth of crops in each sub-region and the same region in the same period before, and realizes the horizontal comparison.
  • users can clearly monitor the growth status of crops in the current region. It should be noted that users can select a single region or even multiple regions to monitor at the same time. For example, Zhangjiakou City and Chengde City can be selected.
  • the growth situation of the crops can be known, and according to the growth situation , Carry out the next crop care work in a targeted manner.
  • the number of acquired sub-regions in this application is at least two. Of course, the more sub-regions are acquired, the more accurate the monitoring information of crop growth in the current region will be.
  • step S20 judge the growth state of the crop according to the acquisition time of the normalized difference vegetation index, and the growth state includes at least the sowing period, the growth period and the maturity period; wherein, each growth state includes at least one reference range,
  • the reference range is the range of the normalized difference vegetation index calculated in advance based on the growth state of the crops.
  • the crops have three different growth states: the sowing stage, the growing stage and the mature stage. It is first necessary to compare the acquisition time of the Normalized Difference Vegetation Index with the time range corresponding to each growth state to determine the current state of the crop. Which one of the growth state is the sowing period, the growth period and the maturity period? The normalized difference vegetation index is then compared with the reference range contained in the growth state to judge the growth condition of the crop. Furthermore, since different crops have different growth states corresponding to different time ranges, in order to obtain the current growth state of the species more accurately.
  • the acquisition time of the normalized difference vegetation index before judging the growth state of the crop according to the acquisition time of the normalized difference vegetation index, it also includes: according to the different growth state of the crop in a year, preset the time range corresponding to each growth state. It can be understood that different crops have different growth states, and those skilled in the art can make adaptive settings according to actual conditions.
  • step S30 is performed, according to the growth state, the normalized difference vegetation index of each sub-region is compared with at least one reference range included in the growth state of the crops, and the corresponding sub-regions located in each reference range are judged and counted. quantity.
  • the normalized normalized vegetation index of crops in each subregion in the current region is sort the normalized normalized vegetation index of crops in each subregion in the current region according to the order of increasing normalized normalized vegetation index, and select the subregion with the smallest normalized normalized vegetation index, and sort its corresponding normalized vegetation index
  • the integrated vegetation index is compared with the preset reference ranges in the current growth state of the crops. If the normalized difference vegetation index is within a certain reference range, the number of sub-regions corresponding to this reference range is increased by one. If the normalized difference vegetation index is not within any reference range, the number of subregions corresponding to each reference range remains unchanged.
  • each reference range there are three reference ranges, namely 20-25, 26-30, and 31-50, and the normalized vegetation index of each sub-region is 22, 35, 21, and 18.
  • the number of sub-regions corresponding to the reference range of 20-25 is 2, and the number of sub-regions corresponding to 31-50 is 1. Since each reference range corresponds to a growing condition, by setting different reference ranges, the growing condition of crops can be understood more accurately. It can be understood that, in order to make the number of sub-regions corresponding to the final reference range accurate, in this embodiment, the reference range needs to be initialized first, that is, the number of sub-regions corresponding to each reference range is reset to zero.
  • the reference range is obtained in advance, and the specific acquisition process is as follows: Firstly, the growth curve of the normalized normalized vegetation index of the crops in each year is obtained in several consecutive years, and the growth curve can represent the normalized normalized vegetation index of the crops in this year. Unified vegetation index. Affected by realistic factors such as geographic location, geographic environment, and crop type, microscopic factors such as surface temperature, humidity, and light intensity are different in different regions, so that even if the same crop is planted in different regions, the normalized difference vegetation index is not the same. same. In order to more accurately monitor the growth of crops in different regions, it is necessary to select the sample data of the current region for many years. For example, select the sample data of the region in the past five years.
  • a normalized difference vegetation index fluctuates with the month. Growth curve.
  • a reference growth curve was obtained.
  • linear fitting can obtain a number of key points by selecting the value of the corresponding point in each growth curve, averaging the values of each point, and connecting several key points in sequence to obtain a reference growth curve. Therefore, the reference growth curve can represent the general growth level of crops in the region in each month. And according to the time corresponding to different growth states, the reference growth curve is divided into a sowing period curve, a growth period curve and a maturity period curve, respectively corresponding to the respective growth states of the crops.
  • One or more reference ranges corresponding to each growth state are obtained by calculating the respective standard deviations in the sowing period curve, the growth period curve and the maturity period curve, and processing the corresponding standard deviations equidistantly.
  • the least square method is used for linear fitting.
  • those skilled in the art may also use other methods for linear fitting, and the specific implementation method is not limited.
  • the process of obtaining at least one reference range corresponding to the maturity period includes:
  • a plurality of numerical values are preset, and the difference between adjacent numerical values is the same, and the plurality of numerical values are sequentially added to the standard deviation to obtain a plurality of first reference values;
  • each reference range is obtained by adding or subtracting the standard deviation to or from a corresponding preset value, and through such equidistant processing.
  • the process of obtaining the reference range of the mature stage is taken as an example.
  • the process of obtaining the reference range of the sowing stage and the growth stage is basically the same as that of the mature stage, and details are not repeated here.
  • the reference range is obtained based on the standard deviation, each reference range can represent the growing state of the crop in the current area. Specifically, M values are preset first to ensure that the difference between adjacent values remains consistent.
  • the standard deviation is used to make a difference with the M values to obtain M second reference values.
  • three values (a 1 , a 2 , a 3 ) can be preset, and the three values obtained after adding the standard deviation are: ⁇ +a 1 , ⁇ +a 2 and ⁇ +a 3 .
  • the differences between the standard deviation and these three values are: ⁇ -a 1 , ⁇ -a 2 and ⁇ -a 3 .
  • the reference range can be ( ⁇ -a 3 , ⁇ -a 2 ), ( ⁇ -a 2 , ⁇ -a 1 ), ( ⁇ -a 1 , ⁇ ), ( ⁇ , ⁇ +a 1 ), ( ⁇ + a 1 , ⁇ +a 2 ) and ( ⁇ +a 2 , ⁇ +a 3 ) six different reference ranges. It can be understood that those skilled in the art can adaptively set the number of reference ranges according to actual needs, which is not limited here.
  • the standard deviation of the normalized difference vegetation index of the month is calculated by formula (1):
  • x i is the normalized difference vegetation index of the i-th month
  • T k-1 is the start time of the mature period
  • T k is the end time of the mature period. It can be understood that the average value of the normalized difference vegetation index is obtained by adding the values of each month in the reference growth curve and then calculating the average, and the specific calculation process will not be repeated here.
  • step S40 includes the following processes:
  • the early warning standard includes a first-level early warning standard, a second-level early warning standard and a third-level early warning standard, and the early warning standard indicates the number of sub-regions.
  • the normalized difference vegetation index exceeds the preset normalized difference vegetation index threshold;
  • the multiple normalized vegetation indices of the current region selected by the user need to divide the current region according to the preset early warning standards, wherein the early warning standards include at least the first level early warning standard, the second level early warning standard and the third level
  • the first-level warning standard is a red warning
  • the second-level warning standard is an orange warning
  • the third-level warning standard is a yellow warning.
  • each early warning standard there is a reference range for the corresponding interval. For example, 10 reference ranges can be preset, and each reference range corresponds to a level.
  • the level corresponding to the reference range in the red early warning is higher than the level corresponding to the reference range in the orange early warning
  • the level corresponding to the reference range in the orange early warning is higher than the level corresponding to the reference range in the yellow early warning.
  • the preset early warning standard is that the warning range of the red warning is one to three levels
  • the warning range of the orange warning is four to six levels
  • the early warning range of the yellow warning is seven to ten levels.
  • the red warning indicates that the crops are in a highly dangerous state at this time, and professionals are urgently needed to enter the scene to intervene to avoid damage to the crops.
  • the severity of the orange warning is lower than that of the red warning, which means that the crops are in a more critical state at this time. Users can choose to send professionals to the orange warning area for crop care after dealing with the red warning area.
  • the severity of the yellow warning is lower than that of the orange warning, which means that although some values of the crops at this time do not meet the safety standard range, they are still in a relatively safe state, and the user does not need to take further care of the crops for the time being.
  • the number of reference ranges in the red warning can be obtained first, and the sub-regions corresponding to each reference range can be added to obtain the number of sub-regions in the red warning. Then use the same method to obtain the number of yellow warning and orange warning neutron regions respectively.
  • the red warning there are 2 reference ranges in the red warning, corresponding to 1 and 2 sub-regions respectively, 3 reference ranges in the orange warning, corresponding to 2, 5 and 3 sub-regions respectively, and 1 reference range in the yellow warning , corresponding to 4 sub-regions. And the above sub-regions are different. According to the statistics, there are 3 red warning neutron areas, 10 orange warning neutron areas, and 4 yellow warning neutron areas. It can be seen that there are many orange warning areas in this area, and professionals are required to go to the scene , to further strengthen management.
  • the user can customize the setting of the warning standard by changing the number of reference ranges included in each warning standard. For example, the user can set the warning range of the red warning to be the first to the fifth reference range, the warning range of the orange warning to be the sixth to the seventh reference range, and the warning range of the yellow warning to be the eighth to the tenth reference range Reference range.
  • This setup can be customized according to the crop characteristics of each region. Further, the set region will display the location, alarm level and degree of the region in detail in the form of a list and maintain an editable state.
  • the number of three-level alarm information in the satellite remote sensing movie star area conforms to the most specific principle of display within the visual range.
  • Users can view the number of alarm information corresponding to different geographical levels by zooming in or out on the remote sensing map. Thereby improving the user monitoring experience. Users can independently set the corresponding trigger conditions. For example, firstly, the standard deviation is processed according to the sample data, and the system will generate a default reference value of the national standard, for example: levels 2 to 4 are yellow warnings, levels 5 to 7 are orange warnings, and levels 8 to 10 are red warn.
  • levels 2 to 4 are yellow warnings
  • levels 5 to 7 are orange warnings
  • levels 8 to 10 are red warn.
  • the range of exceeding the preset normalized difference vegetation index value is 80% to 90%, it is a nine-level warning.
  • the preset normalized difference vegetation index value is exceeded When the range is 90% to 100%, it is ten-level warning.
  • Users refer to the national standard value and adjust the regional standard value up and down according to the geographical location, crop type and environmental conditions of their own samples. When processing sample data, users can further adjust parameters individually to assist crop monitoring and early warning analysis. In the background of remote sensing technology and agriculture, if the real data is too high or too low, it has important practical significance for agricultural forecasting and risk prevention and control.
  • the related data and models can also be deployed on the blockchain to prevent the data from being maliciously tampered with.
  • the crop growth monitoring system includes: a data acquisition module 111 , a growth state acquisition module 112 , a sub-area comparison module 113 and a growth monitoring module 114 .
  • the module referred to in this application refers to a series of computer program segments that can be executed by the processor 13 and can complete fixed functions, and are stored in the memory 12 .
  • the data acquisition module 111 is used to acquire the normalized difference vegetation index of at least two sub-regions of crops in the current region; wherein, the current region includes at least two sub-regions.
  • the normalized difference vegetation index is one of the important parameters that reflect the growth and nutritional information of crops. It is used to detect vegetation growth status, vegetation coverage and eliminate some radiation errors.
  • the normalized difference vegetation index can reflect the background influence of the plant canopy, such as soil, wet ground, snow, dead leaves, roughness, etc., and is related to vegetation coverage.
  • the normalized difference vegetation index of the crops in the current region is based on the satellite images of the growing, sowing and maturing stages of the crops as a reference.
  • the sowing period indicates the period when the seeds of the crops are planted in the soil and has not yet grown and germinated
  • the growth period indicates the period when the crops break out of the ground and start to grow
  • the maturity period indicates the period when the crops can be harvested and fruits can be obtained.
  • the user selects the normalized difference vegetation index (Normalized Difference Vegetation Index, NDVI) image of the satellite image data in the agricultural scene, and selects the corresponding regional interval as the sample data for monitoring and analysis.
  • the current region represents a larger region, for example, divided by city. In order to monitor the growth of crops more comprehensively, the current region can be randomly divided into several different subregions, and each subregion represents a smaller subspace in the current region.
  • the current region is Jinan City, Shandong, and the subregions can be It refers to various districts and counties in Jinan City, such as Lixia District, Shizhong District, Huaiyin District, etc.
  • the crop growth status of the whole city can be further obtained.
  • users can comprehensively understand the growth status of crops according to the anomaly map, year-on-year map and ring-comparison map.
  • the distance map shows the difference between the average growth of crops in each sub-region and the same region, which realizes the overall comparison
  • the year-on-year graph shows the difference between the growth of crops in each sub-region and the same region in the same period before, and realizes the horizontal comparison.
  • users can clearly monitor the growth status of crops in the current region. It should be noted that users can select a single region or even multiple regions to monitor at the same time. For example, Zhangjiakou City and Chengde City can be selected.
  • Zhangjiakou City and Chengde City can be selected.
  • the growth state acquisition module 112 is used to judge the growth state of the crops according to the acquisition time of the normalized difference vegetation index, and the growth state includes at least the sowing stage, the growth stage and the maturity stage; wherein, each growth state includes at least A reference range, where the reference range is the range of the normalized difference vegetation index obtained by pre-calculation based on the growth status of the crops.
  • the crops have three different growth states: the sowing stage, the growing stage and the mature stage. It is first necessary to compare the acquisition time of the Normalized Difference Vegetation Index with the time range corresponding to each growth state to determine the current state of the crop. Which one of the growth state is the sowing period, the growth period and the maturity period? The normalized difference vegetation index is then compared with the reference range contained in the growth state to judge the growth condition of the crop. Furthermore, since different crops have different growth states corresponding to different time ranges, in order to obtain the current growth state of the species more accurately.
  • the acquisition time of the normalized difference vegetation index before judging the growth state of the crop according to the acquisition time of the normalized difference vegetation index, it also includes: according to the different growth state of the crop in a year, preset the time range corresponding to each growth state. It can be understood that different crops have different growth states, and those skilled in the art can make adaptive settings according to actual conditions.
  • the sub-area comparison module 113 is used to compare the normalized difference vegetation index of each sub-area with at least one reference range included in the growth state of the crops according to the growth state, and determine and count the corresponding areas within each reference range. The number of subregions.
  • the normalized normalized vegetation index of crops in each subregion in the current region is sort the normalized normalized vegetation index of crops in each subregion in the current region according to the order of increasing normalized normalized vegetation index, and select the subregion with the smallest normalized normalized vegetation index, and sort its corresponding normalized vegetation index
  • the integrated vegetation index is compared with the preset reference ranges in the current growth state of the crops. If the normalized difference vegetation index is within a certain reference range, the number of sub-regions corresponding to this reference range is increased by one. If the normalized difference vegetation index is not within any reference range, the number of subregions corresponding to each reference range remains unchanged.
  • each reference range there are three reference ranges, namely 20-25, 26-30, and 31-50, and the normalized vegetation index of each sub-region is 22, 35, 21, and 18.
  • the number of sub-regions corresponding to the reference range of 20-25 is 2, and the number of sub-regions corresponding to 31-50 is 1. Since each reference range corresponds to a growing condition, by setting different reference ranges, the growing condition of crops can be understood more accurately. It can be understood that, in order to make the number of sub-regions corresponding to the final reference range accurate, in this embodiment, the reference range needs to be initialized first, that is, the number of sub-regions corresponding to each reference range is reset to zero.
  • the growing situation monitoring module 114 is used to perform hierarchical early warning based on the counted number of sub-regions, wherein the hierarchical early warning standard is preset.
  • the multiple normalized vegetation indices of the current region selected by the user need to divide the current region according to the preset early warning standards, wherein the early warning standards include at least the first level early warning standard, the second level early warning standard and the third level
  • the first-level warning standard is a red warning
  • the second-level warning standard is an orange warning
  • the third-level warning standard is a yellow warning.
  • each early warning standard there is a reference range for the corresponding interval. For example, 10 reference ranges can be preset, and each reference range corresponds to a level.
  • the level corresponding to the reference range in the red early warning is higher than the level corresponding to the reference range in the orange early warning
  • the level corresponding to the reference range in the orange early warning is higher than the level corresponding to the reference range in the yellow early warning.
  • the preset early warning standard is that the warning range of the red warning is one to three levels
  • the warning range of the orange warning is four to six levels
  • the early warning range of the yellow warning is seven to ten levels.
  • the red warning indicates that the crops are in a highly dangerous state at this time, and professionals are urgently needed to enter the scene to intervene to avoid damage to the crops.
  • the severity of the orange warning is lower than that of the red warning, which means that the crops are in a more critical state at this time. Users can choose to send professionals to the orange warning area for crop care after dealing with the red warning area.
  • the severity of the yellow warning is lower than that of the orange warning, which means that although some values of the crops at this time do not meet the safety standard range, they are still in a relatively safe state, and the user does not need to take further care of the crops for the time being.
  • the number of reference ranges in the red warning can be obtained first, and the sub-regions corresponding to each reference range can be added to obtain the number of sub-regions in the red warning. Then use the same method to obtain the number of yellow warning and orange warning neutron regions respectively.
  • the red warning there are 2 reference ranges in the red warning, corresponding to 1 and 2 sub-regions respectively, 3 reference ranges in the orange warning, corresponding to 2, 5 and 3 sub-regions respectively, and 1 reference range in the yellow warning , corresponding to 4 sub-regions. And the above sub-regions are different. According to the statistics, there are 3 red warning neutron areas, 10 orange warning neutron areas, and 4 yellow warning neutron areas. It can be seen that there are many orange warning areas in this area, and professionals are required to go to the scene , to further strengthen management.
  • the user can customize the setting of the warning standard by changing the number of reference ranges included in each warning standard. For example, the user can set the warning range of the red warning to be the first to the fifth reference range, the warning range of the orange warning to be the sixth to the seventh reference range, and the warning range of the yellow warning to be the eighth to the tenth reference range Reference range.
  • This setup can be customized according to the crop characteristics of each region. Further, the set region will display the location, alarm level and degree of the region in detail in the form of a list and maintain an editable state.
  • the number of three-level alarm information in the satellite remote sensing movie star area conforms to the most specific principle of display within the visual range.
  • Users can view the number of alarm information corresponding to different geographical levels by zooming in or out on the remote sensing map. Thereby improving the user monitoring experience. Users can independently set corresponding trigger conditions. Users refer to the national standard value and adjust the regional standard value up and down according to the geographical location, crop type and environmental conditions of their own samples. When processing sample data, users can further adjust parameters individually to assist crop monitoring and early warning analysis. In the background of remote sensing technology and agriculture, if the real data is too high or too low, it has important practical significance for agricultural forecasting and risk prevention and control.
  • the crop growth monitoring system in this embodiment is a system corresponding to the above-mentioned crop growth monitoring method.
  • the crop growth monitoring system of this embodiment can be implemented in cooperation with the crop growth monitoring method.
  • the relevant technical details mentioned in the crop growth monitoring system of this embodiment can also be applied to the above-mentioned crop growth monitoring method.
  • the above functional modules may be fully or partially integrated into one physical entity, and may also be physically separated. And these modules can all be implemented in the form of calling software through processing elements; they can also be implemented in the form of hardware; some modules can also be implemented in the form of calling software through processing elements, and some modules can be implemented in the form of hardware. In addition, all or part of these modules can be integrated together, and can also be implemented independently.
  • the processing element mentioned here may be an integrated circuit with signal processing capabilities.
  • part or all of the steps of the above methods, or the above functional modules may be implemented by hardware integrated logic circuits in the processor element or instructions in the form of software.
  • FIG. 6 it is a schematic structural diagram of the electronic device of the present application.
  • the electronic device 1 may include a memory 12 , a processor 13 and a bus, and may also include a computer program stored in the memory 12 and operable on the processor 13 , such as a character recognition program based on direction detection.
  • the memory 12 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example: SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. .
  • the memory 12 may be an internal storage unit of the electronic device 1 in some embodiments, such as a mobile hard disk of the electronic device 1 .
  • the memory 12 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk equipped on the electronic device 1, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD ) card, flash card (Flash Card), etc.
  • the memory 12 may also include both an internal storage unit of the electronic device 1 and an external storage device.
  • the memory 12 can not only be used to store application software and various data installed in the electronic device 1 , such as the code of the character recognition program based on direction detection, but also can be used to temporarily store outputted or to-be-outputted data.
  • the processor 13 may be composed of integrated circuits, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits with the same function or different functions, including one or more central processing units.
  • Central Processing unit CPU
  • microprocessor digital processing chip
  • graphics processor and a combination of various control chips, etc.
  • the processor 13 is the control core (Control Unit) of the electronic device 1, and uses various interfaces and lines to connect the various components of the entire electronic device 1, and runs or executes programs or modules stored in the memory 12 (such as executing physical examination report verification program, etc.), and call the data stored in the memory 12 to execute various functions of the electronic device 1 and process data.
  • the processor 13 executes the operating system of the electronic device 1 and various installed application programs.
  • the processor 13 executes the application program to implement the steps in the above embodiments of the method for monitoring growth of each crop, such as the steps shown in FIG. 1 .
  • the computer program may be divided into one or more modules, and the one or more modules are stored in the memory 12 and executed by the processor 13 to complete the present application.
  • the one or more modules may be a series of computer program instruction segments capable of accomplishing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device 1 .
  • the computer program can be divided into a data acquisition module 111 , a growth status acquisition module 112 , a sub-area comparison module 113 and a growth monitoring module 114 .
  • the above-mentioned integrated units implemented in the form of software function modules can be stored in a computer-readable storage medium.
  • the above-mentioned software function modules are stored in a storage medium, and include several instructions to enable a computer device (which may be a personal computer, computer device, or network device, etc.) or a processor (processor) to perform the physical examination described in each embodiment of the present application. Partial functionality of the item recommendation method.
  • the computer-readable storage medium may be non-volatile or volatile.
  • Blockchain essentially a decentralized database, is a series of data blocks associated with each other using cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify its Validity of information (anti-counterfeiting) and generation of the next block.
  • the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
  • the bus may be a peripheral component interconnect standard (PCI for short) bus or an extended industry standard architecture (EISA for short) bus or the like.
  • PCI peripheral component interconnect standard
  • EISA extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one arrow is used in FIG. 6 , but it does not mean that there is only one bus or one type of bus.
  • the bus is configured to realize connection and communication between the memory 12 and at least one processor 13 and the like.
  • the crop growth monitoring method, system, equipment and medium of the present application by obtaining multiple normalized vegetation indices in the satellite image of the crops in the current region, the user can analyze the crop growth according to the red, orange and yellow alarm positions and quantities in the region Monitoring and early warning situations.
  • the remote sensing data is not only charted, but also the visualization of alarm information is further realized. This not only improves the intuitive experience and efficiency of user data analysis, but also satisfies the user's data processing to the greatest extent through a number of customized methods.
  • the free space for analysis and display ensures the intuition and image of remote sensing data.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种农作物长势的监测方法、系统、设备及介质，涉及人工智能技术领域。农作物长势的监测方法包括：获取当前地域中农作物的至少两个子地域的归一化植被指数（S1）；根据归一化植被指数的获取时间，判断农作物的生长状态，生长状态至少包括播种期、生长期和成熟期（S2）；其根据生长状态，将各子地域的归一化植被指数与农作物的生长状态包含的至少一个参考范围进行比较，判断并统计位于各参考范围内对应子地域的数量（S3）；根据统计的子地域的数量，进行分级预警（S4）。上述方法将当前地域中农作物的多个归一化植被指数与预设的参考范围进行比较，根据参考范围中对应子地域的数量，监测农作物的长势。实现了告警信息的可视化，更利于用户监测作物的生长状态。

Description

农作物长势的监测方法、系统、设备及介质
优先权申明
本申请要求于 2022年 3月 3日提交中国专利局、申请号为 202210201040.7，发明名称为“ 农作物长势的监测方法、系统、设备及介质”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
本申请涉及人工智能技术领域，特别涉及一种农作物长势的监测方法、系统、设备及介质。
背景技术
随着计算机技术和数字图像处理技术的发展，遥感技术在农业生产中的应用越来越普遍。归一化植被数据在世界范围内被广泛应用于监测干旱、监测和预测农业生产、协助预测存在火险的地域以及绘制沙漠扩侵图等场景。
由于遥感卫星拍摄的原始数据图像是周期性的，图像数据的时间周期横跨农农作物的生长期、播种期和成熟期，需要根据影像归一化植被数据值和农作物归一化植被数据值标准化对应农农作物生长的密度和强度等数据，并通过距平图、同比图、环比图等形式辅助用户对农农作物的长势监测和预警分析。发明人意识到目前市面上尚未有在卫星遥感农业场景下的归一化植被数据监测预警交互策略。
需要说明的是，在上述背景技术部分公开的信息仅用于加强对本公开的背景的理解，因此可以包括不构成对本领域普通技术人员已知的现有技术的信息。
发明内容
本申请的目的在于提供一种农作物长势的监测方法、系统、设备及介质，进而至少在一定程度上克服由于相关技术的限制和缺陷而导致的一个或者多个问题。
为实现上述目的及其他相关目的，本申请提供一种农作物长势的监测方法，包括：
获取当前地域中农作物的若干个子地域的归一化植被指数；其中，所述当前地域包括多个子地域；
根据归一化植被指数的获取时间，判断所述农作物的生长状态，所述生长状态至少包括播种期、生长期和成熟期；其中，每个生长状态包含至少一个参考范围，参考范围是基于所述农作物的生长状态预先计算获得的归一化植被指数的范围；
根据所述生长状态，将各子地域的归一化植被指数与所述农作物的生长状态包含的至少一个参考范围进行比较，判断并统计位于各参考范围内对应子地域的数量；
根据统计的子地域的所述数量，进行分级预警，其中，分级的预警标准是预先设置的。
为实现上述目的及其他相关目的，本申请还提供一种农作物长势的监测系统，包括：
数据获取模块，用于获取当前地域中农作物的至少两个子地域的归一化植被指数；其中，所述当前地域包括多个子地域；
生长状态获取模块，用于根据归一化植被指数的获取时间，判断所述农作物的生长状态，所述生长状态至少包括播种期、生长期和成熟期；其中，每个生长状态包含若干个参考范围，参考范围是基于所述农作物的生长状态预先计算获得的归一化植被指数的范围；
子地域比较模块，用于根据所述生长状态，将各子地域的归一化植被指数与所述农作物的生长状态包含的至少一个参考范围进行比较，判断并统计位于各参考范围内对应子地域的数量；
长势监测模块，用于根据统计的子地域的所述数量，进行分级预警，其中，分级的预警 标准是预先设置的。
为实现上述目的及其他相关目的，本申请还提供一种电子设备，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程序，所述处理器执行所述计算机程序时实现上述方法的步骤。
为实现上述目的及其他相关目的，本申请还提供一种计算机可读存储介质，其上存储于计算机程序，所述计算机程序被处理器执行时实现上述方法的步骤。
本申请的农作物长势的监测方法、系统、设备及介质，获取当前地域农作物卫星图像中，多个归一化植被指数，用户根据地域内红橙黄三色的告警位置和数量分析农作物长势监测和预警情况。通过以上交互策略将遥感数据图表化，实现告警信息的可视化，保证遥感数据的直观和形象。
附图说明
通过参考附图会更加清楚的理解本申请的特征和优点，附图是示意性的而不应理解为对本申请进行任何限制，在附图中：
图1显示为本申请一实施例中农作物长势的监测方法的流程示意图；
图2显示为本申请一实施例中参考范围获得的流程示意图；
图3显示为本申请一实施例中成熟期参考范围获得的流程示意图；
图4显示为本申请一实施例中步骤S40的流程示意图；
图5显示为本申请一实施例中农作物长势的监测系统的结构框图；
图6显示为本申请一实施例中电子设备的结构示意图。
具体实施方式
以下通过特定的具体实例说明本申请的实施方式，本领域技术人员可由本说明书所揭露的内容轻易地了解本申请的其他优点与功效。本申请还可以通过另外不同的具体实施方式加以实施或应用，本说明书中的各项细节也可以基于不同观点与应用，在没有背离本申请的精神下进行各种修饰或改变。
请参阅图1-6。需要说明的是，本实施例中所提供的图示仅以示意方式说明本申请的基本构想，遂图式中仅显示与本申请中有关的组件而非按照实际实施时的组件数目、形状及尺寸绘制，其实际实施时各组件的型态、数量及比例可为一种随意的改变，且其组件布局型态也可能更为复杂。
图1示出了本申请的农作物长势的监测方法的流程示意图。
所述农作物长势的监测方法应用于一个或者多个电子设备中，所述电子设备是一种能够按照事先设定或存储的指令，自动进行数值计算和/或信息处理的设备，其硬件包括但不限于微处理器、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程门阵列(Field－Programmable Gate Array，FPGA)、数字处理器(Digital Signal Processor，DSP)、嵌入式设备等。
所述电子设备可以是任何一种可与用户进行人机交互的电子产品，例如，个人计算机、平板电脑、智能手机、个人数字助理(Personal Digital Assistant，PDA)、游戏机、交互式网络电视(Internet Protocol Television，IPTV)、智能式穿戴式设备等。
所述电子设备还可以包括网络设备和/或用户设备。其中，所述网络设备包括，但不限于单个网络服务器、多个网络服务器组成的服务器组或基于云计算(Cloud Computing)的由大量主机或网络服务器构成的云。
所述电子设备所处的网络包括但不限于互联网、广域网、城域网、局域网、虚拟专用网络(Virtual Private Network，VPN)等。
下面将结合图1来详细阐述本申请的农作物长势的监测方法。
一种农作物长势的监测方法，包括：
S10、获取当前地域中农作物的至少两个子地域的归一化植被指数；其中，所述当前地 域包括至少两个子地域。
归一化植被指数是反应农作物长势和营养信息的重要参数之一，是检测植被生长状态、植被覆盖度和消除部分辐射误差等。归一化植被指数能反映出植物冠层的背景影响，如土壤、潮湿地面、雪、枯叶、粗糙度等，且与植被覆盖有关。在本实施例中，当前地域中农作物的归一化植被指数是以农作物生长期、播种期和成熟期的卫星图像作为参考。其中，播种期表示将农作物的种子等种植到土壤中，尚未生长发芽的时期，生长期表示作物破土而出，开始生长的时期，成熟期表示可以对农作物进行收割，获得果实的时期。用户选择农业场景下的卫星影像数据的归一化植被指数(Normalized Difference Vegetation Index，NDVI)图像，并选取对应的地域区间作为监测分析的样本数据。当前地域表示一个较大的地域范围，例如以市为单位进行划分。为了更加全面的监测作物的长势，可将当前地域随机划分为若干个不同子地域，每一个子地域表征当前地域中一个范围较小的子空间，例如，当前地域是山东济南市，子地域可以是济南市中各个区县，例如历下区、市中区、槐荫区等。通过监测每个区的作物长势，可以进一步获得整个市作物的长势状况。为了更加直观看到农作物长势变化情况，用户可以根据距平图、同比图和环比图综合了解作物的长势状态。其中，距平图表示各子地域农作物与同地域农作物平均长势的差异度，实现全局的比较，同比图表示各子地域农作物与之前同期同地域农作物长势的差异度，实现横向的比较，环比图表示各子地域农作物与上个月同地域农作物长势的差异度，实现纵向的比较。通过这种横向、纵向和全局的比较，用户可以清楚的监测到当前地域农作物的生长状况。需要说明的是，用户可选取单个地区甚至多个地区同时监测，例如选取张家口市和承德市，通过监测对应植被或作物的归一化植被指数，可以获知农作物的长势情况，并可根据长势情况，有针对性的进行下一步作物的护理工作。需要说明的是，考虑到数据测量的准确性，本申请中获取子地域的数量至少为两个，当然，获取的子地域数量越多，最终当前地域农作物长势的监测信息越准确。
接着进行步骤S20、根据归一化植被指数的获取时间，判断所述农作物的生长状态，所述生长状态至少包括播种期、生长期和成熟期；其中，每个生长状态包含至少一个参考范围，参考范围是基于所述农作物的生长状态预先计算获得的归一化植被指数的范围。
本实施例中，由于农作物具有播种期、生长期和成熟期三个不同的生长状态，首先需要将归一化植被指数的获取时间和各生长状态对应的时间范围进行比较，判断当前农作物所处的生长状态具体为播种期、生长期和成熟期中的哪一个。然后将归一化植被指数与该生长状态中包含的参考范围进行比较，判断农作物的长势。进一步地，由于不同的农作物其生长状态对应的时间范围不同，为了更加精确的获得当前物种的生长状态。本实施例中，根据归一化植被指数的获取时间，判断所述农作物的生长状态之前，还包括：根据农作物一年中不同的生长状态，预设各生长状态对应的时间范围。可以理解的是，不同农作物的生长状态各不相同，本领域技术人员可根据实际情况适应性设置。
接着，执行步骤S30、根据所述生长状态，将各子地域的归一化植被指数与所述农作物的生长状态包含的至少一个参考范围进行比较，判断并统计位于各参考范围内对应子地域的数量。
本实施例中，首先按照归一化植被指数递增的顺序，将当前地域中各子地域农作物的归一化植被指数进行排序，并选择归一化植被指数最小的子地域，将其对应的归一化植被指数与农作物当前生长状态中，预设的各参考范围进行比较。若该归一化植被指数处于某一个参考范围内，则此参考范围对应的子地域数量增加一个。若该归一化植被指数不处于任何一个参考范围内，则各参考范围对应的子地域数量保持不变。比较完成后，选择另一个子地域农作物的归一化植被指数继续与各参考范围进行比较，直至当前地域中所有子地域均比较完成后，即可获得当前地域在各参考范围中对应的子地域的数量。作为示例，参考范围有三个，分别为20-25,26-30,31-50，各子地域归一化植被指数为22、35、21、18。则将所有子地域的归一化植被指数与参考范围比较完成后，获得参考范围为20-25对应的子地域数量为2个， 31-50对应的子地域数量为1个。由于每个参考范围对应一种长势状态，通过设定不同的参考范围，可以更精确的了解农作物的长势情形。可以理解的是，为了使最终参考范围对应的子地域数量准确，在本实施例中，需要先对参考范围进行初始化，也即将各参考范围对应的子地域数量清零。
进一步地，如图2所示，所述若干个参考范围是预先计算获得的，具体包括：
S301、获取至少连续两年中，农作物的若干个归一化植被指数生长曲线，每个生长曲线表示农作物一年中每个月的归一化植被指数变化情况；
S302、将若干个所述归一化植被指数生长曲线进行线性拟合，获得农作物的参考生长曲线；
S303、根据预设的生长状态，将所述参考生长曲线划分为播种期曲线、生长期曲线和成熟期曲线；
S304、依次计算所述播种期曲线、生长期曲线和成熟期曲线中，对应的归一化植被指数的标准差，并对各标准差进行等距处理，分别获得与所述播种期、所述生长期和所述成熟期相对应的至少一个参考范围。
在本实施例中，参考范围是预先获得，具体获取过程为：首先获得连续若干年中，每一年农作物归一化植被指数生长曲线，该生长曲线可以表示本年度中，农作物每个月的归一化植被指数。受到地域位置、地理环境和农作物类型等现实因素的影响，导致不同地域的地表温度、湿度、光照强度等微观因素有所差异，从而使得不同地域即使种植同一种作物，归一化植被指数也不相同。为了更加精确的监测不同地域作物的长势，需要选取当前地域连续多年的样本数据，例如，选择近五年该地域的样本数据，对于每一年，均建立一条归一化植被指数随月份波动的生长曲线。将这五条生长曲线进行线性拟合后，获得一条参考生长曲线。其中，线性拟合可通过选取每条生长曲线中对应点的数值，对各点的数值求平均获得若干个关键点，将若干个关键点依次相连，获得参考生长曲线。因此，该参考生长曲线可以表征该地域农作物各月份的普遍生长水平。并根据不同的生长状态对应的时间，将参考生长曲线划分为播种期曲线、生长期曲线和成熟期曲线，分别对应农作物各自的生长状态。通过计算播种期曲线、生长期曲线和成熟期曲线中各自的标准差，分别将对应的标准差等距处理后，获得每个生长状态对应的一个或多个参考范围。需要说明的是，本实施例中使用最小二乘法进行线性拟合，当然，本领域技术人员还可使用其他方法进行线性拟合，具体实现方法不做限定。
进一步地，如图3所示，所述成熟期相对应的至少一个参考范围获得过程包括：
S3041、获得所述成熟期曲线中，各月份归一化植被指数，并计算各月份归一化植被指数的标准差；
S3042、预设有多个数值，且相邻数值之间的差值相同，并将多个数值依次与所述标准差相加，获得多个第一参考值；
S3043、将所述标准差依次减去所述多个数值，获得多个第二参考值；
S3044、将所述多个第一参考值和所述多个第二参考值结合，获得所述成熟期对应的至少一个参考范围。
在本实施例中，通过将标准差加上或减去对应预设的数值，通过这种等距处理的方式，获得若干个参考范围。本实施例中以成熟期的参考范围获得的过程进行举例，当然，可以理解的是，播种期和生长期参考范围的获得过程与成熟期基本相同，在此不做赘述。由于参考范围是根据标准差获得的，因此每个参考范围都可以表示当前地域中作物的长势状态。具体地，首先预设有M个数值，保证相邻数值的差值保持一致。然后将每一个数值分别与标准差相加，获得M个第一参考值，第一参考值的公式为D 1 k＝σ+a k(k＝1,2,…M)，其中，D 1 k为第k个第一参考值，a k为第k个数值。相似地，为了保证数据的等距处理，使用标准差与M个数值作差，获得M个第二参考值。第二参考值的公式为D 2 k＝σ+a k，其中，D 2 k为第k 个第二参考值。作为示例，可预设有3个数值(a 1、a 2、a 3)，加上标准差后得到的3个值为：σ+a 1、σ+a 2和σ+a 3。相应地，标准差与此3个数值的差为：σ-a 1、σ-a 2和σ-a 3。则参考范围可以是(σ-a 3，σ-a 2)、(σ-a 2，σ-a 1)、(σ-a 1，σ)、(σ，σ+a 1)、(σ+a 1，σ+a 2)以及(σ+a 2，σ+a 3)六个不同的参考范围。可以理解的是，本领域技术人员可根据实际需要适应性设置参考范围的数量，在此不做限定。
在本实施例中，通过公式(1)计算所述月份归一化植被指数的标准差：
Figure PCTCN2022089634-appb-000001
其中，
Figure PCTCN2022089634-appb-000002
为归一化植被指数的平均值，x i为第i个月归一化植被指数，T k-1为成熟期的开始时间，T k为成熟期的结束时间。可以理解的是，归一化植被指数的平均值是通过在参考生长曲线中将各月的数值相加后求平均获得，具体计算过程在此不再赘述。
具体地，如图4所示，步骤S40包括以下过程：
S41、基于当前地域中农作物的生长状态，统计每个预警标准中包含的子地域的数量；其中，预警标准包括一级预警标准、二级预警标准和三级预警标准，预警标准表示子地域的归一化植被指数超过预设的归一化植被指数阈值；
S42、将每个预警标准中子地域的数量与对应预设的预警阈值比较，若子地域的数量大于对应的预警阈值，发出对应的预警信息。
本实施例中，用户选取的当前地域的多个归一化植被指数，需要按照预设的预警标准对当前地域进行划分，其中，预警标准至少包括一级预警标准、二级预警标准和三级预警标准，优选地，为了使色彩显示更引人注目，所述一级预警标准为红色预警、所述二级预警标准为橙色预警、所述三级预警标准为黄色预警。在每个预警标准中，都具有对应区间的参考范围。例如，可预先设置10个参考范围，每个参考范围对应一个等级。且红色预警中参考范围对应的等级高于橙色预警中参考范围对应的等级，橙色预警中参考范围对应的等级高于黄色预警中参考范围对应的等级，当作物长势落在对应预警标准内时，可以及时有效提醒用户作物长势。具体地，预设的预警标准为红色预警的预警区间是一到三级，橙色预警的预警区间是四到六级，黄色预警的预警区间是七到十级。红色预警表示此时的作物处于高度危险的状态，急需专业人员进入现场进行干预，从而避免作物受损。橙色预警的严重程度低于红色预警，表示此时的作物处于较危急的状态，用户可以选择在处理完红色预警地域后，派专业人员前往橙色预警地域进行作物护理。黄色预警的严重程度低于橙色预警，表示此时的作物虽然有部分数值不符合安全标准范围，但还处于相对较安全的状态，用户可以暂且不用对作物进行进一步护理。实际操作时，可先获得红色预警中参考范围的数量，并将每一个参考范围对应的子地域相加，获得红色预警中子地域的数量。再使用相同的方式，分别获得黄色预警和橙色预警中子地域的数量。作为示例，红色预警中参考范围有2个，分别对应1个和2个子地域，橙色预警中参考范围有3个，分别对应2个、5个和3个子地域，黄色预警中参考范围有1个，对应有4个子地域。且上述子地域各不相同。统计可知，红色预警中子地域有3个，橙色预警中子地域有10个，黄色预警中子地域有4个，由此可知，该地域中橙色预警的地域数量较多，需要专业人员前往现场，进一步加强管理。
需要说明的是，本申请中，用户可以通过改变每个预警标准含有的参考范围的数量，实现自定义设置预警标准。例如，用户可设置红色预警的预警区间是第一个到第五个参考范围，橙色预警的预警区间是第六个到第七个参考范围，黄色预警的预警区间是第八个到第十个参考范围。这种设置可根据每个地域的作物特色进行自定义设置。进一步地，已设置的地域会以列表的形式详细展示该地域位置、告警等级和告警程度并保持可编辑状态。卫星遥感影星地域内的三级告警信息数量符合视觉范围内展示最具体化原则，用户可根据放大或缩小遥感地图的形式实现观看不同地域层级所对应的告警信息数量。从而提升用户监测体验。用户可 自主设置对应的触发条件。例如，首先根据样本数据进行标准差处理十级分档，系统会生成一个全国标准的默认参考值，例如：二到四级为黄色警告，五到七级为橙色警告，八到十级为红色警告。通过设定当前归一化植被指数的数值超过预设归一化植被指数值的70％则发出红色告警，且在红色告警中分为三个预警区间，当超过预设归一化植被指数值的范围为70％至80％时，为八级预警，当超过预设归一化植被指数值的范围为80％至90％时，为九级预警，当超过预设归一化植被指数值的范围为90％至100％时，为十级预警。用户参考全国标准值并依据己方样本的地域位置、作物种类和环境状况进行上下浮动调整地域标准值，在处理样本数据时可进一步个性化调整参数以辅助农作物监测和预警分析。在遥感技术和农业背景下，如果真实数据过高或者过低则对农业预测和风险防控都有重要现实意义。
需要说明的是，在本申请中，为了进一步保证数据的安全性，还可以将涉及到的数据及模型部署于区块链，以防止数据被恶意篡改。
需要说明的是，上面各种方法的步骤划分，只是为了描述清楚，实现时可以合并为一个步骤或者对某些步骤进行拆分，分解为多个步骤，只要包含相同的逻辑关系，都在本专利的保护范围内；对算法中或者流程中添加无关紧要的修改或者引入无关紧要的设计，但不改变其算法和流程的核心设计都在该专利的保护范围内。
如图5所示，是本申请的农作物长势的监测系统的结构框图。所述农作物长势的监测系统包括：数据获取模块111，生长状态获取模块112，子地域比较模块113和长势监测模块114。本申请所称的模块是指一种能够被处理器13所执行，并且能够完成固定功能的一系列计算机程序段，其存储在存储器12中。
所述数据获取模块111用于获取当前地域中农作物的至少两个子地域的归一化植被指数；其中，所述当前地域包括至少两个子地域。
归一化植被指数是反应农作物长势和营养信息的重要参数之一，是检测植被生长状态、植被覆盖度和消除部分辐射误差等。归一化植被指数能反映出植物冠层的背景影响，如土壤、潮湿地面、雪、枯叶、粗糙度等，且与植被覆盖有关。在本实施例中，当前地域中农作物的归一化植被指数是以农作物生长期、播种期和成熟期的卫星图像作为参考。其中，播种期表示将农作物的种子等种植到土壤中，尚未生长发芽的时期，生长期表示作物破土而出，开始生长的时期，成熟期表示可以对农作物进行收割，获得果实的时期。用户选择农业场景下的卫星影像数据的归一化植被指数(Normalized Difference Vegetation Index，NDVI)图像，并选取对应的地域区间作为监测分析的样本数据。当前地域表示一个较大的地域范围，例如以市为单位进行划分。为了更加全面的监测作物的长势，可将当前地域随机划分为若干个不同子地域，每一个子地域表征当前地域中一个范围较小的子空间，例如，当前地域是山东济南市，子地域可以是济南市中各个区县，例如历下区、市中区、槐荫区等。通过监测每个区的作物长势，可以进一步获得整个市作物的长势状况。为了更加直观看到农作物长势变化情况，用户可以根据距平图、同比图和环比图综合了解作物的长势状态。其中，距平图表示各子地域农作物与同地域农作物平均长势的差异度，实现全局的比较，同比图表示各子地域农作物与之前同期同地域农作物长势的差异度，实现横向的比较，环比图表示各子地域农作物与上个月同地域农作物长势的差异度，实现纵向的比较。通过这种横向、纵向和全局的比较，用户可以清楚的监测到当前地域农作物的生长状况。需要说明的是，用户可选取单个地区甚至多个地区同时监测，例如选取张家口市和承德市，通过监测对应植被或作物的归一化植被指数，可以获知农作物的长势情况，并可根据长势情况，有针对性的进行下一步作物的护理工作。
所述生长状态获取模块112用于根据归一化植被指数的获取时间，判断所述农作物的生长状态，所述生长状态至少包括播种期、生长期和成熟期；其中，每个生长状态包含至少一个参考范围，参考范围是基于所述农作物的生长状态预先计算获得的归一化植被指数的范围。
本实施例中，由于农作物具有播种期、生长期和成熟期三个不同的生长状态，首先需要 将归一化植被指数的获取时间和各生长状态对应的时间范围进行比较，判断当前农作物所处的生长状态具体为播种期、生长期和成熟期中的哪一个。然后将归一化植被指数与该生长状态中包含的参考范围进行比较，判断农作物的长势。进一步地，由于不同的农作物其生长状态对应的时间范围不同，为了更加精确的获得当前物种的生长状态。本实施例中，根据归一化植被指数的获取时间，判断所述农作物的生长状态之前，还包括：根据农作物一年中不同的生长状态，预设各生长状态对应的时间范围。可以理解的是，不同农作物的生长状态各不相同，本领域技术人员可根据实际情况适应性设置。
所述子地域比较模块113用于根据所述生长状态，将各子地域的归一化植被指数与所述农作物的生长状态包含的至少一个参考范围进行比较，判断并统计位于各参考范围内对应子地域的数量。
本实施例中，首先按照归一化植被指数递增的顺序，将当前地域中各子地域农作物的归一化植被指数进行排序，并选择归一化植被指数最小的子地域，将其对应的归一化植被指数与农作物当前生长状态中，预设的各参考范围进行比较。若该归一化植被指数处于某一个参考范围内，则此参考范围对应的子地域数量增加一个。若该归一化植被指数不处于任何一个参考范围内，则各参考范围对应的子地域数量保持不变。比较完成后，选择另一个子地域农作物的归一化植被指数继续与各参考范围进行比较，直至当前地域中所有子地域均比较完成后，即可获得当前地域在各参考范围中对应的子地域的数量。作为示例，参考范围有三个，分别为20-25,26-30,31-50，各子地域归一化植被指数为22、35、21、18。则将所有子地域的归一化植被指数与参考范围比较完成后，获得参考范围为20-25对应的子地域数量为2个，31-50对应的子地域数量为1个。由于每个参考范围对应一种长势状态，通过设定不同的参考范围，可以更精确的了解农作物的长势情形。可以理解的是，为了使最终参考范围对应的子地域数量准确，在本实施例中，需要先对参考范围进行初始化，也即将各参考范围对应的子地域数量清零。
所述长势监测模块114用于根据统计的子地域的所述数量，进行分级预警，其中，分级的预警标准是预先设置的。
本实施例中，用户选取的当前地域的多个归一化植被指数，需要按照预设的预警标准对当前地域进行划分，其中，预警标准至少包括一级预警标准、二级预警标准和三级预警标准，优选地，为了使色彩显示更引人注目，所述一级预警标准为红色预警、所述二级预警标准为橙色预警、所述三级预警标准为黄色预警。在每个预警标准中，都具有对应区间的参考范围。例如，可预先设置10个参考范围，每个参考范围对应一个等级。且红色预警中参考范围对应的等级高于橙色预警中参考范围对应的等级，橙色预警中参考范围对应的等级高于黄色预警中参考范围对应的等级，当作物长势落在对应预警标准内时，可以及时有效提醒用户作物长势。具体地，预设的预警标准为红色预警的预警区间是一到三级，橙色预警的预警区间是四到六级，黄色预警的预警区间是七到十级。红色预警表示此时的作物处于高度危险的状态，急需专业人员进入现场进行干预，从而避免作物受损。橙色预警的严重程度低于红色预警，表示此时的作物处于较危急的状态，用户可以选择在处理完红色预警地域后，派专业人员前往橙色预警地域进行作物护理。黄色预警的严重程度低于橙色预警，表示此时的作物虽然有部分数值不符合安全标准范围，但还处于相对较安全的状态，用户可以暂且不用对作物进行进一步护理。实际操作时，可先获得红色预警中参考范围的数量，并将每一个参考范围对应的子地域相加，获得红色预警中子地域的数量。再使用相同的方式，分别获得黄色预警和橙色预警中子地域的数量。作为示例，红色预警中参考范围有2个，分别对应1个和2个子地域，橙色预警中参考范围有3个，分别对应2个、5个和3个子地域，黄色预警中参考范围有1个，对应有4个子地域。且上述子地域各不相同。统计可知，红色预警中子地域有3个，橙色预警中子地域有10个，黄色预警中子地域有4个，由此可知，该地域中橙色预警的地域数量较多，需要专业人员前往现场，进一步加强管理。
需要说明的是，本申请中，用户可以通过改变每个预警标准含有的参考范围的数量，实现自定义设置预警标准。例如，用户可设置红色预警的预警区间是第一个到第五个参考范围，橙色预警的预警区间是第六个到第七个参考范围，黄色预警的预警区间是第八个到第十个参考范围。这种设置可根据每个地域的作物特色进行自定义设置。进一步地，已设置的地域会以列表的形式详细展示该地域位置、告警等级和告警程度并保持可编辑状态。卫星遥感影星地域内的三级告警信息数量符合视觉范围内展示最具体化原则，用户可根据放大或缩小遥感地图的形式实现观看不同地域层级所对应的告警信息数量。从而提升用户监测体验。用户可自主设置对应的触发条件。用户参考全国标准值并依据己方样本的地域位置、作物种类和环境状况进行上下浮动调整地域标准值，在处理样本数据时可进一步个性化调整参数以辅助农作物监测和预警分析。在遥感技术和农业背景下，如果真实数据过高或者过低则对农业预测和风险防控都有重要现实意义。
需要说明的是，本实施例的农作物长势的监测系统是与上述农作物长势的监测方法相对应的系统。农作物长势的监测系统中的功能模块或者分别对应农作物长势的监测方法中的相应步骤。本实施例的农作物长势的监测系统可与农作物长势的监测方法相互相配合实施。相应地，本实施例的农作物长势的监测系统中提到的相关技术细节也可应用在上述农作物长势的监测方法中。
需要说明的是，上述的各功能模块实际实现时可以全部或部分集成到一个物理实体上，也可以物理上分开。且这些模块可以全部以软件通过处理元件调用的形式实现；也可以全部以硬件的形式实现；还可以部分模块通过处理元件调用软件的形式实现，部分模块通过硬件的形式实现。此外这些模块全部或部分可以集成在一起，也可以独立实现。这里所述的处理元件可以是一种集成电路，具有信号的处理能力。在实现过程中，上述方法的部分或全部步骤，或以上的各功能模块可以通过处理器元件中的硬件的集成逻辑电路或者软件形式的指令完成。
如图6所示，是本申请电子设备的结构示意图。
所述电子设备1可以包括存储器12、处理器13和总线，还可以包括存储在所述存储器12中并可在所述处理器13上运行的计算机程序，例如基于方向检测的文字识别程序。
其中，存储器12至少包括一种类型的可读存储介质，所述可读存储介质包括闪存、移动硬盘、多媒体卡、卡型存储器(例如：SD或DX存储器等)、磁性存储器、磁盘、光盘等。存储器12在一些实施例中可以是电子设备1的内部存储单元，例如该电子设备1的移动硬盘。存储器12在另一些实施例中也可以是电子设备1的外部存储设备，例如电子设备1上配备的插接式移动硬盘、智能存储卡(Smart Media Card,SMC)、安全数字(Secure Digital,SD)卡、闪存卡(Flash Card)等。进一步地，存储器12还可以既包括电子设备1的内部存储单元也包括外部存储设备。存储器12不仅可以用于存储安装于电子设备1的应用软件及各类数据，例如基于方向检测的文字识别程序的代码等，还可以用于暂时地存储已经输出或者将要输出的数据。
处理器13在一些实施例中可以由集成电路组成，例如可以由单个封装的集成电路所组成，也可以是由多个相同功能或不同功能封装的集成电路所组成，包括一个或者多个中央处理器(Central Processing unit，CPU)、微处理器、数字处理芯片、图形处理器及各种控制芯片的组合等。处理器13是所述电子设备1的控制核心(Control Unit)，利用各种接口和线路连接整个电子设备1的各个部件，通过运行或执行存储在所述存储器12内的程序或者模块(例如执行体检报告校验程序等)，以及调用存储在所述存储器12内的数据，以执行电子设备1的各种功能和处理数据。
所述处理器13执行所述电子设备1的操作系统以及安装的各类应用程序。所述处理器13执行所述应用程序以实现上述各个农作物长势的监测方法实施例中的步骤，例如图1所示的步骤。
示例性的，所述计算机程序可以被分割成一个或多个模块，所述一个或者多个模块被存储在所述存储器12中，并由所述处理器13执行，以完成本申请。所述一个或多个模块可以是能够完成特定功能的一系列计算机程序指令段，该指令段用于描述所述计算机程序在所述电子设备1中的执行过程。例如，所述计算机程序可以被分割成数据获取模块111，生长状态获取模块112，子地域比较模块113和长势监测模块114。
上述以软件功能模块的形式实现的集成的单元，可以存储在一个计算机可读取存储介质中。上述软件功能模块存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机、计算机设备，或者网络设备等)或处理器(processor)执行本申请各个实施例所述体检项目推荐方法的部分功能。所述计算机可读存储介质可以是非易失性，也可以是易失性。
本申请所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain)，本质上是一个去中心化的数据库，是一串使用密码学方法相关联产生的数据块，每一个数据块中包含了一批次网络交易的信息，用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
总线可以是外设部件互连标准(peripheral component interconnect，简称PCI)总线或扩展工业标准结构(extended industry standard architecture，简称EISA)总线等。该总线可以分为地址总线、数据总线、控制总线等。为便于表示，在图6中仅用一根箭头表示，但并不表示仅有一根总线或一种类型的总线。所述总线被设置为实现所述存储器12以及至少一个处理器13等之间的连接通信。
本申请的农作物长势的监测方法、系统、设备及介质，通过获取当前地域农作物的卫星图像中，多个归一化植被指数，用户可根据地域内红橙黄三色的告警位置和数量分析农作物长势监测和预警情况。通过以上交互策略不仅将遥感数据进行图表化，并进一步实现告警信息的可视化，这不仅提升用户数据分析的直观感受和效率，更是通过多项自定义的方式在最大程度上满足了用户进行数据分析和展示的自由空间，保证遥感数据的直观和形象。
对于本领域技术人员而言，显然本申请不限于上述示范性实施例的细节，而且在不背离本申请的精神或基本特征的情况下，能够以其他的具体形式实现本申请。
以上实施例仅用以说明本申请的技术方案而非限制，尽管参照较佳实施例对本申请进行了详细说明，本领域的普通技术人员应当理解，可以对本申请的技术方案进行修改或等同替换，而不脱离本申请技术方案的精神和范围。

Claims (20)

  1. 一种农作物长势的监测方法，其中，包括：
    获取当前地域中农作物的至少两个子地域的归一化植被指数；其中，所述当前地域包括至少两个子地域；
    根据归一化植被指数的获取时间，判断所述农作物的生长状态，所述生长状态至少包括播种期、生长期和成熟期；其中，每个生长状态包含至少一个参考范围，参考范围是基于所述农作物的生长状态预先计算获得的归一化植被指数的范围；
    根据所述生长状态，将各子地域的归一化植被指数与所述农作物的生长状态包含的至少一个参考范围进行比较，判断并统计位于各参考范围内对应子地域的数量；
    根据统计的子地域的所述数量，进行分级预警，其中，分级的预警标准是预先设置的。
  2. 根据权利要求1所述的农作物长势的监测方法，其中，所述参考范围是基于所述农作物的生长状态预先计算获得的，具体包括：
    获取至少连续两年中，农作物的多个归一化植被指数生长曲线，每个生长曲线表示农作物一年中各月份的归一化植被指数变化情况；
    将所述多个归一化植被指数生长曲线进行线性拟合，获得农作物的参考生长曲线；
    根据预设的生长状态，将所述参考生长曲线划分为播种期曲线、生长期曲线和成熟期曲线；
    依次计算所述播种期曲线、生长期曲线和成熟期曲线中，对应的归一化植被指数的标准差，并对各标准差进行等距处理，分别获得与所述播种期、所述生长期和所述成熟期相对应的至少一个参考范围。
  3. 根据权利要求2所述的农作物长势的监测方法，其中，所述线性拟合通过选取每个生长曲线中对应点的数值，对各点的数值求平均获得若干个关键点，将若干个关键点依次相连，获得农作物的参考生长曲线。
  4. 根据权利要求2所述的农作物长势的监测方法，其中，使用最小二乘法进行线性拟合。
  5. 根据权利要求2所述的农作物长势的监测方法，其中，所述成熟期相对应的至少一个参考范围获得过程包括：
    获得所述成熟期曲线中，各月份归一化植被指数，并计算各月份归一化植被指数的标准差；
    预设有多个数值，且相邻数值之间的差值相同，并将多个数值依次与所述标准差相加，获得多个第一参考值；
    将所述标准差依次减去所述多个数值，获得多个第二参考值；
  6. 将所述多个第一参考值和所述多个第二参考值结合，获得所述成熟期对应的至少一个参考范围。根据权利要求3所述的农作物长势的监测方法，其中，所述月份归一化植被指数的标准差的计算方法为：
    Figure PCTCN2022089634-appb-100001
    其中，
    Figure PCTCN2022089634-appb-100002
    为归一化植被指数的平均值，x i为第i个月归一化植被指数，T k-1为成熟期的开始时间，T k为成熟期的结束时间。
  7. 根据权利要求1所述的农作物长势的监测方法，其中，所述根据统计的子地域的所述数量，进行分级预警，包括：
    基于当前地域中农作物的生长状态，统计每个预警标准中包含的子地域的数量；其中，预警标准包括一级预警标准、二级预警标准和三级预警标准，预警标准表示子地域的归一化植被指数超过预设的归一化植被指数阈值；
    将每个预警标准中子地域的数量与对应预设的预警阈值比较，若子地域的数量大于对应的预警阈值，发出对应的预警信息。
  8. 根据权利要求7所述的农作物长势的监测方法，其中，所述一级预警标准为红色预警、所述二级预警标准为橙色预警、所述三级预警标准为黄色预警。
  9. 根据权利要求8所述的农作物长势的监测方法，其中，所述每个预警标准中，都具有对应区间的参考范围，每个参考范围对应一个等级。
  10. 根据权利要求9所述的农作物长势的监测方法，其中，所述红色预警中参考范围对应的等级高于所述橙色预警中参考范围对应的等级。
  11. 根据权利要求10所述的农作物长势的监测方法，其中，所述橙色预警中参考范围对应的等级高于所述黄色预警中参考范围对应的等级。
  12. 根据权利要求1所述的农作物长势的监测方法，其中，所述根据归一化植被指数的获取时间，判断所述农作物的生长状态之前，还包括：根据农作物一年中不同的生长状态，预设各生长状态对应的时间范围。
  13. 根据权利要求1所述的农作物长势的监测方法，其中，所述获取当前地域中农作物的若干个子地域的归一化植被指数之前，还包括：将若干个参考范围对应的子地域数量清零。
  14. 根据权利要求1所述的农作物长势的监测方法，其中，所述当前地域中农作物的归一化植被指数以所述农作物生长期、播种期和成熟期的卫星图像为参考。
  15. 根据权利要求1所述的农作物长势的监测方法，其中，所述播种期表示所述农作物未生长发芽的时期。
  16. 根据权利要求1所述的农作物长势的监测方法，其中，所述生长期表示所述农作物破土而出，开始生长的时期。
  17. 根据权利要求1所述的农作物长势的监测方法，其中，所述成熟期表示对所述农作物进行收割，获得果实的时期。
  18. 一种农作物长势的监测系统，其中，包括：
    数据获取模块，用于获取当前地域中农作物的至少两个子地域的归一化植被指数；其中，所述当前地域包括至少两个子地域；
    生长状态获取模块，用于根据归一化植被指数的获取时间，判断所述农作物的生长状态，所述生长状态至少包括播种期、生长期和成熟期；其中，每个生长状态包含至少一个参考范围，每个参考范围是基于所述农作物的生长状态预先计算获得的归一化植被指数的范围；
    子地域比较模块，用于根据所述生长状态，将各子地域的归一化植被指数与所述农作物的生长状态包含的至少一个参考范围进行比较，判断并统计位于各参考范围内对应子地域的数量；
    长势监测模块，用于根据统计的子地域的所述数量，进行分级预警，其中，分级的预警标准是预先设置的。
  19. 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程序，其中，所述处理器执行所述计算机程序时实现权利要求1至17中任一项所述方法的步骤。
  20. 一种计算机可读存储介质，其上存储有计算机程序，其中，所述计算机程序被处理器执行时实现权利要求1至17中任一项所述的方法的步骤。
PCT/CN2022/089634 2022-03-03 2022-04-27 农作物长势的监测方法、系统、设备及介质 WO2023165007A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210201040.7A CN114581401A (zh) 2022-03-03 2022-03-03 农作物长势的监测方法、系统、设备及介质
CN202210201040.7 2022-03-03

Publications (1)

Publication Number Publication Date
WO2023165007A1 true WO2023165007A1 (zh) 2023-09-07

Family

ID=81772382

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/089634 WO2023165007A1 (zh) 2022-03-03 2022-04-27 农作物长势的监测方法、系统、设备及介质

Country Status (2)

Country Link
CN (1) CN114581401A (zh)
WO (1) WO2023165007A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN117541924A (zh) * 2023-11-16 2024-02-09 海南海柠科技有限公司 一种农作物生长状况的监测方法
CN117787573A (zh) * 2024-02-27 2024-03-29 山东省国土空间生态修复中心(山东省地质灾害防治技术指导中心、山东省土地储备中心) 一种盐碱地治理预警方法、设备及介质
CN117859549A (zh) * 2024-03-11 2024-04-12 中化现代农业有限公司 棉花变量打顶方法、装置、电子设备和存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107014753A (zh) * 2017-03-06 2017-08-04 中国科学院遥感与数字地球研究所 作物长势监测方法和系统
CN109211791A (zh) * 2018-08-10 2019-01-15 北京观微科技有限公司 作物长势监测方法及系统
US20200273172A1 (en) * 2019-02-27 2020-08-27 International Business Machines Corporation Crop grading via deep learning
CN112581464A (zh) * 2020-12-25 2021-03-30 武汉禾大科技有限公司 一种作物长势情况分析方法、装置及存储介质
CN113516100A (zh) * 2021-08-02 2021-10-19 中化现代农业有限公司 一种基于植被指数差异性的作物生长分析方法及系统
CN114005039A (zh) * 2021-12-31 2022-02-01 成都国星宇航科技有限公司 基于遥感图像的农作物长势评估方法、装置及电子设备

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111582554B (zh) * 2020-04-17 2024-02-23 北京市农林科学院信息技术研究中心 一种农作物长势预测方法及系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107014753A (zh) * 2017-03-06 2017-08-04 中国科学院遥感与数字地球研究所 作物长势监测方法和系统
CN109211791A (zh) * 2018-08-10 2019-01-15 北京观微科技有限公司 作物长势监测方法及系统
US20200273172A1 (en) * 2019-02-27 2020-08-27 International Business Machines Corporation Crop grading via deep learning
CN112581464A (zh) * 2020-12-25 2021-03-30 武汉禾大科技有限公司 一种作物长势情况分析方法、装置及存储介质
CN113516100A (zh) * 2021-08-02 2021-10-19 中化现代农业有限公司 一种基于植被指数差异性的作物生长分析方法及系统
CN114005039A (zh) * 2021-12-31 2022-02-01 成都国星宇航科技有限公司 基于遥感图像的农作物长势评估方法、装置及电子设备

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117541924A (zh) * 2023-11-16 2024-02-09 海南海柠科技有限公司 一种农作物生长状况的监测方法
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
CN117787573A (zh) * 2024-02-27 2024-03-29 山东省国土空间生态修复中心(山东省地质灾害防治技术指导中心、山东省土地储备中心) 一种盐碱地治理预警方法、设备及介质
CN117787573B (zh) * 2024-02-27 2024-05-28 山东省国土空间生态修复中心(山东省地质灾害防治技术指导中心、山东省土地储备中心) 一种盐碱地治理预警方法、设备及介质
CN117859549A (zh) * 2024-03-11 2024-04-12 中化现代农业有限公司 棉花变量打顶方法、装置、电子设备和存储介质

Also Published As

Publication number Publication date
CN114581401A (zh) 2022-06-03

Similar Documents

Publication Publication Date Title
WO2023165007A1 (zh) 农作物长势的监测方法、系统、设备及介质
US11521380B2 (en) Shadow and cloud masking for remote sensing images in agriculture applications using a multilayer perceptron
Ge et al. Spatiotemporal dynamics of grassland aboveground biomass and its driving factors in North China over the past 20 years
CN110579359B (zh) 自动驾驶失效场景库的优化方法及系统、服务器及介质
López‐Martínez et al. Partitioning the variation of woody plant β‐diversity in a landscape of secondary tropical dry forests across spatial scales
CN110059915B (zh) 一种冬小麦气象灾害综合风险动态评价方法及装置
US20110246073A1 (en) System and method for analyzing trees in lidar data using views
Peters et al. Synergy of very high resolution optical and radar data for object-based olive grove mapping
Gao et al. Object-based classification with features extracted by a semi-automatic feature extraction algorithm–SEaTH
CN116304600B (zh) 基于大数据分析的外来入侵物种预警方法及系统
CN114611941A (zh) 一种考虑空间危险性的滑坡灾害评价方法及系统
CN109859057A (zh) 一种农田数据处理方法、服务器及存储介质
CN107944219B (zh) 一种表征不同时段旱涝致灾特征的方法和装置
Duncan et al. Monitoring spatial patterns of urban vegetation: A comparison of contemporary high-resolution datasets
CN107437262B (zh) 作物种植面积预警方法和系统
CN116579521B (zh) 产量预测时间窗口确定方法、装置、设备及可读存储介质
Kotharkar et al. Numerical analysis of extreme heat in Nagpur city using heat stress indices, all-cause mortality and local climate zone classification
US20120004847A1 (en) System and method for analyzing trees in lidar data using views
KR100785350B1 (ko) 양식장 모니터링 방법 및 그 시스템
Rudstrom et al. Data aggregation issues for crop yield risk analysis
Zhang et al. Improving the accuracy of forest aboveground biomass using Landsat 8 OLI images by quantile regression neural network for Pinus densata forests in southwestern China
CN115271332A (zh) 一种旱情监测方法
CN115293809A (zh) 基于人工智能的台风暴雨风险评级方法及相关设备
Samal et al. Using a Bayesian joint probability approach to improve the skill of medium-range forecasts of the Indian summer monsoon rainfall
JPWO2019003400A1 (ja) 係数算出装置、係数算出方法、及び、係数算出プログラム

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: 22929445

Country of ref document: EP

Kind code of ref document: A1